System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining health screening results and life style information from users; means for analyzing the obtained health screening results and life style information; means for using a generative AI model to generate optimal health care plans based on the analysis results; and means for providing the generated health care plans to the users.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] In modern society, with increasing health awareness, there is a demand for understanding individual lifestyle habits and health conditions and for appropriate health management. However, health checkup results and lifestyle data vary from person to person, and self-managed health management is often ineffective. In addition, health checkup results are written in technical terms, making them difficult for users to understand. Furthermore, there is a lack of systems that provide appropriate feedback and future risk predictions based on the acquired data. In light of this situation, there is a demand for systems that are easy for users to understand and that allow them to continuously manage their health. [Means for solving the problem]

[0005] The present invention provides a means for acquiring health checkup results and lifestyle habit data from a user and analyzing the acquired data. Next, a means for using a generative AI model to generate an optimal health management plan based on the analysis results is provided, and the generated health management plan is provided to the user. Furthermore, a means for generating explanations for the generated health management plan using an expert model and providing them in a format that is easy for the user to understand is also provided. Also provided are a means for collecting user behavioral data and providing immediate feedback based on the behavioral data, and a means for using a generative AI model to predict future health risks and propose specific improvement measures based on the provided feedback. This enables health management that is optimized for each individual user, makes it easier to understand health checkup results, and supports continuous health management.

[0006] "User" refers to an individual who provides health checkup results and lifestyle data and is the beneficiary of a health management plan provided by the generative AI model.

[0007] "Health checkup results" refers to data including the results of measuring health conditions such as blood pressure, cholesterol levels, and blood sugar levels.

[0008] "Lifestyle data" refers to data related to a user's daily activities, such as diet, exercise, and sleep.

[0009] "Analysis" refers to the act of identifying and evaluating health risks and nutrient deficiencies based on the health checkup results and lifestyle data obtained.

[0010] A "generative AI model" refers to an artificial intelligence algorithm or system that uses analysis results as input to generate an optimal health management plan.

[0011] A "health management plan" refers to a plan or program that suggests optimal content regarding diet, exercise, sleep, etc.

[0012] An "expert model" refers to an artificial intelligence or algorithm that provides easy-to-understand explanations of health checkup results and generated health management plans.

[0013] "Behavioral data" refers to data related to the user's actual activities in daily life, such as the user's exercise log, dietary content, and sleep data.

[0014] "Immediate feedback" refers to prompt evaluations and advice based on user behavioral data.

[0015] "Health risks" refer to factors or situations that may harm a user's health in the future.

[0016] "Specific remedial measures" refer to specific actions or measures to reduce or eliminate identified health risks. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[0039] The entire system consists of the user's device, a server, and a generative AI model.

[0040] Data collection and input processing

[0041] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0042] Receiving and analyzing data

[0043] The server receives the health checkup results and lifestyle data sent by the user. The received data is stored in a database and passed to the analysis module. The analysis module identifies health risk factors specific to the user based on the data.

[0044] Generate a health management plan

[0045] The server sends the analysis results to the generative AI model, which then generates an optimal health management plan. For example, for users at risk of high blood pressure, the model suggests a low-salt diet plan and regular aerobic exercise. For users who are sleep-deprived, the model suggests specific ways to increase their sleep time.

[0046] Plan provision and explanation

[0047] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using the expert model to make it easy for the user to understand. The explanation is specific advice such as, "Try to eat more vegetables and fruits to limit salt in your daily diet."

[0048] Feedback and Improvement Suggestions

[0049] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0050] As a concrete example, if a user at risk of high blood pressure inputs their daily step count and dietary details into the app, the server will analyze this information, and the generative AI model will provide specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast."The system also provides continuous feedback on the practices the user has followed, suggesting further improvement measures.

[0051] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user enters health data.

[0055] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[0056] Step 2:

[0057] The server receives the data.

[0058] The server receives the health checkup results and lifestyle habit data sent from the user and stores them in a database.

[0059] Step 3:

[0060] The server analyzes the data.

[0061] The server passes the data received from the database to the analysis module, which uses the data to identify the user's health risk factors and nutrient deficiencies.

[0062] Step 4:

[0063] The generative AI model receives the analysis results.

[0064] The server sends the analysis results to the generative AI model, which then generates the optimal health management plan for each user based on the data.

[0065] Step 5:

[0066] The server provides the health management plan.

[0067] The server then sends the generated health management plan to the user's device, which includes specific suggestions for diet, exercise, sleep, etc.

[0068] Step 6:

[0069] The server generates the description.

[0070] The server uses the expert model to generate an explanation for the generated health care plan and provides it to the user along with the plan. The explanation is provided in a format that is easy for the user to understand.

[0071] Step 7:

[0072] The server collects the behavioral data.

[0073] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[0074] Step 8:

[0075] The server provides feedback.

[0076] The server analyzes the collected behavioral data and provides real-time feedback to the user, including evaluation and advice for the actions the user has taken.

[0077] Step 9:

[0078] A generative AI model suggests improvements.

[0079] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific remedial measures, which are then sent to the user's device.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] While conventional health management systems partially automate the collection and analysis of data from users, they are inadequate in the continuous management of behavioral data and the provision of immediate feedback, making it difficult to generate optimal health management plans for individual users or predict future health risks. Furthermore, they lack a mechanism for providing specific explanations for the generated health management plans, making it difficult for users to properly understand and implement the plans. Furthermore, there is no method for efficiently utilizing generative AI models using prompt sentences.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting behavioral data of the user and providing immediate feedback based on the behavior, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the collected behavioral data and immediate feedback, thereby enabling the provision of a continuous and dynamic health management plan to each individual user.

[0085] "Medical checkup results" are data indicating physiological indicators such as blood pressure, cholesterol level, and blood sugar level obtained when a user undergoes a medical checkup.

[0086] "Lifestyle data" refers to data relating to the user's daily habits, such as diet, exercise, and sleep duration.

[0087] "Behavioral data" refers to data based on the user's actual behavior, such as exercise logs, dietary content, and sleep data.

[0088] A "generative AI model" is an artificial intelligence model that analyzes acquired data and generates an optimal health management plan.

[0089] An "expert model" is an artificial intelligence model that provides specific and expert commentary on the generated health management plan.

[0090] "Immediate feedback" refers to advice and suggestions provided in real time based on behavioral data collected from users.

[0091] A "prompt sentence" is an input sentence used to give specific instructions to a generative AI model.

[0092] A "health management plan" is an optimal health management method and specific action plan created based on the user's health condition and lifestyle habits.

[0093] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users and generates and provides optimal health management plans. The entire system consists of a user's device, a server, and a generative AI model.

[0094] Users use their smartphones or PCs to input health checkup results and lifestyle data. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0095] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database on the server and passed to an analysis module. The analysis module analyzes the data to identify health risk factors specific to the user. Specifically, scripts written in Python and machine learning models are used.

[0096] The server that obtains the analysis results sends them to a generative AI model. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. Based on the analysis results, the generative AI model generates an optimal health management plan. For example, for users at risk of high blood pressure, it suggests a low-salt diet plan and regular aerobic exercise. It also suggests specific ways to increase sleep for users who are sleep-deprived.

[0097] The generated health management plan is sent from the server to the user's device. At this time, an explanation of the plan generated using the expert model is also added. The expert model provides specific advice to help the user understand the generated plan, such as "Try to eat more vegetables and fruits in your daily diet to limit salt intake."

[0098] Furthermore, the server continuously collects user behavioral data, including exercise logs, dietary details, and sleep data. Based on this data, notifications and advice are provided to users as real-time feedback. Additionally, the generative AI model analyzes this behavioral data and predicts future health risks. Specific improvement measures for predicted risks are presented to support ongoing health management.

[0099] As a concrete example, the generative AI model operates using the following prompt sentence:

[0100] User's health check results: Blood pressure 150 / 90, cholesterol 220, blood sugar 110

[0101] User's lifestyle data: 5,000 steps / day, meal contents (breakfast: toast, lunch: salad, dinner: pasta), sleep time: 6 hours

[0102] Analyze this data and suggest a health management plan that suits the user.

[0103] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] Users use their smartphones or PCs to input health checkup results and lifestyle habit data. For example, they input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as lifestyle habit data such as diet, exercise, and sleep duration. This data is sent from the device to a server. Inputs include data manually entered by the user into input forms or applications, and outputs include data sent to the server via HTTP requests.

[0107] Specific behavior:

[0108] The user opens the smartphone application and enters information such as blood pressure and dietary details according to the input form.

[0109] The input data is sent from the terminal application to the server.

[0110] Step 2:

[0111] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database on the server. The input is the data sent from the terminal that arrives at the server as an HTTP request, and the output is the health checkup results and lifestyle habit data stored in the database.

[0112] Specific behavior:

[0113] The server receives the HTTP request and analyzes the data contained in the request.

[0114] Insert the parsed data into a database (for example, by executing an INSERT statement against an SQL database).

[0115] Step 3:

[0116] The analysis module on the server retrieves data from the database and performs analysis. Based on this, health risk factors specific to the user are identified. The input is user data retrieved from the database, and the output is the analysis results of health risk factors.

[0117] Specific behavior:

[0118] The server passes the user's health check results and lifestyle habit data obtained from the database to the analysis module.

[0119] The analysis module analyzes the data using Python scripts and machine learning models.

[0120] Step 4:

[0121] The server sends the analysis results to the generative AI model and makes a request to generate an optimal health care plan. The generated health care plan is sent back to the server. The analysis results are provided as prompt sentences to the generative AI model as input, and the generated health care plan is the output.

[0122] Specific behavior:

[0123] The server creates a prompt for the generative AI model and sends it via an API request.

[0124] The generative AI model analyzes the prompt, generates an appropriate health management plan, and sends it back to the server.

[0125] Step 5:

[0126] The server sends the generated health management plan to the user's terminal. At this time, an explanation is added to the plan generated using the expert model. The input is the generated health management plan, and the output is the plan with the explanation sent to the user's terminal.

[0127] Specific behavior:

[0128] The server generates an HTTP request to transmit the health management plan to the user's terminal.

[0129] The expert model will add specific commentary to the plan and send it along with the plan.

[0130] Step 6:

[0131] The server continuously collects user behavioral data and provides immediate feedback. Furthermore, a generative AI model analyzes the behavioral data, predicts future health risks, and provides specific improvement measures. The input is behavioral data from the user's device, and the output is improvement measures based on feedback and future risk predictions.

[0132] Specific behavior:

[0133] The server periodically collects data such as step counts, meal contents, and sleep data from the user's device.

[0134] The collected data is analyzed and notifications are sent to the user as immediate feedback.

[0135] A generative AI model analyzes behavioral data to predict future health risks and provide remedial measures.

[0136] (Application example 1)

[0137] 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."

[0138] Conventional health management systems are limited to providing users with one-way information, making it difficult to provide immediate feedback on changes in users' daily lifestyles and health conditions or specific improvement measures. Furthermore, they lack ongoing support tailored to individual health risks, leaving users with little motivation to continue managing their health voluntarily. Therefore, there is a need for systems that provide optimal health management plans for individual users and support ongoing health management.

[0139] 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.

[0140] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting the user's daily behavioral data, and means for using the generative AI model to provide real-time feedback based on the collected behavioral data and generate specific improvement measures, thereby enabling continuous and real-time health management for the user.

[0141] "Medical checkup results" are the measurement results of blood pressure, cholesterol level, blood sugar level, etc. based on a medical checkup conducted at a medical institution, etc.

[0142] "Lifestyle data" refers to data related to the user's daily life, including information such as dietary habits, amount of exercise, and sleep duration.

[0143] "Analysis" refers to identifying health risk factors specific to a user based on the health checkup results and lifestyle habit data obtained.

[0144] A "generative AI model" is an artificial intelligence model that generates optimal health management plans and specific improvement measures based on analysis results.

[0145] A "health management plan" is a specific set of guidelines and advice provided by the generative AI model to help users maintain and improve their health.

[0146] An "expert model" is an artificial intelligence model that provides expert commentary on the generated health care plan.

[0147] "Feedback" refers to instant evaluations and advice provided by the generative AI model based on behavioral data provided by the user.

[0148] "Behavioral data" refers to specific data related to the user's daily lifestyle habits, and includes exercise logs, dietary details, sleep data, and the like.

[0149] "Improvements" are specific actions or measures proposed to reduce future health risks based on analysis and feedback.

[0150] This invention relates to a health management system using a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[0151] 1. Data collection and input processing

[0152] Users use their smartphones or computers to input data on their health checkup results and lifestyle habits. Health checkup results include blood pressure, cholesterol levels, blood sugar levels, and other measurement results. Lifestyle information includes dietary details, exercise levels, and sleep duration. This information is sent from the user's device to a server. A secure communication protocol such as HTTPS is used for transmission.

[0153] 2. Data Receipt and Analysis

[0154] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database (e.g., PostgreSQL) and passed to an analysis module (e.g., Python, Pandas). The analysis module identifies health risk factors specific to the user based on the data.

[0155] 3. Generate a health management plan

[0156] The server sends the analysis results to a generative AI model (e.g., GPT-3), which then generates an optimal health management plan. The plan includes specific advice based on the user's health checkup results and lifestyle habits.

[0157] 4. Providing and explaining the plan

[0158] The generated health management plan is sent from the server to the user's smartphone. In addition, an expert model installed separately from the generating AI model provides commentary on the generated plan. The expert model provides specific advice, such as "Try to eat more vegetables and fruits to reduce salt in your daily diet."

[0159] 5. Feedback and Improvement Suggestions

[0160] The server continuously collects the user's daily behavioral data. This behavioral data includes exercise logs, dietary habits, sleep data, etc. This data is obtained from various sensors on the smartphone (GPS, accelerometer, etc.). Based on the collected data, the generative AI model provides immediate feedback. For example, it gives specific advice such as, "You haven't reached your step goal today. Try walking a little longer."

[0161] Furthermore, the generative AI model predicts future health risks and provides specific recommendations for improvement, such as "Aim for 5,000 steps a day" and "Include foods high in fiber for breakfast."

[0162] Examples of prompt statements

[0163] Below are some example prompts that can be presented to the generative AI model based on user-provided data.

[0164] The user's health check results are: Blood pressure: 130 / 85, Cholesterol: 210, Blood sugar: 100.

[0165] Lifestyle data is as follows: Diet: high calorie, low fiber, exercise: low, sleep: 6 hours.

[0166] Based on this data, generate an optimal health management plan for users at risk for high blood pressure and high cholesterol, including specific recommendations.

[0167] As described above, this system provides optimal health management plans tailored to each user's individual circumstances and supports continuous health management.

[0168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0169] Step 1:

[0170] Users use their smartphones or computers to input their health checkup results and lifestyle data. Specifically, users enter health checkup results such as blood pressure, cholesterol levels, and blood sugar levels into the application form, and provide lifestyle data such as diet, exercise, and sleep time. This data is sent to the server via HTTPS.

[0171] Step 2:

[0172] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database (e.g., PostgreSQL), allowing the data to be stored permanently.

[0173] Step 3:

[0174] The server's analysis module analyzes the stored data. Specifically, it uses analysis modules (e.g., Python, Pandas) to identify health risk factors specific to the user. The data is processed by statistical analysis of blood pressure and cholesterol levels to check for abnormal values.

[0175] Step 4:

[0176] The server uses a generative AI model (e.g., GPT-3) based on the analysis results to generate an optimal health management plan. The analysis results are used as input to create a prompt for the generative AI model, which then outputs a specific health management plan. This prompt includes the user's health checkup results and lifestyle habits.

[0177] Step 5:

[0178] The generated health management plan is sent from the server to the user's smartphone. Specifically, the health management plan provided by the generative AI model is displayed in text format in the user's application. At this time, an expert model is also used to add detailed explanations to the plan.

[0179] Step 6:

[0180] The user's daily behavioral data (exercise log, dietary content, sleep data, etc.) is continuously collected from various sensors (GPS, accelerometer, etc.) on the smartphone and sent to a server. The behavioral data sent is then stored in a database.

[0181] Step 7:

[0182] The server analyzes the collected behavioral data and provides immediate feedback. Specifically, it uses a generative AI model to provide specific advice and guidance to the user based on the behavioral data. For example, the user may receive feedback such as, "You haven't reached your step goal today. Try walking a little longer." via the application.

[0183] Step 8:

[0184] Furthermore, the server predicts future health risks and generates specific improvement measures. The generative AI model suggests improvement measures such as "Aim for 5,000 steps a day" or "It's a good idea to include foods high in dietary fiber in your breakfast." These suggestions are also generated using prompt text and provided to the user.

[0185] 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.

[0186] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[0187] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0188] Data collection and input processing

[0189] Users use their smartphones or computers to input data about their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information about lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0190] Receiving and analyzing data

[0191] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" and "dietary imbalance."

[0192] Generate a health management plan

[0193] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be suggested a low-salt diet plan and regular aerobic exercise. Similarly, a user at risk of sleep deprivation would be suggested specific ways to increase their sleep time.

[0194] Incorporating an emotion engine

[0195] Furthermore, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[0196] Plan provision and explanation

[0197] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using an expert model to make it easy for the user to understand. The explanation provides specific advice, such as "On stressful days, try deep breathing or yoga to relax."

[0198] Feedback and Improvement Suggestions

[0199] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0200] For example, if a user at risk of high blood pressure enters their daily step count and dietary details into the app, the server analyzes this information, and the generative AI model provides specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast." Also, if the user is feeling stressed, the emotion engine will detect this and make suggestions such as "It's good to listen to music to relax."

[0201] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual situation and emotional state of the user, enabling continuous health management.

[0202] The processing flow will be explained below.

[0203] Step 1:

[0204] The user enters health data.

[0205] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[0206] Step 2:

[0207] The server receives the data.

[0208] The server receives the health checkup results and lifestyle habit data sent from the user and stores the data in a database.

[0209] Step 3:

[0210] The server analyzes the data.

[0211] The server passes the data received from the database to the analysis module, which then uses the data to identify the user's health risk factors and nutrient deficiencies. For example, if blood pressure is 140 / 90 or higher, it identifies the user as being at risk of high blood pressure.

[0212] Step 4:

[0213] The generative AI model receives the analysis results.

[0214] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be recommended to take a low-salt diet and engage in regular aerobic exercise.

[0215] Step 5:

[0216] The emotion engine retrieves the emotion data.

[0217] While the user is using the device, the emotion engine uses the camera and microphone to perform facial recognition and voice analysis to detect the user's emotional state (e.g., stress level, happiness).

[0218] Step 6:

[0219] The server receives and analyzes the emotion data.

[0220] The emotion data acquired by the emotion engine is sent to a server, which analyzes it and identifies whether the user is feeling stressed or comfortable.

[0221] Step 7:

[0222] A generative AI model takes emotional data into account to tailor a health plan.

[0223] The generative AI model takes emotional data into account to tailor the health plan, for example suggesting relaxation techniques if stress levels are high and adding additional advice to improve mood.

[0224] Step 8:

[0225] The server provides the health management plan.

[0226] The generated health management plan is sent to the user's device. The plan includes specific suggestions for diet, exercise, and sleep, as well as emotional relaxation techniques. For example, the plan might suggest "eating more vegetables every day and incorporating walking into your daily routine."

[0227] Step 9:

[0228] The server generates the description.

[0229] The server uses the expert model to generate commentary for the generated health management plan and provides it to the user along with the plan, such as "Eating a low-salt diet can reduce the risk of high blood pressure."

[0230] Step 10:

[0231] The server collects the behavioral data.

[0232] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[0233] Step 11:

[0234] The server provides feedback.

[0235] The server analyzes the collected behavioral data and provides the user with immediate feedback, such as "Your exercise volume today is below your goal" or "You should incorporate more balance into your diet."

[0236] Step 12:

[0237] A generative AI model suggests improvements.

[0238] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific improvement measures. The proposed improvement measures are sent to the user's device. For example, they could be specific goals such as "Aim for 5,000 steps a day" or suggestions such as "When stress levels rise, we recommend taking deep breaths or listening to music."

[0239] Example 2

[0240] 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."

[0241] In recent years, lifestyle-related diseases and physical and mental health problems have been on the rise, but conventional health management systems can only make simple suggestions based on individual health checkup results and lifestyle data, making it difficult to provide comprehensive health management that takes into account the user's emotional state.In addition, there is a demand for real-time feedback and immediate improvement suggestions, but achieving this requires advanced technology.

[0242] 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 acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to sense the user's emotional state and provide feedback based on that state, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the provided feedback. This enables comprehensive and specific health management based on the user's individual health data and emotional state.

[0243] "Physical examination results" are the results of medical tests to evaluate the user's physical condition and health status.

[0244] "Lifestyle habit data" is information about the user's habits in daily life, such as exercise, diet, and sleep.

[0245] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate optimal health management plans and recommendations for users.

[0246] A "generated health management plan" is a specific proposal or plan for improving or maintaining a user's individual health, created by the generative AI model based on the analysis results.

[0247] "Emotional state" refers to the user's current psychological state, mood, and emotional state.

[0248] An "emotion engine" is a system or software that analyzes a user's emotional state and provides feedback and suggestions based on that analysis.

[0249] An "expert model" is an algorithm or system that provides expert knowledge-based commentary or additional information to the generated health management plan.

[0250] "Behavioral data" is data relating to the user's specific daily activities (exercise, meals, sleep, etc.).

[0251] "Real-time feedback" refers to advice and suggestions provided immediately in response to user input and behavioral data.

[0252] A "health risk" refers to the likelihood of a particular health problem occurring.

[0253] "Improvements" are specific suggestions or courses of action to reduce specific health risks or improve health status.

[0254] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[0255] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0256] Data collection and input processing

[0257] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information on lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0258] Receiving and analyzing data

[0259] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" or "dietary imbalance."

[0260] Generate a health management plan

[0261] The server sends the analysis results to a generative AI model, which uses deep learning technology to generate an optimal health management plan for each user based on the data. For example, a user at risk of high blood pressure will be recommended a low-salt diet plan and regular aerobic exercise. Additionally, a user at risk of sleep deprivation will be recommended specific methods for increasing their sleep time.

[0262] Incorporating an emotion engine

[0263] Additionally, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[0264] Plan provision and explanation

[0265] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the generated plan using an expert model to make it easy for the user to understand. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[0266] Feedback and Improvement Suggestions

[0267] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0268] Examples and prompts

[0269] Example 1: Proposal for hypertension risk

[0270] Data collected: Blood pressure 140 / 90, exercise amount (exercise once a week)

[0271] Analysis results: Risk of hypertension

[0272] Suggestion: "To lower your blood pressure, incorporate aerobic exercise three times a week. Also, limit your salt intake."

[0273] Example 2: How to deal with lack of sleep

[0274] Data collected: Average sleep time: 4 hours

[0275] Analysis result: lack of sleep

[0276] Suggestion: "The ideal amount of sleep is 7-8 hours. Get into the habit of going to bed at the same time every day. Stretching before bed is effective for relaxation."

[0277] Example prompts

[0278] Sample prompt 1: "Enter the user's blood pressure data and weekly exercise frequency, and suggest the optimal health management plan for this user."

[0279] Sample prompt 2: "Based on the user's sleep data, generate improvement measures for users who are sleep deprived."

[0280] The system provided by this invention can generate an optimal health management plan based on the user's health data and emotional state and provide feedback in real time, enabling users to continuously manage their health according to their individual circumstances and supporting the maintenance and improvement of their health.

[0281] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0282] Step 1: User Data Entry

[0283] Specific operation: The user uses a smartphone or computer to enter health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle data (e.g., diet, exercise, sleep time) into the application form.

[0284] Input: Health checkup result data and lifestyle habits data.

[0285] Output: Send health check result data and lifestyle habit data to the server.

[0286] Step 2: Data reception and storage by the server

[0287] Specific operation: The server receives the data sent by the user as an HTTP request, parses it in JSON format, and saves the parsed data in a database along with the user ID and timestamp.

[0288] Input: Health checkup result data and lifestyle habit data submitted by the user.

[0289] Output: Parsed data stored in a database.

[0290] Step 3: Data analysis by the server

[0291] How it works: The analysis module retrieves the necessary data from the database using SQL queries, which are then analyzed using statistical methods and machine learning algorithms to identify risk factors, such as "risk of high blood pressure" or "unbalanced diet."

[0292] Input: Health checkup result data and lifestyle habit data stored in the database.

[0293] Output: Health risk factors as analysis results.

[0294] Step 4: Server sends data to the generative AI model

[0295] Specific operation: The server sends the analysis results, such as health risk factors, in JSON format to the generative AI model, which receives a POST request using the REST API.

[0296] Input: Health risk factor analysis results.

[0297] Output: The analysis results sent to the generative AI model.

[0298] Step 5: Generative AI model generates health management plan

[0299] How it works: The generative AI model uses deep learning techniques to generate a personalized health management plan based on the analysis results it receives. For example, this plan may include a low-salt diet plan and aerobic exercise recommendations for users at risk of high blood pressure.

[0300] Input: Analysis result data.

[0301] Output: Health care plan.

[0302] Step 6: Analyzing the user's emotional state with the emotion engine

[0303] How it works: The emotion engine analyzes facial expressions and tone of voice through the camera and microphone while the user is using the device, and the analysis results are sent to the server in real time.

[0304] Input: User's facial expression and voice data.

[0305] Output: Emotional state analysis result.

[0306] Step 7: Server sends plan and description

[0307] Specific operation: The server receives the health management plan generated by the generative AI model, generates an explanation for the plan using the expert model, and then integrates the plan and explanation and sends them to the user's device.

[0308] Input: Description of health care plan and specialist model.

[0309] Output: Health management plan and explanation sent to user's device.

[0310] Step 8: User enters and submits behavioral data

[0311] How it works: Users enter their daily exercise and food logs through the application, and automatically collect sleep data from devices such as smartwatches.

[0312] Input: Exercise log, food record, sleep data.

[0313] Output: Behavioral data sent to the server.

[0314] Step 9: Server feedback and improvement suggestions

[0315] Specific actions: The server uses the analysis module to analyze new behavioral data and generate real-time feedback. The generative AI model is retrained based on the new data to predict future health risks and suggest specific improvement measures.

[0316] Input: Behavioral data.

[0317] Output: Real-time feedback and remedial measures for health risks.

[0318] (Application example 2)

[0319] 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."

[0320] Conventional health management systems analyze users' health checkup results and lifestyle data, but do not provide advice that takes into account their emotional state. This makes it difficult to provide effective health management plans to users who are under the influence of stress or emotions. It is also difficult to instantly provide optimal advice to users in physical stores. This has led to a demand for detailed responses tailored to individual health and emotional states.

[0321] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to analyze the user's emotional state, and means for providing additional advice based on the emotional state. This enables comprehensive health management that takes into account not only the user's health state but also their emotional state.

[0322] "Health checkup results" refers to data obtained as a result of a diagnosis a user receives at a medical institution or testing facility, and includes information about the user's physical health status, such as blood pressure, cholesterol levels, and blood sugar levels.

[0323] "Lifestyle data" refers to data related to the user's daily life, and includes information such as dietary habits, amount of exercise, and sleep duration.

[0324] A "generative AI model" refers to an algorithm or program that uses machine learning and artificial intelligence technology to generate optimal health management plans based on analyzed data.

[0325] An "emotion engine" refers to a system or software that uses technologies such as facial recognition and voice analysis to detect and analyze a user's emotional state.

[0326] "Expert model" refers to an algorithm or program that provides commentary on the generated plan based on expert knowledge and experience.

[0327] "Behavioral data" refers to data related to the user's daily activities, including exercise logs, dietary details, sleep data, and the like.

[0328] "Feedback" refers to specific advice or suggestions provided to users based on the analysis results and generated plans.

[0329] "Emotional state" indicates the user's current feelings and psychological state, and refers to information including emotions such as stress, joy, and sadness.

[0330] This invention relates to a system that generates and provides an optimal health management plan using a user's health checkup results, lifestyle data, and emotional state. This system consists of a user's terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0331] First, the user uses a device such as a smartphone or tablet to input their health checkup results and lifestyle data. For example, they can input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as information on lifestyle habits such as diet, exercise, and sleep duration. This data is then sent from the device to the server.

[0332] The server stores the received health checkup results and lifestyle data in a database. The data analysis module then analyzes the data to identify the user's health risk factors. For example, risk factors may include "risk of high blood pressure" or "dietary imbalance." These analysis results are sent to a generative AI model, which generates an optimal health management plan for each user based on the identified risk factors.

[0333] The generated health management plan is then sent back to the user's device from the server. Furthermore, an expert model is used to add commentary to the generated plan, making it easier for the user to understand and implement the plan. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[0334] Meanwhile, the emotion engine uses the device's built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this and add relaxation methods and advice for improving mood to the plan. Specifically, it will make suggestions such as, "Listening to music is good for relaxation."

[0335] The system also collects daily behavioral data from users to support ongoing health management. This behavioral data includes exercise logs, dietary habits, and sleep data. Based on this data, the generative AI model provides immediate feedback to users, predicts future health risks, and suggests specific improvement measures. For example, specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's a good idea to include foods high in dietary fiber in your breakfast" are provided.

[0336] As described above, the present invention provides an individualized optimal health management plan based on the user's health condition and emotional state, and supports the user in maintaining their health continuously.

[0337] Examples and prompts

[0338] As a concrete example, consider a scenario in which a user uses a "health management advisor" application while shopping in a physical store. The user inputs their health checkup results and lifestyle habits into their smartphone, and the system analyzes their emotional state while shopping in the store. For example, the system might suggest, "We recommend a low-salt salad for dinner tonight. Also, how about some herbal tea to help you relax?"

[0339] An example prompt is:

[0340] "Generate an optimal health management plan based on the user's health checkup results and lifestyle data. Also, include advice on how to relax, as the user's emotional state is stressed."

[0341] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0342] Step 1:

[0343] Users use devices such as smartphones or tablets to input their health checkup results and lifestyle data. This input includes health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as dietary details, exercise volume, and sleep duration. This data is sent to the server in a standardized format such as JSON.

[0344] Step 2:

[0345] The server receives the health checkup results and lifestyle habit data sent by the user and stores them in a database. At this time, it validates that the data format is correct. For example, it checks whether numerical data has been entered in the correct format. If the entered data is correct, it is saved in the database.

[0346] Step 3:

[0347] The server passes the accumulated health checkup results and lifestyle data to the analysis module. The analysis module uses this data to identify the user's health risk factors. For example, if blood pressure is high, it will identify a "risk of high blood pressure," and if the diet is unbalanced, it will detect a "dietary imbalance." The results of the analysis are listed as risk factors.

[0348] Step 4:

[0349] The server sends the analysis results to a generative AI model, which then inputs the list of risk factors as prompts and generates an optimal health management plan. For example, it generates a low-salt meal plan for "high blood pressure risk" and a nutritionally balanced meal plan for "dietary imbalance."

[0350] Step 5:

[0351] The server sends the health management plan obtained from the generative AI model to the user's device. It also uses the expert model to generate an easy-to-understand explanation of the health management plan and provides it to the user. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" can be added.

[0352] Step 6:

[0353] Using the device's built-in camera and microphone, the emotion engine analyzes the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this.

[0354] Step 7:

[0355] The emotion engine sends the detected emotional state to a server, which receives this data and runs the generative AI model again to generate additional advice based on the emotional state, such as "We recommend listening to music to relax."

[0356] Step 8:

[0357] The server then sends the generated additional advice to the user's device, where the user can take specific actions, such as practicing yoga or listening to music to relax.

[0358] In this way, a mechanism is realized in which the entire system supports comprehensive health management that takes into account the user's health and emotional state.

[0359] 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.

[0360] 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.

[0361] 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.

[0362] [Second embodiment]

[0363] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0364] 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.

[0365] 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).

[0366] 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.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] 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."

[0375] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[0376] The entire system consists of the user's device, a server, and a generative AI model.

[0377] Data collection and input processing

[0378] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0379] Receiving and analyzing data

[0380] The server receives the health checkup results and lifestyle data sent by the user. The received data is stored in a database and passed to the analysis module. The analysis module identifies health risk factors specific to the user based on the data.

[0381] Generate a health management plan

[0382] The server sends the analysis results to the generative AI model, which then generates an optimal health management plan. For example, for users at risk of high blood pressure, the model suggests a low-salt diet plan and regular aerobic exercise. For users who are sleep-deprived, the model suggests specific ways to increase their sleep time.

[0383] Plan provision and explanation

[0384] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using the expert model to make it easy for the user to understand. The explanation is specific advice such as, "Try to eat more vegetables and fruits to limit salt in your daily diet."

[0385] Feedback and Improvement Suggestions

[0386] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0387] As a concrete example, if a user at risk of high blood pressure inputs their daily step count and dietary details into the app, the server will analyze this information, and the generative AI model will provide specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast."The system also provides continuous feedback on the practices the user has followed, suggesting further improvement measures.

[0388] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[0389] The processing flow will be explained below.

[0390] Step 1:

[0391] The user enters health data.

[0392] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[0393] Step 2:

[0394] The server receives the data.

[0395] The server receives the health checkup results and lifestyle habit data sent from the user and stores them in a database.

[0396] Step 3:

[0397] The server analyzes the data.

[0398] The server passes the data received from the database to the analysis module, which uses the data to identify the user's health risk factors and nutrient deficiencies.

[0399] Step 4:

[0400] The generative AI model receives the analysis results.

[0401] The server sends the analysis results to the generative AI model, which then generates the optimal health management plan for each user based on the data.

[0402] Step 5:

[0403] The server provides the health management plan.

[0404] The server then sends the generated health management plan to the user's device, which includes specific suggestions for diet, exercise, sleep, etc.

[0405] Step 6:

[0406] The server generates the description.

[0407] The server uses the expert model to generate an explanation for the generated health care plan and provides it to the user along with the plan. The explanation is provided in a format that is easy for the user to understand.

[0408] Step 7:

[0409] The server collects the behavioral data.

[0410] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[0411] Step 8:

[0412] The server provides feedback.

[0413] The server analyzes the collected behavioral data and provides real-time feedback to the user, including evaluation and advice for the actions the user has taken.

[0414] Step 9:

[0415] A generative AI model suggests improvements.

[0416] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific remedial measures, which are then sent to the user's device.

[0417] Example 1

[0418] 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."

[0419] While conventional health management systems partially automate the collection and analysis of data from users, they are inadequate in the continuous management of behavioral data and the provision of immediate feedback, making it difficult to generate optimal health management plans for individual users or predict future health risks. Furthermore, they lack a mechanism for providing specific explanations for the generated health management plans, making it difficult for users to properly understand and implement the plans. Furthermore, there is no method for efficiently utilizing generative AI models using prompt sentences.

[0420] 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.

[0421] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting behavioral data of the user and providing immediate feedback based on the behavior, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the collected behavioral data and immediate feedback, thereby enabling the provision of a continuous and dynamic health management plan to each individual user.

[0422] "Medical checkup results" are data indicating physiological indicators such as blood pressure, cholesterol level, and blood sugar level obtained when a user undergoes a medical checkup.

[0423] "Lifestyle data" refers to data relating to the user's daily habits, such as diet, exercise, and sleep duration.

[0424] "Behavioral data" refers to data based on the user's actual behavior, such as exercise logs, dietary content, and sleep data.

[0425] A "generative AI model" is an artificial intelligence model that analyzes acquired data and generates an optimal health management plan.

[0426] An "expert model" is an artificial intelligence model that provides specific and expert commentary on the generated health management plan.

[0427] "Immediate feedback" refers to advice and suggestions provided in real time based on behavioral data collected from users.

[0428] A "prompt sentence" is an input sentence used to give specific instructions to a generative AI model.

[0429] A "health management plan" is an optimal health management method and specific action plan created based on the user's health condition and lifestyle habits.

[0430] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users and generates and provides optimal health management plans. The entire system consists of a user's device, a server, and a generative AI model.

[0431] Users use their smartphones or PCs to input health checkup results and lifestyle data. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0432] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database on the server and passed to an analysis module. The analysis module analyzes the data to identify health risk factors specific to the user. Specifically, scripts written in Python and machine learning models are used.

[0433] The server that obtains the analysis results sends them to a generative AI model. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. Based on the analysis results, the generative AI model generates an optimal health management plan. For example, for users at risk of high blood pressure, it suggests a low-salt diet plan and regular aerobic exercise. It also suggests specific ways to increase sleep for users who are sleep-deprived.

[0434] The generated health management plan is sent from the server to the user's device. At this time, an explanation of the plan generated using the expert model is also added. The expert model provides specific advice to help the user understand the generated plan, such as "Try to eat more vegetables and fruits in your daily diet to limit salt intake."

[0435] Furthermore, the server continuously collects user behavioral data, including exercise logs, dietary details, and sleep data. Based on this data, notifications and advice are provided to users as real-time feedback. Additionally, the generative AI model analyzes this behavioral data and predicts future health risks. Specific improvement measures for predicted risks are presented to support ongoing health management.

[0436] As a concrete example, the generative AI model operates using the following prompt sentence:

[0437] User's health check results: Blood pressure 150 / 90, cholesterol 220, blood sugar 110

[0438] User's lifestyle data: 5,000 steps / day, meal contents (breakfast: toast, lunch: salad, dinner: pasta), sleep time: 6 hours

[0439] Analyze this data and suggest a health management plan that suits the user.

[0440] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[0441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0442] Step 1:

[0443] Users use their smartphones or PCs to input health checkup results and lifestyle habit data. For example, they input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as lifestyle habit data such as diet, exercise, and sleep duration. This data is sent from the device to a server. Inputs include data manually entered by the user into input forms or applications, and outputs include data sent to the server via HTTP requests.

[0444] Specific behavior:

[0445] The user opens the smartphone application and enters information such as blood pressure and dietary details according to the input form.

[0446] The input data is sent from the terminal application to the server.

[0447] Step 2:

[0448] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database on the server. The input is the data sent from the terminal that arrives at the server as an HTTP request, and the output is the health checkup results and lifestyle habit data stored in the database.

[0449] Specific behavior:

[0450] The server receives the HTTP request and analyzes the data contained in the request.

[0451] Insert the parsed data into a database (for example, by executing an INSERT statement against an SQL database).

[0452] Step 3:

[0453] The analysis module on the server retrieves data from the database and performs analysis. Based on this, health risk factors specific to the user are identified. The input is user data retrieved from the database, and the output is the analysis results of health risk factors.

[0454] Specific behavior:

[0455] The server passes the user's health check results and lifestyle habit data obtained from the database to the analysis module.

[0456] The analysis module analyzes the data using Python scripts and machine learning models.

[0457] Step 4:

[0458] The server sends the analysis results to the generative AI model and makes a request to generate an optimal health care plan. The generated health care plan is sent back to the server. The analysis results are provided as prompt sentences to the generative AI model as input, and the generated health care plan is the output.

[0459] Specific behavior:

[0460] The server creates a prompt for the generative AI model and sends it via an API request.

[0461] The generative AI model analyzes the prompt, generates an appropriate health management plan, and sends it back to the server.

[0462] Step 5:

[0463] The server sends the generated health management plan to the user's terminal. At this time, an explanation is added to the plan generated using the expert model. The input is the generated health management plan, and the output is the plan with the explanation sent to the user's terminal.

[0464] Specific behavior:

[0465] The server generates an HTTP request to transmit the health management plan to the user's terminal.

[0466] The expert model will add specific commentary to the plan and send it along with the plan.

[0467] Step 6:

[0468] The server continuously collects user behavioral data and provides immediate feedback. Furthermore, a generative AI model analyzes the behavioral data, predicts future health risks, and provides specific improvement measures. The input is behavioral data from the user's device, and the output is improvement measures based on feedback and future risk predictions.

[0469] Specific behavior:

[0470] The server periodically collects data such as step counts, meal contents, and sleep data from the user's device.

[0471] The collected data is analyzed and notifications are sent to the user as immediate feedback.

[0472] A generative AI model analyzes behavioral data to predict future health risks and provide remedial measures.

[0473] (Application example 1)

[0474] 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."

[0475] Conventional health management systems are limited to providing users with one-way information, making it difficult to provide immediate feedback on changes in users' daily lifestyles and health conditions or specific improvement measures. Furthermore, they lack ongoing support tailored to individual health risks, leaving users with little motivation to continue managing their health voluntarily. Therefore, there is a need for systems that provide optimal health management plans for individual users and support ongoing health management.

[0476] 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.

[0477] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting the user's daily behavioral data, and means for using the generative AI model to provide real-time feedback based on the collected behavioral data and generate specific improvement measures, thereby enabling continuous and real-time health management for the user.

[0478] "Medical checkup results" are the measurement results of blood pressure, cholesterol level, blood sugar level, etc. based on a medical checkup conducted at a medical institution, etc.

[0479] "Lifestyle data" refers to data related to the user's daily life, including information such as dietary habits, amount of exercise, and sleep duration.

[0480] "Analysis" refers to identifying health risk factors specific to a user based on the health checkup results and lifestyle habit data obtained.

[0481] A "generative AI model" is an artificial intelligence model that generates optimal health management plans and specific improvement measures based on analysis results.

[0482] A "health management plan" is a specific set of guidelines and advice provided by the generative AI model to help users maintain and improve their health.

[0483] An "expert model" is an artificial intelligence model that provides expert commentary on the generated health care plan.

[0484] "Feedback" refers to instant evaluations and advice provided by the generative AI model based on behavioral data provided by the user.

[0485] "Behavioral data" refers to specific data related to the user's daily lifestyle habits, and includes exercise logs, dietary details, sleep data, and the like.

[0486] "Improvements" are specific actions or measures proposed to reduce future health risks based on analysis and feedback.

[0487] This invention relates to a health management system using a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[0488] 1. Data collection and input processing

[0489] Users use their smartphones or computers to input data on their health checkup results and lifestyle habits. Health checkup results include blood pressure, cholesterol levels, blood sugar levels, and other measurement results. Lifestyle information includes dietary details, exercise levels, and sleep duration. This information is sent from the user's device to a server. A secure communication protocol such as HTTPS is used for transmission.

[0490] 2. Data Receipt and Analysis

[0491] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database (e.g., PostgreSQL) and passed to an analysis module (e.g., Python, Pandas). The analysis module identifies health risk factors specific to the user based on the data.

[0492] 3. Generate a health management plan

[0493] The server sends the analysis results to a generative AI model (e.g., GPT-3), which then generates an optimal health management plan. The plan includes specific advice based on the user's health checkup results and lifestyle habits.

[0494] 4. Providing and explaining the plan

[0495] The generated health management plan is sent from the server to the user's smartphone. In addition, an expert model installed separately from the generating AI model provides commentary on the generated plan. The expert model provides specific advice, such as "Try to eat more vegetables and fruits to reduce salt in your daily diet."

[0496] 5. Feedback and Improvement Suggestions

[0497] The server continuously collects the user's daily behavioral data. This behavioral data includes exercise logs, dietary habits, sleep data, etc. This data is obtained from various sensors on the smartphone (GPS, accelerometer, etc.). Based on the collected data, the generative AI model provides immediate feedback. For example, it gives specific advice such as, "You haven't reached your step goal today. Try walking a little longer."

[0498] Furthermore, the generative AI model predicts future health risks and provides specific recommendations for improvement, such as "Aim for 5,000 steps a day" and "Include foods high in fiber for breakfast."

[0499] Examples of prompt statements

[0500] Below are some example prompts that can be presented to the generative AI model based on user-provided data.

[0501] The user's health check results are: Blood pressure: 130 / 85, Cholesterol: 210, Blood sugar: 100.

[0502] Lifestyle data is as follows: Diet: high calorie, low fiber, exercise: low, sleep: 6 hours.

[0503] Based on this data, generate an optimal health management plan for users at risk for high blood pressure and high cholesterol, including specific recommendations.

[0504] As described above, this system provides optimal health management plans tailored to each user's individual circumstances and supports continuous health management.

[0505] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0506] Step 1:

[0507] Users use their smartphones or computers to input their health checkup results and lifestyle data. Specifically, users enter health checkup results such as blood pressure, cholesterol levels, and blood sugar levels into the application form, and provide lifestyle data such as diet, exercise, and sleep time. This data is sent to the server via HTTPS.

[0508] Step 2:

[0509] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database (e.g., PostgreSQL), allowing the data to be stored permanently.

[0510] Step 3:

[0511] The server's analysis module analyzes the stored data. Specifically, it uses analysis modules (e.g., Python, Pandas) to identify health risk factors specific to the user. The data is processed by statistical analysis of blood pressure and cholesterol levels to check for abnormal values.

[0512] Step 4:

[0513] The server uses a generative AI model (e.g., GPT-3) based on the analysis results to generate an optimal health management plan. The analysis results are used as input to create a prompt for the generative AI model, which then outputs a specific health management plan. This prompt includes the user's health checkup results and lifestyle habits.

[0514] Step 5:

[0515] The generated health management plan is sent from the server to the user's smartphone. Specifically, the health management plan provided by the generative AI model is displayed in text format in the user's application. At this time, an expert model is also used to add detailed explanations to the plan.

[0516] Step 6:

[0517] The user's daily behavioral data (exercise log, dietary content, sleep data, etc.) is continuously collected from various sensors (GPS, accelerometer, etc.) on the smartphone and sent to a server. The behavioral data sent is then stored in a database.

[0518] Step 7:

[0519] The server analyzes the collected behavioral data and provides immediate feedback. Specifically, it uses a generative AI model to provide specific advice and guidance to the user based on the behavioral data. For example, the user may receive feedback such as, "You haven't reached your step goal today. Try walking a little longer." via the application.

[0520] Step 8:

[0521] Furthermore, the server predicts future health risks and generates specific improvement measures. The generative AI model suggests improvement measures such as "Aim for 5,000 steps a day" or "It's a good idea to include foods high in dietary fiber in your breakfast." These suggestions are also generated using prompt text and provided to the user.

[0522] 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.

[0523] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[0524] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0525] Data collection and input processing

[0526] Users use their smartphones or computers to input data about their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information about lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0527] Receiving and analyzing data

[0528] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" and "dietary imbalance."

[0529] Generate a health management plan

[0530] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be suggested a low-salt diet plan and regular aerobic exercise. Similarly, a user at risk of sleep deprivation would be suggested specific ways to increase their sleep time.

[0531] Incorporating an emotion engine

[0532] Furthermore, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[0533] Plan provision and explanation

[0534] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using an expert model to make it easy for the user to understand. The explanation provides specific advice, such as "On stressful days, try deep breathing or yoga to relax."

[0535] Feedback and Improvement Suggestions

[0536] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0537] For example, if a user at risk of high blood pressure enters their daily step count and dietary details into the app, the server analyzes this information, and the generative AI model provides specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast." Also, if the user is feeling stressed, the emotion engine will detect this and make suggestions such as "It's good to listen to music to relax."

[0538] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual situation and emotional state of the user, enabling continuous health management.

[0539] The processing flow will be explained below.

[0540] Step 1:

[0541] The user enters health data.

[0542] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[0543] Step 2:

[0544] The server receives the data.

[0545] The server receives the health checkup results and lifestyle habit data sent from the user and stores the data in a database.

[0546] Step 3:

[0547] The server analyzes the data.

[0548] The server passes the data received from the database to the analysis module, which then uses the data to identify the user's health risk factors and nutrient deficiencies. For example, if blood pressure is 140 / 90 or higher, it identifies the user as being at risk of high blood pressure.

[0549] Step 4:

[0550] The generative AI model receives the analysis results.

[0551] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be recommended to take a low-salt diet and engage in regular aerobic exercise.

[0552] Step 5:

[0553] The emotion engine retrieves the emotion data.

[0554] While the user is using the device, the emotion engine uses the camera and microphone to perform facial recognition and voice analysis to detect the user's emotional state (e.g., stress level, happiness).

[0555] Step 6:

[0556] The server receives and analyzes the emotion data.

[0557] The emotion data acquired by the emotion engine is sent to a server, which analyzes it and identifies whether the user is feeling stressed or comfortable.

[0558] Step 7:

[0559] A generative AI model takes emotional data into account to tailor a health plan.

[0560] The generative AI model takes emotional data into account to tailor the health plan, for example suggesting relaxation techniques if stress levels are high and adding additional advice to improve mood.

[0561] Step 8:

[0562] The server provides the health management plan.

[0563] The generated health management plan is sent to the user's device. The plan includes specific suggestions for diet, exercise, and sleep, as well as emotional relaxation techniques. For example, the plan might suggest "eating more vegetables every day and incorporating walking into your daily routine."

[0564] Step 9:

[0565] The server generates the description.

[0566] The server uses the expert model to generate commentary for the generated health management plan and provides it to the user along with the plan, such as "Eating a low-salt diet can reduce the risk of high blood pressure."

[0567] Step 10:

[0568] The server collects the behavioral data.

[0569] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[0570] Step 11:

[0571] The server provides feedback.

[0572] The server analyzes the collected behavioral data and provides the user with immediate feedback, such as "Your exercise volume today is below your goal" or "You should incorporate more balance into your diet."

[0573] Step 12:

[0574] A generative AI model suggests improvements.

[0575] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific improvement measures. The proposed improvement measures are sent to the user's device. For example, they could be specific goals such as "Aim for 5,000 steps a day" or suggestions such as "When stress levels rise, we recommend taking deep breaths or listening to music."

[0576] Example 2

[0577] 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."

[0578] In recent years, lifestyle-related diseases and physical and mental health problems have been on the rise, but conventional health management systems can only make simple suggestions based on individual health checkup results and lifestyle data, making it difficult to provide comprehensive health management that takes into account the user's emotional state.In addition, there is a demand for real-time feedback and immediate improvement suggestions, but achieving this requires advanced technology.

[0579] 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 acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to sense the user's emotional state and provide feedback based on that state, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the provided feedback. This enables comprehensive and specific health management based on the user's individual health data and emotional state.

[0580] "Physical examination results" are the results of medical tests to evaluate the user's physical condition and health status.

[0581] "Lifestyle habit data" is information about the user's habits in daily life, such as exercise, diet, and sleep.

[0582] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate optimal health management plans and recommendations for users.

[0583] A "generated health management plan" is a specific proposal or plan for improving or maintaining a user's individual health, created by the generative AI model based on the analysis results.

[0584] "Emotional state" refers to the user's current psychological state, mood, and emotional state.

[0585] An "emotion engine" is a system or software that analyzes a user's emotional state and provides feedback and suggestions based on that analysis.

[0586] An "expert model" is an algorithm or system that provides expert knowledge-based commentary or additional information to the generated health management plan.

[0587] "Behavioral data" is data relating to the user's specific daily activities (exercise, meals, sleep, etc.).

[0588] "Real-time feedback" refers to advice and suggestions provided immediately in response to user input and behavioral data.

[0589] A "health risk" refers to the likelihood of a particular health problem occurring.

[0590] "Improvements" are specific suggestions or courses of action to reduce specific health risks or improve health status.

[0591] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[0592] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0593] Data collection and input processing

[0594] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information on lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0595] Receiving and analyzing data

[0596] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" or "dietary imbalance."

[0597] Generate a health management plan

[0598] The server sends the analysis results to a generative AI model, which uses deep learning technology to generate an optimal health management plan for each user based on the data. For example, a user at risk of high blood pressure will be recommended a low-salt diet plan and regular aerobic exercise. Additionally, a user at risk of sleep deprivation will be recommended specific methods for increasing their sleep time.

[0599] Incorporating an emotion engine

[0600] Additionally, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[0601] Plan provision and explanation

[0602] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the generated plan using an expert model to make it easy for the user to understand. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[0603] Feedback and Improvement Suggestions

[0604] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0605] Examples and prompts

[0606] Example 1: Proposal for hypertension risk

[0607] Data collected: Blood pressure 140 / 90, exercise amount (exercise once a week)

[0608] Analysis results: Risk of hypertension

[0609] Suggestion: "To lower your blood pressure, incorporate aerobic exercise three times a week. Also, limit your salt intake."

[0610] Example 2: How to deal with lack of sleep

[0611] Data collected: Average sleep time: 4 hours

[0612] Analysis result: lack of sleep

[0613] Suggestion: "The ideal amount of sleep is 7-8 hours. Get into the habit of going to bed at the same time every day. Stretching before bed is effective for relaxation."

[0614] Example prompts

[0615] Sample prompt 1: "Enter the user's blood pressure data and weekly exercise frequency, and suggest the optimal health management plan for this user."

[0616] Sample prompt 2: "Based on the user's sleep data, generate improvement measures for users who are sleep deprived."

[0617] The system provided by this invention can generate an optimal health management plan based on the user's health data and emotional state and provide feedback in real time, enabling users to continuously manage their health according to their individual circumstances and supporting the maintenance and improvement of their health.

[0618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0619] Step 1: User Data Entry

[0620] Specific operation: The user uses a smartphone or computer to enter health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle data (e.g., diet, exercise, sleep time) into the application form.

[0621] Input: Health checkup result data and lifestyle habits data.

[0622] Output: Send health check result data and lifestyle habit data to the server.

[0623] Step 2: Data reception and storage by the server

[0624] Specific operation: The server receives the data sent by the user as an HTTP request, parses it in JSON format, and saves the parsed data in a database along with the user ID and timestamp.

[0625] Input: Health checkup result data and lifestyle habit data submitted by the user.

[0626] Output: Parsed data stored in a database.

[0627] Step 3: Data analysis by the server

[0628] How it works: The analysis module retrieves the necessary data from the database using SQL queries, which are then analyzed using statistical methods and machine learning algorithms to identify risk factors, such as "risk of high blood pressure" or "unbalanced diet."

[0629] Input: Health checkup result data and lifestyle habit data stored in the database.

[0630] Output: Health risk factors as analysis results.

[0631] Step 4: Server sends data to the generative AI model

[0632] Specific operation: The server sends the analysis results, such as health risk factors, in JSON format to the generative AI model, which receives a POST request using the REST API.

[0633] Input: Health risk factor analysis results.

[0634] Output: The analysis results sent to the generative AI model.

[0635] Step 5: Generative AI model generates health management plan

[0636] How it works: The generative AI model uses deep learning techniques to generate a personalized health management plan based on the analysis results it receives. For example, this plan may include a low-salt diet plan and aerobic exercise recommendations for users at risk of high blood pressure.

[0637] Input: Analysis result data.

[0638] Output: Health care plan.

[0639] Step 6: Analyzing the user's emotional state with the emotion engine

[0640] How it works: The emotion engine analyzes facial expressions and tone of voice through the camera and microphone while the user is using the device, and the analysis results are sent to the server in real time.

[0641] Input: User's facial expression and voice data.

[0642] Output: Emotional state analysis result.

[0643] Step 7: Server sends plan and description

[0644] Specific operation: The server receives the health management plan generated by the generative AI model, generates an explanation for the plan using the expert model, and then integrates the plan and explanation and sends them to the user's device.

[0645] Input: Description of health care plan and specialist model.

[0646] Output: Health management plan and explanation sent to user's device.

[0647] Step 8: User enters and submits behavioral data

[0648] How it works: Users enter their daily exercise and food logs through the application, and automatically collect sleep data from devices such as smartwatches.

[0649] Input: Exercise log, food record, sleep data.

[0650] Output: Behavioral data sent to the server.

[0651] Step 9: Server feedback and improvement suggestions

[0652] Specific actions: The server uses the analysis module to analyze new behavioral data and generate real-time feedback. The generative AI model is retrained based on the new data to predict future health risks and suggest specific improvement measures.

[0653] Input: Behavioral data.

[0654] Output: Real-time feedback and remedial measures for health risks.

[0655] (Application example 2)

[0656] 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."

[0657] Conventional health management systems analyze users' health checkup results and lifestyle data, but do not provide advice that takes into account their emotional state. This makes it difficult to provide effective health management plans to users who are under the influence of stress or emotions. It is also difficult to instantly provide optimal advice to users in physical stores. This has led to a demand for detailed responses tailored to individual health and emotional states.

[0658] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to analyze the user's emotional state, and means for providing additional advice based on the emotional state. This enables comprehensive health management that takes into account not only the user's health state but also their emotional state.

[0659] "Health checkup results" refers to data obtained as a result of a diagnosis a user receives at a medical institution or testing facility, and includes information about the user's physical health status, such as blood pressure, cholesterol levels, and blood sugar levels.

[0660] "Lifestyle data" refers to data related to the user's daily life, and includes information such as dietary habits, amount of exercise, and sleep duration.

[0661] A "generative AI model" refers to an algorithm or program that uses machine learning and artificial intelligence technology to generate optimal health management plans based on analyzed data.

[0662] An "emotion engine" refers to a system or software that uses technologies such as facial recognition and voice analysis to detect and analyze a user's emotional state.

[0663] "Expert model" refers to an algorithm or program that provides commentary on the generated plan based on expert knowledge and experience.

[0664] "Behavioral data" refers to data related to the user's daily activities, including exercise logs, dietary details, sleep data, and the like.

[0665] "Feedback" refers to specific advice or suggestions provided to users based on the analysis results and generated plans.

[0666] "Emotional state" indicates the user's current feelings and psychological state, and refers to information including emotions such as stress, joy, and sadness.

[0667] This invention relates to a system that generates and provides an optimal health management plan using a user's health checkup results, lifestyle data, and emotional state. This system consists of a user's terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0668] First, the user uses a device such as a smartphone or tablet to input their health checkup results and lifestyle data. For example, they can input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as information on lifestyle habits such as diet, exercise, and sleep duration. This data is then sent from the device to the server.

[0669] The server stores the received health checkup results and lifestyle data in a database. The data analysis module then analyzes the data to identify the user's health risk factors. For example, risk factors may include "risk of high blood pressure" or "dietary imbalance." These analysis results are sent to a generative AI model, which generates an optimal health management plan for each user based on the identified risk factors.

[0670] The generated health management plan is then sent back to the user's device from the server. Furthermore, an expert model is used to add commentary to the generated plan, making it easier for the user to understand and implement the plan. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[0671] Meanwhile, the emotion engine uses the device's built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this and add relaxation methods and advice for improving mood to the plan. Specifically, it will make suggestions such as, "Listening to music is good for relaxation."

[0672] The system also collects daily behavioral data from users to support ongoing health management. This behavioral data includes exercise logs, dietary habits, and sleep data. Based on this data, the generative AI model provides immediate feedback to users, predicts future health risks, and suggests specific improvement measures. For example, specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's a good idea to include foods high in dietary fiber in your breakfast" are provided.

[0673] As described above, the present invention provides an individualized optimal health management plan based on the user's health condition and emotional state, and supports the user in maintaining their health continuously.

[0674] Examples and prompts

[0675] As a concrete example, consider a scenario in which a user uses a "health management advisor" application while shopping in a physical store. The user inputs their health checkup results and lifestyle habits into their smartphone, and the system analyzes their emotional state while shopping in the store. For example, the system might suggest, "We recommend a low-salt salad for dinner tonight. Also, how about some herbal tea to help you relax?"

[0676] An example prompt is:

[0677] "Generate an optimal health management plan based on the user's health checkup results and lifestyle data. Also, include advice on how to relax, as the user's emotional state is stressed."

[0678] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0679] Step 1:

[0680] Users use devices such as smartphones or tablets to input their health checkup results and lifestyle data. This input includes health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as dietary details, exercise volume, and sleep duration. This data is sent to the server in a standardized format such as JSON.

[0681] Step 2:

[0682] The server receives the health checkup results and lifestyle habit data sent by the user and stores them in a database. At this time, it validates that the data format is correct. For example, it checks whether numerical data has been entered in the correct format. If the entered data is correct, it is saved in the database.

[0683] Step 3:

[0684] The server passes the accumulated health checkup results and lifestyle data to the analysis module. The analysis module uses this data to identify the user's health risk factors. For example, if blood pressure is high, it will identify a "risk of high blood pressure," and if the diet is unbalanced, it will detect a "dietary imbalance." The results of the analysis are listed as risk factors.

[0685] Step 4:

[0686] The server sends the analysis results to a generative AI model, which then inputs the list of risk factors as prompts and generates an optimal health management plan. For example, it generates a low-salt meal plan for "high blood pressure risk" and a nutritionally balanced meal plan for "dietary imbalance."

[0687] Step 5:

[0688] The server sends the health management plan obtained from the generative AI model to the user's device. It also uses the expert model to generate an easy-to-understand explanation of the health management plan and provides it to the user. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" can be added.

[0689] Step 6:

[0690] Using the device's built-in camera and microphone, the emotion engine analyzes the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this.

[0691] Step 7:

[0692] The emotion engine sends the detected emotional state to a server, which receives this data and runs the generative AI model again to generate additional advice based on the emotional state, such as "We recommend listening to music to relax."

[0693] Step 8:

[0694] The server then sends the generated additional advice to the user's device, where the user can take specific actions, such as practicing yoga or listening to music to relax.

[0695] In this way, a mechanism is realized in which the entire system supports comprehensive health management that takes into account the user's health and emotional state.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] [Third embodiment]

[0700] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0701] 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.

[0702] 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).

[0703] 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.

[0704] 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.

[0705] 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).

[0706] 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.

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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."

[0712] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[0713] The entire system consists of the user's device, a server, and a generative AI model.

[0714] Data collection and input processing

[0715] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0716] Receiving and analyzing data

[0717] The server receives the health checkup results and lifestyle data sent by the user. The received data is stored in a database and passed to the analysis module. The analysis module identifies health risk factors specific to the user based on the data.

[0718] Generate a health management plan

[0719] The server sends the analysis results to the generative AI model, which then generates an optimal health management plan. For example, for users at risk of high blood pressure, the model suggests a low-salt diet plan and regular aerobic exercise. For users who are sleep-deprived, the model suggests specific ways to increase their sleep time.

[0720] Plan provision and explanation

[0721] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using the expert model to make it easy for the user to understand. The explanation is specific advice such as, "Try to eat more vegetables and fruits to limit salt in your daily diet."

[0722] Feedback and Improvement Suggestions

[0723] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0724] As a concrete example, if a user at risk of high blood pressure inputs their daily step count and dietary details into the app, the server will analyze this information, and the generative AI model will provide specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast."The system also provides continuous feedback on the practices the user has followed, suggesting further improvement measures.

[0725] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[0726] The processing flow will be explained below.

[0727] Step 1:

[0728] The user enters health data.

[0729] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[0730] Step 2:

[0731] The server receives the data.

[0732] The server receives the health checkup results and lifestyle habit data sent from the user and stores them in a database.

[0733] Step 3:

[0734] The server analyzes the data.

[0735] The server passes the data received from the database to the analysis module, which uses the data to identify the user's health risk factors and nutrient deficiencies.

[0736] Step 4:

[0737] The generative AI model receives the analysis results.

[0738] The server sends the analysis results to the generative AI model, which then generates the optimal health management plan for each user based on the data.

[0739] Step 5:

[0740] The server provides the health management plan.

[0741] The server then sends the generated health management plan to the user's device, which includes specific suggestions for diet, exercise, sleep, etc.

[0742] Step 6:

[0743] The server generates the description.

[0744] The server uses the expert model to generate an explanation for the generated health care plan and provides it to the user along with the plan. The explanation is provided in a format that is easy for the user to understand.

[0745] Step 7:

[0746] The server collects the behavioral data.

[0747] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[0748] Step 8:

[0749] The server provides feedback.

[0750] The server analyzes the collected behavioral data and provides real-time feedback to the user, including evaluation and advice for the actions the user has taken.

[0751] Step 9:

[0752] A generative AI model suggests improvements.

[0753] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific remedial measures, which are then sent to the user's device.

[0754] Example 1

[0755] 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."

[0756] While conventional health management systems partially automate the collection and analysis of data from users, they are inadequate in the continuous management of behavioral data and the provision of immediate feedback, making it difficult to generate optimal health management plans for individual users or predict future health risks. Furthermore, they lack a mechanism for providing specific explanations for the generated health management plans, making it difficult for users to properly understand and implement the plans. Furthermore, there is no method for efficiently utilizing generative AI models using prompt sentences.

[0757] 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.

[0758] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting behavioral data of the user and providing immediate feedback based on the behavior, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the collected behavioral data and immediate feedback, thereby enabling the provision of a continuous and dynamic health management plan to each individual user.

[0759] "Medical checkup results" are data indicating physiological indicators such as blood pressure, cholesterol level, and blood sugar level obtained when a user undergoes a medical checkup.

[0760] "Lifestyle data" refers to data relating to the user's daily habits, such as diet, exercise, and sleep duration.

[0761] "Behavioral data" refers to data based on the user's actual behavior, such as exercise logs, dietary content, and sleep data.

[0762] A "generative AI model" is an artificial intelligence model that analyzes acquired data and generates an optimal health management plan.

[0763] An "expert model" is an artificial intelligence model that provides specific and expert commentary on the generated health management plan.

[0764] "Immediate feedback" refers to advice and suggestions provided in real time based on behavioral data collected from users.

[0765] A "prompt sentence" is an input sentence used to give specific instructions to a generative AI model.

[0766] A "health management plan" is an optimal health management method and specific action plan created based on the user's health condition and lifestyle habits.

[0767] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users and generates and provides optimal health management plans. The entire system consists of a user's device, a server, and a generative AI model.

[0768] Users use their smartphones or PCs to input health checkup results and lifestyle data. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0769] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database on the server and passed to an analysis module. The analysis module analyzes the data to identify health risk factors specific to the user. Specifically, scripts written in Python and machine learning models are used.

[0770] The server that obtains the analysis results sends them to a generative AI model. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. Based on the analysis results, the generative AI model generates an optimal health management plan. For example, for users at risk of high blood pressure, it suggests a low-salt diet plan and regular aerobic exercise. It also suggests specific ways to increase sleep for users who are sleep-deprived.

[0771] The generated health management plan is sent from the server to the user's device. At this time, an explanation of the plan generated using the expert model is also added. The expert model provides specific advice to help the user understand the generated plan, such as "Try to eat more vegetables and fruits in your daily diet to limit salt intake."

[0772] Furthermore, the server continuously collects user behavioral data, including exercise logs, dietary details, and sleep data. Based on this data, notifications and advice are provided to users as real-time feedback. Additionally, the generative AI model analyzes this behavioral data and predicts future health risks. Specific improvement measures for predicted risks are presented to support ongoing health management.

[0773] As a concrete example, the generative AI model operates using the following prompt sentence:

[0774] User's health check results: Blood pressure 150 / 90, cholesterol 220, blood sugar 110

[0775] User's lifestyle data: 5,000 steps / day, meal contents (breakfast: toast, lunch: salad, dinner: pasta), sleep time: 6 hours

[0776] Analyze this data and suggest a health management plan that suits the user.

[0777] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[0778] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0779] Step 1:

[0780] Users use their smartphones or PCs to input health checkup results and lifestyle habit data. For example, they input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as lifestyle habit data such as diet, exercise, and sleep duration. This data is sent from the device to a server. Inputs include data manually entered by the user into input forms or applications, and outputs include data sent to the server via HTTP requests.

[0781] Specific behavior:

[0782] The user opens the smartphone application and enters information such as blood pressure and dietary details according to the input form.

[0783] The input data is sent from the terminal application to the server.

[0784] Step 2:

[0785] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database on the server. The input is the data sent from the terminal that arrives at the server as an HTTP request, and the output is the health checkup results and lifestyle habit data stored in the database.

[0786] Specific behavior:

[0787] The server receives the HTTP request and analyzes the data contained in the request.

[0788] Insert the parsed data into a database (for example, by executing an INSERT statement against an SQL database).

[0789] Step 3:

[0790] The analysis module on the server retrieves data from the database and performs analysis. Based on this, health risk factors specific to the user are identified. The input is user data retrieved from the database, and the output is the analysis results of health risk factors.

[0791] Specific behavior:

[0792] The server passes the user's health check results and lifestyle habit data obtained from the database to the analysis module.

[0793] The analysis module analyzes the data using Python scripts and machine learning models.

[0794] Step 4:

[0795] The server sends the analysis results to the generative AI model and makes a request to generate an optimal health care plan. The generated health care plan is sent back to the server. The analysis results are provided as prompt sentences to the generative AI model as input, and the generated health care plan is the output.

[0796] Specific behavior:

[0797] The server creates a prompt for the generative AI model and sends it via an API request.

[0798] The generative AI model analyzes the prompt, generates an appropriate health management plan, and sends it back to the server.

[0799] Step 5:

[0800] The server sends the generated health management plan to the user's terminal. At this time, an explanation is added to the plan generated using the expert model. The input is the generated health management plan, and the output is the plan with the explanation sent to the user's terminal.

[0801] Specific behavior:

[0802] The server generates an HTTP request to transmit the health management plan to the user's terminal.

[0803] The expert model will add specific commentary to the plan and send it along with the plan.

[0804] Step 6:

[0805] The server continuously collects user behavioral data and provides immediate feedback. Furthermore, a generative AI model analyzes the behavioral data, predicts future health risks, and provides specific improvement measures. The input is behavioral data from the user's device, and the output is improvement measures based on feedback and future risk predictions.

[0806] Specific behavior:

[0807] The server periodically collects data such as step counts, meal contents, and sleep data from the user's device.

[0808] The collected data is analyzed and notifications are sent to the user as immediate feedback.

[0809] A generative AI model analyzes behavioral data to predict future health risks and provide remedial measures.

[0810] (Application example 1)

[0811] 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."

[0812] Conventional health management systems are limited to providing users with one-way information, making it difficult to provide immediate feedback on changes in users' daily lifestyles and health conditions or specific improvement measures. Furthermore, they lack ongoing support tailored to individual health risks, leaving users with little motivation to continue managing their health voluntarily. Therefore, there is a need for systems that provide optimal health management plans for individual users and support ongoing health management.

[0813] 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.

[0814] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting the user's daily behavioral data, and means for using the generative AI model to provide real-time feedback based on the collected behavioral data and generate specific improvement measures, thereby enabling continuous and real-time health management for the user.

[0815] "Medical checkup results" are the measurement results of blood pressure, cholesterol level, blood sugar level, etc. based on a medical checkup conducted at a medical institution, etc.

[0816] "Lifestyle data" refers to data related to the user's daily life, including information such as dietary habits, amount of exercise, and sleep duration.

[0817] "Analysis" refers to identifying health risk factors specific to a user based on the health checkup results and lifestyle habit data obtained.

[0818] A "generative AI model" is an artificial intelligence model that generates optimal health management plans and specific improvement measures based on analysis results.

[0819] A "health management plan" is a specific set of guidelines and advice provided by the generative AI model to help users maintain and improve their health.

[0820] An "expert model" is an artificial intelligence model that provides expert commentary on the generated health care plan.

[0821] "Feedback" refers to instant evaluations and advice provided by the generative AI model based on behavioral data provided by the user.

[0822] "Behavioral data" refers to specific data related to the user's daily lifestyle habits, and includes exercise logs, dietary details, sleep data, and the like.

[0823] "Improvements" are specific actions or measures proposed to reduce future health risks based on analysis and feedback.

[0824] This invention relates to a health management system using a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[0825] 1. Data collection and input processing

[0826] Users use their smartphones or computers to input data on their health checkup results and lifestyle habits. Health checkup results include blood pressure, cholesterol levels, blood sugar levels, and other measurement results. Lifestyle information includes dietary details, exercise levels, and sleep duration. This information is sent from the user's device to a server. A secure communication protocol such as HTTPS is used for transmission.

[0827] 2. Data Receipt and Analysis

[0828] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database (e.g., PostgreSQL) and passed to an analysis module (e.g., Python, Pandas). The analysis module identifies health risk factors specific to the user based on the data.

[0829] 3. Generate a health management plan

[0830] The server sends the analysis results to a generative AI model (e.g., GPT-3), which then generates an optimal health management plan. The plan includes specific advice based on the user's health checkup results and lifestyle habits.

[0831] 4. Providing and explaining the plan

[0832] The generated health management plan is sent from the server to the user's smartphone. In addition, an expert model installed separately from the generating AI model provides commentary on the generated plan. The expert model provides specific advice, such as "Try to eat more vegetables and fruits to reduce salt in your daily diet."

[0833] 5. Feedback and Improvement Suggestions

[0834] The server continuously collects the user's daily behavioral data. This behavioral data includes exercise logs, dietary habits, sleep data, etc. This data is obtained from various sensors on the smartphone (GPS, accelerometer, etc.). Based on the collected data, the generative AI model provides immediate feedback. For example, it gives specific advice such as, "You haven't reached your step goal today. Try walking a little longer."

[0835] Furthermore, the generative AI model predicts future health risks and provides specific recommendations for improvement, such as "Aim for 5,000 steps a day" and "Include foods high in fiber for breakfast."

[0836] Examples of prompt statements

[0837] Below are some example prompts that can be presented to the generative AI model based on user-provided data.

[0838] The user's health check results are: Blood pressure: 130 / 85, Cholesterol: 210, Blood sugar: 100.

[0839] Lifestyle data is as follows: Diet: high calorie, low fiber, exercise: low, sleep: 6 hours.

[0840] Based on this data, generate an optimal health management plan for users at risk for high blood pressure and high cholesterol, including specific recommendations.

[0841] As described above, this system provides optimal health management plans tailored to each user's individual circumstances and supports continuous health management.

[0842] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0843] Step 1:

[0844] Users use their smartphones or computers to input their health checkup results and lifestyle data. Specifically, users enter health checkup results such as blood pressure, cholesterol levels, and blood sugar levels into the application form, and provide lifestyle data such as diet, exercise, and sleep time. This data is sent to the server via HTTPS.

[0845] Step 2:

[0846] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database (e.g., PostgreSQL), allowing the data to be stored permanently.

[0847] Step 3:

[0848] The server's analysis module analyzes the stored data. Specifically, it uses analysis modules (e.g., Python, Pandas) to identify health risk factors specific to the user. The data is processed by statistical analysis of blood pressure and cholesterol levels to check for abnormal values.

[0849] Step 4:

[0850] The server uses a generative AI model (e.g., GPT-3) based on the analysis results to generate an optimal health management plan. The analysis results are used as input to create a prompt for the generative AI model, which then outputs a specific health management plan. This prompt includes the user's health checkup results and lifestyle habits.

[0851] Step 5:

[0852] The generated health management plan is sent from the server to the user's smartphone. Specifically, the health management plan provided by the generative AI model is displayed in text format in the user's application. At this time, an expert model is also used to add detailed explanations to the plan.

[0853] Step 6:

[0854] The user's daily behavioral data (exercise log, dietary content, sleep data, etc.) is continuously collected from various sensors (GPS, accelerometer, etc.) on the smartphone and sent to a server. The behavioral data sent is then stored in a database.

[0855] Step 7:

[0856] The server analyzes the collected behavioral data and provides immediate feedback. Specifically, it uses a generative AI model to provide specific advice and guidance to the user based on the behavioral data. For example, the user may receive feedback such as, "You haven't reached your step goal today. Try walking a little longer." via the application.

[0857] Step 8:

[0858] Furthermore, the server predicts future health risks and generates specific improvement measures. The generative AI model suggests improvement measures such as "Aim for 5,000 steps a day" or "It's a good idea to include foods high in dietary fiber in your breakfast." These suggestions are also generated using prompt text and provided to the user.

[0859] 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.

[0860] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[0861] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0862] Data collection and input processing

[0863] Users use their smartphones or computers to input data about their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information about lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0864] Receiving and analyzing data

[0865] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" and "dietary imbalance."

[0866] Generate a health management plan

[0867] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be suggested a low-salt diet plan and regular aerobic exercise. Similarly, a user at risk of sleep deprivation would be suggested specific ways to increase their sleep time.

[0868] Incorporating an emotion engine

[0869] Furthermore, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[0870] Plan provision and explanation

[0871] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using an expert model to make it easy for the user to understand. The explanation provides specific advice, such as "On stressful days, try deep breathing or yoga to relax."

[0872] Feedback and Improvement Suggestions

[0873] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0874] For example, if a user at risk of high blood pressure enters their daily step count and dietary details into the app, the server analyzes this information, and the generative AI model provides specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast." Also, if the user is feeling stressed, the emotion engine will detect this and make suggestions such as "It's good to listen to music to relax."

[0875] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual situation and emotional state of the user, enabling continuous health management.

[0876] The processing flow will be explained below.

[0877] Step 1:

[0878] The user enters health data.

[0879] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[0880] Step 2:

[0881] The server receives the data.

[0882] The server receives the health checkup results and lifestyle habit data sent from the user and stores the data in a database.

[0883] Step 3:

[0884] The server analyzes the data.

[0885] The server passes the data received from the database to the analysis module, which then uses the data to identify the user's health risk factors and nutrient deficiencies. For example, if blood pressure is 140 / 90 or higher, it identifies the user as being at risk of high blood pressure.

[0886] Step 4:

[0887] The generative AI model receives the analysis results.

[0888] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be recommended to take a low-salt diet and engage in regular aerobic exercise.

[0889] Step 5:

[0890] The emotion engine retrieves the emotion data.

[0891] While the user is using the device, the emotion engine uses the camera and microphone to perform facial recognition and voice analysis to detect the user's emotional state (e.g., stress level, happiness).

[0892] Step 6:

[0893] The server receives and analyzes the emotion data.

[0894] The emotion data acquired by the emotion engine is sent to a server, which analyzes it and identifies whether the user is feeling stressed or comfortable.

[0895] Step 7:

[0896] A generative AI model takes emotional data into account to tailor a health plan.

[0897] The generative AI model takes emotional data into account to tailor the health plan, for example suggesting relaxation techniques if stress levels are high and adding additional advice to improve mood.

[0898] Step 8:

[0899] The server provides the health management plan.

[0900] The generated health management plan is sent to the user's device. The plan includes specific suggestions for diet, exercise, and sleep, as well as emotional relaxation techniques. For example, the plan might suggest "eating more vegetables every day and incorporating walking into your daily routine."

[0901] Step 9:

[0902] The server generates the description.

[0903] The server uses the expert model to generate commentary for the generated health management plan and provides it to the user along with the plan, such as "Eating a low-salt diet can reduce the risk of high blood pressure."

[0904] Step 10:

[0905] The server collects the behavioral data.

[0906] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[0907] Step 11:

[0908] The server provides feedback.

[0909] The server analyzes the collected behavioral data and provides the user with immediate feedback, such as "Your exercise volume today is below your goal" or "You should incorporate more balance into your diet."

[0910] Step 12:

[0911] A generative AI model suggests improvements.

[0912] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific improvement measures. The proposed improvement measures are sent to the user's device. For example, they could be specific goals such as "Aim for 5,000 steps a day" or suggestions such as "When stress levels rise, we recommend taking deep breaths or listening to music."

[0913] Example 2

[0914] 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."

[0915] In recent years, lifestyle-related diseases and physical and mental health problems have been on the rise, but conventional health management systems can only make simple suggestions based on individual health checkup results and lifestyle data, making it difficult to provide comprehensive health management that takes into account the user's emotional state.In addition, there is a demand for real-time feedback and immediate improvement suggestions, but achieving this requires advanced technology.

[0916] 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 acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to sense the user's emotional state and provide feedback based on that state, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the provided feedback. This enables comprehensive and specific health management based on the user's individual health data and emotional state.

[0917] "Physical examination results" are the results of medical tests to evaluate the user's physical condition and health status.

[0918] "Lifestyle habit data" is information about the user's habits in daily life, such as exercise, diet, and sleep.

[0919] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate optimal health management plans and recommendations for users.

[0920] A "generated health management plan" is a specific proposal or plan for improving or maintaining a user's individual health, created by the generative AI model based on the analysis results.

[0921] "Emotional state" refers to the user's current psychological state, mood, and emotional state.

[0922] An "emotion engine" is a system or software that analyzes a user's emotional state and provides feedback and suggestions based on that analysis.

[0923] An "expert model" is an algorithm or system that provides expert knowledge-based commentary or additional information to the generated health management plan.

[0924] "Behavioral data" is data relating to the user's specific daily activities (exercise, meals, sleep, etc.).

[0925] "Real-time feedback" refers to advice and suggestions provided immediately in response to user input and behavioral data.

[0926] A "health risk" refers to the likelihood of a particular health problem occurring.

[0927] "Improvements" are specific suggestions or courses of action to reduce specific health risks or improve health status.

[0928] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[0929] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[0930] Data collection and input processing

[0931] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information on lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[0932] Receiving and analyzing data

[0933] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" or "dietary imbalance."

[0934] Generate a health management plan

[0935] The server sends the analysis results to a generative AI model, which uses deep learning technology to generate an optimal health management plan for each user based on the data. For example, a user at risk of high blood pressure will be recommended a low-salt diet plan and regular aerobic exercise. Additionally, a user at risk of sleep deprivation will be recommended specific methods for increasing their sleep time.

[0936] Incorporating an emotion engine

[0937] Additionally, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[0938] Plan provision and explanation

[0939] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the generated plan using an expert model to make it easy for the user to understand. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[0940] Feedback and Improvement Suggestions

[0941] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[0942] Examples and prompts

[0943] Example 1: Proposal for hypertension risk

[0944] Data collected: Blood pressure 140 / 90, exercise amount (exercise once a week)

[0945] Analysis results: Risk of hypertension

[0946] Suggestion: "To lower your blood pressure, incorporate aerobic exercise three times a week. Also, limit your salt intake."

[0947] Example 2: How to deal with lack of sleep

[0948] Data collected: Average sleep time: 4 hours

[0949] Analysis result: lack of sleep

[0950] Suggestion: "The ideal amount of sleep is 7-8 hours. Get into the habit of going to bed at the same time every day. Stretching before bed is effective for relaxation."

[0951] Example prompts

[0952] Sample prompt 1: "Enter the user's blood pressure data and weekly exercise frequency, and suggest the optimal health management plan for this user."

[0953] Sample prompt 2: "Based on the user's sleep data, generate improvement measures for users who are sleep deprived."

[0954] The system provided by this invention can generate an optimal health management plan based on the user's health data and emotional state and provide feedback in real time, enabling users to continuously manage their health according to their individual circumstances and supporting the maintenance and improvement of their health.

[0955] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0956] Step 1: User Data Entry

[0957] Specific operation: The user uses a smartphone or computer to enter health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle data (e.g., diet, exercise, sleep time) into the application form.

[0958] Input: Health checkup result data and lifestyle habits data.

[0959] Output: Send health check result data and lifestyle habit data to the server.

[0960] Step 2: Data reception and storage by the server

[0961] Specific operation: The server receives the data sent by the user as an HTTP request, parses it in JSON format, and saves the parsed data in a database along with the user ID and timestamp.

[0962] Input: Health checkup result data and lifestyle habit data submitted by the user.

[0963] Output: Parsed data stored in a database.

[0964] Step 3: Data analysis by the server

[0965] How it works: The analysis module retrieves the necessary data from the database using SQL queries, which are then analyzed using statistical methods and machine learning algorithms to identify risk factors, such as "risk of high blood pressure" or "unbalanced diet."

[0966] Input: Health checkup result data and lifestyle habit data stored in the database.

[0967] Output: Health risk factors as analysis results.

[0968] Step 4: Server sends data to the generative AI model

[0969] Specific operation: The server sends the analysis results, such as health risk factors, in JSON format to the generative AI model, which receives a POST request using the REST API.

[0970] Input: Health risk factor analysis results.

[0971] Output: The analysis results sent to the generative AI model.

[0972] Step 5: Generative AI model generates health management plan

[0973] How it works: The generative AI model uses deep learning techniques to generate a personalized health management plan based on the analysis results it receives. For example, this plan may include a low-salt diet plan and aerobic exercise recommendations for users at risk of high blood pressure.

[0974] Input: Analysis result data.

[0975] Output: Health care plan.

[0976] Step 6: Analyzing the user's emotional state with the emotion engine

[0977] How it works: The emotion engine analyzes facial expressions and tone of voice through the camera and microphone while the user is using the device, and the analysis results are sent to the server in real time.

[0978] Input: User's facial expression and voice data.

[0979] Output: Emotional state analysis result.

[0980] Step 7: Server sends plan and description

[0981] Specific operation: The server receives the health management plan generated by the generative AI model, generates an explanation for the plan using the expert model, and then integrates the plan and explanation and sends them to the user's device.

[0982] Input: Description of health care plan and specialist model.

[0983] Output: Health management plan and explanation sent to user's device.

[0984] Step 8: User enters and submits behavioral data

[0985] How it works: Users enter their daily exercise and food logs through the application, and automatically collect sleep data from devices such as smartwatches.

[0986] Input: Exercise log, food record, sleep data.

[0987] Output: Behavioral data sent to the server.

[0988] Step 9: Server feedback and improvement suggestions

[0989] Specific actions: The server uses the analysis module to analyze new behavioral data and generate real-time feedback. The generative AI model is retrained based on the new data to predict future health risks and suggest specific improvement measures.

[0990] Input: Behavioral data.

[0991] Output: Real-time feedback and remedial measures for health risks.

[0992] (Application example 2)

[0993] 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."

[0994] Conventional health management systems analyze users' health checkup results and lifestyle data, but do not provide advice that takes into account their emotional state. This makes it difficult to provide effective health management plans to users who are under the influence of stress or emotions. It is also difficult to instantly provide optimal advice to users in physical stores. This has led to a demand for detailed responses tailored to individual health and emotional states.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to analyze the user's emotional state, and means for providing additional advice based on the emotional state. This enables comprehensive health management that takes into account not only the user's health state but also their emotional state.

[0996] "Health checkup results" refers to data obtained as a result of a diagnosis a user receives at a medical institution or testing facility, and includes information about the user's physical health status, such as blood pressure, cholesterol levels, and blood sugar levels.

[0997] "Lifestyle data" refers to data related to the user's daily life, and includes information such as dietary habits, amount of exercise, and sleep duration.

[0998] A "generative AI model" refers to an algorithm or program that uses machine learning and artificial intelligence technology to generate optimal health management plans based on analyzed data.

[0999] An "emotion engine" refers to a system or software that uses technologies such as facial recognition and voice analysis to detect and analyze a user's emotional state.

[1000] "Expert model" refers to an algorithm or program that provides commentary on the generated plan based on expert knowledge and experience.

[1001] "Behavioral data" refers to data related to the user's daily activities, including exercise logs, dietary details, sleep data, and the like.

[1002] "Feedback" refers to specific advice or suggestions provided to users based on the analysis results and generated plans.

[1003] "Emotional state" indicates the user's current feelings and psychological state, and refers to information including emotions such as stress, joy, and sadness.

[1004] This invention relates to a system that generates and provides an optimal health management plan using a user's health checkup results, lifestyle data, and emotional state. This system consists of a user's terminal, a server, a generative AI model, an emotion engine, and an expert model.

[1005] First, the user uses a device such as a smartphone or tablet to input their health checkup results and lifestyle data. For example, they can input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as information on lifestyle habits such as diet, exercise, and sleep duration. This data is then sent from the device to the server.

[1006] The server stores the received health checkup results and lifestyle data in a database. The data analysis module then analyzes the data to identify the user's health risk factors. For example, risk factors may include "risk of high blood pressure" or "dietary imbalance." These analysis results are sent to a generative AI model, which generates an optimal health management plan for each user based on the identified risk factors.

[1007] The generated health management plan is then sent back to the user's device from the server. Furthermore, an expert model is used to add commentary to the generated plan, making it easier for the user to understand and implement the plan. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[1008] Meanwhile, the emotion engine uses the device's built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this and add relaxation methods and advice for improving mood to the plan. Specifically, it will make suggestions such as, "Listening to music is good for relaxation."

[1009] The system also collects daily behavioral data from users to support ongoing health management. This behavioral data includes exercise logs, dietary habits, and sleep data. Based on this data, the generative AI model provides immediate feedback to users, predicts future health risks, and suggests specific improvement measures. For example, specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's a good idea to include foods high in dietary fiber in your breakfast" are provided.

[1010] As described above, the present invention provides an individualized optimal health management plan based on the user's health condition and emotional state, and supports the user in maintaining their health continuously.

[1011] Examples and prompts

[1012] As a concrete example, consider a scenario in which a user uses a "health management advisor" application while shopping in a physical store. The user inputs their health checkup results and lifestyle habits into their smartphone, and the system analyzes their emotional state while shopping in the store. For example, the system might suggest, "We recommend a low-salt salad for dinner tonight. Also, how about some herbal tea to help you relax?"

[1013] An example prompt is:

[1014] "Generate an optimal health management plan based on the user's health checkup results and lifestyle data. Also, include advice on how to relax, as the user's emotional state is stressed."

[1015] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1016] Step 1:

[1017] Users use devices such as smartphones or tablets to input their health checkup results and lifestyle data. This input includes health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as dietary details, exercise volume, and sleep duration. This data is sent to the server in a standardized format such as JSON.

[1018] Step 2:

[1019] The server receives the health checkup results and lifestyle habit data sent by the user and stores them in a database. At this time, it validates that the data format is correct. For example, it checks whether numerical data has been entered in the correct format. If the entered data is correct, it is saved in the database.

[1020] Step 3:

[1021] The server passes the accumulated health checkup results and lifestyle data to the analysis module. The analysis module uses this data to identify the user's health risk factors. For example, if blood pressure is high, it will identify a "risk of high blood pressure," and if the diet is unbalanced, it will detect a "dietary imbalance." The results of the analysis are listed as risk factors.

[1022] Step 4:

[1023] The server sends the analysis results to a generative AI model, which then inputs the list of risk factors as prompts and generates an optimal health management plan. For example, it generates a low-salt meal plan for "high blood pressure risk" and a nutritionally balanced meal plan for "dietary imbalance."

[1024] Step 5:

[1025] The server sends the health management plan obtained from the generative AI model to the user's device. It also uses the expert model to generate an easy-to-understand explanation of the health management plan and provides it to the user. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" can be added.

[1026] Step 6:

[1027] Using the device's built-in camera and microphone, the emotion engine analyzes the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this.

[1028] Step 7:

[1029] The emotion engine sends the detected emotional state to a server, which receives this data and runs the generative AI model again to generate additional advice based on the emotional state, such as "We recommend listening to music to relax."

[1030] Step 8:

[1031] The server then sends the generated additional advice to the user's device, where the user can take specific actions, such as practicing yoga or listening to music to relax.

[1032] In this way, a mechanism is realized in which the entire system supports comprehensive health management that takes into account the user's health and emotional state.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] [Fourth embodiment]

[1037] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1038] 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.

[1039] 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).

[1040] 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.

[1041] 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.

[1042] 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).

[1043] 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.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] 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.

[1048] 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.

[1049] 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."

[1050] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[1051] The entire system consists of the user's device, a server, and a generative AI model.

[1052] Data collection and input processing

[1053] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[1054] Receiving and analyzing data

[1055] The server receives the health checkup results and lifestyle data sent by the user. The received data is stored in a database and passed to the analysis module. The analysis module identifies health risk factors specific to the user based on the data.

[1056] Generate a health management plan

[1057] The server sends the analysis results to the generative AI model, which then generates an optimal health management plan. For example, for users at risk of high blood pressure, the model suggests a low-salt diet plan and regular aerobic exercise. For users who are sleep-deprived, the model suggests specific ways to increase their sleep time.

[1058] Plan provision and explanation

[1059] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using the expert model to make it easy for the user to understand. The explanation is specific advice such as, "Try to eat more vegetables and fruits to limit salt in your daily diet."

[1060] Feedback and Improvement Suggestions

[1061] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[1062] As a concrete example, if a user at risk of high blood pressure inputs their daily step count and dietary details into the app, the server will analyze this information, and the generative AI model will provide specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast."The system also provides continuous feedback on the practices the user has followed, suggesting further improvement measures.

[1063] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[1064] The processing flow will be explained below.

[1065] Step 1:

[1066] The user enters health data.

[1067] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[1068] Step 2:

[1069] The server receives the data.

[1070] The server receives the health checkup results and lifestyle habit data sent from the user and stores them in a database.

[1071] Step 3:

[1072] The server analyzes the data.

[1073] The server passes the data received from the database to the analysis module, which uses the data to identify the user's health risk factors and nutrient deficiencies.

[1074] Step 4:

[1075] The generative AI model receives the analysis results.

[1076] The server sends the analysis results to the generative AI model, which then generates the optimal health management plan for each user based on the data.

[1077] Step 5:

[1078] The server provides the health management plan.

[1079] The server then sends the generated health management plan to the user's device, which includes specific suggestions for diet, exercise, sleep, etc.

[1080] Step 6:

[1081] The server generates the description.

[1082] The server uses the expert model to generate an explanation for the generated health care plan and provides it to the user along with the plan. The explanation is provided in a format that is easy for the user to understand.

[1083] Step 7:

[1084] The server collects the behavioral data.

[1085] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[1086] Step 8:

[1087] The server provides feedback.

[1088] The server analyzes the collected behavioral data and provides real-time feedback to the user, including evaluation and advice for the actions the user has taken.

[1089] Step 9:

[1090] A generative AI model suggests improvements.

[1091] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific remedial measures, which are then sent to the user's device.

[1092] Example 1

[1093] 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."

[1094] While conventional health management systems partially automate the collection and analysis of data from users, they are inadequate in the continuous management of behavioral data and the provision of immediate feedback, making it difficult to generate optimal health management plans for individual users or predict future health risks. Furthermore, they lack a mechanism for providing specific explanations for the generated health management plans, making it difficult for users to properly understand and implement the plans. Furthermore, there is no method for efficiently utilizing generative AI models using prompt sentences.

[1095] 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.

[1096] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting behavioral data of the user and providing immediate feedback based on the behavior, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the collected behavioral data and immediate feedback, thereby enabling the provision of a continuous and dynamic health management plan to each individual user.

[1097] "Medical checkup results" are data indicating physiological indicators such as blood pressure, cholesterol level, and blood sugar level obtained when a user undergoes a medical checkup.

[1098] "Lifestyle data" refers to data relating to the user's daily habits, such as diet, exercise, and sleep duration.

[1099] "Behavioral data" refers to data based on the user's actual behavior, such as exercise logs, dietary content, and sleep data.

[1100] A "generative AI model" is an artificial intelligence model that analyzes acquired data and generates an optimal health management plan.

[1101] An "expert model" is an artificial intelligence model that provides specific and expert commentary on the generated health management plan.

[1102] "Immediate feedback" refers to advice and suggestions provided in real time based on behavioral data collected from users.

[1103] A "prompt sentence" is an input sentence used to give specific instructions to a generative AI model.

[1104] A "health management plan" is an optimal health management method and specific action plan created based on the user's health condition and lifestyle habits.

[1105] This invention is a health management system that uses a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users and generates and provides optimal health management plans. The entire system consists of a user's device, a server, and a generative AI model.

[1106] Users use their smartphones or PCs to input health checkup results and lifestyle data. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results, and provide lifestyle information such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[1107] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database on the server and passed to an analysis module. The analysis module analyzes the data to identify health risk factors specific to the user. Specifically, scripts written in Python and machine learning models are used.

[1108] The server that obtains the analysis results sends them to a generative AI model. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. Based on the analysis results, the generative AI model generates an optimal health management plan. For example, for users at risk of high blood pressure, it suggests a low-salt diet plan and regular aerobic exercise. It also suggests specific ways to increase sleep for users who are sleep-deprived.

[1109] The generated health management plan is sent from the server to the user's device. At this time, an explanation of the plan generated using the expert model is also added. The expert model provides specific advice to help the user understand the generated plan, such as "Try to eat more vegetables and fruits in your daily diet to limit salt intake."

[1110] Furthermore, the server continuously collects user behavioral data, including exercise logs, dietary details, and sleep data. Based on this data, notifications and advice are provided to users as real-time feedback. Additionally, the generative AI model analyzes this behavioral data and predicts future health risks. Specific improvement measures for predicted risks are presented to support ongoing health management.

[1111] As a concrete example, the generative AI model operates using the following prompt sentence:

[1112] User's health check results: Blood pressure 150 / 90, cholesterol 220, blood sugar 110

[1113] User's lifestyle data: 5,000 steps / day, meal contents (breakfast: toast, lunch: salad, dinner: pasta), sleep time: 6 hours

[1114] Analyze this data and suggest a health management plan that suits the user.

[1115] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual circumstances of each user, enabling continuous health management.

[1116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] Users use their smartphones or PCs to input health checkup results and lifestyle habit data. For example, they input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as lifestyle habit data such as diet, exercise, and sleep duration. This data is sent from the device to a server. Inputs include data manually entered by the user into input forms or applications, and outputs include data sent to the server via HTTP requests.

[1119] Specific behavior:

[1120] The user opens the smartphone application and enters information such as blood pressure and dietary details according to the input form.

[1121] The input data is sent from the terminal application to the server.

[1122] Step 2:

[1123] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database on the server. The input is the data sent from the terminal that arrives at the server as an HTTP request, and the output is the health checkup results and lifestyle habit data stored in the database.

[1124] Specific behavior:

[1125] The server receives the HTTP request and analyzes the data contained in the request.

[1126] Insert the parsed data into a database (for example, by executing an INSERT statement against an SQL database).

[1127] Step 3:

[1128] The analysis module on the server retrieves data from the database and performs analysis. Based on this, health risk factors specific to the user are identified. The input is user data retrieved from the database, and the output is the analysis results of health risk factors.

[1129] Specific behavior:

[1130] The server passes the user's health check results and lifestyle habit data obtained from the database to the analysis module.

[1131] The analysis module analyzes the data using Python scripts and machine learning models.

[1132] Step 4:

[1133] The server sends the analysis results to the generative AI model and makes a request to generate an optimal health care plan. The generated health care plan is sent back to the server. The analysis results are provided as prompt sentences to the generative AI model as input, and the generated health care plan is the output.

[1134] Specific behavior:

[1135] The server creates a prompt for the generative AI model and sends it via an API request.

[1136] The generative AI model analyzes the prompt, generates an appropriate health management plan, and sends it back to the server.

[1137] Step 5:

[1138] The server sends the generated health management plan to the user's terminal. At this time, an explanation is added to the plan generated using the expert model. The input is the generated health management plan, and the output is the plan with the explanation sent to the user's terminal.

[1139] Specific behavior:

[1140] The server generates an HTTP request to transmit the health management plan to the user's terminal.

[1141] The expert model will add specific commentary to the plan and send it along with the plan.

[1142] Step 6:

[1143] The server continuously collects user behavioral data and provides immediate feedback. Furthermore, a generative AI model analyzes the behavioral data, predicts future health risks, and provides specific improvement measures. The input is behavioral data from the user's device, and the output is improvement measures based on feedback and future risk predictions.

[1144] Specific behavior:

[1145] The server periodically collects data such as step counts, meal contents, and sleep data from the user's device.

[1146] The collected data is analyzed and notifications are sent to the user as immediate feedback.

[1147] A generative AI model analyzes behavioral data to predict future health risks and provide remedial measures.

[1148] (Application example 1)

[1149] 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."

[1150] Conventional health management systems are limited to providing users with one-way information, making it difficult to provide immediate feedback on changes in users' daily lifestyles and health conditions or specific improvement measures. Furthermore, they lack ongoing support tailored to individual health risks, leaving users with little motivation to continue managing their health voluntarily. Therefore, there is a need for systems that provide optimal health management plans for individual users and support ongoing health management.

[1151] 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.

[1152] In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for continuously collecting the user's daily behavioral data, and means for using the generative AI model to provide real-time feedback based on the collected behavioral data and generate specific improvement measures, thereby enabling continuous and real-time health management for the user.

[1153] "Medical checkup results" are the measurement results of blood pressure, cholesterol level, blood sugar level, etc. based on a medical checkup conducted at a medical institution, etc.

[1154] "Lifestyle data" refers to data related to the user's daily life, including information such as dietary habits, amount of exercise, and sleep duration.

[1155] "Analysis" refers to identifying health risk factors specific to a user based on the health checkup results and lifestyle habit data obtained.

[1156] A "generative AI model" is an artificial intelligence model that generates optimal health management plans and specific improvement measures based on analysis results.

[1157] A "health management plan" is a specific set of guidelines and advice provided by the generative AI model to help users maintain and improve their health.

[1158] An "expert model" is an artificial intelligence model that provides expert commentary on the generated health care plan.

[1159] "Feedback" refers to instant evaluations and advice provided by the generative AI model based on behavioral data provided by the user.

[1160] "Behavioral data" refers to specific data related to the user's daily lifestyle habits, and includes exercise logs, dietary details, sleep data, and the like.

[1161] "Improvements" are specific actions or measures proposed to reduce future health risks based on analysis and feedback.

[1162] This invention relates to a health management system using a generative AI model. The system analyzes health checkup results and lifestyle habit data obtained from users to generate and provide optimal health management plans.

[1163] 1. Data collection and input processing

[1164] Users use their smartphones or computers to input data on their health checkup results and lifestyle habits. Health checkup results include blood pressure, cholesterol levels, blood sugar levels, and other measurement results. Lifestyle information includes dietary details, exercise levels, and sleep duration. This information is sent from the user's device to a server. A secure communication protocol such as HTTPS is used for transmission.

[1165] 2. Data Receipt and Analysis

[1166] The server receives health checkup results and lifestyle habit data sent by users. The received data is stored in a database (e.g., PostgreSQL) and passed to an analysis module (e.g., Python, Pandas). The analysis module identifies health risk factors specific to the user based on the data.

[1167] 3. Generate a health management plan

[1168] The server sends the analysis results to a generative AI model (e.g., GPT-3), which then generates an optimal health management plan. The plan includes specific advice based on the user's health checkup results and lifestyle habits.

[1169] 4. Providing and explaining the plan

[1170] The generated health management plan is sent from the server to the user's smartphone. In addition, an expert model installed separately from the generating AI model provides commentary on the generated plan. The expert model provides specific advice, such as "Try to eat more vegetables and fruits to reduce salt in your daily diet."

[1171] 5. Feedback and Improvement Suggestions

[1172] The server continuously collects the user's daily behavioral data. This behavioral data includes exercise logs, dietary habits, sleep data, etc. This data is obtained from various sensors on the smartphone (GPS, accelerometer, etc.). Based on the collected data, the generative AI model provides immediate feedback. For example, it gives specific advice such as, "You haven't reached your step goal today. Try walking a little longer."

[1173] Furthermore, the generative AI model predicts future health risks and provides specific recommendations for improvement, such as "Aim for 5,000 steps a day" and "Include foods high in fiber for breakfast."

[1174] Examples of prompt statements

[1175] Below are some example prompts that can be presented to the generative AI model based on user-provided data.

[1176] The user's health check results are: Blood pressure: 130 / 85, Cholesterol: 210, Blood sugar: 100.

[1177] Lifestyle data is as follows: Diet: high calorie, low fiber, exercise: low, sleep: 6 hours.

[1178] Based on this data, generate an optimal health management plan for users at risk for high blood pressure and high cholesterol, including specific recommendations.

[1179] As described above, this system provides optimal health management plans tailored to each user's individual circumstances and supports continuous health management.

[1180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1181] Step 1:

[1182] Users use their smartphones or computers to input their health checkup results and lifestyle data. Specifically, users enter health checkup results such as blood pressure, cholesterol levels, and blood sugar levels into the application form, and provide lifestyle data such as diet, exercise, and sleep time. This data is sent to the server via HTTPS.

[1183] Step 2:

[1184] The server receives the health checkup results and lifestyle habit data sent by the user. The received data is stored in a database (e.g., PostgreSQL), allowing the data to be stored permanently.

[1185] Step 3:

[1186] The server's analysis module analyzes the stored data. Specifically, it uses analysis modules (e.g., Python, Pandas) to identify health risk factors specific to the user. The data is processed by statistical analysis of blood pressure and cholesterol levels to check for abnormal values.

[1187] Step 4:

[1188] The server uses a generative AI model (e.g., GPT-3) based on the analysis results to generate an optimal health management plan. The analysis results are used as input to create a prompt for the generative AI model, which then outputs a specific health management plan. This prompt includes the user's health checkup results and lifestyle habits.

[1189] Step 5:

[1190] The generated health management plan is sent from the server to the user's smartphone. Specifically, the health management plan provided by the generative AI model is displayed in text format in the user's application. At this time, an expert model is also used to add detailed explanations to the plan.

[1191] Step 6:

[1192] The user's daily behavioral data (exercise log, dietary content, sleep data, etc.) is continuously collected from various sensors (GPS, accelerometer, etc.) on the smartphone and sent to a server. The behavioral data sent is then stored in a database.

[1193] Step 7:

[1194] The server analyzes the collected behavioral data and provides immediate feedback. Specifically, it uses a generative AI model to provide specific advice and guidance to the user based on the behavioral data. For example, the user may receive feedback such as, "You haven't reached your step goal today. Try walking a little longer." via the application.

[1195] Step 8:

[1196] Furthermore, the server predicts future health risks and generates specific improvement measures. The generative AI model suggests improvement measures such as "Aim for 5,000 steps a day" or "It's a good idea to include foods high in dietary fiber in your breakfast." These suggestions are also generated using prompt text and provided to the user.

[1197] 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.

[1198] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[1199] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[1200] Data collection and input processing

[1201] Users use their smartphones or computers to input data about their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information about lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[1202] Receiving and analyzing data

[1203] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" and "dietary imbalance."

[1204] Generate a health management plan

[1205] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be suggested a low-salt diet plan and regular aerobic exercise. Similarly, a user at risk of sleep deprivation would be suggested specific ways to increase their sleep time.

[1206] Incorporating an emotion engine

[1207] Furthermore, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[1208] Plan provision and explanation

[1209] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the plan generated using an expert model to make it easy for the user to understand. The explanation provides specific advice, such as "On stressful days, try deep breathing or yoga to relax."

[1210] Feedback and Improvement Suggestions

[1211] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[1212] For example, if a user at risk of high blood pressure enters their daily step count and dietary details into the app, the server analyzes this information, and the generative AI model provides specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's good to include foods high in dietary fiber in your breakfast." Also, if the user is feeling stressed, the emotion engine will detect this and make suggestions such as "It's good to listen to music to relax."

[1213] In this way, the health management system according to the present invention provides an optimal health management plan according to the individual situation and emotional state of the user, enabling continuous health management.

[1214] The processing flow will be explained below.

[1215] Step 1:

[1216] The user enters health data.

[1217] Users use their smartphones or computers to input data about their health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle habits (e.g., diet, exercise, sleep duration). This data is then sent from the user's device to the server.

[1218] Step 2:

[1219] The server receives the data.

[1220] The server receives the health checkup results and lifestyle habit data sent from the user and stores the data in a database.

[1221] Step 3:

[1222] The server analyzes the data.

[1223] The server passes the data received from the database to the analysis module, which then uses the data to identify the user's health risk factors and nutrient deficiencies. For example, if blood pressure is 140 / 90 or higher, it identifies the user as being at risk of high blood pressure.

[1224] Step 4:

[1225] The generative AI model receives the analysis results.

[1226] The server sends the analysis results to a generative AI model, which then uses the data to generate an optimal health management plan for each user. For example, a user at risk of high blood pressure would be recommended to take a low-salt diet and engage in regular aerobic exercise.

[1227] Step 5:

[1228] The emotion engine retrieves the emotion data.

[1229] While the user is using the device, the emotion engine uses the camera and microphone to perform facial recognition and voice analysis to detect the user's emotional state (e.g., stress level, happiness).

[1230] Step 6:

[1231] The server receives and analyzes the emotion data.

[1232] The emotion data acquired by the emotion engine is sent to a server, which analyzes it and identifies whether the user is feeling stressed or comfortable.

[1233] Step 7:

[1234] A generative AI model takes emotional data into account to tailor a health plan.

[1235] The generative AI model takes emotional data into account to tailor the health plan, for example suggesting relaxation techniques if stress levels are high and adding additional advice to improve mood.

[1236] Step 8:

[1237] The server provides the health management plan.

[1238] The generated health management plan is sent to the user's device. The plan includes specific suggestions for diet, exercise, and sleep, as well as emotional relaxation techniques. For example, the plan might suggest "eating more vegetables every day and incorporating walking into your daily routine."

[1239] Step 9:

[1240] The server generates the description.

[1241] The server uses the expert model to generate commentary for the generated health management plan and provides it to the user along with the plan, such as "Eating a low-salt diet can reduce the risk of high blood pressure."

[1242] Step 10:

[1243] The server collects the behavioral data.

[1244] The server periodically collects behavioral data (e.g., exercise logs, dietary details, and sleep data) from user devices and stores them in a database.

[1245] Step 11:

[1246] The server provides feedback.

[1247] The server analyzes the collected behavioral data and provides the user with immediate feedback, such as "Your exercise volume today is below your goal" or "You should incorporate more balance into your diet."

[1248] Step 12:

[1249] A generative AI model suggests improvements.

[1250] Based on the feedback, the server uses a generative AI model to predict future health risks and propose specific improvement measures. The proposed improvement measures are sent to the user's device. For example, they could be specific goals such as "Aim for 5,000 steps a day" or suggestions such as "When stress levels rise, we recommend taking deep breaths or listening to music."

[1251] Example 2

[1252] 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."

[1253] In recent years, lifestyle-related diseases and physical and mental health problems have been on the rise, but conventional health management systems can only make simple suggestions based on individual health checkup results and lifestyle data, making it difficult to provide comprehensive health management that takes into account the user's emotional state.In addition, there is a demand for real-time feedback and immediate improvement suggestions, but achieving this requires advanced technology.

[1254] 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 acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to sense the user's emotional state and provide feedback based on that state, and means for using a generative AI model to predict future health risks and propose specific improvement measures based on the provided feedback. This enables comprehensive and specific health management based on the user's individual health data and emotional state.

[1255] "Physical examination results" are the results of medical tests to evaluate the user's physical condition and health status.

[1256] "Lifestyle habit data" is information about the user's habits in daily life, such as exercise, diet, and sleep.

[1257] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate optimal health management plans and recommendations for users.

[1258] A "generated health management plan" is a specific proposal or plan for improving or maintaining a user's individual health, created by the generative AI model based on the analysis results.

[1259] "Emotional state" refers to the user's current psychological state, mood, and emotional state.

[1260] An "emotion engine" is a system or software that analyzes a user's emotional state and provides feedback and suggestions based on that analysis.

[1261] An "expert model" is an algorithm or system that provides expert knowledge-based commentary or additional information to the generated health management plan.

[1262] "Behavioral data" is data relating to the user's specific daily activities (exercise, meals, sleep, etc.).

[1263] "Real-time feedback" refers to advice and suggestions provided immediately in response to user input and behavioral data.

[1264] A "health risk" refers to the likelihood of a particular health problem occurring.

[1265] "Improvements" are specific suggestions or courses of action to reduce specific health risks or improve health status.

[1266] This invention is a health management system that uses a generative AI model and an emotion engine. The system analyzes the user's health checkup results and lifestyle data, and also recognizes the user's emotional state, with the aim of generating and providing an optimal health management plan.

[1267] The entire system consists of a user terminal, a server, a generative AI model, an emotion engine, and an expert model.

[1268] Data collection and input processing

[1269] Users use their smartphones or PCs to input data on their health checkup results and lifestyle habits. For example, they input blood pressure, cholesterol levels, blood sugar levels, etc. as health checkup results. They also provide information on lifestyle habits such as diet, exercise, and sleep duration. This information is sent from the device to the server.

[1270] Receiving and analyzing data

[1271] The server receives the health checkup results and lifestyle data sent by the user and stores them in a database. The received data is passed to an analysis module, which uses the data to identify the user's health risk factors, such as "risk of high blood pressure" or "dietary imbalance."

[1272] Generate a health management plan

[1273] The server sends the analysis results to a generative AI model, which uses deep learning technology to generate an optimal health management plan for each user based on the data. For example, a user at risk of high blood pressure will be recommended a low-salt diet plan and regular aerobic exercise. Additionally, a user at risk of sleep deprivation will be recommended specific methods for increasing their sleep time.

[1274] Incorporating an emotion engine

[1275] Additionally, an emotion engine is used to sense the user's emotional state. The emotion engine detects emotions through facial recognition technology and voice analysis while the user is using the device. For example, if the user is feeling stressed, the system will suggest ways to relax and provide advice to improve their mood.

[1276] Plan provision and explanation

[1277] The generated health management plan is sent from the server to the user's device. Furthermore, an explanation is added to the generated plan using an expert model to make it easy for the user to understand. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[1278] Feedback and Improvement Suggestions

[1279] The server continuously collects user behavioral data, including exercise logs, dietary habits, and sleep data. This data is used to provide immediate feedback, and a generative AI model predicts future health risks. Specific improvement measures are proposed for predicted risks, supporting ongoing health management.

[1280] Examples and prompts

[1281] Example 1: Proposal for hypertension risk

[1282] Data collected: Blood pressure 140 / 90, exercise amount (exercise once a week)

[1283] Analysis results: Risk of hypertension

[1284] Suggestion: "To lower your blood pressure, incorporate aerobic exercise three times a week. Also, limit your salt intake."

[1285] Example 2: How to deal with lack of sleep

[1286] Data collected: Average sleep time: 4 hours

[1287] Analysis result: lack of sleep

[1288] Suggestion: "The ideal amount of sleep is 7-8 hours. Get into the habit of going to bed at the same time every day. Stretching before bed is effective for relaxation."

[1289] Example prompts

[1290] Sample prompt 1: "Enter the user's blood pressure data and weekly exercise frequency, and suggest the optimal health management plan for this user."

[1291] Sample prompt 2: "Based on the user's sleep data, generate improvement measures for users who are sleep deprived."

[1292] The system provided by this invention can generate an optimal health management plan based on the user's health data and emotional state and provide feedback in real time, enabling users to continuously manage their health according to their individual circumstances and supporting the maintenance and improvement of their health.

[1293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1294] Step 1: User Data Entry

[1295] Specific operation: The user uses a smartphone or computer to enter health checkup results (e.g., blood pressure, cholesterol levels, blood sugar levels) and lifestyle data (e.g., diet, exercise, sleep time) into the application form.

[1296] Input: Health checkup result data and lifestyle habits data.

[1297] Output: Send health check result data and lifestyle habit data to the server.

[1298] Step 2: Data reception and storage by the server

[1299] Specific operation: The server receives the data sent by the user as an HTTP request, parses it in JSON format, and saves the parsed data in a database along with the user ID and timestamp.

[1300] Input: Health checkup result data and lifestyle habit data submitted by the user.

[1301] Output: Parsed data stored in a database.

[1302] Step 3: Data analysis by the server

[1303] How it works: The analysis module retrieves the necessary data from the database using SQL queries, which are then analyzed using statistical methods and machine learning algorithms to identify risk factors, such as "risk of high blood pressure" or "unbalanced diet."

[1304] Input: Health checkup result data and lifestyle habit data stored in the database.

[1305] Output: Health risk factors as analysis results.

[1306] Step 4: Server sends data to the generative AI model

[1307] Specific operation: The server sends the analysis results, such as health risk factors, in JSON format to the generative AI model, which receives a POST request using the REST API.

[1308] Input: Health risk factor analysis results.

[1309] Output: The analysis results sent to the generative AI model.

[1310] Step 5: Generative AI model generates health management plan

[1311] How it works: The generative AI model uses deep learning techniques to generate a personalized health management plan based on the analysis results it receives. For example, this plan may include a low-salt diet plan and aerobic exercise recommendations for users at risk of high blood pressure.

[1312] Input: Analysis result data.

[1313] Output: Health care plan.

[1314] Step 6: Analyzing the user's emotional state with the emotion engine

[1315] How it works: The emotion engine analyzes facial expressions and tone of voice through the camera and microphone while the user is using the device, and the analysis results are sent to the server in real time.

[1316] Input: User's facial expression and voice data.

[1317] Output: Emotional state analysis result.

[1318] Step 7: Server sends plan and description

[1319] Specific operation: The server receives the health management plan generated by the generative AI model, generates an explanation for the plan using the expert model, and then integrates the plan and explanation and sends them to the user's device.

[1320] Input: Description of health care plan and specialist model.

[1321] Output: Health management plan and explanation sent to user's device.

[1322] Step 8: User enters and submits behavioral data

[1323] How it works: Users enter their daily exercise and food logs through the application, and automatically collect sleep data from devices such as smartwatches.

[1324] Input: Exercise log, food record, sleep data.

[1325] Output: Behavioral data sent to the server.

[1326] Step 9: Server feedback and improvement suggestions

[1327] Specific actions: The server uses the analysis module to analyze new behavioral data and generate real-time feedback. The generative AI model is retrained based on the new data to predict future health risks and suggest specific improvement measures.

[1328] Input: Behavioral data.

[1329] Output: Real-time feedback and remedial measures for health risks.

[1330] (Application example 2)

[1331] 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."

[1332] Conventional health management systems analyze users' health checkup results and lifestyle data, but do not provide advice that takes into account their emotional state. This makes it difficult to provide effective health management plans to users who are under the influence of stress or emotions. It is also difficult to instantly provide optimal advice to users in physical stores. This has led to a demand for detailed responses tailored to individual health and emotional states.

[1333] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring health checkup results and lifestyle habit data from a user, means for analyzing the acquired health checkup results and lifestyle habit data, means for using a generative AI model to generate an optimal health management plan based on the analysis results, means for providing the generated health management plan to the user, means for using an emotion engine to analyze the user's emotional state, and means for providing additional advice based on the emotional state. This enables comprehensive health management that takes into account not only the user's health state but also their emotional state.

[1334] "Health checkup results" refers to data obtained as a result of a diagnosis a user receives at a medical institution or testing facility, and includes information about the user's physical health status, such as blood pressure, cholesterol levels, and blood sugar levels.

[1335] "Lifestyle data" refers to data related to the user's daily life, and includes information such as dietary habits, amount of exercise, and sleep duration.

[1336] A "generative AI model" refers to an algorithm or program that uses machine learning and artificial intelligence technology to generate optimal health management plans based on analyzed data.

[1337] An "emotion engine" refers to a system or software that uses technologies such as facial recognition and voice analysis to detect and analyze a user's emotional state.

[1338] "Expert model" refers to an algorithm or program that provides commentary on the generated plan based on expert knowledge and experience.

[1339] "Behavioral data" refers to data related to the user's daily activities, including exercise logs, dietary details, sleep data, and the like.

[1340] "Feedback" refers to specific advice or suggestions provided to users based on the analysis results and generated plans.

[1341] "Emotional state" indicates the user's current feelings and psychological state, and refers to information including emotions such as stress, joy, and sadness.

[1342] This invention relates to a system that generates and provides an optimal health management plan using a user's health checkup results, lifestyle data, and emotional state. This system consists of a user's terminal, a server, a generative AI model, an emotion engine, and an expert model.

[1343] First, the user uses a device such as a smartphone or tablet to input their health checkup results and lifestyle data. For example, they can input health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as information on lifestyle habits such as diet, exercise, and sleep duration. This data is then sent from the device to the server.

[1344] The server stores the received health checkup results and lifestyle data in a database. The data analysis module then analyzes the data to identify the user's health risk factors. For example, risk factors may include "risk of high blood pressure" or "dietary imbalance." These analysis results are sent to a generative AI model, which generates an optimal health management plan for each user based on the identified risk factors.

[1345] The generated health management plan is then sent back to the user's device from the server. Furthermore, an expert model is used to add commentary to the generated plan, making it easier for the user to understand and implement the plan. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" is provided.

[1346] Meanwhile, the emotion engine uses the device's built-in camera and microphone to analyze the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this and add relaxation methods and advice for improving mood to the plan. Specifically, it will make suggestions such as, "Listening to music is good for relaxation."

[1347] The system also collects daily behavioral data from users to support ongoing health management. This behavioral data includes exercise logs, dietary habits, and sleep data. Based on this data, the generative AI model provides immediate feedback to users, predicts future health risks, and suggests specific improvement measures. For example, specific goals such as "Aim for 5,000 steps a day" and dietary advice such as "It's a good idea to include foods high in dietary fiber in your breakfast" are provided.

[1348] As described above, the present invention provides an individualized optimal health management plan based on the user's health condition and emotional state, and supports the user in maintaining their health continuously.

[1349] Examples and prompts

[1350] As a concrete example, consider a scenario in which a user uses a "health management advisor" application while shopping in a physical store. The user inputs their health checkup results and lifestyle habits into their smartphone, and the system analyzes their emotional state while shopping in the store. For example, the system might suggest, "We recommend a low-salt salad for dinner tonight. Also, how about some herbal tea to help you relax?"

[1351] An example prompt is:

[1352] "Generate an optimal health management plan based on the user's health checkup results and lifestyle data. Also, include advice on how to relax, as the user's emotional state is stressed."

[1353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1354] Step 1:

[1355] Users use devices such as smartphones or tablets to input their health checkup results and lifestyle data. This input includes health checkup results such as blood pressure, cholesterol levels, and blood sugar levels, as well as dietary details, exercise volume, and sleep duration. This data is sent to the server in a standardized format such as JSON.

[1356] Step 2:

[1357] The server receives the health checkup results and lifestyle habit data sent by the user and stores them in a database. At this time, it validates that the data format is correct. For example, it checks whether numerical data has been entered in the correct format. If the entered data is correct, it is saved in the database.

[1358] Step 3:

[1359] The server passes the accumulated health checkup results and lifestyle data to the analysis module. The analysis module uses this data to identify the user's health risk factors. For example, if blood pressure is high, it will identify a "risk of high blood pressure," and if the diet is unbalanced, it will detect a "dietary imbalance." The results of the analysis are listed as risk factors.

[1360] Step 4:

[1361] The server sends the analysis results to a generative AI model, which then inputs the list of risk factors as prompts and generates an optimal health management plan. For example, it generates a low-salt meal plan for "high blood pressure risk" and a nutritionally balanced meal plan for "dietary imbalance."

[1362] Step 5:

[1363] The server sends the health management plan obtained from the generative AI model to the user's device. It also uses the expert model to generate an easy-to-understand explanation of the health management plan and provides it to the user. For example, specific advice such as "On stressful days, try deep breathing or yoga to relax" can be added.

[1364] Step 6:

[1365] Using the device's built-in camera and microphone, the emotion engine analyzes the user's emotional state in real time. For example, if the user is feeling stressed, the emotion engine will detect this.

[1366] Step 7:

[1367] The emotion engine sends the detected emotional state to a server, which receives this data and runs the generative AI model again to generate additional advice based on the emotional state, such as "We recommend listening to music to relax."

[1368] Step 8:

[1369] The server then sends the generated additional advice to the user's device, where the user can take specific actions, such as practicing yoga or listening to music to relax.

[1370] In this way, a mechanism is realized in which the entire system supports comprehensive health management that takes into account the user's health and emotional state.

[1371] 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.

[1372] 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.

[1373] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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).

[1378] 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.

[1379] 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."

[1380] 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.

[1381] 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).

[1382] 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] The following is further disclosed regarding the above embodiment.

[1393] (Claim 1)

[1394] A means for obtaining health checkup results and lifestyle habit data from users;

[1395] A means for analyzing the acquired health examination results and lifestyle habit data;

[1396] A means for using a generative AI model to generate an optimal health management plan based on the analysis results;

[1397] A system including a means for providing the generated health care plan to a user.

[1398] (Claim 2)

[1399] 10. The system of claim 1, further comprising means for using an expert model to generate commentary for the generated healthcare plan.

[1400] (Claim 3)

[1401] a means for collecting user behavioral data and providing immediate feedback based on that behavior;

[1402] 10. The system of claim 1, including means for using a generative AI model to predict future health risks and suggest specific remedial actions based on the provided feedback.

[1403] "Example 1"

[1404] (Claim 1)

[1405] A means for obtaining health checkup results and lifestyle habit data from users;

[1406] A means for analyzing the acquired health examination results and lifestyle habit data;

[1407] A means for using a generative AI model to generate an optimal health management plan based on the analysis results;

[1408] A means for providing the generated health management plan to a user;

[1409] a means for continuously collecting user behavioral data and providing immediate feedback based on that behavior;

[1410] A system that includes a means of using generative AI models to predict future health risks and suggest specific remedial measures based on collected behavioral data and real-time feedback.

[1411] (Claim 2)

[1412] 10. The system of claim 1, further comprising means for using an expert model to generate commentary for the generated healthcare plan.

[1413] (Claim 3)

[1414] The system of claim 1, wherein the server includes means for generating prompt sentences for the generative AI model and providing the generated health management plan.

[1415] "Application Example 1"

[1416] (Claim 1)

[1417] A means for obtaining health checkup results and lifestyle habit data from users;

[1418] A means for analyzing the acquired health examination results and lifestyle habit data;

[1419] A means for using a generative AI model to generate an optimal health management plan based on the analysis results;

[1420] A means for providing the generated health management plan to a user;

[1421] A means of continuously collecting data on users' daily behavior;

[1422] A system that includes a means for using generative AI models to provide immediate feedback and generate specific improvement actions based on collected behavioral data.

[1423] (Claim 2)

[1424] 10. The system of claim 1, further comprising means for using an expert model to generate commentary for the generated healthcare plan.

[1425] (Claim 3)

[1426] The system of claim 1, including means for using a generative AI model to predict future health risks based on collected behavioral data and suggest specific remedial measures.

[1427] "Example 2: Combining Emotion Engines"

[1428] (Claim 1)

[1429] A means for obtaining health checkup results and lifestyle habit data from users;

[1430] A means for analyzing the acquired health examination results and lifestyle habit data;

[1431] A means for using a generative AI model to generate an optimal health management plan based on the analysis results;

[1432] A means for providing the generated health management plan to a user;

[1433] means for using an emotion engine to sense a user's emotional state and provide feedback based on that state;

[1434] A system that includes a means for using a generative AI model to predict future health risks and suggest specific remedial actions based on the feedback provided.

[1435] (Claim 2)

[1436] 10. The system of claim 1, further comprising means for using an expert model to generate commentary for the generated healthcare plan.

[1437] (Claim 3)

[1438] 10. The system of claim 1, further comprising means for collecting user behavior data and providing real-time feedback based on the behavior.

[1439] "Application example 2 when combining emotion engines"

[1440] (Claim 1)

[1441] A means for obtaining health checkup results and lifestyle habit data from users;

[1442] A means for analyzing the acquired health examination results and lifestyle habit data;

[1443] A means for using a generative AI model to generate an optimal health management plan based on the analysis results;

[1444] A means for providing the generated health management plan to a user;

[1445] using an emotion engine to analyze the user's emotional state;

[1446] a means for providing additional advice based on emotional state;

[1447] A system including:

[1448] (Claim 2)

[1449] 10. The system of claim 1, further comprising means for using an expert model to generate commentary for the generated healthcare plan.

[1450] (Claim 3)

[1451] A means for analyzing data acquired using a camera or microphone when providing the plan and advice;

[1452] 10. The system of claim 1, further comprising means for providing customized advice to the user based on the analysis results. [Explanation of symbols]

[1453] 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 for obtaining health checkup results and lifestyle habit data from users; A means for analyzing the acquired health examination results and lifestyle habit data; A means for using a generative AI model to generate an optimal health management plan based on the analysis results; A system including a means for providing the generated health care plan to a user.

2. 10. The system of claim 1, further comprising means for using an expert model to generate commentary for the generated healthcare plan.

3. a means for collecting user behavioral data and providing immediate feedback based on that behavior; 10. The system of claim 1, further comprising means for using a generative AI model to predict future health risks and suggest specific remedial measures based on the provided feedback.

Images