system

Abstract

We provide the system. [Solution] Means of collecting health checkup data, A means for imputing missing values ​​and removing outliers from the aforementioned health checkup data, A means for training a machine learning model to predict health risks using the aforementioned supplemented and removed data, A means for providing the results of the health risk prediction to the user terminal, A means for performing a health simulation based on changes in dietary habits and exercise routines, and for presenting the results to the user's terminal, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the reception and management of health examination data, there is a problem that it is difficult for individual employees to actually be aware of their own health status and to encourage actions towards improvement. Furthermore, the results of health examinations cannot be linked to specific actions, and there is concern about the occurrence of health damage due to the detection of potential health risks and delays in response. In response to these problems, it is necessary to realize individualized future risk analysis and improvement proposals, which have been difficult to provide with conventional health management systems.

Means for Solving the Problems

[0005] This invention provides a system that predicts future health risks by collecting health checkup data, generating an accurate dataset by imputing missing values ​​and removing outliers, and training a machine learning model based on that data. The predicted results are provided to the user's device, and the system includes functions to suggest specific lifestyle improvements and simulate the effects of diet and exercise habits. This system continuously improves its accuracy by incorporating user feedback and retraining the generated AI model. As a result, it promotes increased health awareness and lifestyle improvements among users.

[0006] "Health checkup data" refers to the results of tests conducted at medical institutions to understand the health status of individual subjects, and includes blood test results and physical measurement data.

[0007] "Missing value imputation" is a process that improves the completeness of data by filling in some missing information in a dataset using statistical methods or inference.

[0008] "Outlier removal" is the process of identifying data points in a dataset that exhibit unusually large deviations and eliminating or adjusting them to improve the accuracy of statistical analysis.

[0009] A "machine learning model" is a set of computational algorithms that learn from data, acquire patterns and knowledge, and are therefore capable of making predictions and judgments about new data.

[0010] "Health risk prediction" refers to the process of statistically estimating the likelihood of future health deterioration or disease onset based on collected data.

[0011] "Generative AI" is a form of artificial intelligence that generates knowledge from large amounts of data and uses it for learning to perform specific tasks such as prediction and classification.

[0012] A "simulation function" is a feature that assumes actions under specific conditions and virtually reproduces the predicted effects as a result, making those effects available to experience in a digital environment.

[0013] "Feedback data" refers to information about the system's status and usage provided by system users. This information is used to further improve the system and enhance its accuracy. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the language used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that enables individual users to effectively understand future health risks and promote lifestyle improvements by utilizing their health checkup data. This system mainly consists of three components: a server, terminals, and users.

[0036] First, the server periodically collects digital health checkup data from health checkup agencies and medical institutions. This data includes basic health information of users (e.g., blood pressure, blood sugar levels, weight, etc.) and information about their lifestyle. The collected data is preprocessed on the server, with missing values ​​imputed and outliers removed, to prepare it for analysis.

[0037] Next, the server trains a generative AI model using the pre-processed data. This AI model is designed to predict health risks based on gender, age, and lifestyle. The server uses this model to quantify each user's future health risks and calculate the probability of developing specific diseases.

[0038] The user's device sends their health checkup results to a server and receives a health risk prediction based on those results. The device then visually presents the received prediction data to the user. For example, it might display a graph showing the percentage of the user's risk of developing high blood pressure or diabetes in the future and provide advice on necessary lifestyle changes.

[0039] Furthermore, the device provides a health simulation function based on the user's input of new dietary and exercise habits. This function allows users to visually see the impact of different behaviors on their health. For example, it can simulate how blood pressure improves by increasing exercise.

[0040] Furthermore, user feedback data is sent to the server and used to improve the accuracy of the generated AI model. The updated model can provide more accurate and personalized health risk predictions. Through this cycle, the system continuously learns and improves, enhancing the quality of support for users' health management.

[0041] As a concrete example, consider the case of a 40-year-old male user of the system. When the user enters his latest health check results into the system, the server predicts that he has a 25% risk of developing high blood pressure. A simulation showing that he adds 30 minutes of walking to his daily routine could reduce his risk to 20%. This encourages the user to make actual behavioral changes and improve his health.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server periodically collects users' health checkup data from health checkup agencies and medical institutions. This includes biological data such as blood pressure, weight, blood sugar levels, and cholesterol levels, as well as data related to lifestyle habits.

[0045] Step 2:

[0046] The server fills in missing data from the collected data. Using statistical methods, it fills in missing values, for example, by applying mean values ​​based on age and gender. It also removes or adjusts outliers that are abnormally skewed.

[0047] Step 3:

[0048] The server uses pre-processed data to train a generative AI model. The model learns how factors such as gender, age, and lifestyle influence future health risks, thereby improving the accuracy of health risk predictions.

[0049] Step 4:

[0050] Users upload their latest health check results from their devices to the server. The user's input forms the basis for analysis by an AI model.

[0051] Step 5:

[0052] The server receives the user's health checkup data and analyzes health risks using a generated AI model. It quantifies the risk of future disease onset and predicts the likelihood of specific illnesses.

[0053] Step 6:

[0054] The terminal visually presents the user with predictive data received from the server. Charts and lists are used to clearly illustrate the percentage of disease risk and provide advice.

[0055] Step 7:

[0056] The device accepts changes to the user's diet and exercise habits and runs a simulation function. For example, it predicts changes in health status if a specific action is taken and shows the results to the user.

[0057] Step 8:

[0058] Based on the information provided, users decide on actions to improve their lifestyle. If necessary, they send feedback back to the server via their device.

[0059] Step 9:

[0060] The server collects user feedback data and uses it to retrain the generated AI model. This allows for further improvement in the model's accuracy and the provision of more personalized predictions.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In recent years, the importance of health management has increased, but many individuals face the challenge of accurately understanding their own health status and making appropriate behavioral changes. Furthermore, conventional health risk assessment methods do not fully utilize individual lifestyles and individual health data, resulting in inaccurate predictions. In addition, the lack of real-time feedback on user behavioral changes makes it difficult to maintain motivation for health management.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for collecting health-related data, means for supplementing missing information and removing outliers from the health-related data, and means for training a learning model to predict risk using the supplemented and removed data. This enables highly accurate risk prediction based on individual health data. Furthermore, users are offered specific action plans based on the health prediction results and can visualize the actual impact of behavioral changes on their health, thereby promoting more effective health management.

[0066] "Health-related data" refers to information about an individual's health status and lifestyle. This data includes physical indicators such as blood pressure, blood sugar levels, and weight, as well as daily diet and exercise levels.

[0067] "Imputing missing information" refers to the process of filling in missing portions of a dataset using appropriate methods. This resolves data inconsistencies and improves the accuracy of analysis.

[0068] "Outlier removal" refers to the process of removing values ​​that exhibit abnormal deviations within a dataset. This process reduces the impact of extreme values ​​and allows for more accurate analysis results.

[0069] A "learning model" refers to an algorithm that learns specific rules or patterns based on data. This model is used to predict future events by utilizing machine learning and statistical methods.

[0070] An "information terminal" refers to an electronic device used by a user to input and output various types of data. Generally, this includes smartphones, tablets, and personal computers.

[0071] "Health prediction" refers to analyzing and predicting future health conditions and risks based on collected data. This prediction allows for the suggestion of preventative health management and improvement measures.

[0072] A "generative model" refers to an algorithm that identifies patterns in data and generates new data based on that knowledge. This model has the ability to produce an appropriate output for a given input.

[0073] "Response data" refers to information about user feedback and behavior obtained after using a system. This data can be used to improve the quality of services and products.

[0074] This invention is a system designed to enable individual users to effectively understand their own health status and promote improvements in their lifestyle. The system mainly consists of three elements: a server, a terminal, and a user.

[0075] The server automatically collects health-related data from health checkup agencies and other medical facilities. The collected data undergoes preprocessing, such as filling in missing information and removing outliers. Specifically, it uses programming languages ​​such as Python and data processing libraries such as NumPy and Pandas to clean and structure the data.

[0076] Next, the server uses the pre-processed data to train the generative AI model. This model is built using machine learning frameworks such as TENSORFLOW® or PyTorch to predict the user's health risks. For example, prompts such as "40-year-old male, 170cm tall, 70kg weight, exercise habits: 3 times a week" are input to the AI ​​model.

[0077] The user's device receives health risk prediction results from the server and visualizes the analysis results. Visualization libraries such as D3.js and Chart.js are used to present the results in an intuitively understandable format for the user. For example, a user predicted to have a high risk of hypertension will be given specific action suggestions to reduce that risk.

[0078] Furthermore, the device uses a generative AI model to provide a health status simulation based on newly entered data on the user's diet and exercise habits. This simulation allows the user to visualize the specific impacts of different behaviors on their health. For example, it can present simulation results on the impact of daily walking on blood pressure.

[0079] User feedback data is sent to the server and used to improve the accuracy of the generated AI model. Subsequent system updates will utilize this feedback data for learning, resulting in more accurate individual risk assessments.

[0080] This invention effectively supports users' health management through real-time risk prediction and functions that assist in individual user behavioral changes.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server collects health-related data from medical facilities via APIs and database connections. Inputs are anonymized biometric data such as user blood pressure, blood glucose levels, and weight, while output is raw, unprocessed data. This raw data is stored within the system.

[0084] Step 2:

[0085] The server processes the collected raw data, performing operations to impute missing information and remove outliers. The input is the previously stored raw data, and the output is a clean dataset with missing values ​​imputed and outliers removed. Specifically, it uses Python's NumPy and Pandas to examine each data element, impute missing parts with the median, and remove outliers exceeding 3 standard deviations.

[0086] Step 3:

[0087] The server uses a clean dataset to train a generative AI model. The input is the preprocessed data obtained in step 2, and the output is the trained AI model. Here, TensorFlow or PyTorch is used to optimize the model parameters based on the data.

[0088] Step 4:

[0089] The server uses a pre-trained AI model to individually predict each user's health risk. The input is a prompt containing user information (e.g., "40-year-old male, 170cm tall, 70kg weight, exercise habits: 3 times a week"), and the output is the user's health risk score. This risk score is quantified as the probability of developing a specific disease.

[0090] Step 5:

[0091] The user's device receives a health risk score sent from the server and visualizes it in an easy-to-understand format for the user. The input is the health risk score, and the output is displayed in graph or chart format. D3.js and Chart.js are used to visualize the score and present the user with their risks and ways to improve them.

[0092] Step 6:

[0093] The device uses a generative AI model to simulate the user's health status based on newly entered data on changes in their eating habits and exercise routines. The input is the user's set data on lifestyle changes, and the output is a simulation result showing the impact of those changes on health risks. This allows the user to concretely understand the effects of behavioral changes.

[0094] Step 7:

[0095] User feedback data is sent to the server and used to retrain the generated AI model. The input is user feedback data, and the output is an updated AI model for improved accuracy. This continuous feedback loop improves the system's predictive accuracy, enabling more personalized health risk assessments.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] This invention aims to not only utilize individual health checkup information to predict health risks, but also to automatically apply benefits for related goods and services in electronic transactions based on those predictions. Conventionally, the use of health information has been limited to individual health management, making it difficult to extract multifaceted direct added value to specific commercial transactions. This invention aims to solve the problem of stimulating consumer behavior and promoting health awareness by providing specific benefits tailored to individual health conditions.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for collecting health checkup information, means for supplementing missing information and removing outliers from the health checkup information, means for training a machine learning model to predict health risks using the supplemented and removed information, means for performing health simulations based on changes in diet and exercise habits, and means for automatically applying discounts on related products and services during electronic transactions based on the health risk prediction results. This enables users to manage their health while enjoying benefits based on the prediction results.

[0101] "Health checkup information" refers to data related to an individual's health status obtained from medical institutions, etc., and includes basic indicators such as blood pressure, blood sugar levels, and weight.

[0102] "Completing missing data" is the process of supplementing missing data points in health checkup information through estimation to create a complete dataset.

[0103] "Removing outliers" is a process that improves the accuracy of data by removing unnatural values ​​or data that is statistically considered abnormal from health checkup information.

[0104] A "machine learning model" refers to an algorithm or mathematical method that learns patterns and relationships based on collected data and uses them to make predictions about future data.

[0105] "Changes in dietary and exercise habits" means altering daily eating and exercise patterns to improve an individual's health, with the aim of reducing health risks.

[0106] A "health simulation" is a method that demonstrates to users the impact of specific improvement measures by virtually testing how their health status would change under certain conditions.

[0107] "Automatically applying discounts during electronic transactions" refers to a feature that reduces the price of goods or services when a user purchases them online, provided they meet pre-set conditions.

[0108] This invention is a system that effectively utilizes health checkup information to provide users with personalized health risk predictions and benefits in commercial transactions. The system operates primarily using servers, user terminals, and cloud resources.

[0109] The server collects health checkup information based on a predefined protocol. Before storing the collected information in the database, it uses the Pandas library to impute missing information and remove outliers. This cleansed information is then used to train a generative AI model using TensorFlow, providing a function to predict health risks.

[0110] The terminal is responsible for receiving health risk prediction results from the server after the user inputs health checkup information. Based on these results, a user interface is built using ReactJS, providing the user with visual feedback. Users can also input changes to their daily eating habits and exercise routines as feedback, which triggers simulations. When the user executes an electronic transaction, the server automatically applies appropriate discounts and benefits.

[0111] As a concrete example, consider a scenario where a user shops at a supermarket's online store. Based on health checkup information entered by the user beforehand, a generating AI model evaluates their health status, and if it shows a trend toward improvement, a discount on a vegetable set is offered during the next online payment. This process is designed so that users can consciously improve their health while simultaneously receiving concrete benefits through actual commercial transactions.

[0112] An example of a prompt for the generating AI model would be: "Based on the user's age, gender, and recent health check results, please suggest lifestyle changes that can be expected to improve before the next check-up."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server collects health checkup information from health checkup providers. The input information includes basic health indicators such as the user's blood pressure, blood sugar level, and weight. This information is stored in a database on the server and prepared for the next step.

[0116] Step 2:

[0117] The server uses the Pandas library to impute missing information and remove outliers from the collected health checkup data. The input is raw data, and the output of this step is a clean and complete dataset. Mathematical imputation and statistical analysis are used in this data processing to ensure data consistency and accuracy.

[0118] Step 3:

[0119] The server trains a generative AI model using TensorFlow with preprocessed data. The input here is the cleaned dataset, and the output is the model parameters for predicting health risks. The model uses the user's historical data and prediction algorithm to quantify individual health risks.

[0120] Step 4:

[0121] The device receives health risk prediction results sent from the server. The input is the health risk quantified by the model, and the output is a visual display on the user interface. Here, ReactJS is used to provide a graphical display that allows the user to intuitively understand the risk.

[0122] Step 5:

[0123] Users input changes to their diet and exercise habits into a terminal. Based on this input, the server combines pre-processed data with the new lifestyle data to perform a simulation. The output is a predicted change in health status, which is displayed on the user's terminal.

[0124] Step 6:

[0125] The server applies incentives in commercial transactions based on these health risk prediction results and user feedback data. Here, applicable discounts and coupons are selected from the incentive database based on the prediction results and the user's improvement trends, and are automatically used during electronic transactions. The input is a risk assessment by a generative AI model, and the output is specific commercial transaction incentives.

[0126] Step 7:

[0127] The server collects feedback data from users and uses it to retrain the generative AI model. The input to this step is the feedback data, and the output is new model parameters that reflect the improved accuracy of the model. This allows the system to continuously learn and provide more accurate predictions.

[0128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0129] This invention is a system for accurately understanding a user's health status and supporting appropriate health management. This system combines three entities—a server, a terminal, and the user—with an emotion engine that recognizes the user's emotional state.

[0130] First, the server collects health checkup data from health checkup agencies and medical institutions. This data includes biological data such as blood pressure, blood sugar levels, weight, and cholesterol levels. To maintain data integrity, the server performs data imputation and outlier removal.

[0131] Next, the server trains a generative AI model using the adjusted data to predict health risks. This model quantifies the health risks for each user and calculates the likelihood of developing specific diseases. Furthermore, an emotion engine is used to analyze the user's emotional state and evaluate their reaction to the health risk predictions and their stress levels.

[0132] The device prompts the user to submit health checkup data and visually displays the health risk prediction and emotion analysis results received from the server. For example, if the risk is high, it provides advice that takes stress levels into consideration and encourages behavioral improvement with positive messages. Furthermore, based on the emotion engine's analysis, it adjusts lifestyle improvement suggestions to match the user's psychological state.

[0133] Furthermore, the device simulates changes in the user's chosen diet and exercise habits and visualizes their effects. The emotion engine evaluates how the user reacts to this simulation and prepares to send feedback to the server.

[0134] Based on the information obtained from the system, users implement lifestyle improvements and provide feedback on their emotions and health status. This feedback is collected by the server and used to retrain the generative AI model. As a result, more personalized health management support becomes possible.

[0135] As a concrete example, consider a 50-year-old female user of this system. The user sends her latest health check results to the server, and the system, after evaluating her emotional state, notifies her that she is at high risk of diabetes. At this point, the emotion engine recognizes that the user is experiencing stress, and suggestions for relaxation and dietary improvement advice that also serves as stress relief are displayed on the device. The user can use this information to take actions to reduce their health risks.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server collects users' health checkup data from health checkup agencies and medical institutions. This data includes key health indicators such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0139] Step 2:

[0140] The server imputes missing values ​​and removes outliers from the collected health checkup data. For example, it ensures the integrity of the dataset by imputing the mean using statistical methods.

[0141] Step 3:

[0142] The server trains a generative AI model using pre-processed data. Based on past data patterns, it creates a model to predict each user's health risk.

[0143] Step 4:

[0144] The user's device transmits health check results and basic information to the server. The device also provides an input interface, allowing the user to easily enter the necessary information.

[0145] Step 5:

[0146] The server uses a generated AI model to predict health risks based on the data submitted by the user. It quantifies the risk of developing a disease and calculates the likelihood of developing a specific illness.

[0147] Step 6:

[0148] The server uses an emotion engine to recognize the user's emotional state. This function acquires and analyzes data from the user's facial expressions and tone of voice while they are using the device.

[0149] Step 7:

[0150] The server sends the results of health risk prediction and sentiment analysis to the user's terminal. It creates advice that considers the user's emotional state, rather than just suggesting health risks.

[0151] Step 8:

[0152] The device visually displays health risk predictions and lifestyle improvement suggestions tailored to the user's emotions. If the user's stress level is high, it provides advice on relaxation methods and stress reduction.

[0153] Step 9:

[0154] The device simulates health status based on changes in diet and exercise habits, and presents the results to the user. This allows the user to develop a concrete improvement plan.

[0155] Step 10:

[0156] Users review their lifestyle habits based on information provided by the system and send feedback to the server via their device. This feedback includes the effectiveness of the suggestions and their emotional response.

[0157] Step 11:

[0158] The server collects user feedback data and uses it to retrain the generative AI model. This improves the system's predictive accuracy and enables more personalized support.

[0159] (Example 2)

[0160] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0161] In modern times, personal health management is extremely important. However, conventional systems do not adequately predict health risks based on individual health information or provide lifestyle improvement suggestions that take into account responses based on emotional states. As a result, there is a challenge in supporting health management that reflects the individual characteristics of each user.

[0162] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0163] In this invention, the server includes means for collecting health information, means for supplementing missing data and removing anomalous data, means for training a machine learning model to estimate health risks, and means for analyzing emotional states. This makes it possible to provide more accurate and personalized health risk predictions and lifestyle improvement suggestions that take into account the user's emotional state.

[0164] "Health information" refers to various data that indicate an individual's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0165] "Completing missing data" refers to supplementing the data that is missing from the collected health information based on statistical methods and past data patterns.

[0166] "Removing abnormal data" is a technique that detects data in health information that deviates from the normal range and prevents it from affecting the analysis.

[0167] "Training a machine learning model" means optimizing the parameters of an algorithm that predicts health risks based on a large amount of health information data.

[0168] "Analyzing emotional state" means using text and audio information obtained from the user to evaluate their psychological state and stress level.

[0169] A "terminal device" is a device used to provide information to users, and is used to visually display health risk prediction results and lifestyle improvement suggestions.

[0170] This invention is a system that evaluates individual health risks based on the user's health information and proposes appropriate lifestyle improvements. This system is primarily composed of three components: a server, a terminal, and the user.

[0171] The server is the primary component responsible for managing health information and processing data. It collects various health information, performs data completion (missing data) and removal (removing anomalous data). This process utilizes statistical methods and machine learning algorithms. Furthermore, it leverages generative AI models to predict health risks using the collected health information data. These models can quantify the risk of developing specific diseases.

[0172] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine combines natural language processing and speech analysis technologies to evaluate the user's psychological state and stress level.

[0173] The terminal functions as a user interface and visualizes information. It receives health risk prediction results and sentiment analysis results transmitted from the server and displays them in a user-friendly format. For example, it might present risk assessment results as infographics or graphs and offer specific advice for health improvement as actionable suggestions.

[0174] Users refer to the information provided by the system and use it for health management in their daily lives. Users provide feedback through their devices, and this feedback is collected on the server and used to retrain the generated AI model. This enables personalized health support for each user.

[0175] As a concrete example, when a user uses this system, the following prompt message could be used: "Assess the user's current health status, take their emotional state into consideration, and present health risks and suggested solutions."

[0176] In this way, the present invention provides specific means and processes for realizing highly personalized health management.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The server collects users' health information from health checkup agencies and medical institutions. This health information includes blood pressure, blood sugar levels, weight, cholesterol levels, etc. The collected data is received as input and stored in a database. This prepares the basic data for subsequent processing.

[0180] Step 2:

[0181] The server verifies the collected health information, imputing missing data and removing anomalous data. This is done using statistical methods and estimations based on past data patterns. The input to this process is health information, and the output is a well-organized dataset. This ensures data integrity and prepares the system for improving the accuracy of subsequent health risk predictions.

[0182] Step 3:

[0183] The server trains a generative AI model using a prepared dataset. It uses machine learning algorithms to develop a model capable of quantifying health risks. The input requires a prepared dataset, and the output is a trained generative AI model. This model is used to predict risks that differ for each user.

[0184] Step 4:

[0185] The server uses an emotion engine to analyze the user's emotional state. It takes user text and voice information as input and evaluates their psychological state and stress level as output. This analysis allows for consideration of the user's response to the health risk prediction results.

[0186] Step 5:

[0187] The terminal visually displays health risk prediction results and sentiment analysis results obtained from the server. It processes the received data as input and presents it to the user as infographics and advice. This allows the user to intuitively understand their own health status and recognize the suggested improvement methods.

[0188] Step 6:

[0189] The device simulates changes to the user's chosen eating and exercise habits. This visualizes the impact of these changes on health, taking the user's choices as input and outputting estimated health effects. This helps users understand their lifestyle choices.

[0190] Step 7:

[0191] Users improve their lifestyle habits based on feedback from the system. Furthermore, they provide feedback on their emotions and health status, which is reported to the server. The input consists of the user's experiences and impressions, and the output serves as input for the next model retraining, contributing to the overall improvement of the system's accuracy.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0194] Modern in-store health management solutions struggle to provide customized recommendations based on the individual health and emotional states of each user. In particular, there is a need for immediate analysis of on-site health check data and the corresponding recommendations of appropriate products and services. However, existing systems have limitations in providing recommendations that adequately consider the emotional state of the user, resulting in insufficient personalized health management support.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for collecting health checkup information, means for evaluating emotional states and adjusting suggestions based on health simulation results to suit the user's psychological state, and means for collecting user feedback information and retraining a generated AI model using the collected information. This makes it possible to offer customized products and services in physical stores that take into account the individual user's health status and emotions.

[0197] "Health checkup information" refers to data that quantifies the user's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0198] "Completing missing information" refers to the process of supplementing data that is missing from health checkup information through estimation or derivation.

[0199] "Removal of abnormal information" is the process of detecting and removing data from health checkup information that falls outside the normal range.

[0200] A "machine learning algorithm" is a computational method for building models that automatically perform specific tasks using large amounts of data.

[0201] An "information presentation device" is a device that provides users with analysis results and suggestions visually or audibly.

[0202] "Health simulation" is a process that predicts and visualizes the impact that changes in diet and exercise habits will have on a user's health.

[0203] "Emotional state" refers to a state that reflects the user's psychological and emotional health.

[0204] A "generative AI model" is an artificial intelligence system that learns from large amounts of data and performs predictions and generation.

[0205] "Feedback information" refers to opinions and data provided by users, based on their experiences and results.

[0206] To implement this invention, a system is configured in which a server, terminal, and user work in cooperation. First, the server collects health checkup information from health checkup institutions and medical institutions. The collected data is processed using Python to impute missing information and remove anomalous information. Next, a machine learning algorithm is trained using TensorFlow to predict the health risk for each user.

[0207] Furthermore, the server analyzes the emotional state using an NLP library. Based on these results, it provides personalized suggestions to the information presentation device using a generative AI model. These suggestions include products and services that take into account the user's health and emotional state.

[0208] The device, through a frontend built with React Native, presents users with health risk predictions and specific suggestions. Based on these results, users can run simulations to change their eating habits and exercise routines, and visually confirm the results.

[0209] Users manage their health based on the provided suggestions and send feedback information to the server via their device. The server uses the collected feedback information to retrain the generative AI model and further improve its accuracy.

[0210] As a concrete example, a user participates in a health event at a physical store and enters their health checkup information via their smartphone. Based on this information, the server immediately predicts health risks and suggests supplements and fitness plans tailored to the user's stress level.

[0211] Examples of prompts to input into a generative AI model:

[0212] "Based on the user's age, health checkup data (blood pressure, blood sugar levels, etc.), and emotional state (e.g., high stress level), please propose the most suitable health improvement measures."

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The server collects health checkup information from health checkup institutions and medical facilities. The collected data is entered into the server as JSON format data. This data includes blood pressure, blood sugar levels, weight, cholesterol levels, etc.

[0216] Step 2:

[0217] The server uses Python to fill in missing information from collected health checkup data. This employs methods such as substitution using common values ​​and machine learning-based completion techniques. Unfilled data is input, and filled-in data is output.

[0218] Step 3:

[0219] Next, the server removes anomalous information from the completed data. Here, it detects and removes outliers based on a pre-defined normal range. The completed data becomes the input, and a clean dataset is output.

[0220] Step 4:

[0221] Using a clean dataset, the server trains a machine learning algorithm using TensorFlow. This generates a model for predicting health risks. The input is a clean dataset, and the output is a health risk score.

[0222] Step 5:

[0223] The server uses an NLP library to evaluate the user's emotional state. It performs sentiment analysis from the user's written text and calculates stress levels and emotional state scores. The input is the user's text data, and the output is the evaluation result of the emotional state.

[0224] Step 6:

[0225] The device uses a frontend built with React Native to display health risk scores and emotional states received from the server to the user. The displayed information is presented through a visual interface. Input is the evaluation results from the server, and output is the information displayed on the user interface.

[0226] Step 7:

[0227] Based on the presented results, the user simulates their diet and exercise habits. The device calculates the simulation results and presents the effects to the user. The input is the simulation conditions selected by the user, and the output is the predicted health improvement effect.

[0228] Step 8:

[0229] Users send feedback information to the server via their device. This feedback includes actions taken by the user and the effects they perceived. The input is the user's feedback data, and the output is the feedback repository on the server.

[0230] Step 9:

[0231] The server uses the collected feedback information to retrain the generative AI model. This retraining improves the model's prediction accuracy. The input is the feedback information, and the output is the newly adjusted AI model.

[0232] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0233] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0234] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0238] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0239] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0240] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0241] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0242] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0243] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0244] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0245] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0246] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0247] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0248] This invention is a system that enables individual users to effectively understand future health risks and promote lifestyle improvements by utilizing their health checkup data. This system mainly consists of three components: a server, terminals, and users.

[0249] First, the server periodically collects digital health checkup data from health checkup agencies and medical institutions. This data includes basic health information of users (e.g., blood pressure, blood sugar levels, weight, etc.) and information about their lifestyle. The collected data is preprocessed on the server, with missing values ​​imputed and outliers removed, to prepare it for analysis.

[0250] Next, the server trains a generative AI model using the pre-processed data. This AI model is designed to predict health risks based on gender, age, and lifestyle. The server uses this model to quantify each user's future health risks and calculate the probability of developing specific diseases.

[0251] The user's device sends their health checkup results to a server and receives a health risk prediction based on those results. The device then visually presents the received prediction data to the user. For example, it might display a graph showing the percentage of the user's risk of developing high blood pressure or diabetes in the future and provide advice on necessary lifestyle changes.

[0252] Furthermore, the device provides a health simulation function based on the user's input of new dietary and exercise habits. This function allows users to visually see the impact of different behaviors on their health. For example, it can simulate how blood pressure improves by increasing exercise.

[0253] Furthermore, user feedback data is sent to the server and used to improve the accuracy of the generated AI model. The updated model can provide more accurate and personalized health risk predictions. Through this cycle, the system continuously learns and improves, enhancing the quality of support for users' health management.

[0254] As a concrete example, consider the case of a 40-year-old male user of the system. When the user enters his latest health check results into the system, the server predicts that he has a 25% risk of developing high blood pressure. A simulation showing that he adds 30 minutes of walking to his daily routine could reduce his risk to 20%. This encourages the user to make actual behavioral changes and improve his health.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server periodically collects users' health checkup data from health checkup agencies and medical institutions. This includes biological data such as blood pressure, weight, blood sugar levels, and cholesterol levels, as well as data related to lifestyle habits.

[0258] Step 2:

[0259] The server fills in missing data from the collected data. Using statistical methods, it fills in missing values, for example, by applying mean values ​​based on age and gender. It also removes or adjusts outliers that are abnormally skewed.

[0260] Step 3:

[0261] The server uses pre-processed data to train a generative AI model. The model learns how factors such as gender, age, and lifestyle influence future health risks, thereby improving the accuracy of health risk predictions.

[0262] Step 4:

[0263] Users upload their latest health check results from their devices to the server. The user's input forms the basis for analysis by an AI model.

[0264] Step 5:

[0265] The server receives the user's health checkup data and analyzes health risks using a generated AI model. It quantifies the risk of future disease onset and predicts the likelihood of specific illnesses.

[0266] Step 6:

[0267] The terminal visually presents the user with predictive data received from the server. Charts and lists are used to clearly illustrate the percentage of disease risk and provide advice.

[0268] Step 7:

[0269] The device accepts changes to the user's diet and exercise habits and runs a simulation function. For example, it predicts changes in health status if a specific action is taken and shows the results to the user.

[0270] Step 8:

[0271] Based on the information provided, users decide on actions to improve their lifestyle. If necessary, they send feedback back to the server via their device.

[0272] Step 9:

[0273] The server collects user feedback data and uses it to retrain the generated AI model. This allows for further improvement in the model's accuracy and the provision of more personalized predictions.

[0274] (Example 1)

[0275] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0276] In recent years, the importance of health management has increased, but many individuals face the challenge of accurately understanding their own health status and making appropriate behavioral changes. Furthermore, conventional health risk assessment methods do not fully utilize individual lifestyles and individual health data, resulting in inaccurate predictions. In addition, the lack of real-time feedback on user behavioral changes makes it difficult to maintain motivation for health management.

[0277] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0278] In this invention, the server includes means for collecting health-related data, means for complementing missing information and eliminating abnormal values from the health-related data, and means for training a learning model that predicts risks by utilizing the complemented and eliminated data. As a result, highly accurate risk prediction based on individual health data becomes possible. In addition, the user is proposed a specific action plan based on the health prediction result, and the impact of behavior changes on actual health can be visualized, thus promoting more effective health management.

[0279] "Health-related data" refers to information regarding an individual's health status and lifestyle habits. This data includes physical indicators such as blood pressure, blood sugar level, weight, as well as daily diet content, amount of exercise, etc.

[0280] "Complementing missing information" refers to the process of filling in the missing parts within a dataset using an appropriate method. This can resolve data inconsistencies and improve the accuracy of analysis.

[0281] "Eliminating abnormal values" refers to the process of removing values that show abnormal deviations within a dataset. This process can reduce the influence of extreme values and obtain more accurate analysis results.

[0282] "Learning model" refers to an algorithm that learns specific rules and patterns based on data. This model is used to predict future events by utilizing machine learning and statistical methods.

[0283] "Information terminal" refers to an electronic device used by a user to input and output various data. Generally, smartphones, tablets, personal computers, etc. fall under this category.

[0284] "Health prediction" refers to analyzing and predicting future health status and risks based on the collected data. Through this prediction, preventive health management and proposals for improvement measures are carried out.

[0285] A "generative model" refers to an algorithm that discovers patterns from data and generates new data based on that knowledge. This model has the ability to generate appropriate outputs for specific inputs.

[0286] "Reaction data" refers to information regarding users' feedback and actions obtained after using the system. This can be utilized to improve the quality of services and products.

[0287] This invention is a system for individual users to effectively understand their own health conditions and promote the improvement of their lifestyles. The system mainly consists of three elements: a server, a terminal, and a user.

[0288] The server automatically collects health-related data from health diagnosis institutions and other medical facilities. The collected data is preprocessed, such as complementing missing information and eliminating abnormal values. Specifically, data cleaning and structuring are performed using programming languages like Python and data processing libraries such as NumPy and Pandas.

[0289] Next, the server utilizes the preprocessed data to proceed with the training of the generative AI model. This model is constructed using machine learning frameworks, such as TensorFlow or PyTorch, to predict the health risks of users. Examples of prompt texts, such as information like "40-year-old male, height 170 cm, weight 70 kg, exercise habit: three times a week", are input into the AI model.

[0290] The user's terminal receives the health risk prediction results from the server and visualizes the analysis results. For visualization, visualization libraries such as D3.js or Chart.js are utilized to present them in a form that is intuitive and easy for users to understand. For example, specific action proposals for reducing risks are provided to users for whom high blood pressure risks are predicted.

[0291] Furthermore, the device uses a generative AI model to provide a health status simulation based on newly entered data on the user's diet and exercise habits. This simulation allows the user to visualize the specific impacts of different behaviors on their health. For example, it can present simulation results on the impact of daily walking on blood pressure.

[0292] User feedback data is sent to the server and used to improve the accuracy of the generated AI model. Subsequent system updates will utilize this feedback data for learning, resulting in more accurate individual risk assessments.

[0293] This invention effectively supports users' health management through real-time risk prediction and functions that assist in individual user behavioral changes.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The server collects health-related data from medical facilities via APIs and database connections. Inputs are anonymized biometric data such as user blood pressure, blood glucose levels, and weight, while output is raw, unprocessed data. This raw data is stored within the system.

[0297] Step 2:

[0298] The server processes the collected raw data, performing operations to impute missing information and remove outliers. The input is the previously stored raw data, and the output is a clean dataset with missing values ​​imputed and outliers removed. Specifically, it uses Python's NumPy and Pandas to examine each data element, impute missing parts with the median, and remove outliers exceeding 3 standard deviations.

[0299] Step 3:

[0300] The server trains the generative AI model by leveraging a clean dataset. The input is the preprocessed data obtained in Step 2, and the output is the AI model after training. Here, a process of optimizing the model parameters based on the data is performed using TensorFlow or PyTorch.

[0301] Step 4:

[0302] The server uses the trained AI model to individually predict the health risks for each user. The input is a prompt sentence containing user information (e.g., "40-year-old male, height 170 cm, weight 70 kg, exercise habit: 3 times a week"), and the output is the health risk score for that user. This risk score is quantified as the probability of developing a specific disease.

[0303] Step 5:

[0304] The user's terminal receives the health risk score sent from the server and visualizes it in an easy-to-understand manner for the user. The input is the health risk score, and the output is a display in the form of a graph or chart. Using D3.js or Chart.js, the score is visualized and the risk and its improvement methods are presented to the user.

[0305] Step 6:

[0306] The terminal simulates the health status by leveraging the generative AI model based on the data on the changes in the user's diet and exercise habits newly input by the user. The input is the data on the changes in the lifestyle settings set by the user, and the output is the simulation result showing the impact of the changes on the health risk. This enables the user to specifically understand the impact of behavioral changes.

[0307] Step 7:

[0308] User feedback data is sent to the server and used to retrain the generated AI model. The input is user feedback data, and the output is an updated AI model for improved accuracy. This continuous feedback loop improves the system's predictive accuracy, enabling more personalized health risk assessments.

[0309] (Application Example 1)

[0310] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0311] This invention aims to not only utilize individual health checkup information to predict health risks, but also to automatically apply benefits for related goods and services in electronic transactions based on those predictions. Conventionally, the use of health information has been limited to individual health management, making it difficult to extract multifaceted direct added value to specific commercial transactions. This invention aims to solve the problem of stimulating consumer behavior and promoting health awareness by providing specific benefits tailored to individual health conditions.

[0312] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0313] In this invention, the server includes means for collecting health checkup information, means for supplementing missing information and removing outliers from the health checkup information, means for training a machine learning model to predict health risks using the supplemented and removed information, means for performing health simulations based on changes in diet and exercise habits, and means for automatically applying discounts on related products and services during electronic transactions based on the health risk prediction results. This enables users to manage their health while enjoying benefits based on the prediction results.

[0314] "Health checkup information" refers to data related to an individual's health status obtained from medical institutions, etc., and includes basic indicators such as blood pressure, blood sugar levels, and weight.

[0315] "Completing missing data" is the process of supplementing missing data points in health checkup information through estimation to create a complete dataset.

[0316] "Removing outliers" is a process that improves the accuracy of data by removing unnatural values ​​or data that is statistically considered abnormal from health checkup information.

[0317] A "machine learning model" refers to an algorithm or mathematical method that learns patterns and relationships based on collected data and uses them to make predictions about future data.

[0318] "Changes in dietary and exercise habits" means altering daily eating and exercise patterns to improve an individual's health, with the aim of reducing health risks.

[0319] A "health simulation" is a method that demonstrates to users the impact of specific improvement measures by virtually testing how their health status would change under certain conditions.

[0320] "Automatically applying discounts during electronic transactions" refers to a feature that reduces the price of goods or services when a user purchases them online, provided they meet pre-set conditions.

[0321] This invention is a system that effectively utilizes health checkup information to provide users with personalized health risk predictions and benefits in commercial transactions. The system operates primarily using servers, user terminals, and cloud resources.

[0322] The server collects health checkup information based on a predefined protocol. Before storing the collected information in the database, it uses the Pandas library to impute missing information and remove outliers. This cleansed information is then used to train a generative AI model using TensorFlow, providing a function to predict health risks.

[0323] The terminal is responsible for receiving health risk prediction results from the server after the user inputs health checkup information. Based on these results, a user interface is built using ReactJS, providing the user with visual feedback. Users can also input changes to their daily eating habits and exercise routines as feedback, which triggers simulations. When the user executes an electronic transaction, the server automatically applies appropriate discounts and benefits.

[0324] As a concrete example, consider a scenario where a user shops at a supermarket's online store. Based on health checkup information entered by the user beforehand, a generating AI model evaluates their health status, and if it shows a trend toward improvement, a discount on a vegetable set is offered during the next online payment. This process is designed so that users can consciously improve their health while simultaneously receiving concrete benefits through actual commercial transactions.

[0325] An example of a prompt for the generating AI model would be: "Based on the user's age, gender, and recent health check results, please suggest lifestyle changes that can be expected to improve before the next check-up."

[0326] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0327] Step 1:

[0328] The server collects health checkup information from health checkup providers. The input information includes basic health indicators such as the user's blood pressure, blood sugar level, and weight. This information is stored in a database on the server and prepared for the next step.

[0329] Step 2:

[0330] The server uses the Pandas library to impute missing information and remove outliers from the collected health checkup data. The input is raw data, and the output of this step is a clean and complete dataset. Mathematical imputation and statistical analysis are used in this data processing to ensure data consistency and accuracy.

[0331] Step 3:

[0332] The server trains a generative AI model using TensorFlow with preprocessed data. The input here is the cleaned dataset, and the output is the model parameters for predicting health risks. The model uses the user's historical data and prediction algorithm to quantify individual health risks.

[0333] Step 4:

[0334] The device receives health risk prediction results sent from the server. The input is the health risk quantified by the model, and the output is a visual display on the user interface. Here, ReactJS is used to provide a graphical display that allows the user to intuitively understand the risk.

[0335] Step 5:

[0336] Users input changes to their diet and exercise habits into a terminal. Based on this input, the server combines pre-processed data with the new lifestyle data to perform a simulation. The output is a predicted change in health status, which is displayed on the user's terminal.

[0337] Step 6:

[0338] The server applies incentives in commercial transactions based on these health risk prediction results and user feedback data. Here, applicable discounts and coupons are selected from the incentive database based on the prediction results and the user's improvement trends, and are automatically used during electronic transactions. The input is a risk assessment by a generative AI model, and the output is specific commercial transaction incentives.

[0339] Step 7:

[0340] The server collects feedback data from users and uses it to retrain the generative AI model. The input to this step is the feedback data, and the output is new model parameters that reflect the improved accuracy of the model. This allows the system to continuously learn and provide more accurate predictions.

[0341] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0342] This invention is a system for accurately understanding a user's health status and supporting appropriate health management. This system combines three entities—a server, a terminal, and the user—with an emotion engine that recognizes the user's emotional state.

[0343] First, the server collects health checkup data from health checkup agencies and medical institutions. This data includes biological data such as blood pressure, blood sugar levels, weight, and cholesterol levels. To maintain data integrity, the server performs data imputation and outlier removal.

[0344] Next, the server trains a generative AI model using the adjusted data to predict health risks. This model quantifies the health risks for each user and calculates the likelihood of developing specific diseases. Furthermore, an emotion engine is used to analyze the user's emotional state and evaluate their reaction to the health risk predictions and their stress levels.

[0345] The device prompts the user to submit health checkup data and visually displays the health risk prediction and emotion analysis results received from the server. For example, if the risk is high, it provides advice that takes stress levels into consideration and encourages behavioral improvement with positive messages. Furthermore, based on the emotion engine's analysis, it adjusts lifestyle improvement suggestions to match the user's psychological state.

[0346] Furthermore, the device simulates changes in the user's chosen diet and exercise habits and visualizes their effects. The emotion engine evaluates how the user reacts to this simulation and prepares to send feedback to the server.

[0347] Based on the information obtained from the system, users implement lifestyle improvements and provide feedback on their emotions and health status. This feedback is collected by the server and used to retrain the generative AI model. As a result, more personalized health management support becomes possible.

[0348] As a concrete example, consider a 50-year-old female user of this system. The user sends her latest health check results to the server, and the system, after evaluating her emotional state, notifies her that she is at high risk of diabetes. At this point, the emotion engine recognizes that the user is experiencing stress, and suggestions for relaxation and dietary improvement advice that also serves as stress relief are displayed on the device. The user can use this information to take actions to reduce their health risks.

[0349] The following describes the processing flow.

[0350] Step 1:

[0351] The server collects users' health checkup data from health checkup agencies and medical institutions. This data includes key health indicators such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0352] Step 2:

[0353] The server imputes missing values ​​and removes outliers from the collected health checkup data. For example, it ensures the integrity of the dataset by imputing the mean using statistical methods.

[0354] Step 3:

[0355] The server trains a generative AI model using pre-processed data. Based on past data patterns, it creates a model to predict each user's health risk.

[0356] Step 4:

[0357] The user's device transmits health check results and basic information to the server. The device also provides an input interface, allowing the user to easily enter the necessary information.

[0358] Step 5:

[0359] The server uses a generated AI model to predict health risks based on the data submitted by the user. It quantifies the risk of developing a disease and calculates the likelihood of developing a specific illness.

[0360] Step 6:

[0361] The server uses an emotion engine to recognize the user's emotional state. This function acquires and analyzes data from the user's facial expressions and tone of voice while they are using the device.

[0362] Step 7:

[0363] The server sends the results of health risk prediction and sentiment analysis to the user's terminal. It creates advice that considers the user's emotional state, rather than just suggesting health risks.

[0364] Step 8:

[0365] The device visually displays health risk predictions and lifestyle improvement suggestions tailored to the user's emotions. If the user's stress level is high, it provides advice on relaxation methods and stress reduction.

[0366] Step 9:

[0367] The device simulates health status based on changes in diet and exercise habits, and presents the results to the user. This allows the user to develop a concrete improvement plan.

[0368] Step 10:

[0369] Users review their lifestyle habits based on information provided by the system and send feedback to the server via their device. This feedback includes the effectiveness of the suggestions and their emotional response.

[0370] Step 11:

[0371] The server collects user feedback data and uses it to retrain the generative AI model. This improves the system's predictive accuracy and enables more personalized support.

[0372] (Example 2)

[0373] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0374] In modern times, personal health management is extremely important. However, conventional systems do not adequately predict health risks based on individual health information or provide lifestyle improvement suggestions that take into account responses based on emotional states. As a result, there is a challenge in supporting health management that reflects the individual characteristics of each user.

[0375] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0376] In this invention, the server includes means for collecting health information, means for supplementing missing data and removing anomalous data, means for training a machine learning model to estimate health risks, and means for analyzing emotional states. This makes it possible to provide more accurate and personalized health risk predictions and lifestyle improvement suggestions that take into account the user's emotional state.

[0377] "Health information" refers to various data that indicate an individual's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0378] "Completing missing data" refers to supplementing the data that is missing from the collected health information based on statistical methods and past data patterns.

[0379] "Removing abnormal data" is a technique that detects data in health information that deviates from the normal range and prevents it from affecting the analysis.

[0380] "Training a machine learning model" means optimizing the parameters of an algorithm that predicts health risks based on a large amount of health information data.

[0381] "Analyzing emotional state" means using text and audio information obtained from the user to evaluate their psychological state and stress level.

[0382] A "terminal device" is a device used to provide information to users, and is used to visually display health risk prediction results and lifestyle improvement suggestions.

[0383] This invention is a system that evaluates individual health risks based on the user's health information and proposes appropriate lifestyle improvements. This system is primarily composed of three components: a server, a terminal, and the user.

[0384] The server is the primary component responsible for managing health information and processing data. It collects various health information, performs data completion (missing data) and removal (removing anomalous data). This process utilizes statistical methods and machine learning algorithms. Furthermore, it leverages generative AI models to predict health risks using the collected health information data. These models can quantify the risk of developing specific diseases.

[0385] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine combines natural language processing and speech analysis technologies to evaluate the user's psychological state and stress level.

[0386] The terminal functions as a user interface and visualizes information. It receives health risk prediction results and sentiment analysis results transmitted from the server and displays them in a user-friendly format. For example, it might present risk assessment results as infographics or graphs and offer specific advice for health improvement as actionable suggestions.

[0387] Users refer to the information provided by the system and use it for health management in their daily lives. Users provide feedback through their devices, and this feedback is collected on the server and used to retrain the generated AI model. This enables personalized health support for each user.

[0388] As a concrete example, when a user uses this system, the following prompt message could be used: "Assess the user's current health status, take their emotional state into consideration, and present health risks and suggested solutions."

[0389] In this way, the present invention provides specific means and processes for realizing highly personalized health management.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The server collects users' health information from health checkup agencies and medical institutions. This health information includes blood pressure, blood sugar levels, weight, cholesterol levels, etc. The collected data is received as input and stored in a database. This prepares the basic data for subsequent processing.

[0393] Step 2:

[0394] The server verifies the collected health information, imputing missing data and removing anomalous data. This is done using statistical methods and estimations based on past data patterns. The input to this process is health information, and the output is a well-organized dataset. This ensures data integrity and prepares the system for improving the accuracy of subsequent health risk predictions.

[0395] Step 3:

[0396] The server trains a generative AI model using a prepared dataset. It uses machine learning algorithms to develop a model capable of quantifying health risks. The input requires a prepared dataset, and the output is a trained generative AI model. This model is used to predict risks that differ for each user.

[0397] Step 4:

[0398] The server uses an emotion engine to analyze the user's emotional state. It takes user text and voice information as input and evaluates their psychological state and stress level as output. This analysis allows for consideration of the user's response to the health risk prediction results.

[0399] Step 5:

[0400] The terminal visually displays health risk prediction results and sentiment analysis results obtained from the server. It processes the received data as input and presents it to the user as infographics and advice. This allows the user to intuitively understand their own health status and recognize the suggested improvement methods.

[0401] Step 6:

[0402] The device simulates changes to the user's chosen eating and exercise habits. This visualizes the impact of these changes on health, taking the user's choices as input and outputting estimated health effects. This helps users understand their lifestyle choices.

[0403] Step 7:

[0404] Users improve their lifestyle habits based on feedback from the system. Furthermore, they provide feedback on their emotions and health status, which is reported to the server. The input consists of the user's experiences and impressions, and the output serves as input for the next model retraining, contributing to the overall improvement of the system's accuracy.

[0405] (Application Example 2)

[0406] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0407] Modern in-store health management solutions struggle to provide customized recommendations based on the individual health and emotional states of each user. In particular, there is a need for immediate analysis of on-site health check data and the corresponding recommendations of appropriate products and services. However, existing systems have limitations in providing recommendations that adequately consider the emotional state of the user, resulting in insufficient personalized health management support.

[0408] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0409] In this invention, the server includes means for collecting health checkup information, means for evaluating emotional states and adjusting suggestions based on health simulation results to suit the user's psychological state, and means for collecting user feedback information and retraining a generated AI model using the collected information. This makes it possible to offer customized products and services in physical stores that take into account the individual user's health status and emotions.

[0410] "Health checkup information" refers to data that quantifies the user's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0411] "Completing missing information" refers to the process of supplementing data that is missing from health checkup information through estimation or derivation.

[0412] "Removal of abnormal information" is the process of detecting and removing data from health checkup information that falls outside the normal range.

[0413] A "machine learning algorithm" is a computational method for building models that automatically perform specific tasks using large amounts of data.

[0414] An "information presentation device" is a device that provides users with analysis results and suggestions visually or audibly.

[0415] "Health simulation" is a process that predicts and visualizes the impact that changes in diet and exercise habits will have on a user's health.

[0416] "Emotional state" refers to a state that reflects the user's psychological and emotional health.

[0417] A "generative AI model" is an artificial intelligence system that learns from large amounts of data and performs predictions and generation.

[0418] "Feedback information" refers to opinions and data provided by users, based on their experiences and results.

[0419] To implement this invention, a system is configured in which a server, terminal, and user work in cooperation. First, the server collects health checkup information from health checkup institutions and medical institutions. The collected data is processed using Python to impute missing information and remove anomalous information. Next, a machine learning algorithm is trained using TensorFlow to predict the health risk for each user.

[0420] Furthermore, the server analyzes the emotional state using an NLP library. Based on these results, it provides personalized suggestions to the information presentation device using a generative AI model. These suggestions include products and services that take into account the user's health and emotional state.

[0421] The device, through a frontend built with React Native, presents users with health risk predictions and specific suggestions. Based on these results, users can run simulations to change their eating habits and exercise routines, and visually confirm the results.

[0422] Users manage their health based on the provided suggestions and send feedback information to the server via their device. The server uses the collected feedback information to retrain the generative AI model and further improve its accuracy.

[0423] As a concrete example, a user participates in a health event at a physical store and enters their health checkup information via their smartphone. Based on this information, the server immediately predicts health risks and suggests supplements and fitness plans tailored to the user's stress level.

[0424] Examples of prompts to input into a generative AI model:

[0425] "Based on the user's age, health checkup data (blood pressure, blood sugar levels, etc.), and emotional state (e.g., high stress level), please propose the most suitable health improvement measures."

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The server collects health checkup information from health checkup institutions and medical facilities. The collected data is entered into the server as JSON format data. This data includes blood pressure, blood sugar levels, weight, cholesterol levels, etc.

[0429] Step 2:

[0430] The server uses Python to fill in missing information from collected health checkup data. This employs methods such as substitution using common values ​​and machine learning-based completion techniques. Unfilled data is input, and filled-in data is output.

[0431] Step 3:

[0432] Next, the server removes anomalous information from the completed data. Here, it detects and removes outliers based on a pre-defined normal range. The completed data becomes the input, and a clean dataset is output.

[0433] Step 4:

[0434] Using a clean dataset, the server trains a machine learning algorithm using TensorFlow. This generates a model for predicting health risks. The input is a clean dataset, and the output is a health risk score.

[0435] Step 5:

[0436] The server uses an NLP library to evaluate the user's emotional state. It performs sentiment analysis from the user's written text and calculates stress levels and emotional state scores. The input is the user's text data, and the output is the evaluation result of the emotional state.

[0437] Step 6:

[0438] The device uses a frontend built with React Native to display health risk scores and emotional states received from the server to the user. The displayed information is presented through a visual interface. Input is the evaluation results from the server, and output is the information displayed on the user interface.

[0439] Step 7:

[0440] Based on the presented results, the user simulates their diet and exercise habits. The device calculates the simulation results and presents the effects to the user. The input is the simulation conditions selected by the user, and the output is the predicted health improvement effect.

[0441] Step 8:

[0442] Users send feedback information to the server via their device. This feedback includes actions taken by the user and the effects they perceived. The input is the user's feedback data, and the output is the feedback repository on the server.

[0443] Step 9:

[0444] The server uses the collected feedback information to retrain the generative AI model. This retraining improves the model's prediction accuracy. The input is the feedback information, and the output is the newly adjusted AI model.

[0445] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0446] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0447] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0448] [Third Embodiment]

[0449] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0450] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0451] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0452] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0453] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0454] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0455] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0456] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0457] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0458] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0459] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0460] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0461] This invention is a system that enables individual users to effectively understand future health risks and promote lifestyle improvements by utilizing their health checkup data. This system mainly consists of three components: a server, terminals, and users.

[0462] First, the server periodically collects digital health checkup data from health checkup agencies and medical institutions. This data includes basic health information of users (e.g., blood pressure, blood sugar levels, weight, etc.) and information about their lifestyle. The collected data is preprocessed on the server, with missing values ​​imputed and outliers removed, to prepare it for analysis.

[0463] Next, the server trains a generative AI model using the pre-processed data. This AI model is designed to predict health risks based on gender, age, and lifestyle. The server uses this model to quantify each user's future health risks and calculate the probability of developing specific diseases.

[0464] The user's device sends their health checkup results to a server and receives a health risk prediction based on those results. The device then visually presents the received prediction data to the user. For example, it might display a graph showing the percentage of the user's risk of developing high blood pressure or diabetes in the future and provide advice on necessary lifestyle changes.

[0465] Furthermore, the device provides a health simulation function based on the user's input of new dietary and exercise habits. This function allows users to visually see the impact of different behaviors on their health. For example, it can simulate how blood pressure improves by increasing exercise.

[0466] Furthermore, user feedback data is sent to the server and used to improve the accuracy of the generated AI model. The updated model can provide more accurate and personalized health risk predictions. Through this cycle, the system continuously learns and improves, enhancing the quality of support for users' health management.

[0467] As a concrete example, consider the case of a 40-year-old male user of the system. When the user enters his latest health check results into the system, the server predicts that he has a 25% risk of developing high blood pressure. A simulation showing that he adds 30 minutes of walking to his daily routine could reduce his risk to 20%. This encourages the user to make actual behavioral changes and improve his health.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] The server periodically collects users' health checkup data from health checkup agencies and medical institutions. This includes biological data such as blood pressure, weight, blood sugar levels, and cholesterol levels, as well as data related to lifestyle habits.

[0471] Step 2:

[0472] The server fills in missing data from the collected data. Using statistical methods, it fills in missing values, for example, by applying mean values ​​based on age and gender. It also removes or adjusts outliers that are abnormally skewed.

[0473] Step 3:

[0474] The server uses pre-processed data to train a generative AI model. The model learns how factors such as gender, age, and lifestyle influence future health risks, thereby improving the accuracy of health risk predictions.

[0475] Step 4:

[0476] Users upload their latest health check results from their devices to the server. The user's input forms the basis for analysis by an AI model.

[0477] Step 5:

[0478] The server receives the user's health checkup data and analyzes health risks using a generated AI model. It quantifies the risk of future disease onset and predicts the likelihood of specific illnesses.

[0479] Step 6:

[0480] The terminal visually presents the user with predictive data received from the server. Charts and lists are used to clearly illustrate the percentage of disease risk and provide advice.

[0481] Step 7:

[0482] The device accepts changes to the user's diet and exercise habits and runs a simulation function. For example, it predicts changes in health status if a specific action is taken and shows the results to the user.

[0483] Step 8:

[0484] Based on the information provided, users decide on actions to improve their lifestyle. If necessary, they send feedback back to the server via their device.

[0485] Step 9:

[0486] The server collects user feedback data and uses it to retrain the generated AI model. This allows for further improvement in the model's accuracy and the provision of more personalized predictions.

[0487] (Example 1)

[0488] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0489] In recent years, the importance of health management has increased, but many individuals face the challenge of accurately understanding their own health status and making appropriate behavioral changes. Furthermore, conventional health risk assessment methods do not fully utilize individual lifestyles and individual health data, resulting in inaccurate predictions. In addition, the lack of real-time feedback on user behavioral changes makes it difficult to maintain motivation for health management.

[0490] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0491] In this invention, the server includes means for collecting health-related data, means for supplementing missing information and removing outliers from the health-related data, and means for training a learning model to predict risk using the supplemented and removed data. This enables highly accurate risk prediction based on individual health data. Furthermore, users are offered specific action plans based on the health prediction results and can visualize the actual impact of behavioral changes on their health, thereby promoting more effective health management.

[0492] "Health-related data" refers to information about an individual's health status and lifestyle. This data includes physical indicators such as blood pressure, blood sugar levels, and weight, as well as daily diet and exercise levels.

[0493] "Imputing missing information" refers to the process of filling in missing portions of a dataset using appropriate methods. This resolves data inconsistencies and improves the accuracy of analysis.

[0494] "Outlier removal" refers to the process of removing values ​​that exhibit abnormal deviations within a dataset. This process reduces the impact of extreme values ​​and allows for more accurate analysis results.

[0495] A "learning model" refers to an algorithm that learns specific rules or patterns based on data. This model is used to predict future events by utilizing machine learning and statistical methods.

[0496] An "information terminal" refers to an electronic device used by a user to input and output various types of data. Generally, this includes smartphones, tablets, and personal computers.

[0497] "Health prediction" refers to analyzing and predicting future health conditions and risks based on collected data. This prediction allows for the suggestion of preventative health management and improvement measures.

[0498] A "generative model" refers to an algorithm that identifies patterns in data and generates new data based on that knowledge. This model has the ability to produce an appropriate output for a given input.

[0499] "Response data" refers to information about user feedback and behavior obtained after using a system. This data can be used to improve the quality of services and products.

[0500] This invention is a system designed to enable individual users to effectively understand their own health status and promote improvements in their lifestyle. The system mainly consists of three elements: a server, a terminal, and a user.

[0501] The server automatically collects health-related data from health checkup agencies and other medical facilities. The collected data undergoes preprocessing, such as filling in missing information and removing outliers. Specifically, it uses programming languages ​​such as Python and data processing libraries such as NumPy and Pandas to clean and structure the data.

[0502] Next, the server uses the pre-processed data to train the generative AI model. This model is built using machine learning frameworks, such as TensorFlow or PyTorch, to predict the user's health risks. For example, prompts such as "40-year-old male, 170cm tall, 70kg weight, exercise habits: 3 times a week" are input to the AI ​​model.

[0503] The user's device receives health risk prediction results from the server and visualizes the analysis results. Visualization libraries such as D3.js and Chart.js are used to present the results in an intuitively understandable format for the user. For example, a user predicted to have a high risk of hypertension will be given specific action suggestions to reduce that risk.

[0504] Furthermore, the device uses a generative AI model to provide a health status simulation based on newly entered data on the user's diet and exercise habits. This simulation allows the user to visualize the specific impacts of different behaviors on their health. For example, it can present simulation results on the impact of daily walking on blood pressure.

[0505] User feedback data is sent to the server and used to improve the accuracy of the generated AI model. Subsequent system updates will utilize this feedback data for learning, resulting in more accurate individual risk assessments.

[0506] This invention effectively supports users' health management through real-time risk prediction and functions that assist in individual user behavioral changes.

[0507] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0508] Step 1:

[0509] The server collects health-related data from medical facilities via APIs and database connections. Inputs are anonymized biometric data such as user blood pressure, blood glucose levels, and weight, while output is raw, unprocessed data. This raw data is stored within the system.

[0510] Step 2:

[0511] The server processes the collected raw data, performing operations to impute missing information and remove outliers. The input is the previously stored raw data, and the output is a clean dataset with missing values ​​imputed and outliers removed. Specifically, it uses Python's NumPy and Pandas to examine each data element, impute missing parts with the median, and remove outliers exceeding 3 standard deviations.

[0512] Step 3:

[0513] The server uses a clean dataset to train a generative AI model. The input is the preprocessed data obtained in step 2, and the output is the trained AI model. Here, TensorFlow or PyTorch is used to optimize the model parameters based on the data.

[0514] Step 4:

[0515] The server uses a pre-trained AI model to individually predict each user's health risk. The input is a prompt containing user information (e.g., "40-year-old male, 170cm tall, 70kg weight, exercise habits: 3 times a week"), and the output is the user's health risk score. This risk score is quantified as the probability of developing a specific disease.

[0516] Step 5:

[0517] The user's device receives a health risk score sent from the server and visualizes it in an easy-to-understand format for the user. The input is the health risk score, and the output is displayed in graph or chart format. D3.js and Chart.js are used to visualize the score and present the user with their risks and ways to improve them.

[0518] Step 6:

[0519] The device uses a generative AI model to simulate the user's health status based on newly entered data on changes in their eating habits and exercise routines. The input is the user's set data on lifestyle changes, and the output is a simulation result showing the impact of those changes on health risks. This allows the user to concretely understand the effects of behavioral changes.

[0520] Step 7:

[0521] User feedback data is sent to the server and used to retrain the generated AI model. The input is user feedback data, and the output is an updated AI model for improved accuracy. This continuous feedback loop improves the system's predictive accuracy, enabling more personalized health risk assessments.

[0522] (Application Example 1)

[0523] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0524] This invention aims to not only utilize individual health checkup information to predict health risks, but also to automatically apply benefits for related goods and services in electronic transactions based on those predictions. Conventionally, the use of health information has been limited to individual health management, making it difficult to extract multifaceted direct added value to specific commercial transactions. This invention aims to solve the problem of stimulating consumer behavior and promoting health awareness by providing specific benefits tailored to individual health conditions.

[0525] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0526] In this invention, the server includes means for collecting health checkup information, means for supplementing missing information and removing outliers from the health checkup information, means for training a machine learning model to predict health risks using the supplemented and removed information, means for performing health simulations based on changes in diet and exercise habits, and means for automatically applying discounts on related products and services during electronic transactions based on the health risk prediction results. This enables users to manage their health while enjoying benefits based on the prediction results.

[0527] "Health checkup information" refers to data related to an individual's health status obtained from medical institutions, etc., and includes basic indicators such as blood pressure, blood sugar levels, and weight.

[0528] "Completing missing data" is the process of supplementing missing data points in health checkup information through estimation to create a complete dataset.

[0529] "Removing outliers" is a process that improves the accuracy of data by removing unnatural values ​​or data that is statistically considered abnormal from health checkup information.

[0530] A "machine learning model" refers to an algorithm or mathematical method that learns patterns and relationships based on collected data and uses them to make predictions about future data.

[0531] "Changes in dietary and exercise habits" means altering daily eating and exercise patterns to improve an individual's health, with the aim of reducing health risks.

[0532] A "health simulation" is a method that demonstrates to users the impact of specific improvement measures by virtually testing how their health status would change under certain conditions.

[0533] "Automatically applying discounts during electronic transactions" refers to a feature that reduces the price of goods or services when a user purchases them online, provided they meet pre-set conditions.

[0534] This invention is a system that effectively utilizes health checkup information to provide users with personalized health risk predictions and benefits in commercial transactions. The system operates primarily using servers, user terminals, and cloud resources.

[0535] The server collects health checkup information based on a predefined protocol. Before storing the collected information in the database, it uses the Pandas library to impute missing information and remove outliers. This cleansed information is then used to train a generative AI model using TensorFlow, providing a function to predict health risks.

[0536] The terminal is responsible for receiving health risk prediction results from the server after the user inputs health checkup information. Based on these results, a user interface is built using ReactJS, providing the user with visual feedback. Users can also input changes to their daily eating habits and exercise routines as feedback, which triggers simulations. When the user executes an electronic transaction, the server automatically applies appropriate discounts and benefits.

[0537] As a concrete example, consider a scenario where a user shops at a supermarket's online store. Based on health checkup information entered by the user beforehand, a generating AI model evaluates their health status, and if it shows a trend toward improvement, a discount on a vegetable set is offered during the next online payment. This process is designed so that users can consciously improve their health while simultaneously receiving concrete benefits through actual commercial transactions.

[0538] An example of a prompt for the generating AI model would be: "Based on the user's age, gender, and recent health check results, please suggest lifestyle changes that can be expected to improve before the next check-up."

[0539] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0540] Step 1:

[0541] The server collects health checkup information from health checkup providers. The input information includes basic health indicators such as the user's blood pressure, blood sugar level, and weight. This information is stored in a database on the server and prepared for the next step.

[0542] Step 2:

[0543] The server uses the Pandas library to impute missing information and remove outliers from the collected health checkup data. The input is raw data, and the output of this step is a clean and complete dataset. Mathematical imputation and statistical analysis are used in this data processing to ensure data consistency and accuracy.

[0544] Step 3:

[0545] The server trains a generative AI model using TensorFlow with preprocessed data. The input here is the cleaned dataset, and the output is the model parameters for predicting health risks. The model uses the user's historical data and prediction algorithm to quantify individual health risks.

[0546] Step 4:

[0547] The device receives health risk prediction results sent from the server. The input is the health risk quantified by the model, and the output is a visual display on the user interface. Here, ReactJS is used to provide a graphical display that allows the user to intuitively understand the risk.

[0548] Step 5:

[0549] Users input changes to their diet and exercise habits into a terminal. Based on this input, the server combines pre-processed data with the new lifestyle data to perform a simulation. The output is a predicted change in health status, which is displayed on the user's terminal.

[0550] Step 6:

[0551] The server applies incentives in commercial transactions based on these health risk prediction results and user feedback data. Here, applicable discounts and coupons are selected from the incentive database based on the prediction results and the user's improvement trends, and are automatically used during electronic transactions. The input is a risk assessment by a generative AI model, and the output is specific commercial transaction incentives.

[0552] Step 7:

[0553] The server collects feedback data from users and uses it to retrain the generative AI model. The input to this step is the feedback data, and the output is new model parameters that reflect the improved accuracy of the model. This allows the system to continuously learn and provide more accurate predictions.

[0554] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0555] This invention is a system for accurately understanding a user's health status and supporting appropriate health management. This system combines three entities—a server, a terminal, and the user—with an emotion engine that recognizes the user's emotional state.

[0556] First, the server collects health checkup data from health checkup agencies and medical institutions. This data includes biological data such as blood pressure, blood sugar levels, weight, and cholesterol levels. To maintain data integrity, the server performs data imputation and outlier removal.

[0557] Next, the server trains a generative AI model using the adjusted data to predict health risks. This model quantifies the health risks for each user and calculates the likelihood of developing specific diseases. Furthermore, an emotion engine is used to analyze the user's emotional state and evaluate their reaction to the health risk predictions and their stress levels.

[0558] The device prompts the user to submit health checkup data and visually displays the health risk prediction and emotion analysis results received from the server. For example, if the risk is high, it provides advice that takes stress levels into consideration and encourages behavioral improvement with positive messages. Furthermore, based on the emotion engine's analysis, it adjusts lifestyle improvement suggestions to match the user's psychological state.

[0559] Furthermore, the device simulates changes in the user's chosen diet and exercise habits and visualizes their effects. The emotion engine evaluates how the user reacts to this simulation and prepares to send feedback to the server.

[0560] Based on the information obtained from the system, users implement lifestyle improvements and provide feedback on their emotions and health status. This feedback is collected by the server and used to retrain the generative AI model. As a result, more personalized health management support becomes possible.

[0561] As a concrete example, consider a 50-year-old female user of this system. The user sends her latest health check results to the server, and the system, after evaluating her emotional state, notifies her that she is at high risk of diabetes. At this point, the emotion engine recognizes that the user is experiencing stress, and suggestions for relaxation and dietary improvement advice that also serves as stress relief are displayed on the device. The user can use this information to take actions to reduce their health risks.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The server collects users' health checkup data from health checkup agencies and medical institutions. This data includes key health indicators such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0565] Step 2:

[0566] The server imputes missing values ​​and removes outliers from the collected health checkup data. For example, it ensures the integrity of the dataset by imputing the mean using statistical methods.

[0567] Step 3:

[0568] The server trains a generative AI model using pre-processed data. Based on past data patterns, it creates a model to predict each user's health risk.

[0569] Step 4:

[0570] The user's device transmits health check results and basic information to the server. The device also provides an input interface, allowing the user to easily enter the necessary information.

[0571] Step 5:

[0572] The server uses a generated AI model to predict health risks based on the data submitted by the user. It quantifies the risk of developing a disease and calculates the likelihood of developing a specific illness.

[0573] Step 6:

[0574] The server uses an emotion engine to recognize the user's emotional state. This function acquires and analyzes data from the user's facial expressions and tone of voice while they are using the device.

[0575] Step 7:

[0576] The server sends the results of health risk prediction and sentiment analysis to the user's terminal. It creates advice that considers the user's emotional state, rather than just suggesting health risks.

[0577] Step 8:

[0578] The device visually displays health risk predictions and lifestyle improvement suggestions tailored to the user's emotions. If the user's stress level is high, it provides advice on relaxation methods and stress reduction.

[0579] Step 9:

[0580] The device simulates health status based on changes in diet and exercise habits, and presents the results to the user. This allows the user to develop a concrete improvement plan.

[0581] Step 10:

[0582] Users review their lifestyle habits based on information provided by the system and send feedback to the server via their device. This feedback includes the effectiveness of the suggestions and their emotional response.

[0583] Step 11:

[0584] The server collects user feedback data and uses it to retrain the generative AI model. This improves the system's predictive accuracy and enables more personalized support.

[0585] (Example 2)

[0586] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0587] In modern times, personal health management is extremely important. However, conventional systems do not adequately predict health risks based on individual health information or provide lifestyle improvement suggestions that take into account responses based on emotional states. As a result, there is a challenge in supporting health management that reflects the individual characteristics of each user.

[0588] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0589] In this invention, the server includes means for collecting health information, means for supplementing missing data and removing anomalous data, means for training a machine learning model to estimate health risks, and means for analyzing emotional states. This makes it possible to provide more accurate and personalized health risk predictions and lifestyle improvement suggestions that take into account the user's emotional state.

[0590] "Health information" refers to various data that indicate an individual's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0591] "Completing missing data" refers to supplementing the data that is missing from the collected health information based on statistical methods and past data patterns.

[0592] "Removing abnormal data" is a technique that detects data in health information that deviates from the normal range and prevents it from affecting the analysis.

[0593] "Training a machine learning model" means optimizing the parameters of an algorithm that predicts health risks based on a large amount of health information data.

[0594] "Analyzing emotional state" means using text and audio information obtained from the user to evaluate their psychological state and stress level.

[0595] A "terminal device" is a device used to provide information to users, and is used to visually display health risk prediction results and lifestyle improvement suggestions.

[0596] This invention is a system that evaluates individual health risks based on the user's health information and proposes appropriate lifestyle improvements. This system is primarily composed of three components: a server, a terminal, and the user.

[0597] The server is the primary component responsible for managing health information and processing data. It collects various health information, performs data completion (missing data) and removal (removing anomalous data). This process utilizes statistical methods and machine learning algorithms. Furthermore, it leverages generative AI models to predict health risks using the collected health information data. These models can quantify the risk of developing specific diseases.

[0598] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine combines natural language processing and speech analysis technologies to evaluate the user's psychological state and stress level.

[0599] The terminal functions as a user interface and visualizes information. It receives health risk prediction results and sentiment analysis results transmitted from the server and displays them in a user-friendly format. For example, it might present risk assessment results as infographics or graphs and offer specific advice for health improvement as actionable suggestions.

[0600] Users refer to the information provided by the system and use it for health management in their daily lives. Users provide feedback through their devices, and this feedback is collected on the server and used to retrain the generated AI model. This enables personalized health support for each user.

[0601] As a concrete example, when a user uses this system, the following prompt message could be used: "Assess the user's current health status, take their emotional state into consideration, and present health risks and suggested solutions."

[0602] In this way, the present invention provides specific means and processes for realizing highly personalized health management.

[0603] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0604] Step 1:

[0605] The server collects users' health information from health checkup agencies and medical institutions. This health information includes blood pressure, blood sugar levels, weight, cholesterol levels, etc. The collected data is received as input and stored in a database. This prepares the basic data for subsequent processing.

[0606] Step 2:

[0607] The server verifies the collected health information, imputing missing data and removing anomalous data. This is done using statistical methods and estimations based on past data patterns. The input to this process is health information, and the output is a well-organized dataset. This ensures data integrity and prepares the system for improving the accuracy of subsequent health risk predictions.

[0608] Step 3:

[0609] The server trains a generative AI model using a prepared dataset. It uses machine learning algorithms to develop a model capable of quantifying health risks. The input requires a prepared dataset, and the output is a trained generative AI model. This model is used to predict risks that differ for each user.

[0610] Step 4:

[0611] The server uses an emotion engine to analyze the user's emotional state. It takes user text and voice information as input and evaluates their psychological state and stress level as output. This analysis allows for consideration of the user's response to the health risk prediction results.

[0612] Step 5:

[0613] The terminal visually displays health risk prediction results and sentiment analysis results obtained from the server. It processes the received data as input and presents it to the user as infographics and advice. This allows the user to intuitively understand their own health status and recognize the suggested improvement methods.

[0614] Step 6:

[0615] The device simulates changes to the user's chosen eating and exercise habits. This visualizes the impact of these changes on health, taking the user's choices as input and outputting estimated health effects. This helps users understand their lifestyle choices.

[0616] Step 7:

[0617] Users improve their lifestyle habits based on feedback from the system. Furthermore, they provide feedback on their emotions and health status, which is reported to the server. The input consists of the user's experiences and impressions, and the output serves as input for the next model retraining, contributing to the overall improvement of the system's accuracy.

[0618] (Application Example 2)

[0619] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0620] Modern in-store health management solutions struggle to provide customized recommendations based on the individual health and emotional states of each user. In particular, there is a need for immediate analysis of on-site health check data and the corresponding recommendations of appropriate products and services. However, existing systems have limitations in providing recommendations that adequately consider the emotional state of the user, resulting in insufficient personalized health management support.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0622] In this invention, the server includes means for collecting health checkup information, means for evaluating emotional states and adjusting suggestions based on health simulation results to suit the user's psychological state, and means for collecting user feedback information and retraining a generated AI model using the collected information. This makes it possible to offer customized products and services in physical stores that take into account the individual user's health status and emotions.

[0623] "Health checkup information" refers to data that quantifies the user's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0624] "Completing missing information" refers to the process of supplementing data that is missing from health checkup information through estimation or derivation.

[0625] "Removal of abnormal information" is the process of detecting and removing data from health checkup information that falls outside the normal range.

[0626] A "machine learning algorithm" is a computational method for building models that automatically perform specific tasks using large amounts of data.

[0627] An "information presentation device" is a device that provides users with analysis results and suggestions visually or audibly.

[0628] "Health simulation" is a process that predicts and visualizes the impact that changes in diet and exercise habits will have on a user's health.

[0629] "Emotional state" refers to a state that reflects the user's psychological and emotional health.

[0630] A "generative AI model" is an artificial intelligence system that learns from large amounts of data and performs predictions and generation.

[0631] "Feedback information" refers to opinions and data provided by users, based on their experiences and results.

[0632] To implement this invention, a system is configured in which a server, terminal, and user work in cooperation. First, the server collects health checkup information from health checkup institutions and medical institutions. The collected data is processed using Python to impute missing information and remove anomalous information. Next, a machine learning algorithm is trained using TensorFlow to predict the health risk for each user.

[0633] Furthermore, the server analyzes the emotional state using an NLP library. Based on these results, it provides personalized suggestions to the information presentation device using a generative AI model. These suggestions include products and services that take into account the user's health and emotional state.

[0634] The device, through a frontend built with React Native, presents users with health risk predictions and specific suggestions. Based on these results, users can run simulations to change their eating habits and exercise routines, and visually confirm the results.

[0635] Users manage their health based on the provided suggestions and send feedback information to the server via their device. The server uses the collected feedback information to retrain the generative AI model and further improve its accuracy.

[0636] As a concrete example, a user participates in a health event at a physical store and enters their health checkup information via their smartphone. Based on this information, the server immediately predicts health risks and suggests supplements and fitness plans tailored to the user's stress level.

[0637] Examples of prompts to input into a generative AI model:

[0638] "Based on the user's age, health checkup data (blood pressure, blood sugar levels, etc.), and emotional state (e.g., high stress level), please propose the most suitable health improvement measures."

[0639] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0640] Step 1:

[0641] The server collects health checkup information from health checkup institutions and medical facilities. The collected data is entered into the server as JSON format data. This data includes blood pressure, blood sugar levels, weight, cholesterol levels, etc.

[0642] Step 2:

[0643] The server uses Python to fill in missing information from collected health checkup data. This employs methods such as substitution using common values ​​and machine learning-based completion techniques. Unfilled data is input, and filled-in data is output.

[0644] Step 3:

[0645] Next, the server removes anomalous information from the completed data. Here, it detects and removes outliers based on a pre-defined normal range. The completed data becomes the input, and a clean dataset is output.

[0646] Step 4:

[0647] Using a clean dataset, the server trains a machine learning algorithm using TensorFlow. This generates a model for predicting health risks. The input is a clean dataset, and the output is a health risk score.

[0648] Step 5:

[0649] The server uses an NLP library to evaluate the user's emotional state. It performs sentiment analysis from the user's written text and calculates stress levels and emotional state scores. The input is the user's text data, and the output is the evaluation result of the emotional state.

[0650] Step 6:

[0651] The device uses a frontend built with React Native to display health risk scores and emotional states received from the server to the user. The displayed information is presented through a visual interface. Input is the evaluation results from the server, and output is the information displayed on the user interface.

[0652] Step 7:

[0653] Based on the presented results, the user simulates their diet and exercise habits. The device calculates the simulation results and presents the effects to the user. The input is the simulation conditions selected by the user, and the output is the predicted health improvement effect.

[0654] Step 8:

[0655] Users send feedback information to the server via their device. This feedback includes actions taken by the user and the effects they perceived. The input is the user's feedback data, and the output is the feedback repository on the server.

[0656] Step 9:

[0657] The server uses the collected feedback information to retrain the generative AI model. This retraining improves the model's prediction accuracy. The input is the feedback information, and the output is the newly adjusted AI model.

[0658] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0659] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0660] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0661] [Fourth Embodiment]

[0662] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0663] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0664] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0665] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0666] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0667] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0668] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0669] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0670] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0671] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0672] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0673] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0674] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0675] This invention is a system that enables individual users to effectively understand future health risks and promote lifestyle improvements by utilizing their health checkup data. This system mainly consists of three components: a server, terminals, and users.

[0676] First, the server periodically collects digital health checkup data from health checkup agencies and medical institutions. This data includes basic health information of users (e.g., blood pressure, blood sugar levels, weight, etc.) and information about their lifestyle. The collected data is preprocessed on the server, with missing values ​​imputed and outliers removed, to prepare it for analysis.

[0677] Next, the server trains a generative AI model using the pre-processed data. This AI model is designed to predict health risks based on gender, age, and lifestyle. The server uses this model to quantify each user's future health risks and calculate the probability of developing specific diseases.

[0678] The user's device sends their health checkup results to a server and receives a health risk prediction based on those results. The device then visually presents the received prediction data to the user. For example, it might display a graph showing the percentage of the user's risk of developing high blood pressure or diabetes in the future and provide advice on necessary lifestyle changes.

[0679] Furthermore, the device provides a health simulation function based on the user's input of new dietary and exercise habits. This function allows users to visually see the impact of different behaviors on their health. For example, it can simulate how blood pressure improves by increasing exercise.

[0680] Furthermore, user feedback data is sent to the server and used to improve the accuracy of the generated AI model. The updated model can provide more accurate and personalized health risk predictions. Through this cycle, the system continuously learns and improves, enhancing the quality of support for users' health management.

[0681] As a concrete example, consider the case of a 40-year-old male user of the system. When the user enters his latest health check results into the system, the server predicts that he has a 25% risk of developing high blood pressure. A simulation showing that he adds 30 minutes of walking to his daily routine could reduce his risk to 20%. This encourages the user to make actual behavioral changes and improve his health.

[0682] The following describes the processing flow.

[0683] Step 1:

[0684] The server periodically collects users' health checkup data from health checkup agencies and medical institutions. This includes biological data such as blood pressure, weight, blood sugar levels, and cholesterol levels, as well as data related to lifestyle habits.

[0685] Step 2:

[0686] The server fills in missing data from the collected data. Using statistical methods, it fills in missing values, for example, by applying mean values ​​based on age and gender. It also removes or adjusts outliers that are abnormally skewed.

[0687] Step 3:

[0688] The server uses pre-processed data to train a generative AI model. The model learns how factors such as gender, age, and lifestyle influence future health risks, thereby improving the accuracy of health risk predictions.

[0689] Step 4:

[0690] Users upload their latest health check results from their devices to the server. The user's input forms the basis for analysis by an AI model.

[0691] Step 5:

[0692] The server receives the user's health checkup data and analyzes health risks using a generated AI model. It quantifies the risk of future disease onset and predicts the likelihood of specific illnesses.

[0693] Step 6:

[0694] The terminal visually presents the user with predictive data received from the server. Charts and lists are used to clearly illustrate the percentage of disease risk and provide advice.

[0695] Step 7:

[0696] The device accepts changes to the user's diet and exercise habits and runs a simulation function. For example, it predicts changes in health status if a specific action is taken and shows the results to the user.

[0697] Step 8:

[0698] Based on the information provided, users decide on actions to improve their lifestyle. If necessary, they send feedback back to the server via their device.

[0699] Step 9:

[0700] The server collects user feedback data and uses it to retrain the generated AI model. This allows for further improvement in the model's accuracy and the provision of more personalized predictions.

[0701] (Example 1)

[0702] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] In recent years, the importance of health management has increased, but many individuals face the challenge of accurately understanding their own health status and making appropriate behavioral changes. Furthermore, conventional health risk assessment methods do not fully utilize individual lifestyles and individual health data, resulting in inaccurate predictions. In addition, the lack of real-time feedback on user behavioral changes makes it difficult to maintain motivation for health management.

[0704] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0705] In this invention, the server includes means for collecting health-related data, means for supplementing missing information and removing outliers from the health-related data, and means for training a learning model to predict risk using the supplemented and removed data. This enables highly accurate risk prediction based on individual health data. Furthermore, users are offered specific action plans based on the health prediction results and can visualize the actual impact of behavioral changes on their health, thereby promoting more effective health management.

[0706] "Health-related data" refers to information about an individual's health status and lifestyle. This data includes physical indicators such as blood pressure, blood sugar levels, and weight, as well as daily diet and exercise levels.

[0707] "Imputing missing information" refers to the process of filling in missing portions of a dataset using appropriate methods. This resolves data inconsistencies and improves the accuracy of analysis.

[0708] "Outlier removal" refers to the process of removing values ​​that exhibit abnormal deviations within a dataset. This process reduces the impact of extreme values ​​and allows for more accurate analysis results.

[0709] A "learning model" refers to an algorithm that learns specific rules or patterns based on data. This model is used to predict future events by utilizing machine learning and statistical methods.

[0710] An "information terminal" refers to an electronic device used by a user to input and output various types of data. Generally, this includes smartphones, tablets, and personal computers.

[0711] "Health prediction" refers to analyzing and predicting future health conditions and risks based on collected data. This prediction allows for the suggestion of preventative health management and improvement measures.

[0712] A "generative model" refers to an algorithm that identifies patterns in data and generates new data based on that knowledge. This model has the ability to produce an appropriate output for a given input.

[0713] "Response data" refers to information about user feedback and behavior obtained after using a system. This data can be used to improve the quality of services and products.

[0714] This invention is a system designed to enable individual users to effectively understand their own health status and promote improvements in their lifestyle. The system mainly consists of three elements: a server, a terminal, and a user.

[0715] The server automatically collects health-related data from health checkup agencies and other medical facilities. The collected data undergoes preprocessing, such as filling in missing information and removing outliers. Specifically, it uses programming languages ​​such as Python and data processing libraries such as NumPy and Pandas to clean and structure the data.

[0716] Next, the server uses the pre-processed data to train the generative AI model. This model is built using machine learning frameworks, such as TensorFlow or PyTorch, to predict the user's health risks. For example, prompts such as "40-year-old male, 170cm tall, 70kg weight, exercise habits: 3 times a week" are input to the AI ​​model.

[0717] The user's device receives health risk prediction results from the server and visualizes the analysis results. Visualization libraries such as D3.js and Chart.js are used to present the results in an intuitively understandable format for the user. For example, a user predicted to have a high risk of hypertension will be given specific action suggestions to reduce that risk.

[0718] Furthermore, the device uses a generative AI model to provide a health status simulation based on newly entered data on the user's diet and exercise habits. This simulation allows the user to visualize the specific impacts of different behaviors on their health. For example, it can present simulation results on the impact of daily walking on blood pressure.

[0719] User feedback data is sent to the server and used to improve the accuracy of the generated AI model. Subsequent system updates will utilize this feedback data for learning, resulting in more accurate individual risk assessments.

[0720] This invention effectively supports users' health management through real-time risk prediction and functions that assist in individual user behavioral changes.

[0721] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0722] Step 1:

[0723] The server collects health-related data from medical facilities via APIs and database connections. Inputs are anonymized biometric data such as user blood pressure, blood glucose levels, and weight, while output is raw, unprocessed data. This raw data is stored within the system.

[0724] Step 2:

[0725] The server processes the collected raw data, performing operations to impute missing information and remove outliers. The input is the previously stored raw data, and the output is a clean dataset with missing values ​​imputed and outliers removed. Specifically, it uses Python's NumPy and Pandas to examine each data element, impute missing parts with the median, and remove outliers exceeding 3 standard deviations.

[0726] Step 3:

[0727] The server uses a clean dataset to train a generative AI model. The input is the preprocessed data obtained in step 2, and the output is the trained AI model. Here, TensorFlow or PyTorch is used to optimize the model parameters based on the data.

[0728] Step 4:

[0729] The server uses a pre-trained AI model to individually predict each user's health risk. The input is a prompt containing user information (e.g., "40-year-old male, 170cm tall, 70kg weight, exercise habits: 3 times a week"), and the output is the user's health risk score. This risk score is quantified as the probability of developing a specific disease.

[0730] Step 5:

[0731] The user's device receives a health risk score sent from the server and visualizes it in an easy-to-understand format for the user. The input is the health risk score, and the output is displayed in graph or chart format. D3.js and Chart.js are used to visualize the score and present the user with their risks and ways to improve them.

[0732] Step 6:

[0733] The device uses a generative AI model to simulate the user's health status based on newly entered data on changes in their eating habits and exercise routines. The input is the user's set data on lifestyle changes, and the output is a simulation result showing the impact of those changes on health risks. This allows the user to concretely understand the effects of behavioral changes.

[0734] Step 7:

[0735] User feedback data is sent to the server and used to retrain the generated AI model. The input is user feedback data, and the output is an updated AI model for improved accuracy. This continuous feedback loop improves the system's predictive accuracy, enabling more personalized health risk assessments.

[0736] (Application Example 1)

[0737] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] This invention aims to not only utilize individual health checkup information to predict health risks, but also to automatically apply benefits for related goods and services in electronic transactions based on those predictions. Conventionally, the use of health information has been limited to individual health management, making it difficult to extract multifaceted direct added value to specific commercial transactions. This invention aims to solve the problem of stimulating consumer behavior and promoting health awareness by providing specific benefits tailored to individual health conditions.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0740] In this invention, the server includes means for collecting health checkup information, means for supplementing missing information and removing outliers from the health checkup information, means for training a machine learning model to predict health risks using the supplemented and removed information, means for performing health simulations based on changes in diet and exercise habits, and means for automatically applying discounts on related products and services during electronic transactions based on the health risk prediction results. This enables users to manage their health while enjoying benefits based on the prediction results.

[0741] "Health checkup information" refers to data related to an individual's health status obtained from medical institutions, etc., and includes basic indicators such as blood pressure, blood sugar levels, and weight.

[0742] "Completing missing data" is the process of supplementing missing data points in health checkup information through estimation to create a complete dataset.

[0743] "Removing outliers" is a process that improves the accuracy of data by removing unnatural values ​​or data that is statistically considered abnormal from health checkup information.

[0744] A "machine learning model" refers to an algorithm or mathematical method that learns patterns and relationships based on collected data and uses them to make predictions about future data.

[0745] "Changes in dietary and exercise habits" means altering daily eating and exercise patterns to improve an individual's health, with the aim of reducing health risks.

[0746] A "health simulation" is a method that demonstrates to users the impact of specific improvement measures by virtually testing how their health status would change under certain conditions.

[0747] "Automatically applying discounts during electronic transactions" refers to a feature that reduces the price of goods or services when a user purchases them online, provided they meet pre-set conditions.

[0748] This invention is a system that effectively utilizes health checkup information to provide users with personalized health risk predictions and benefits in commercial transactions. The system operates primarily using servers, user terminals, and cloud resources.

[0749] The server collects health checkup information based on a predefined protocol. Before storing the collected information in the database, it uses the Pandas library to impute missing information and remove outliers. This cleansed information is then used to train a generative AI model using TensorFlow, providing a function to predict health risks.

[0750] The terminal is responsible for receiving health risk prediction results from the server after the user inputs health checkup information. Based on these results, a user interface is built using ReactJS, providing the user with visual feedback. Users can also input changes to their daily eating habits and exercise routines as feedback, which triggers simulations. When the user executes an electronic transaction, the server automatically applies appropriate discounts and benefits.

[0751] As a concrete example, consider a scenario where a user shops at a supermarket's online store. Based on health checkup information entered by the user beforehand, a generating AI model evaluates their health status, and if it shows a trend toward improvement, a discount on a vegetable set is offered during the next online payment. This process is designed so that users can consciously improve their health while simultaneously receiving concrete benefits through actual commercial transactions.

[0752] An example of a prompt for the generating AI model would be: "Based on the user's age, gender, and recent health check results, please suggest lifestyle changes that can be expected to improve before the next check-up."

[0753] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0754] Step 1:

[0755] The server collects health checkup information from health checkup providers. The input information includes basic health indicators such as the user's blood pressure, blood sugar level, and weight. This information is stored in a database on the server and prepared for the next step.

[0756] Step 2:

[0757] The server uses the Pandas library to impute missing information and remove outliers from the collected health checkup data. The input is raw data, and the output of this step is a clean and complete dataset. Mathematical imputation and statistical analysis are used in this data processing to ensure data consistency and accuracy.

[0758] Step 3:

[0759] The server trains a generative AI model using TensorFlow with preprocessed data. The input here is the cleaned dataset, and the output is the model parameters for predicting health risks. The model uses the user's historical data and prediction algorithm to quantify individual health risks.

[0760] Step 4:

[0761] The device receives health risk prediction results sent from the server. The input is the health risk quantified by the model, and the output is a visual display on the user interface. Here, ReactJS is used to provide a graphical display that allows the user to intuitively understand the risk.

[0762] Step 5:

[0763] Users input changes to their diet and exercise habits into a terminal. Based on this input, the server combines pre-processed data with the new lifestyle data to perform a simulation. The output is a predicted change in health status, which is displayed on the user's terminal.

[0764] Step 6:

[0765] The server applies incentives in commercial transactions based on these health risk prediction results and user feedback data. Here, applicable discounts and coupons are selected from the incentive database based on the prediction results and the user's improvement trends, and are automatically used during electronic transactions. The input is a risk assessment by a generative AI model, and the output is specific commercial transaction incentives.

[0766] Step 7:

[0767] The server collects feedback data from users and uses it to retrain the generative AI model. The input to this step is the feedback data, and the output is new model parameters that reflect the improved accuracy of the model. This allows the system to continuously learn and provide more accurate predictions.

[0768] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0769] This invention is a system for accurately understanding a user's health status and supporting appropriate health management. This system combines three entities—a server, a terminal, and the user—with an emotion engine that recognizes the user's emotional state.

[0770] First, the server collects health checkup data from health checkup agencies and medical institutions. This data includes biological data such as blood pressure, blood sugar levels, weight, and cholesterol levels. To maintain data integrity, the server performs data imputation and outlier removal.

[0771] Next, the server trains a generative AI model using the adjusted data to predict health risks. This model quantifies the health risks for each user and calculates the likelihood of developing specific diseases. Furthermore, an emotion engine is used to analyze the user's emotional state and evaluate their reaction to the health risk predictions and their stress levels.

[0772] The device prompts the user to submit health checkup data and visually displays the health risk prediction and emotion analysis results received from the server. For example, if the risk is high, it provides advice that takes stress levels into consideration and encourages behavioral improvement with positive messages. Furthermore, based on the emotion engine's analysis, it adjusts lifestyle improvement suggestions to match the user's psychological state.

[0773] Furthermore, the device simulates changes in the user's chosen diet and exercise habits and visualizes their effects. The emotion engine evaluates how the user reacts to this simulation and prepares to send feedback to the server.

[0774] Based on the information obtained from the system, users implement lifestyle improvements and provide feedback on their emotions and health status. This feedback is collected by the server and used to retrain the generative AI model. As a result, more personalized health management support becomes possible.

[0775] As a concrete example, consider a 50-year-old female user of this system. The user sends her latest health check results to the server, and the system, after evaluating her emotional state, notifies her that she is at high risk of diabetes. At this point, the emotion engine recognizes that the user is experiencing stress, and suggestions for relaxation and dietary improvement advice that also serves as stress relief are displayed on the device. The user can use this information to take actions to reduce their health risks.

[0776] The following describes the processing flow.

[0777] Step 1:

[0778] The server collects users' health checkup data from health checkup agencies and medical institutions. This data includes key health indicators such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0779] Step 2:

[0780] The server imputes missing values ​​and removes outliers from the collected health checkup data. For example, it ensures the integrity of the dataset by imputing the mean using statistical methods.

[0781] Step 3:

[0782] The server trains a generative AI model using pre-processed data. Based on past data patterns, it creates a model to predict each user's health risk.

[0783] Step 4:

[0784] The user's device transmits health check results and basic information to the server. The device also provides an input interface, allowing the user to easily enter the necessary information.

[0785] Step 5:

[0786] The server uses a generated AI model to predict health risks based on the data submitted by the user. It quantifies the risk of developing a disease and calculates the likelihood of developing a specific illness.

[0787] Step 6:

[0788] The server uses an emotion engine to recognize the user's emotional state. This function acquires and analyzes data from the user's facial expressions and tone of voice while they are using the device.

[0789] Step 7:

[0790] The server sends the results of health risk prediction and sentiment analysis to the user's terminal. It creates advice that considers the user's emotional state, rather than just suggesting health risks.

[0791] Step 8:

[0792] The device visually displays health risk predictions and lifestyle improvement suggestions tailored to the user's emotions. If the user's stress level is high, it provides advice on relaxation methods and stress reduction.

[0793] Step 9:

[0794] The device simulates health status based on changes in diet and exercise habits, and presents the results to the user. This allows the user to develop a concrete improvement plan.

[0795] Step 10:

[0796] Users review their lifestyle habits based on information provided by the system and send feedback to the server via their device. This feedback includes the effectiveness of the suggestions and their emotional response.

[0797] Step 11:

[0798] The server collects user feedback data and uses it to retrain the generative AI model. This improves the system's predictive accuracy and enables more personalized support.

[0799] (Example 2)

[0800] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0801] In modern times, personal health management is extremely important. However, conventional systems do not adequately predict health risks based on individual health information or provide lifestyle improvement suggestions that take into account responses based on emotional states. As a result, there is a challenge in supporting health management that reflects the individual characteristics of each user.

[0802] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0803] In this invention, the server includes means for collecting health information, means for supplementing missing data and removing anomalous data, means for training a machine learning model to estimate health risks, and means for analyzing emotional states. This makes it possible to provide more accurate and personalized health risk predictions and lifestyle improvement suggestions that take into account the user's emotional state.

[0804] "Health information" refers to various data that indicate an individual's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0805] "Completing missing data" refers to supplementing the data that is missing from the collected health information based on statistical methods and past data patterns.

[0806] "Removing abnormal data" is a technique that detects data in health information that deviates from the normal range and prevents it from affecting the analysis.

[0807] "Training a machine learning model" means optimizing the parameters of an algorithm that predicts health risks based on a large amount of health information data.

[0808] "Analyzing emotional state" means using text and audio information obtained from the user to evaluate their psychological state and stress level.

[0809] A "terminal device" is a device used to provide information to users, and is used to visually display health risk prediction results and lifestyle improvement suggestions.

[0810] This invention is a system that evaluates individual health risks based on the user's health information and proposes appropriate lifestyle improvements. This system is primarily composed of three components: a server, a terminal, and the user.

[0811] The server is the primary component responsible for managing health information and processing data. It collects various health information, performs data completion (missing data) and removal (removing anomalous data). This process utilizes statistical methods and machine learning algorithms. Furthermore, it leverages generative AI models to predict health risks using the collected health information data. These models can quantify the risk of developing specific diseases.

[0812] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine combines natural language processing and speech analysis technologies to evaluate the user's psychological state and stress level.

[0813] The terminal functions as a user interface and visualizes information. It receives health risk prediction results and sentiment analysis results transmitted from the server and displays them in a user-friendly format. For example, it might present risk assessment results as infographics or graphs and offer specific advice for health improvement as actionable suggestions.

[0814] Users refer to the information provided by the system and use it for health management in their daily lives. Users provide feedback through their devices, and this feedback is collected on the server and used to retrain the generated AI model. This enables personalized health support for each user.

[0815] As a concrete example, when a user uses this system, the following prompt message could be used: "Assess the user's current health status, take their emotional state into consideration, and present health risks and suggested solutions."

[0816] In this way, the present invention provides specific means and processes for realizing highly personalized health management.

[0817] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0818] Step 1:

[0819] The server collects users' health information from health checkup agencies and medical institutions. This health information includes blood pressure, blood sugar levels, weight, cholesterol levels, etc. The collected data is received as input and stored in a database. This prepares the basic data for subsequent processing.

[0820] Step 2:

[0821] The server verifies the collected health information, imputing missing data and removing anomalous data. This is done using statistical methods and estimations based on past data patterns. The input to this process is health information, and the output is a well-organized dataset. This ensures data integrity and prepares the system for improving the accuracy of subsequent health risk predictions.

[0822] Step 3:

[0823] The server trains a generative AI model using a prepared dataset. It uses machine learning algorithms to develop a model capable of quantifying health risks. The input requires a prepared dataset, and the output is a trained generative AI model. This model is used to predict risks that differ for each user.

[0824] Step 4:

[0825] The server uses an emotion engine to analyze the user's emotional state. It takes user text and voice information as input and evaluates their psychological state and stress level as output. This analysis allows for consideration of the user's response to the health risk prediction results.

[0826] Step 5:

[0827] The terminal visually displays health risk prediction results and sentiment analysis results obtained from the server. It processes the received data as input and presents it to the user as infographics and advice. This allows the user to intuitively understand their own health status and recognize the suggested improvement methods.

[0828] Step 6:

[0829] The device simulates changes to the user's chosen eating and exercise habits. This visualizes the impact of these changes on health, taking the user's choices as input and outputting estimated health effects. This helps users understand their lifestyle choices.

[0830] Step 7:

[0831] Users improve their lifestyle habits based on feedback from the system. Furthermore, they provide feedback on their emotions and health status, which is reported to the server. The input consists of the user's experiences and impressions, and the output serves as input for the next model retraining, contributing to the overall improvement of the system's accuracy.

[0832] (Application Example 2)

[0833] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0834] Modern in-store health management solutions struggle to provide customized recommendations based on the individual health and emotional states of each user. In particular, there is a need for immediate analysis of on-site health check data and the corresponding recommendations of appropriate products and services. However, existing systems have limitations in providing recommendations that adequately consider the emotional state of the user, resulting in insufficient personalized health management support.

[0835] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0836] In this invention, the server includes means for collecting health checkup information, means for evaluating emotional states and adjusting suggestions based on health simulation results to suit the user's psychological state, and means for collecting user feedback information and retraining a generated AI model using the collected information. This makes it possible to offer customized products and services in physical stores that take into account the individual user's health status and emotions.

[0837] "Health checkup information" refers to data that quantifies the user's health status, such as blood pressure, blood sugar levels, weight, and cholesterol levels.

[0838] "Completing missing information" refers to the process of supplementing data that is missing from health checkup information through estimation or derivation.

[0839] "Removal of abnormal information" is the process of detecting and removing data from health checkup information that falls outside the normal range.

[0840] A "machine learning algorithm" is a computational method for building models that automatically perform specific tasks using large amounts of data.

[0841] An "information presentation device" is a device that provides users with analysis results and suggestions visually or audibly.

[0842] "Health simulation" is a process that predicts and visualizes the impact that changes in diet and exercise habits will have on a user's health.

[0843] "Emotional state" refers to a state that reflects the user's psychological and emotional health.

[0844] A "generative AI model" is an artificial intelligence system that learns from large amounts of data and performs predictions and generation.

[0845] "Feedback information" refers to opinions and data provided by users, based on their experiences and results.

[0846] To implement this invention, a system is configured in which a server, terminal, and user work in cooperation. First, the server collects health checkup information from health checkup institutions and medical institutions. The collected data is processed using Python to impute missing information and remove anomalous information. Next, a machine learning algorithm is trained using TensorFlow to predict the health risk for each user.

[0847] Furthermore, the server analyzes the emotional state using an NLP library. Based on these results, it provides personalized suggestions to the information presentation device using a generative AI model. These suggestions include products and services that take into account the user's health and emotional state.

[0848] The device, through a frontend built with React Native, presents users with health risk predictions and specific suggestions. Based on these results, users can run simulations to change their eating habits and exercise routines, and visually confirm the results.

[0849] Users manage their health based on the provided suggestions and send feedback information to the server via their device. The server uses the collected feedback information to retrain the generative AI model and further improve its accuracy.

[0850] As a concrete example, a user participates in a health event at a physical store and enters their health checkup information via their smartphone. Based on this information, the server immediately predicts health risks and suggests supplements and fitness plans tailored to the user's stress level.

[0851] Examples of prompts to input into a generative AI model:

[0852] "Based on the user's age, health checkup data (blood pressure, blood sugar levels, etc.), and emotional state (e.g., high stress level), please propose the most suitable health improvement measures."

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] The server collects health checkup information from health checkup institutions and medical facilities. The collected data is entered into the server as JSON format data. This data includes blood pressure, blood sugar levels, weight, cholesterol levels, etc.

[0856] Step 2:

[0857] The server uses Python to fill in missing information from collected health checkup data. This employs methods such as substitution using common values ​​and machine learning-based completion techniques. Unfilled data is input, and filled-in data is output.

[0858] Step 3:

[0859] Next, the server removes anomalous information from the completed data. Here, it detects and removes outliers based on a pre-defined normal range. The completed data becomes the input, and a clean dataset is output.

[0860] Step 4:

[0861] Using a clean dataset, the server trains a machine learning algorithm using TensorFlow. This generates a model for predicting health risks. The input is a clean dataset, and the output is a health risk score.

[0862] Step 5:

[0863] The server uses an NLP library to evaluate the user's emotional state. It performs sentiment analysis from the user's written text and calculates stress levels and emotional state scores. The input is the user's text data, and the output is the evaluation result of the emotional state.

[0864] Step 6:

[0865] The device uses a frontend built with React Native to display health risk scores and emotional states received from the server to the user. The displayed information is presented through a visual interface. Input is the evaluation results from the server, and output is the information displayed on the user interface.

[0866] Step 7:

[0867] Based on the presented results, the user simulates their diet and exercise habits. The device calculates the simulation results and presents the effects to the user. The input is the simulation conditions selected by the user, and the output is the predicted health improvement effect.

[0868] Step 8:

[0869] Users send feedback information to the server via their device. This feedback includes actions taken by the user and the effects they perceived. The input is the user's feedback data, and the output is the feedback repository on the server.

[0870] Step 9:

[0871] The server uses the collected feedback information to retrain the generative AI model. This retraining improves the model's prediction accuracy. The input is the feedback information, and the output is the newly adjusted AI model.

[0872] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0873] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0874] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0875] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0876] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0877] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0878] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0879] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0880] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0881] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0882] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0883] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0884] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0885] 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.

[0886] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0887] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0888] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0889] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0890] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0891] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0892] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0893] The following is further disclosed regarding the embodiments described above.

[0894] (Claim 1)

[0895] Means of collecting health checkup data,

[0896] A means for imputing missing values ​​and removing outliers from the aforementioned health checkup data,

[0897] A means for training a machine learning model to predict health risks using the aforementioned supplemented and removed data,

[0898] A means for providing the results of the health risk prediction to the user terminal,

[0899] A means for performing a health simulation based on changes in dietary habits and exercise routines, and for presenting the results to the user's terminal,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising means for visually displaying on a user terminal specific suggestions for lifestyle improvements based on the aforementioned health risk prediction results.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising means for collecting user feedback data and using the collected feedback data to retrain a generative AI model to improve the accuracy of health risk prediction.

[0905] "Example 1"

[0906] (Claim 1)

[0907] Means of collecting health-related data,

[0908] A means for supplementing missing information and eliminating outliers from the aforementioned health-related data,

[0909] A means for training a learning model that predicts risk using the aforementioned supplemented and excluded data,

[0910] A means for providing the results of quantifying the aforementioned risks to an information terminal,

[0911] A means for performing health predictions based on changes in dietary and exercise-related habits and displaying the results on an information terminal,

[0912] A means of evaluating individual user future risks using a retrained model,

[0913] A means of visualizing the impact of behavioral changes on risk,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, further comprising means for visually displaying specific suggestions for habitual improvement based on the aforementioned risk quantification results on an information terminal.

[0917] (Claim 3)

[0918] The system according to claim 1, further comprising means for collecting response data from the user and using the collected response data to retrain a generative model to improve the accuracy of risk prediction.

[0919] "Application Example 1"

[0920] (Claim 1)

[0921] Means of collecting health checkup information,

[0922] A means for supplementing missing information and removing abnormal values ​​from the aforementioned health examination information,

[0923] A means for training a machine learning model that predicts health risks using the aforementioned supplemented and removed information,

[0924] A means for providing the results of the health risk prediction to the user's terminal,

[0925] A means for performing a health simulation based on changes in dietary habits and exercise routines, and for displaying the results on the user's terminal,

[0926] A means for automatically applying discounts on related products and services during electronic transactions based on the aforementioned health risk prediction results,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, further comprising means for visually displaying specific lifestyle improvement suggestions based on the aforementioned health risk prediction results on a user terminal.

[0930] (Claim 3)

[0931] The system according to claim 1, further comprising means for collecting user feedback information and using the collected feedback information to retrain a generative AI model for improving the accuracy of health risk prediction.

[0932] "Example 2 of combining an emotion engine"

[0933] (Claim 1)

[0934] Means of collecting health information,

[0935] Means for supplementing missing data and removing abnormal data from the aforementioned health information,

[0936] A means for training a machine learning model to estimate health risks using the aforementioned supplemented and removed data,

[0937] Means for providing the results of the estimated health risk to a terminal device,

[0938] By analyzing emotional states, a means of evaluating users' responses to health risk predictions,

[0939] A means for performing a health simulation based on changes in eating habits and exercise habits, and for presenting the results on a terminal device,

[0940] A system that includes this.

[0941] (Claim 2)

[0942] The system according to claim 1, further comprising means for visually displaying on a terminal device detailed lifestyle improvement suggestions based on the aforementioned health risk prediction results.

[0943] (Claim 3)

[0944] The system according to claim 1, further comprising means for collecting user feedback information and using the collected feedback information to retrain a generative AI model to improve the accuracy of health risk prediction.

[0945] "Application example 2 of combining emotional engines"

[0946] (Claim 1)

[0947] Means of collecting health checkup information,

[0948] Means for supplementing missing information and removing abnormal information from the aforementioned health examination information,

[0949] A means for training a machine learning algorithm that predicts health risks using the aforementioned supplemented and removed information,

[0950] Means for providing the results of the health risk prediction to an information display device,

[0951] A means for performing a health simulation based on changes in dietary habits and exercise habits, and for presenting the results on an information display device,

[0952] A means for evaluating the user's emotional state and adjusting the suggestions based on the results of the health simulation to suit the user's psychological state,

[0953] A system that includes this.

[0954] (Claim 2)

[0955] The system according to claim 1, further comprising means for visually displaying specific lifestyle improvement suggestions based on the aforementioned health risk prediction results on an information display device.

[0956] (Claim 3)

[0957] The system according to claim 1, further comprising means for collecting user feedback information and using the collected feedback information to retrain a generative AI model to improve the accuracy of health risk prediction. [Explanation of Symbols]

[0958] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting health checkup data, A means for imputing missing values ​​and removing outliers from the aforementioned health checkup data, A means for training a machine learning model to predict health risks using the aforementioned supplemented and removed data, A means for providing the results of the health risk prediction to the user terminal, A means for performing a health simulation based on changes in dietary habits and exercise routines, and for presenting the results to the user's terminal, A system that includes this.

2. The system according to claim 1, further comprising means for visually displaying on a user terminal specific suggestions for lifestyle improvements based on the aforementioned health risk prediction results.

3. The system according to claim 1, further comprising means for collecting user feedback data and using the collected feedback data to retrain a generative AI model to improve the accuracy of health risk prediction.

Images