System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information on a lifestyle and a family medical history from a user; means for predicting a disease that may develop in the future based on the collected information; means for evaluating a risk level based on a prediction result of the disease; means for proposing an additional examination item to the user based on the evaluation; and means for notifying the user of a proposal content in a report format.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Early detection and treatment are essential to increasing disease cure rates and reducing the risk of recurrence, metastasis, and mortality. However, current health checkups and comprehensive medical examinations do not fully achieve these goals. It is particularly difficult for working adults to undergo regular health checkups, which can result in the delayed detection of many serious illnesses. Furthermore, the test items are fixed, making it difficult to respond flexibly to individual risks. Therefore, there is a need for a system that allows users to grasp their own health risks early and take appropriate preventive measures. [Means for solving the problem]

[0005] This invention is a system that collects information from a user about lifestyle habits and family medical history, predicts potential future illnesses based on the collected information, and assesses risk levels based on the predictions. Specifically, the system stores the collected information in a database and analyzes it using a machine learning algorithm. It then provides a means for suggesting appropriate additional tests based on the predicted disease risk level. The system also notifies the user of the suggestions in a report format, which the user can view on their device. Furthermore, the system periodically reassesses the user's health risk based on the latest medical information and notifies them of new suggestions and preventive measures. This allows users to quickly identify their own health risks and take appropriate measures.

[0006] "Lifestyle habits" refers to the behaviors and habits of individuals in their daily lives, including diet, exercise, smoking, and drinking.

[0007] "Family medical history" refers to the history of illnesses that the user's family members have had in the past, and is collected to take into account genetic factors.

[0008] "Means for collecting information" refers to a method or device for a user to input information such as lifestyle habits and family medical history through a questionnaire or the like, and obtain that information as data.

[0009] "Prediction methods" refer to machine learning algorithms and statistical models that analyze collected data and predict future disease development.

[0010] "Means for evaluation" refers to the criteria or methods for determining the risk level of disease based on the prediction results and classifying it as low risk, medium risk, or high risk.

[0011] "Suggestion means" refers to a method or device for informing users of additional tests or preventative measures that may be required depending on the risk level.

[0012] "Means for notifying in the form of a report" refers to a method for documenting the diagnostic results and the details of any proposed additional tests and notifying the user electronically or in paper form.

[0013] "Terminal" refers to an electronic device or apparatus (e.g., smartphone, tablet, or PC) through which a user receives and checks reports.

[0014] "Means for reassessment" refers to a method or device for reanalyzing the user's health risks and re-proposing necessary preventive measures based on regularly collected new data and the latest medical information. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention is a system that predicts future illnesses based on information about the user's lifestyle and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. The main parts of this system are a server, a terminal, and user interaction.

[0037] 1. Data Collection

[0038] User

[0039] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[0040] Terminal

[0041] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[0042] server

[0043] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[0044] 2. Data Analysis

[0045] server

[0046] The data stored on the server is passed to an AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[0047] 3. Risk Assessment

[0048] server

[0049] Based on the prediction results, the server evaluates the risk level of each disease and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[0050] 4. Inspection proposal

[0051] server

[0052] Based on the risk assessment, the server suggests additional tests the user may need: if the risk is high, it suggests more detailed tests (e.g., MRI or CT scan), and if the risk is medium, it recommends blood tests or ultrasound.

[0053] 5. Notifications and Feedback

[0054] server

[0055] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[0056] User

[0057] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0058] 6. Follow-up

[0059] server

[0060] The server periodically reassess the user's health risk based on the latest medical information and new data about the user, and sends new suggestions and notifications to the user to take preventative measures as needed.

[0061] Specific examples

[0062] User A's case

[0063] User A

[0064] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[0065] Terminal

[0066] The terminal transmits this information to the server.

[0067] server

[0068] The server stores the received data and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[0069] server

[0070] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[0071] server

[0072] A report including the proposal is sent to User A's terminal.

[0073] User A

[0074] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[0075] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[0079] Step 2:

[0080] The terminal validates the entered information, formats it in the specified format, and sends it to the server.

[0081] Step 3:

[0082] The server stores the received data in a database and performs validation to check the completeness and consistency of the data.

[0083] Step 4:

[0084] The server adds the stored data to a processing queue and triggers the AI ​​model to use machine learning algorithms.

[0085] Step 5:

[0086] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict potential future illnesses.

[0087] Step 6:

[0088] The server evaluates the risk level of each disease based on the prediction results and classifies them as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[0089] Step 7:

[0090] The server will suggest additional tests that may be needed depending on the risk assessment: for high risk, further testing (e.g., MRI or CT scan) and for medium risk, blood tests or ultrasound are recommended.

[0091] Step 8:

[0092] The server generates a report containing the diagnosis results and recommended tests and sends it to the user's device, including details of the risk assessment and the reasons for the suggested tests.

[0093] Step 9:

[0094] The user checks the report received on the terminal and decides whether to undergo the proposed examination, if necessary.

[0095] Step 10:

[0096] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures as needed.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] Conventional health management systems have not adequately predicted or assessed health risks based on users' lifestyle habits and family medical history, making it difficult to recommend effective preventive measures or additional tests. In particular, they lack real-time reassessment based on the latest medical information and individualized support based on user-specific data.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes: means for collecting information from a user regarding lifestyle habits, family medical history, dietary habits, exercise habits, and smoking and drinking habits; means for checking the format of the collected information and transmitting it to the server in the correct format; means for analyzing the data stored in the server using a machine learning algorithm and predicting future diseases based on the user's data; means for assessing the risk level of each disease based on the prediction results and classifying it as low, medium, or high risk; means for suggesting additional tests to the user based on the risk assessment; means for generating the suggestions in report format and transmitting them to the user's terminal; and means for periodically reassessing health risks based on the latest medical information and new user data and notifying the user of new suggestions and preventive measures. This enables users to grasp their own health risks early and take appropriate preventive measures.

[0102] "Lifestyle habits" refers to the entire range of daily behaviors and habits that affect health, such as diet, exercise, sleep, smoking, and drinking habits.

[0103] "Family medical history" refers to the history of any illnesses or health conditions experienced by a user's family members, past and present, and is important information when assessing genetic risk.

[0104] "Diet" refers to all activities related to eating, including the quality and quantity of food a user consumes on a daily basis, meal frequency, and balanced eating habits.

[0105] "Exercise habits" refers to the pattern of physical exercise and fitness activities that a user regularly engages in, and is an important factor in maintaining and improving health.

[0106] "Smoking and drinking habits" refers to the amount and frequency of smoking that a user does on a daily basis, and the type, amount, and frequency of alcohol that a user drinks.

[0107] A "machine learning algorithm" is a computational method used to learn patterns and rules from data, which can then be used to predict future events and trends.

[0108] "Risk level" is an assessment that classifies a person into low risk, medium risk, or high risk based on the predicted outcome of a disease that may occur in the future.

[0109] "Additional test items" are specific tests or diagnostic procedures suggested to the user based on the risk assessment, and are useful for early detection and follow-up of disease.

[0110] The "report format" refers to a document format that visually summarizes information such as diagnostic results and suggested test items in an easy-to-understand format, and is used to notify users.

[0111] "Latest medical information" refers to the results of medical research and clinical trials, as well as the latest knowledge and data on new treatments and diagnostic techniques.

[0112] "Health risk reassessment" is the process of periodically reassessing a user's health status and risks based on the user's latest data and medical information, and making new predictions and suggestions.

[0113] "Notification" refers to the act of sending messages or alerts to users to inform them of risk assessment results and recommendations.

[0114] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[0115] 1. Data Collection

[0116] User

[0117] Users access a dedicated questionnaire and enter information about their lifestyle, family medical history, diet, exercise habits, smoking and drinking habits, etc. The questionnaire is designed to comprehensively assess the user's health status.

[0118] 2. Data Transmission

[0119] Terminal

[0120] The terminal receives data entered by the user and checks whether the data format is correct. If there are no errors, it formats the data in the specified format and sends it to the server. For example, it validates the input data and sends it to the server as an HTTP request.

[0121] 3. Data storage

[0122] server

[0123] The server receives the data sent from the terminal and stores it in a database. When storing the data, validation is performed to check the completeness and consistency of the data. The received data is temporarily stored in memory, and once the validation is complete, it is stored in the database.

[0124] 4. Data Analysis

[0125] server

[0126] The data stored on the server is passed to an AI model for analysis. Machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to predict future diseases based on the user's data. The necessary data is extracted from the database and fed into the analysis model using a Python script. The analysis results are temporarily stored on the server.

[0127] 5. Risk Assessment

[0128] server

[0129] The server evaluates the risk level of each disease based on the analysis results. The evaluation is classified into three categories: low risk, medium risk, and high risk, and measures are suggested according to each risk level. The evaluation algorithm categorizes the analysis results and also calculates a confidence score within them. The result is added to the user's profile.

[0130] 6. Inspection Proposal

[0131] server

[0132] Based on the risk assessment, the server recommends additional tests that the user may need. If a high risk is detected, detailed tests (e.g., MRI or CT scan) are recommended, while if a medium risk is detected, blood tests or ultrasound examinations are recommended. The recommendations are generated using templates, and a report is created that includes the appropriate tests and the reasons for them.

[0133] 7. Notifications and Feedback

[0134] server

[0135] The server generates a report containing the risk assessment and recommendations, and notifies the user's device. The report is generated in a visually easy-to-understand format such as PDF. The report is generated using a document template engine (e.g., JasperReports or iText), and is notified to the user's email address or a dedicated app.

[0136] User

[0137] Users can review the report received on their device and consider any suggested tests or preventative measures. They will receive an email or in-app notification with a link they can click to download or view the report.

[0138] 8. Follow-up

[0139] server

[0140] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new recommendations and preventative measures as needed. The server periodically runs the reassessment process using a scheduled task (e.g., cron job or cloud scheduler) and updates the report based on the new data.

[0141] Specific examples

[0142] User A's case

[0143] User A

[0144] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[0145] Terminal

[0146] The terminal checks the format of this information before sending it to the server.

[0147] server

[0148] The server stores the received data in a database and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[0149] server

[0150] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[0151] server

[0152] A report including the proposal is sent to User A's terminal.

[0153] User A

[0154] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[0155] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[0156] Example prompt sentence:

[0157] Describe the processing steps and specific behavior of a system that predicts potential future illnesses based on a user's lifestyle and family medical history, performs a risk assessment, and suggests necessary preventative measures or additional testing.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1:

[0160] Data collection

[0161] User

[0162] Users access a special questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[0163] Input: The user enters information about lifestyle habits and family medical history into a questionnaire.

[0164] How it works: Using a web browser or mobile application, you enter your answers into each section of the questionnaire and click the "Submit" button.

[0165] Output: Information about lifestyle habits and family medical history entered.

[0166] Step 2:

[0167] Data transmission

[0168] Terminal

[0169] The terminal receives the data entered by the user and checks whether the format of the data is correct. If there are no errors, it formats the data in the specified format and sends it to the server.

[0170] Input: Information about lifestyle habits and family medical history that you enter into your device.

[0171] Operation: The terminal validates the input data and checks whether characters have been entered in fields that should be entered as numbers. The validated data is sent to the server as an HTTP request.

[0172] Output: Formatted lifestyle and family medical history information sent to the server.

[0173] Step 3:

[0174] Data storage

[0175] server

[0176] The server receives the data sent from the terminal and stores it in a database, where it performs validation to check the completeness and consistency of the data.

[0177] Input: Formatted lifestyle and family medical history information sent from your device.

[0178] How it works: The server temporarily stores the received data in memory and validates it against existing rules before storing it in the database. Once validation is complete, it performs an INSERT operation on the database.

[0179] Output: Information about lifestyle habits and family medical history stored in a database.

[0180] Step 4:

[0181] Data analysis

[0182] server

[0183] The data stored on the server is then passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to predict future illnesses based on the user's data.

[0184] Input: Data about the user's lifestyle and family medical history stored in a database.

[0185] How it works: The server extracts the necessary data from the database and feeds the input data into the analytical model using Python scripts. The analytical results are temporarily stored on the server.

[0186] Output: Prediction of future potential illnesses.

[0187] Step 5:

[0188] Risk Assessment

[0189] server

[0190] The server evaluates the risk level of each disease based on the analysis results, categorizing the risk into three categories: low risk, medium risk, and high risk, and suggests countermeasures according to each risk level.

[0191] Input: Predictions of future disease outcomes obtained from a generative AI model.

[0192] How it works: The rating algorithm categorizes the analysis results and also calculates a confidence score within them, which is added to the user profile.

[0193] Output: Assessment results categorized by risk level.

[0194] Step 6:

[0195] Inspection proposal

[0196] server

[0197] Based on the risk assessment, the server recommends additional tests that the user may need: if a high risk is detected, a detailed examination (e.g., MRI or CT scan) is recommended, and if a medium risk is detected, blood tests or ultrasound examinations are recommended.

[0198] Input: Assessment results categorized by risk level.

[0199] How it works: Recommendations are generated using templates, and a report is created with the appropriate tests and their reasons.

[0200] Output: A report with suggested additional tests for the user.

[0201] Step 7:

[0202] Notifications and Feedback

[0203] server

[0204] The server generates a report containing the risk assessment and recommendations, and sends it to the user's device in a visually easy-to-understand format such as PDF.

[0205] Input: Report with additional tests.

[0206] How it works: Reports are generated using a document template engine (e.g. JasperReports or iText) and then notified to the user via email or a dedicated app.

[0207] Output: A report of risk assessment and inspection suggestions that is communicated to the user.

[0208] User

[0209] The user reviews the report received on the device and considers any suggested tests or preventative measures.

[0210] Input: Risk assessment and inspection suggestion report posted to the terminal.

[0211] How it works: Users receive an email or in-app notification with a link they click to download or view the report.

[0212] Output: User action (getting tested, taking preventative measures, etc.).

[0213] Step 8:

[0214] Follow-up

[0215] server

[0216] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new suggestions and preventative measures as needed.

[0217] Input: Latest medical data and new user data.

[0218] How it works: The server periodically runs the re-evaluation process using a scheduled task (e.g. cron job or cloud scheduler) and updates the reports with new data.

[0219] Output: Notification with reassessment results and new suggestions and preventative measures.

[0220] (Application example 1)

[0221] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0222] Existing health risk assessment systems have the problem that users have to enter information about their lifestyle habits and family medical history, which requires a lot of time and effort. Furthermore, risk assessment results and test recommendations are not notified in real time, which hinders users' ability to respond quickly. Furthermore, the low accuracy of analysis and the low reliability of prediction results make effective health management difficult.

[0223] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0224] In this invention, the server includes means for collecting information on lifestyle habits and family medical history from a user, means for predicting future diseases based on the collected information, means for assessing risk levels based on the disease prediction results, means for providing an interface that is easy for users to input via a smart device, and means for analyzing data using a generative AI model and performing risk assessment and recommendations in real time, thereby enabling users to easily input information and receive accurate health risk assessments and appropriate test recommendations in real time.

[0225] "Lifestyle habits" refers to the user's daily activities and habits, specifically behavioral patterns such as eating, drinking, exercise, smoking, and alcohol consumption.

[0226] "Family medical history" refers to the history of illnesses experienced by the user's blood relatives, past or present.

[0227] "Means for collecting information" refers to devices and systems for obtaining data such as lifestyle habits and family medical history from users.

[0228] "Means for predicting diseases that may occur in the future" refers to a device or system that predicts diseases that a user may suffer from in the future based on collected data.

[0229] "Means for assessing risk level" refers to a device or system for classifying the likelihood of developing a predicted disease into categories such as low risk, medium risk, or high risk.

[0230] "Means for suggesting additional examination items" refers to a device or system for recommending further examination or diagnostic items that a user should undergo based on the evaluation results.

[0231] "Means for notifying the proposed contents in the form of a report" refers to a device or system for documenting the evaluation results and proposed inspection items and notifying the user.

[0232] "Smart device" refers to an electronic device with internet connectivity that a user uses to enter information and view results.

[0233] "Interface" refers to operation screens, input forms, dialogue systems, etc. that make it easier for users to input information via smart devices.

[0234] A "generative AI model" refers to an artificial intelligence model that uses machine learning and data analysis techniques to analyze collected data and assess health risks.

[0235] "Real-time means" refers to devices or systems that analyze and evaluate information within an extremely short time from the time it is entered by the user, and immediately notify the results.

[0236] This invention is a system that predicts future illnesses based on information such as lifestyle habits and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[0237] 1. Data Collection

[0238] User

[0239] Using a smart device interface, users input information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[0240] Terminal

[0241] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[0242] server

[0243] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[0244] 2. Data Analysis

[0245] server

[0246] The data stored on the server is passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[0247] 3. Risk Assessment

[0248] server

[0249] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[0250] 4. Inspection proposal

[0251] server

[0252] Based on the risk assessment, the server suggests additional tests to the user: if the risk is high, more in-depth tests are suggested, and if the risk is medium, simpler tests are recommended.

[0253] 5. Notifications and Feedback

[0254] server

[0255] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[0256] User

[0257] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[0258] 6. Follow-up

[0259] server

[0260] The server periodically reassess the user's health risk based on the latest medical information and new user data, and sends the user new suggestions and notifications to take preventative measures as needed.

[0261] Specific examples

[0262] For example, if a 45-year-old male user enters information such as "family history of diabetes," "drinks alcohol 1-2 times a week," and "does moderate exercise" into a medical questionnaire, this data is sent to the server via the smart device. The server analyzes the data using a generative AI model and evaluates the user as being at medium risk for diabetes and alcoholic liver disease. Based on this evaluation, the server recommends a "blood sugar test" and an "abdominal ultrasound test," and notifies the user of the results in the form of a report. This system allows users to understand their health risks early and take appropriate preventive measures.

[0263] Prompt Sentence Examples

[0264] "What are the health risks for a 45-year-old man with a family history of diabetes, who consumes alcohol 1-2 times a week, and engages in moderate exercise?"

[0265] "Please make a list of diseases that the user is at high risk of developing based on their family history and lifestyle habits, and suggest the necessary tests."

[0266] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0267] Step 1:

[0268] User data entry

[0269] Users use the interface of a smart device (e.g., smart glasses) to input information such as lifestyle habits and family medical history. Specifically, they answer a questionnaire in the form of questions, and the data is entered into the terminal.

[0270] Input: Lifestyle and family medical history data (e.g., drinking habits, smoking habits, exercise habits, family history, etc.)

[0271] Output: Formatted user data

[0272] Step 2:

[0273] Data transmission and format check

[0274] The terminal checks the format of the collected data, formats it into the specified format, and then sends it to the server.

[0275] Specifically, it validates whether the data input format is correct and transfers the formatted data to the server.

[0276] Input: Data entered by the user

[0277] Output: Formatted data sent to the server

[0278] Step 3:

[0279] Data Storage and Validation

[0280] The server receives the data sent from the terminal and stores it in a database. When storing the data, it checks its integrity and consistency.

[0281] Specifically, it checks whether the data is accurate and consistent before saving and approves it for writing to the database.

[0282] Input: Formatted data

[0283] Output: Saved user data

[0284] Step 4:

[0285] Disease prediction through data analysis

[0286] The server passes the stored data to a generative AI model to predict future diseases.

[0287] Specifically, data analysis is performed using machine learning algorithms (e.g., deep learning models) to create a list of diseases at risk of developing.

[0288] Input: Saved user data

[0289] Output: Disease prediction results

[0290] Step 5:

[0291] Risk Level Assessment

[0292] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[0293] Specifically, the likelihood of developing each predicted disease is calculated and a risk level is defined.

[0294] Input: Disease prediction results

[0295] Output: Risk level classification results

[0296] Step 6:

[0297] Proposal of test items

[0298] Based on the results of the risk assessment, the server suggests to the user what additional tests are required.

[0299] Specifically, in high-risk cases, detailed examinations (e.g., MRI or CT scans) are recommended, and in medium-risk cases, blood tests and ultrasound examinations are recommended.

[0300] Input: Risk level classification results

[0301] Output: Suggested tests

[0302] Step 7:

[0303] Reporting and Notifications

[0304] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the recommended tests.

[0305] Specifically, the prediction results and proposals are compiled into a text report and sent to the terminal.

[0306] Input: Proposed test items, risk assessment details

[0307] Output: Report sent to the user

[0308] Step 8:

[0309] User report review and action

[0310] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[0311] Specifically, they review the report contents and carry out any tests or preventative measures they deem necessary.

[0312] Input: Report sent to user

[0313] Output: User's health care behavior

[0314] Step 9:

[0315] Regular follow-up

[0316] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures.

[0317] Specifically, the database is updated periodically and the results of the reevaluation are notified to the user.

[0318] Input: Latest medical information, new data from users

[0319] Output: New evaluation results and recommendations

[0320] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0321] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[0322] 1. Data Collection

[0323] User

[0324] Users access a questionnaire and enter information about their lifestyle, family medical history, diet, exercise, smoking and drinking habits, etc. This allows detailed data to be collected about their individual health risks.

[0325] Terminal

[0326] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[0327] server

[0328] The server stores the data received from the terminal in a database. When storing the data, it validates the data to ensure its completeness and consistency. The server also adds the data to a queue for analysis.

[0329] 2. Data analysis and risk assessment

[0330] server

[0331] The server then passes the stored data to a machine learning algorithm for analysis. Using machine learning algorithms (e.g., deep learning or decision tree models), the system predicts future diseases based on the user's lifestyle and family medical history. The system then assesses the risk level of each disease based on the prediction results, categorizing it as low, medium, or high risk. The assessment results also include the accuracy and reliability of the diagnosis.

[0332] 3. Emotion Recognition by Emotion Engine

[0333] Emotion Engine

[0334] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[0335] 4. Testing recommendations and mental health assessment

[0336] server

[0337] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest additional tests that the user needs. If the risk is high, more detailed tests (e.g., MRI or CT scan) will be suggested, and if the risk is medium, blood tests or ultrasound scans will be recommended. It will also suggest psychological support and counseling depending on the user's emotional state.

[0338] 5. Notifications and Feedback

[0339] server

[0340] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[0341] User

[0342] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0343] 6. Follow-up

[0344] server

[0345] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[0346] Specific examples

[0347] User B's case

[0348] User B

[0349] User B inputs the following: "I go to the gym three times a week," "I drink beer on weekends," and "My family has a history of myocardial infarction." User B also inputs that he is in a stressful work environment.

[0350] Terminal

[0351] The terminal transmits this information to the server.

[0352] server

[0353] The server stores the received data and analyzes it using an AI model. The analysis results predict a medium risk of heart disease and a low risk of alcohol-related illness. The emotion engine also recognizes that User B has a high stress level.

[0354] server

[0355] Based on this, the server suggests to User B that he undergo an echocardiogram or electrocardiogram, and also suggests counseling to improve his mental health.

[0356] server

[0357] A report including the proposal is sent to User B's device.

[0358] User B

[0359] User B checks the report on the terminal and decides whether to undergo the recommended tests and counseling.

[0360] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[0361] The processing flow will be explained below.

[0362] Step 1:

[0363] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[0364] Step 2:

[0365] The terminal checks the format of the entered information and transmits it to the server in the specified format.

[0366] Step 3:

[0367] The server stores the data received from the terminal in a database and performs validation to check the completeness and consistency of the data.

[0368] Step 4:

[0369] The server adds the stored data to a processing queue and triggers an AI model that uses machine learning algorithms.

[0370] Step 5:

[0371] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict future illnesses based on the user's lifestyle and family medical history.

[0372] Step 6:

[0373] The server evaluates the risk level of each disease based on the prediction results and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[0374] Step 7:

[0375] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[0376] Step 8:

[0377] Based on the risk assessment results and the analysis results of the emotion engine, the server will suggest additional examinations to the user, recommending detailed examinations (e.g., MRI or CT scan) for high-risk patients and blood tests or ultrasound scans for medium-risk patients, and will also suggest psychological support or counseling depending on the user's emotional state.

[0378] Step 9:

[0379] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[0380] Step 10:

[0381] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0382] Step 11:

[0383] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[0384] Example 2

[0385] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0386] In modern society, the development of lifestyle-related diseases and diseases based on genetic risk is a major issue. While it is important to identify these risks early and take appropriate preventive measures, it is difficult for users to accurately assess these risks themselves. There is also a need for comprehensive health management that takes into account the user's mental health status. The present invention aims to achieve comprehensive health management by assessing the risk of disease based on the user's lifestyle and family medical history, and by analyzing the user's emotional state.

[0387] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting diseases that may occur in the future based on the collected information, means for evaluating the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the evaluation, means for notifying the user of the suggestions in the form of a report, means for analyzing the user's emotional state and evaluating the user's mental health state, and means for suggesting psychological support based on the user's emotional state. This enables the user to manage their health comprehensively, including not only physical health risks but also mental health state.

[0388] "Lifestyle habits" refers to the user's daily actions and habits, and specifically includes patterns of eating, exercise, sleeping, smoking, drinking, and the like.

[0389] "Family medical history" refers to information about the illnesses and medical history of the user's relatives in the past.

[0390] "Means for collecting information" refers to methods and devices for obtaining data from users, and specifically includes web applications and mobile applications.

[0391] "Disease prediction methods" refer to algorithms and models that analyze collected data to predict the likelihood of future disease development.

[0392] "Means for assessing risk level" refers to a method for classifying the predicted probability of developing a disease based on certain criteria and assessing it as low risk, medium risk, or high risk.

[0393] "Means for suggesting additional examination items" refers to a method or device for suggesting detailed health examinations to be recommended to a user based on a risk assessment.

[0394] "Means for notifying the user in the form of a report" refers to methods and techniques for notifying the user of a report summarizing the evaluation results and inspection proposals.

[0395] "Emotional state" refers to the user's current psychological and emotional state, and specifically includes emotions such as stress, anxiety, joy, and sadness.

[0396] "Means for analyzing emotional state" refers to methods or algorithms for determining a user's emotions using text analysis, facial recognition technology, etc.

[0397] "Means for assessing mental health status" refers to a method for measuring and assessing the psychological health of a user based on the analyzed emotional state.

[0398] "Means for suggesting psychological support" refers to methods and techniques for suggesting appropriate counseling, psychotherapy, etc. depending on the user's mental health condition.

[0399] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional testing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[0400] 1. Data Collection

[0401] Users access a questionnaire using a dedicated web or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels, which allows detailed data to be collected about individual health risks.

[0402] The terminal checks the format and content of the input information in real time and transmits it to the server in the correct format. The terminal used here is a general computing device such as a smartphone or PC.

[0403] 2. Receipt and storage of data

[0404] The server receives the data sent from the terminal. Upon receiving the data, it validates it to ensure its completeness and consistency, and if there are no problems, it stores it in the database. The stored data is also added to the queue for analysis.

[0405] 3. Perform risk prediction

[0406] The server inputs the user information stored in the database into machine learning algorithms, including deep learning and decision tree models. The algorithms then predict future diseases based on the user's lifestyle and family medical history. The prediction results are categorized into risk levels for each disease (low, medium, or high risk). The risk assessment also includes the accuracy and reliability of the diagnosis.

[0407] 4. Emotion Recognition

[0408] The server uses an emotion engine to analyze the user's input data and reactions, using text analysis and facial recognition technology to identify the user's emotional state, such as stress, anxiety, joy, or sadness.

[0409] 5. Inspection and support proposals

[0410] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations and psychological support that the user may need. For example, an echocardiogram or electrocardiogram may be recommended for a user at high risk of heart disease. Furthermore, if a high stress level is detected, psychological counseling or other support may also be suggested.

[0411] 6. Notification of results and feedback

[0412] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for psychological support.

[0413] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0414] 7. Ongoing follow-up

[0415] The server periodically reassess health risks based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures. The emotion engine also continuously monitors the user's mental state and provides appropriate support.

[0416] Specific examples

[0417] User B's case

[0418] User B enters that he "goes to the gym three times a week," "drinks beer on weekends," and "has a family history of myocardial infarction," and further enters that his work environment is very stressful.

[0419] The terminal checks the format of this information and then sends it to the server.

[0420] The server validates the received data and stores it in a database. The machine learning model then analyzes the data to predict medium risk of heart disease and low risk of alcohol-related diseases. The emotion engine also recognizes User B's high stress level.

[0421] Based on the analysis results, the server suggests that User B undergo an echocardiogram or electrocardiogram, and also recommends counseling to improve his or her mental health.

[0422] The server generates a report containing these suggestions and sends it to User B's device.

[0423] User B checks the report on the terminal and decides whether to undergo the proposed examination and counseling.

[0424] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[0425] Example input to a generative AI model

[0426] You can input the generative AI model using prompt sentences like the following:

[0427] "Based on the user's lifestyle habits and family medical history, predict which diseases the user is at high risk for. Recommend any additional tests the user may need and any measures to address the stress the user is experiencing."

[0428] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0429] Step 1:

[0430] Users access a questionnaire using a dedicated web app or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels. The data entered by the user includes data in text format and checkbox format. This allows detailed data on the user's health risks to be collected. The entered information is temporarily stored on the device.

[0431] Input: lifestyle habits, family medical history, dietary habits, exercise habits, smoking, drinking, stress levels

[0432] Output: Temporarily saved data

[0433] Step 2:

[0434] The terminal checks the format and content of the data entered by the user in real time to ensure that it is in the correct format. If the data format is successfully verified, the data that does not need to be modified is encrypted and sent to the server in the specified format. An API call is made on the terminal to send the data.

[0435] Input: Data entered by the user

[0436] Output: Data sent to the server

[0437] Step 3:

[0438] The server receives data sent from the device. The received data undergoes a validation process to check the data's completeness and consistency, and is then stored in a database. The stored data is then added to a queue for analysis, ensuring the data's format and consistency.

[0439] Input: Data sent from the terminal

[0440] Output: Data stored in the database, data queued for analysis

[0441] Step 4:

[0442] The server inputs the user information stored in the database into a machine learning algorithm (e.g., a deep learning model or a decision tree model). Here, the algorithm predicts future diseases based on the user's lifestyle and family medical history. The risk level (low, medium, or high risk) is also assessed, and the accuracy and reliability of the diagnosis are calculated. The output risk assessment results are then stored back in the database.

[0443] Input: User information stored in the database

[0444] Output: Disease prediction results, risk level, diagnostic accuracy and confidence

[0445] Step 5:

[0446] The server uses an emotion engine to analyze the user's input data and reactions. The emotion engine uses text analysis and facial recognition technology to recognize the user's emotional state, such as stress, anxiety, joy, or sadness. The results of this analysis are stored in a database as the user's emotional state.

[0447] Input: User input data, user response data

[0448] Output: Data parsed as emotional states

[0449] Step 6:

[0450] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations or psychological support to the user. For example, if a user is at high risk of heart disease, an echocardiogram or electrocardiogram will be suggested. If a user shows high stress levels, psychological counseling will be suggested. These suggestions are stored in a database.

[0451] Input: Risk assessment results, emotion engine analysis results

[0452] Output: Suggestions for additional testing items, psychological support

[0453] Step 7:

[0454] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment, the reasons for the proposed tests, and suggestions for psychological support. The report is generated in a dedicated format and sent to the user's device in real time.

[0455] Input: diagnosis results, test item suggestions, psychological support suggestions

[0456] Output: Report sent to user's terminal

[0457] Step 8:

[0458] The user receives a report on their device, which includes details of the risk assessment, reasons for the proposed testing, and suggestions for psychological support, allowing them to make a decision about whether to undergo further testing or take preventative measures.

[0459] Input: Report sent from the server

[0460] Output: User reviews the report and takes necessary action

[0461] Step 9:

[0462] The server periodically reassesses health risks based on the latest medical information and new user data. Based on the risk assessment, new recommendations and preventative measures are generated and notified to the user. Additionally, an emotion engine is used to track changes in mental health status and provide appropriate support.

[0463] Input: Latest medical information, new data from users

[0464] Output: Reassessed health risks, new recommendations and preventative measures

[0465] (Application example 2)

[0466] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0467] In modern society, lifestyle-related diseases and mental stress are on the rise, making it necessary to detect these risks early and take appropriate preventive measures. However, many users lack accurate information about their own health risks and preventive measures, leading to inadequate health management. In addition, there is a problem in that users are not motivated to actively work to maintain their health due to a lack of incentives for health-related expenditures.

[0468] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting future diseases based on the collected information, means for assessing the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the assessment, means for notifying the user of the suggestions in the form of a report, means for awarding points or cash back for health-related expenditures, and means for suggesting to the user a health support plan customized according to the health risk assessment and mental health state. This allows the user to accurately understand their own health risks and take preventive measures, and encourages them to take a proactive approach to health management through incentives.

[0469] "Information about lifestyle habits and family medical history" refers to detailed data about a user's diet, exercise habits, smoking and drinking habits, sleep patterns, stress levels, as well as family health and medical history.

[0470] "Means for predicting future diseases" refers to technology that uses machine learning algorithms and deep learning models based on collected data to predict diseases that a user may develop in the future.

[0471] "Means for assessing risk level" refers to a technique for classifying the predicted disease risk into low risk, medium risk, or high risk, and for assessing the accuracy of the diagnosis, including the reliability.

[0472] The "means for suggesting additional test items to the user" is a technology for individually suggesting necessary additional tests to the user based on the assessed risk level.

[0473] "Means for notifying the user of the proposal content in report format" refers to a technology for compiling the evaluation results and the inspection proposal content into a report and sending the report to the user's terminal.

[0474] "Means for awarding points or cash back for health-related expenditures" refers to technology that awards points or cash back as an incentive to users for purchasing products or using services related to health maintenance or preventive medicine.

[0475] The "means for proposing a customized health support plan to a user" is a technology for proposing an individually optimized health support plan based on the user's health risk assessment and mental health status.

[0476] A specific embodiment of the present invention will be described. This system supports users in managing their health by evaluating their health risks based on their lifestyle habits and family medical history, and by providing an incentive system for health-related expenditures.

[0477] 1. Data Collection

[0478] User

[0479] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns) and family medical history into the device, as well as their mental health status, such as stress levels.

[0480] Terminal

[0481] The terminal receives the data entered by the user, checks the data format, and then transmits it to the server. This terminal can be a smartphone, tablet, or other device.

[0482] server

[0483] The server stores all received data in a database, where it is validated to ensure data integrity and consistency.

[0484] 2. Health Risk Assessment

[0485] server

[0486] The server uses the data stored in the database to predict the user's future potential illnesses based on prediction results obtained using machine learning algorithms (e.g., deep learning models and decision tree models), and also evaluates the risk level (low risk, medium risk, high risk) and considers the reliability of the prediction.

[0487] 3. Mental Health Assessment

[0488] Emotion Engine

[0489] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., increased stress, depression, etc.), which is also sent to the server and used for a comprehensive health risk assessment.

[0490] 4. Inspection proposals and incentives

[0491] server

[0492] Based on the risk assessment and the analysis results of the emotion engine, the server will individually suggest to the user the additional tests that may be required (e.g., MRI, CT scan, blood test, etc.) and also provide a means to reward points and cashback for health-related expenditures.

[0493] 5. Notifications and Reports

[0494] server

[0495] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[0496] User

[0497] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[0498] 6. Follow-up

[0499] server

[0500] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[0501] Specific examples

[0502] User A's case

[0503] User A

[0504] User A enters the following information: "I run every morning," "I drink two cups of green tea a day," "I have a family history of diabetes," and "I feel stressed at work." Based on this, the system determines that User A is at medium risk for diabetes and recognizes that his stress level is high.

[0505] server

[0506] Based on this, the server will suggest a blood glucose test and a stress management program to User A, and will also give points towards the monthly fitness club membership fee.

[0507] Prompt Sentence Examples

[0508] Evaluate the health risks of a user who has entered information such as "running every morning," "two cups of green tea a day," "having a family history of diabetes," and "feeling stressed at work," and suggest the necessary tests and support. Furthermore, calculate cashback on fitness club membership fees.

[0509] This system allows users to clearly understand their health risks, take appropriate preventive measures, and receive incentives for health-related spending.

[0510] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0511] Step 1:

[0512] User

[0513] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns), family medical history, and mental health status (e.g., stress level) into the device. The input data includes specific items such as "I run every morning" and "I drink beer on weekends."

[0514] Input: lifestyle information, family medical history information, mental health status data

[0515] Output: Formatted user data

[0516] Step 2:

[0517] Terminal

[0518] The terminal receives the data entered by the user, checks the data format, and then sends it to the server in the specified format. The data format check checks for missing values ​​and the consistency of the input format.

[0519] Input: formatted user data

[0520] Output: User data with integrity checked

[0521] Step 3:

[0522] server

[0523] The server saves the data sent from the terminal in a database. Validation is performed when saving the data to ensure the data's completeness and consistency. Data is stored separately for each user in the database.

[0524] Input: User data with integrity checked

[0525] Output: User data stored in the database

[0526] Step 4:

[0527] server

[0528] The server uses the data stored in the database to apply machine learning algorithms (e.g., deep learning models or decision tree models) to predict the user's future potential illnesses. Based on the prediction results, the server evaluates the risk level (low risk, medium risk, or high risk) and calculates the reliability.

[0529] Input: User data stored in the database

[0530] Output: Predicted disease risk level and confidence level

[0531] Step 5:

[0532] Emotion Engine

[0533] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., stress, depression, etc.) using facial recognition and text analysis techniques.

[0534] Input: User emotion data

[0535] Output: Parsed emotional state

[0536] Step 6:

[0537] server

[0538] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest to the user which additional tests (e.g., MRI, CT scan, blood test, etc.) are required, and also provide a means to reward points and cashback for health-related expenditures.

[0539] Input: Risk assessment results, analyzed emotional state

[0540] Output: Proposal for additional tests and incentives

[0541] Step 7:

[0542] server

[0543] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[0544] Input: Proposal for additional tests and incentives

[0545] Output: Report format of diagnostic results and recommendations

[0546] Step 8:

[0547] User

[0548] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[0549] Input: Report format diagnostic results and recommendations

[0550] Output: Any additional checks or precautions taken, transaction history

[0551] Step 9:

[0552] server

[0553] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[0554] Input: Latest medical information, new data from users

[0555] Output: Reassessed health risks and new proposed notices

[0556] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0557] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0558] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0559] [Second embodiment]

[0560] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0561] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0562] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0563] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0564] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0565] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0566] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0567] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0568] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0569] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0570] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0571] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0572] This invention is a system that predicts future illnesses based on information about the user's lifestyle and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. The main parts of this system are a server, a terminal, and user interaction.

[0573] 1. Data Collection

[0574] User

[0575] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[0576] Terminal

[0577] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[0578] server

[0579] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[0580] 2. Data Analysis

[0581] server

[0582] The data stored on the server is passed to an AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[0583] 3. Risk Assessment

[0584] server

[0585] Based on the prediction results, the server evaluates the risk level of each disease and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[0586] 4. Inspection proposal

[0587] server

[0588] Based on the risk assessment, the server suggests additional tests the user may need: if the risk is high, it suggests more detailed tests (e.g., MRI or CT scan), and if the risk is medium, it recommends blood tests or ultrasound.

[0589] 5. Notifications and Feedback

[0590] server

[0591] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[0592] User

[0593] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0594] 6. Follow-up

[0595] server

[0596] The server periodically reassess the user's health risk based on the latest medical information and new data about the user, and sends new suggestions and notifications to the user to take preventative measures as needed.

[0597] Specific examples

[0598] User A's case

[0599] User A

[0600] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[0601] Terminal

[0602] The terminal transmits this information to the server.

[0603] server

[0604] The server stores the received data and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[0605] server

[0606] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[0607] server

[0608] A report including the proposal is sent to User A's terminal.

[0609] User A

[0610] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[0611] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[0612] The processing flow will be explained below.

[0613] Step 1:

[0614] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[0615] Step 2:

[0616] The terminal validates the entered information, formats it in the specified format, and sends it to the server.

[0617] Step 3:

[0618] The server stores the received data in a database and performs validation to check the completeness and consistency of the data.

[0619] Step 4:

[0620] The server adds the stored data to a processing queue and triggers the AI ​​model to use machine learning algorithms.

[0621] Step 5:

[0622] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict potential future illnesses.

[0623] Step 6:

[0624] The server evaluates the risk level of each disease based on the prediction results and classifies them as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[0625] Step 7:

[0626] The server will suggest additional tests that may be needed depending on the risk assessment: for high risk, further testing (e.g., MRI or CT scan) and for medium risk, blood tests or ultrasound are recommended.

[0627] Step 8:

[0628] The server generates a report containing the diagnosis results and recommended tests and sends it to the user's device, including details of the risk assessment and the reasons for the suggested tests.

[0629] Step 9:

[0630] The user checks the report received on the terminal and decides whether to undergo the proposed examination, if necessary.

[0631] Step 10:

[0632] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures as needed.

[0633] Example 1

[0634] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0635] Conventional health management systems have not adequately predicted or assessed health risks based on users' lifestyle habits and family medical history, making it difficult to recommend effective preventive measures or additional tests. In particular, they lack real-time reassessment based on the latest medical information and individualized support based on user-specific data.

[0636] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0637] In this invention, the server includes: means for collecting information from a user regarding lifestyle habits, family medical history, dietary habits, exercise habits, and smoking and drinking habits; means for checking the format of the collected information and transmitting it to the server in the correct format; means for analyzing the data stored in the server using a machine learning algorithm and predicting future diseases based on the user's data; means for assessing the risk level of each disease based on the prediction results and classifying it as low, medium, or high risk; means for suggesting additional tests to the user based on the risk assessment; means for generating the suggestions in report format and transmitting them to the user's terminal; and means for periodically reassessing health risks based on the latest medical information and new user data and notifying the user of new suggestions and preventive measures. This enables users to grasp their own health risks early and take appropriate preventive measures.

[0638] "Lifestyle habits" refers to the entire range of daily behaviors and habits that affect health, such as diet, exercise, sleep, smoking, and drinking habits.

[0639] "Family medical history" refers to the history of any illnesses or health conditions experienced by a user's family members, past and present, and is important information when assessing genetic risk.

[0640] "Diet" refers to all activities related to eating, including the quality and quantity of food a user consumes on a daily basis, meal frequency, and balanced eating habits.

[0641] "Exercise habits" refers to the pattern of physical exercise and fitness activities that a user regularly engages in, and is an important factor in maintaining and improving health.

[0642] "Smoking and drinking habits" refers to the amount and frequency of smoking that a user does on a daily basis, and the type, amount, and frequency of alcohol that a user drinks.

[0643] A "machine learning algorithm" is a computational method used to learn patterns and rules from data, which can then be used to predict future events and trends.

[0644] "Risk level" is an assessment that classifies a person into low risk, medium risk, or high risk based on the predicted outcome of a disease that may occur in the future.

[0645] "Additional test items" are specific tests or diagnostic procedures suggested to the user based on the risk assessment, and are useful for early detection and follow-up of disease.

[0646] The "report format" refers to a document format that visually summarizes information such as diagnostic results and suggested test items in an easy-to-understand format, and is used to notify users.

[0647] "Latest medical information" refers to the results of medical research and clinical trials, as well as the latest knowledge and data on new treatments and diagnostic techniques.

[0648] "Health risk reassessment" is the process of periodically reassessing a user's health status and risks based on the user's latest data and medical information, and making new predictions and suggestions.

[0649] "Notification" refers to the act of sending messages or alerts to users to inform them of risk assessment results and recommendations.

[0650] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[0651] 1. Data Collection

[0652] User

[0653] Users access a dedicated questionnaire and enter information about their lifestyle, family medical history, diet, exercise habits, smoking and drinking habits, etc. The questionnaire is designed to comprehensively assess the user's health status.

[0654] 2. Data Transmission

[0655] Terminal

[0656] The terminal receives data entered by the user and checks whether the data format is correct. If there are no errors, it formats the data in the specified format and sends it to the server. For example, it validates the input data and sends it to the server as an HTTP request.

[0657] 3. Data storage

[0658] server

[0659] The server receives the data sent from the terminal and stores it in a database. When storing the data, validation is performed to check the completeness and consistency of the data. The received data is temporarily stored in memory, and once the validation is complete, it is stored in the database.

[0660] 4. Data Analysis

[0661] server

[0662] The data stored on the server is passed to an AI model for analysis. Machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to predict future diseases based on the user's data. The necessary data is extracted from the database and fed into the analysis model using a Python script. The analysis results are temporarily stored on the server.

[0663] 5. Risk Assessment

[0664] server

[0665] The server evaluates the risk level of each disease based on the analysis results. The evaluation is classified into three categories: low risk, medium risk, and high risk, and measures are suggested according to each risk level. The evaluation algorithm categorizes the analysis results and also calculates a confidence score within them. The result is added to the user's profile.

[0666] 6. Inspection Proposal

[0667] server

[0668] Based on the risk assessment, the server recommends additional tests that the user may need. If a high risk is detected, detailed tests (e.g., MRI or CT scan) are recommended, while if a medium risk is detected, blood tests or ultrasound examinations are recommended. The recommendations are generated using templates, and a report is created that includes the appropriate tests and the reasons for them.

[0669] 7. Notifications and Feedback

[0670] server

[0671] The server generates a report containing the risk assessment and recommendations, and notifies the user's device. The report is generated in a visually easy-to-understand format such as PDF. The report is generated using a document template engine (e.g., JasperReports or iText), and is notified to the user's email address or a dedicated app.

[0672] User

[0673] Users can review the report received on their device and consider any suggested tests or preventative measures. They will receive an email or in-app notification with a link they can click to download or view the report.

[0674] 8. Follow-up

[0675] server

[0676] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new recommendations and preventative measures as needed. The server periodically runs the reassessment process using a scheduled task (e.g., cron job or cloud scheduler) and updates the report based on the new data.

[0677] Specific examples

[0678] User A's case

[0679] User A

[0680] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[0681] Terminal

[0682] The terminal checks the format of this information before sending it to the server.

[0683] server

[0684] The server stores the received data in a database and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[0685] server

[0686] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[0687] server

[0688] A report including the proposal is sent to User A's terminal.

[0689] User A

[0690] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[0691] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[0692] Example prompt sentence:

[0693] Describe the processing steps and specific behavior of a system that predicts potential future illnesses based on a user's lifestyle and family medical history, performs a risk assessment, and suggests necessary preventative measures or additional testing.

[0694] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0695] Step 1:

[0696] Data collection

[0697] User

[0698] Users access a special questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[0699] Input: The user enters information about lifestyle habits and family medical history into a questionnaire.

[0700] How it works: Using a web browser or mobile application, you enter your answers into each section of the questionnaire and click the "Submit" button.

[0701] Output: Information about lifestyle habits and family medical history entered.

[0702] Step 2:

[0703] Data transmission

[0704] Terminal

[0705] The terminal receives the data entered by the user and checks whether the format of the data is correct. If there are no errors, it formats the data in the specified format and sends it to the server.

[0706] Input: Information about lifestyle habits and family medical history that you enter into your device.

[0707] Operation: The terminal validates the input data and checks whether characters have been entered in fields that should be entered as numbers. The validated data is sent to the server as an HTTP request.

[0708] Output: Formatted lifestyle and family medical history information sent to the server.

[0709] Step 3:

[0710] Data storage

[0711] server

[0712] The server receives the data sent from the terminal and stores it in a database, where it performs validation to check the completeness and consistency of the data.

[0713] Input: Formatted lifestyle and family medical history information sent from your device.

[0714] How it works: The server temporarily stores the received data in memory and validates it against existing rules before storing it in the database. Once validation is complete, it performs an INSERT operation on the database.

[0715] Output: Information about lifestyle habits and family medical history stored in a database.

[0716] Step 4:

[0717] Data analysis

[0718] server

[0719] The data stored on the server is then passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to predict future illnesses based on the user's data.

[0720] Input: Data about the user's lifestyle and family medical history stored in a database.

[0721] How it works: The server extracts the necessary data from the database and feeds the input data into the analytical model using Python scripts. The analytical results are temporarily stored on the server.

[0722] Output: Prediction of future potential illnesses.

[0723] Step 5:

[0724] Risk Assessment

[0725] server

[0726] The server evaluates the risk level of each disease based on the analysis results, categorizing the risk into three categories: low risk, medium risk, and high risk, and suggests countermeasures according to each risk level.

[0727] Input: Predictions of future disease outcomes obtained from a generative AI model.

[0728] How it works: The rating algorithm categorizes the analysis results and also calculates a confidence score within them, which is added to the user profile.

[0729] Output: Assessment results categorized by risk level.

[0730] Step 6:

[0731] Inspection proposal

[0732] server

[0733] Based on the risk assessment, the server recommends additional tests that the user may need: if a high risk is detected, a detailed examination (e.g., MRI or CT scan) is recommended, and if a medium risk is detected, blood tests or ultrasound examinations are recommended.

[0734] Input: Assessment results categorized by risk level.

[0735] How it works: Recommendations are generated using templates, and a report is created with the appropriate tests and their reasons.

[0736] Output: A report with suggested additional tests for the user.

[0737] Step 7:

[0738] Notifications and Feedback

[0739] server

[0740] The server generates a report containing the risk assessment and recommendations, and sends it to the user's device in a visually easy-to-understand format such as PDF.

[0741] Input: Report with additional tests.

[0742] How it works: Reports are generated using a document template engine (e.g. JasperReports or iText) and then notified to the user via email or a dedicated app.

[0743] Output: A report of risk assessment and inspection suggestions that is communicated to the user.

[0744] User

[0745] The user reviews the report received on the device and considers any suggested tests or preventative measures.

[0746] Input: Risk assessment and inspection suggestion report posted to the terminal.

[0747] How it works: Users receive an email or in-app notification with a link they click to download or view the report.

[0748] Output: User action (getting tested, taking preventative measures, etc.).

[0749] Step 8:

[0750] Follow-up

[0751] server

[0752] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new suggestions and preventative measures as needed.

[0753] Input: Latest medical data and new user data.

[0754] How it works: The server periodically runs the re-evaluation process using a scheduled task (e.g. cron job or cloud scheduler) and updates the reports with new data.

[0755] Output: Notification with reassessment results and new suggestions and preventative measures.

[0756] (Application example 1)

[0757] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0758] Existing health risk assessment systems have the problem that users have to enter information about their lifestyle habits and family medical history, which requires a lot of time and effort. Furthermore, risk assessment results and test recommendations are not notified in real time, which hinders users' ability to respond quickly. Furthermore, the low accuracy of analysis and the low reliability of prediction results make effective health management difficult.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0760] In this invention, the server includes means for collecting information on lifestyle habits and family medical history from a user, means for predicting future diseases based on the collected information, means for assessing risk levels based on the disease prediction results, means for providing an interface that is easy for users to input via a smart device, and means for analyzing data using a generative AI model and performing risk assessment and recommendations in real time, thereby enabling users to easily input information and receive accurate health risk assessments and appropriate test recommendations in real time.

[0761] "Lifestyle habits" refers to the user's daily activities and habits, specifically behavioral patterns such as eating, drinking, exercise, smoking, and alcohol consumption.

[0762] "Family medical history" refers to the history of illnesses experienced by the user's blood relatives, past or present.

[0763] "Means for collecting information" refers to devices and systems for obtaining data such as lifestyle habits and family medical history from users.

[0764] "Means for predicting diseases that may occur in the future" refers to a device or system that predicts diseases that a user may suffer from in the future based on collected data.

[0765] "Means for assessing risk level" refers to a device or system for classifying the likelihood of developing a predicted disease into categories such as low risk, medium risk, or high risk.

[0766] "Means for suggesting additional examination items" refers to a device or system for recommending further examination or diagnostic items that a user should undergo based on the evaluation results.

[0767] "Means for notifying the proposed contents in the form of a report" refers to a device or system for documenting the evaluation results and proposed inspection items and notifying the user.

[0768] "Smart device" refers to an electronic device with internet connectivity that a user uses to enter information and view results.

[0769] "Interface" refers to operation screens, input forms, dialogue systems, etc. that make it easier for users to input information via smart devices.

[0770] A "generative AI model" refers to an artificial intelligence model that uses machine learning and data analysis techniques to analyze collected data and assess health risks.

[0771] "Real-time means" refers to devices or systems that analyze and evaluate information within an extremely short time from the time it is entered by the user, and immediately notify the results.

[0772] This invention is a system that predicts future illnesses based on information such as lifestyle habits and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[0773] 1. Data Collection

[0774] User

[0775] Using a smart device interface, users input information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[0776] Terminal

[0777] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[0778] server

[0779] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[0780] 2. Data Analysis

[0781] server

[0782] The data stored on the server is passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[0783] 3. Risk Assessment

[0784] server

[0785] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[0786] 4. Inspection proposal

[0787] server

[0788] Based on the risk assessment, the server suggests additional tests to the user: if the risk is high, more in-depth tests are suggested, and if the risk is medium, simpler tests are recommended.

[0789] 5. Notifications and Feedback

[0790] server

[0791] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[0792] User

[0793] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[0794] 6. Follow-up

[0795] server

[0796] The server periodically reassess the user's health risk based on the latest medical information and new user data, and sends the user new suggestions and notifications to take preventative measures as needed.

[0797] Specific examples

[0798] For example, if a 45-year-old male user enters information such as "family history of diabetes," "drinks alcohol 1-2 times a week," and "does moderate exercise" into a medical questionnaire, this data is sent to the server via the smart device. The server analyzes the data using a generative AI model and evaluates the user as being at medium risk for diabetes and alcoholic liver disease. Based on this evaluation, the server recommends a "blood sugar test" and an "abdominal ultrasound test," and notifies the user of the results in the form of a report. This system allows users to understand their health risks early and take appropriate preventive measures.

[0799] Prompt Sentence Examples

[0800] "What are the health risks for a 45-year-old man with a family history of diabetes, who consumes alcohol 1-2 times a week, and engages in moderate exercise?"

[0801] "Please make a list of diseases that the user is at high risk of developing based on their family history and lifestyle habits, and suggest the necessary tests."

[0802] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0803] Step 1:

[0804] User data entry

[0805] Users use the interface of a smart device (e.g., smart glasses) to input information such as lifestyle habits and family medical history. Specifically, they answer a questionnaire in the form of questions, and the data is entered into the terminal.

[0806] Input: Lifestyle and family medical history data (e.g., drinking habits, smoking habits, exercise habits, family history, etc.)

[0807] Output: Formatted user data

[0808] Step 2:

[0809] Data transmission and format check

[0810] The terminal checks the format of the collected data, formats it into the specified format, and then sends it to the server.

[0811] Specifically, it validates whether the data input format is correct and transfers the formatted data to the server.

[0812] Input: Data entered by the user

[0813] Output: Formatted data sent to the server

[0814] Step 3:

[0815] Data Storage and Validation

[0816] The server receives the data sent from the terminal and stores it in a database. When storing the data, it checks its integrity and consistency.

[0817] Specifically, it checks whether the data is accurate and consistent before saving and approves it for writing to the database.

[0818] Input: Formatted data

[0819] Output: Saved user data

[0820] Step 4:

[0821] Disease prediction through data analysis

[0822] The server passes the stored data to a generative AI model to predict future diseases.

[0823] Specifically, data analysis is performed using machine learning algorithms (e.g., deep learning models) to create a list of diseases at risk of developing.

[0824] Input: Saved user data

[0825] Output: Disease prediction results

[0826] Step 5:

[0827] Risk Level Assessment

[0828] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[0829] Specifically, the likelihood of developing each predicted disease is calculated and a risk level is defined.

[0830] Input: Disease prediction results

[0831] Output: Risk level classification results

[0832] Step 6:

[0833] Proposal of test items

[0834] Based on the results of the risk assessment, the server suggests to the user what additional tests are required.

[0835] Specifically, in high-risk cases, detailed examinations (e.g., MRI or CT scans) are recommended, and in medium-risk cases, blood tests and ultrasound examinations are recommended.

[0836] Input: Risk level classification results

[0837] Output: Suggested tests

[0838] Step 7:

[0839] Reporting and Notifications

[0840] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the recommended tests.

[0841] Specifically, the prediction results and proposals are compiled into a text report and sent to the terminal.

[0842] Input: Proposed test items, risk assessment details

[0843] Output: Report sent to the user

[0844] Step 8:

[0845] User report review and action

[0846] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[0847] Specifically, they review the report contents and carry out any tests or preventative measures they deem necessary.

[0848] Input: Report sent to user

[0849] Output: User's health care behavior

[0850] Step 9:

[0851] Regular follow-up

[0852] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures.

[0853] Specifically, the database is updated periodically and the results of the reevaluation are notified to the user.

[0854] Input: Latest medical information, new data from users

[0855] Output: New evaluation results and recommendations

[0856] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0857] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[0858] 1. Data Collection

[0859] User

[0860] Users access a questionnaire and enter information about their lifestyle, family medical history, diet, exercise, smoking and drinking habits, etc. This allows detailed data to be collected about their individual health risks.

[0861] Terminal

[0862] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[0863] server

[0864] The server stores the data received from the terminal in a database. When storing the data, it validates the data to ensure its completeness and consistency. The server also adds the data to a queue for analysis.

[0865] 2. Data analysis and risk assessment

[0866] server

[0867] The server then passes the stored data to a machine learning algorithm for analysis. Using machine learning algorithms (e.g., deep learning or decision tree models), the system predicts future diseases based on the user's lifestyle and family medical history. The system then assesses the risk level of each disease based on the prediction results, categorizing it as low, medium, or high risk. The assessment results also include the accuracy and reliability of the diagnosis.

[0868] 3. Emotion Recognition by Emotion Engine

[0869] Emotion Engine

[0870] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[0871] 4. Testing recommendations and mental health assessment

[0872] server

[0873] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest additional tests that the user needs. If the risk is high, more detailed tests (e.g., MRI or CT scan) will be suggested, and if the risk is medium, blood tests or ultrasound scans will be recommended. It will also suggest psychological support and counseling depending on the user's emotional state.

[0874] 5. Notifications and Feedback

[0875] server

[0876] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[0877] User

[0878] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0879] 6. Follow-up

[0880] server

[0881] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[0882] Specific examples

[0883] User B's case

[0884] User B

[0885] User B inputs the following: "I go to the gym three times a week," "I drink beer on weekends," and "My family has a history of myocardial infarction." User B also inputs that he is in a stressful work environment.

[0886] Terminal

[0887] The terminal transmits this information to the server.

[0888] server

[0889] The server stores the received data and analyzes it using an AI model. The analysis results predict a medium risk of heart disease and a low risk of alcohol-related illness. The emotion engine also recognizes that User B has a high stress level.

[0890] server

[0891] Based on this, the server suggests to User B that he undergo an echocardiogram or electrocardiogram, and also suggests counseling to improve his mental health.

[0892] server

[0893] A report including the proposal is sent to User B's device.

[0894] User B

[0895] User B checks the report on the terminal and decides whether to undergo the recommended tests and counseling.

[0896] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[0897] The processing flow will be explained below.

[0898] Step 1:

[0899] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[0900] Step 2:

[0901] The terminal checks the format of the entered information and transmits it to the server in the specified format.

[0902] Step 3:

[0903] The server stores the data received from the terminal in a database and performs validation to check the completeness and consistency of the data.

[0904] Step 4:

[0905] The server adds the stored data to a processing queue and triggers an AI model that uses machine learning algorithms.

[0906] Step 5:

[0907] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict future illnesses based on the user's lifestyle and family medical history.

[0908] Step 6:

[0909] The server evaluates the risk level of each disease based on the prediction results and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[0910] Step 7:

[0911] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[0912] Step 8:

[0913] Based on the risk assessment results and the analysis results of the emotion engine, the server will suggest additional examinations to the user, recommending detailed examinations (e.g., MRI or CT scan) for high-risk patients and blood tests or ultrasound scans for medium-risk patients, and will also suggest psychological support or counseling depending on the user's emotional state.

[0914] Step 9:

[0915] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[0916] Step 10:

[0917] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0918] Step 11:

[0919] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[0920] Example 2

[0921] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0922] In modern society, the development of lifestyle-related diseases and diseases based on genetic risk is a major issue. While it is important to identify these risks early and take appropriate preventive measures, it is difficult for users to accurately assess these risks themselves. There is also a need for comprehensive health management that takes into account the user's mental health status. The present invention aims to achieve comprehensive health management by assessing the risk of disease based on the user's lifestyle and family medical history, and by analyzing the user's emotional state.

[0923] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting diseases that may occur in the future based on the collected information, means for evaluating the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the evaluation, means for notifying the user of the suggestions in the form of a report, means for analyzing the user's emotional state and evaluating the user's mental health state, and means for suggesting psychological support based on the user's emotional state. This enables the user to manage their health comprehensively, including not only physical health risks but also mental health state.

[0924] "Lifestyle habits" refers to the user's daily actions and habits, and specifically includes patterns of eating, exercise, sleeping, smoking, drinking, and the like.

[0925] "Family medical history" refers to information about the illnesses and medical history of the user's relatives in the past.

[0926] "Means for collecting information" refers to methods and devices for obtaining data from users, and specifically includes web applications and mobile applications.

[0927] "Disease prediction methods" refer to algorithms and models that analyze collected data to predict the likelihood of future disease development.

[0928] "Means for assessing risk level" refers to a method for classifying the predicted probability of developing a disease based on certain criteria and assessing it as low risk, medium risk, or high risk.

[0929] "Means for suggesting additional examination items" refers to a method or device for suggesting detailed health examinations to be recommended to a user based on a risk assessment.

[0930] "Means for notifying the user in the form of a report" refers to methods and techniques for notifying the user of a report summarizing the evaluation results and inspection proposals.

[0931] "Emotional state" refers to the user's current psychological and emotional state, and specifically includes emotions such as stress, anxiety, joy, and sadness.

[0932] "Means for analyzing emotional state" refers to methods or algorithms for determining a user's emotions using text analysis, facial recognition technology, etc.

[0933] "Means for assessing mental health status" refers to a method for measuring and assessing the psychological health of a user based on the analyzed emotional state.

[0934] "Means for suggesting psychological support" refers to methods and techniques for suggesting appropriate counseling, psychotherapy, etc. depending on the user's mental health condition.

[0935] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional testing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[0936] 1. Data Collection

[0937] Users access a questionnaire using a dedicated web or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels, which allows detailed data to be collected about individual health risks.

[0938] The terminal checks the format and content of the input information in real time and transmits it to the server in the correct format. The terminal used here is a general computing device such as a smartphone or PC.

[0939] 2. Receipt and storage of data

[0940] The server receives the data sent from the terminal. Upon receiving the data, it validates it to ensure its completeness and consistency, and if there are no problems, it stores it in the database. The stored data is also added to the queue for analysis.

[0941] 3. Perform risk prediction

[0942] The server inputs the user information stored in the database into machine learning algorithms, including deep learning and decision tree models. The algorithms then predict future diseases based on the user's lifestyle and family medical history. The prediction results are categorized into risk levels for each disease (low, medium, or high risk). The risk assessment also includes the accuracy and reliability of the diagnosis.

[0943] 4. Emotion Recognition

[0944] The server uses an emotion engine to analyze the user's input data and reactions, using text analysis and facial recognition technology to identify the user's emotional state, such as stress, anxiety, joy, or sadness.

[0945] 5. Inspection and support proposals

[0946] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations and psychological support that the user may need. For example, an echocardiogram or electrocardiogram may be recommended for a user at high risk of heart disease. Furthermore, if a high stress level is detected, psychological counseling or other support may also be suggested.

[0947] 6. Notification of results and feedback

[0948] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for psychological support.

[0949] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[0950] 7. Ongoing follow-up

[0951] The server periodically reassess health risks based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures. The emotion engine also continuously monitors the user's mental state and provides appropriate support.

[0952] Specific examples

[0953] User B's case

[0954] User B enters that he "goes to the gym three times a week," "drinks beer on weekends," and "has a family history of myocardial infarction," and further enters that his work environment is very stressful.

[0955] The terminal checks the format of this information and then sends it to the server.

[0956] The server validates the received data and stores it in a database. The machine learning model then analyzes the data to predict medium risk of heart disease and low risk of alcohol-related diseases. The emotion engine also recognizes User B's high stress level.

[0957] Based on the analysis results, the server suggests that User B undergo an echocardiogram or electrocardiogram, and also recommends counseling to improve his or her mental health.

[0958] The server generates a report containing these suggestions and sends it to User B's device.

[0959] User B checks the report on the terminal and decides whether to undergo the proposed examination and counseling.

[0960] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[0961] Example input to a generative AI model

[0962] You can input the generative AI model using prompt sentences like the following:

[0963] "Based on the user's lifestyle habits and family medical history, predict which diseases the user is at high risk for. Recommend any additional tests the user may need and any measures to address the stress the user is experiencing."

[0964] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0965] Step 1:

[0966] Users access a questionnaire using a dedicated web app or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels. The data entered by the user includes data in text format and checkbox format. This allows detailed data on the user's health risks to be collected. The entered information is temporarily stored on the device.

[0967] Input: lifestyle habits, family medical history, dietary habits, exercise habits, smoking, drinking, stress levels

[0968] Output: Temporarily saved data

[0969] Step 2:

[0970] The terminal checks the format and content of the data entered by the user in real time to ensure that it is in the correct format. If the data format is successfully verified, the data that does not need to be modified is encrypted and sent to the server in the specified format. An API call is made on the terminal to send the data.

[0971] Input: Data entered by the user

[0972] Output: Data sent to the server

[0973] Step 3:

[0974] The server receives data sent from the device. The received data undergoes a validation process to check the data's completeness and consistency, and is then stored in a database. The stored data is then added to a queue for analysis, ensuring the data's format and consistency.

[0975] Input: Data sent from the terminal

[0976] Output: Data stored in the database, data queued for analysis

[0977] Step 4:

[0978] The server inputs the user information stored in the database into a machine learning algorithm (e.g., a deep learning model or a decision tree model). Here, the algorithm predicts future diseases based on the user's lifestyle and family medical history. The risk level (low, medium, or high risk) is also assessed, and the accuracy and reliability of the diagnosis are calculated. The output risk assessment results are then stored back in the database.

[0979] Input: User information stored in the database

[0980] Output: Disease prediction results, risk level, diagnostic accuracy and confidence

[0981] Step 5:

[0982] The server uses an emotion engine to analyze the user's input data and reactions. The emotion engine uses text analysis and facial recognition technology to recognize the user's emotional state, such as stress, anxiety, joy, or sadness. The results of this analysis are stored in a database as the user's emotional state.

[0983] Input: User input data, user response data

[0984] Output: Data parsed as emotional states

[0985] Step 6:

[0986] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations or psychological support to the user. For example, if a user is at high risk of heart disease, an echocardiogram or electrocardiogram will be suggested. If a user shows high stress levels, psychological counseling will be suggested. These suggestions are stored in a database.

[0987] Input: Risk assessment results, emotion engine analysis results

[0988] Output: Suggestions for additional testing items, psychological support

[0989] Step 7:

[0990] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment, the reasons for the proposed tests, and suggestions for psychological support. The report is generated in a dedicated format and sent to the user's device in real time.

[0991] Input: diagnosis results, test item suggestions, psychological support suggestions

[0992] Output: Report sent to user's terminal

[0993] Step 8:

[0994] The user receives a report on their device, which includes details of the risk assessment, reasons for the proposed testing, and suggestions for psychological support, allowing them to make a decision about whether to undergo further testing or take preventative measures.

[0995] Input: Report sent from the server

[0996] Output: User reviews the report and takes necessary action

[0997] Step 9:

[0998] The server periodically reassesses health risks based on the latest medical information and new user data. Based on the risk assessment, new recommendations and preventative measures are generated and notified to the user. Additionally, an emotion engine is used to track changes in mental health status and provide appropriate support.

[0999] Input: Latest medical information, new data from users

[1000] Output: Reassessed health risks, new recommendations and preventative measures

[1001] (Application example 2)

[1002] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1003] In modern society, lifestyle-related diseases and mental stress are on the rise, making it necessary to detect these risks early and take appropriate preventive measures. However, many users lack accurate information about their own health risks and preventive measures, leading to inadequate health management. In addition, there is a problem in that users are not motivated to actively work to maintain their health due to a lack of incentives for health-related expenditures.

[1004] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting future diseases based on the collected information, means for assessing the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the assessment, means for notifying the user of the suggestions in the form of a report, means for awarding points or cash back for health-related expenditures, and means for suggesting to the user a health support plan customized according to the health risk assessment and mental health state. This allows the user to accurately understand their own health risks and take preventive measures, and encourages them to take a proactive approach to health management through incentives.

[1005] "Information about lifestyle habits and family medical history" refers to detailed data about a user's diet, exercise habits, smoking and drinking habits, sleep patterns, stress levels, as well as family health and medical history.

[1006] "Means for predicting future diseases" refers to technology that uses machine learning algorithms and deep learning models based on collected data to predict diseases that a user may develop in the future.

[1007] "Means for assessing risk level" refers to a technique for classifying the predicted disease risk into low risk, medium risk, or high risk, and for assessing the accuracy of the diagnosis, including the reliability.

[1008] The "means for suggesting additional test items to the user" is a technology for individually suggesting necessary additional tests to the user based on the assessed risk level.

[1009] "Means for notifying the user of the proposal content in report format" refers to a technology for compiling the evaluation results and the inspection proposal content into a report and sending the report to the user's terminal.

[1010] "Means for awarding points or cash back for health-related expenditures" refers to technology that awards points or cash back as an incentive to users for purchasing products or using services related to health maintenance or preventive medicine.

[1011] The "means for proposing a customized health support plan to a user" is a technology for proposing an individually optimized health support plan based on the user's health risk assessment and mental health status.

[1012] A specific embodiment of the present invention will be described. This system supports users in managing their health by evaluating their health risks based on their lifestyle habits and family medical history, and by providing an incentive system for health-related expenditures.

[1013] 1. Data Collection

[1014] User

[1015] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns) and family medical history into the device, as well as their mental health status, such as stress levels.

[1016] Terminal

[1017] The terminal receives the data entered by the user, checks the data format, and then transmits it to the server. This terminal can be a smartphone, tablet, or other device.

[1018] server

[1019] The server stores all received data in a database, where it is validated to ensure data integrity and consistency.

[1020] 2. Health Risk Assessment

[1021] server

[1022] The server uses the data stored in the database to predict the user's future potential illnesses based on prediction results obtained using machine learning algorithms (e.g., deep learning models and decision tree models), and also evaluates the risk level (low risk, medium risk, high risk) and considers the reliability of the prediction.

[1023] 3. Mental Health Assessment

[1024] Emotion Engine

[1025] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., increased stress, depression, etc.), which is also sent to the server and used for a comprehensive health risk assessment.

[1026] 4. Inspection proposals and incentives

[1027] server

[1028] Based on the risk assessment and the analysis results of the emotion engine, the server will individually suggest to the user the additional tests that may be required (e.g., MRI, CT scan, blood test, etc.) and also provide a means to reward points and cashback for health-related expenditures.

[1029] 5. Notifications and Reports

[1030] server

[1031] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[1032] User

[1033] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[1034] 6. Follow-up

[1035] server

[1036] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[1037] Specific examples

[1038] User A's case

[1039] User A

[1040] User A enters the following information: "I run every morning," "I drink two cups of green tea a day," "I have a family history of diabetes," and "I feel stressed at work." Based on this, the system determines that User A is at medium risk for diabetes and recognizes that his stress level is high.

[1041] server

[1042] Based on this, the server will suggest a blood glucose test and a stress management program to User A, and will also give points towards the monthly fitness club membership fee.

[1043] Prompt Sentence Examples

[1044] Evaluate the health risks of a user who has entered information such as "running every morning," "two cups of green tea a day," "having a family history of diabetes," and "feeling stressed at work," and suggest the necessary tests and support. Furthermore, calculate cashback on fitness club membership fees.

[1045] This system allows users to clearly understand their health risks, take appropriate preventive measures, and receive incentives for health-related spending.

[1046] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1047] Step 1:

[1048] User

[1049] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns), family medical history, and mental health status (e.g., stress level) into the device. The input data includes specific items such as "I run every morning" and "I drink beer on weekends."

[1050] Input: lifestyle information, family medical history information, mental health status data

[1051] Output: Formatted user data

[1052] Step 2:

[1053] Terminal

[1054] The terminal receives the data entered by the user, checks the data format, and then sends it to the server in the specified format. The data format check checks for missing values ​​and the consistency of the input format.

[1055] Input: formatted user data

[1056] Output: User data with integrity checked

[1057] Step 3:

[1058] server

[1059] The server saves the data sent from the terminal in a database. Validation is performed when saving the data to ensure the data's completeness and consistency. Data is stored separately for each user in the database.

[1060] Input: User data with integrity checked

[1061] Output: User data stored in the database

[1062] Step 4:

[1063] server

[1064] The server uses the data stored in the database to apply machine learning algorithms (e.g., deep learning models or decision tree models) to predict the user's future potential illnesses. Based on the prediction results, the server evaluates the risk level (low risk, medium risk, or high risk) and calculates the reliability.

[1065] Input: User data stored in the database

[1066] Output: Predicted disease risk level and confidence level

[1067] Step 5:

[1068] Emotion Engine

[1069] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., stress, depression, etc.) using facial recognition and text analysis techniques.

[1070] Input: User emotion data

[1071] Output: Parsed emotional state

[1072] Step 6:

[1073] server

[1074] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest to the user which additional tests (e.g., MRI, CT scan, blood test, etc.) are required, and also provide a means to reward points and cashback for health-related expenditures.

[1075] Input: Risk assessment results, analyzed emotional state

[1076] Output: Proposal for additional tests and incentives

[1077] Step 7:

[1078] server

[1079] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[1080] Input: Proposal for additional tests and incentives

[1081] Output: Report format of diagnostic results and recommendations

[1082] Step 8:

[1083] User

[1084] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[1085] Input: Report format diagnostic results and recommendations

[1086] Output: Any additional checks or precautions taken, transaction history

[1087] Step 9:

[1088] server

[1089] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[1090] Input: Latest medical information, new data from users

[1091] Output: Reassessed health risks and new proposed notices

[1092] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1093] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1094] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1095] [Third embodiment]

[1096] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1097] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1098] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1099] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1100] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1101] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1102] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1103] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1104] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1106] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1107] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1108] This invention is a system that predicts future illnesses based on information about the user's lifestyle and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. The main parts of this system are a server, a terminal, and user interaction.

[1109] 1. Data Collection

[1110] User

[1111] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[1112] Terminal

[1113] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[1114] server

[1115] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[1116] 2. Data Analysis

[1117] server

[1118] The data stored on the server is passed to an AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[1119] 3. Risk Assessment

[1120] server

[1121] Based on the prediction results, the server evaluates the risk level of each disease and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[1122] 4. Inspection proposal

[1123] server

[1124] Based on the risk assessment, the server suggests additional tests the user may need: if the risk is high, it suggests more detailed tests (e.g., MRI or CT scan), and if the risk is medium, it recommends blood tests or ultrasound.

[1125] 5. Notifications and Feedback

[1126] server

[1127] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[1128] User

[1129] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1130] 6. Follow-up

[1131] server

[1132] The server periodically reassess the user's health risk based on the latest medical information and new data about the user, and sends new suggestions and notifications to the user to take preventative measures as needed.

[1133] Specific examples

[1134] User A's case

[1135] User A

[1136] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[1137] Terminal

[1138] The terminal transmits this information to the server.

[1139] server

[1140] The server stores the received data and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[1141] server

[1142] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[1143] server

[1144] A report including the proposal is sent to User A's terminal.

[1145] User A

[1146] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[1147] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[1148] The processing flow will be explained below.

[1149] Step 1:

[1150] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[1151] Step 2:

[1152] The terminal validates the entered information, formats it in the specified format, and sends it to the server.

[1153] Step 3:

[1154] The server stores the received data in a database and performs validation to check the completeness and consistency of the data.

[1155] Step 4:

[1156] The server adds the stored data to a processing queue and triggers the AI ​​model to use machine learning algorithms.

[1157] Step 5:

[1158] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict potential future illnesses.

[1159] Step 6:

[1160] The server evaluates the risk level of each disease based on the prediction results and classifies them as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[1161] Step 7:

[1162] The server will suggest additional tests that may be needed depending on the risk assessment: for high risk, further testing (e.g., MRI or CT scan) and for medium risk, blood tests or ultrasound are recommended.

[1163] Step 8:

[1164] The server generates a report containing the diagnosis results and recommended tests and sends it to the user's device, including details of the risk assessment and the reasons for the suggested tests.

[1165] Step 9:

[1166] The user checks the report received on the terminal and decides whether to undergo the proposed examination, if necessary.

[1167] Step 10:

[1168] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures as needed.

[1169] Example 1

[1170] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1171] Conventional health management systems have not adequately predicted or assessed health risks based on users' lifestyle habits and family medical history, making it difficult to recommend effective preventive measures or additional tests. In particular, they lack real-time reassessment based on the latest medical information and individualized support based on user-specific data.

[1172] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1173] In this invention, the server includes: means for collecting information from a user regarding lifestyle habits, family medical history, dietary habits, exercise habits, and smoking and drinking habits; means for checking the format of the collected information and transmitting it to the server in the correct format; means for analyzing the data stored in the server using a machine learning algorithm and predicting future diseases based on the user's data; means for assessing the risk level of each disease based on the prediction results and classifying it as low, medium, or high risk; means for suggesting additional tests to the user based on the risk assessment; means for generating the suggestions in report format and transmitting them to the user's terminal; and means for periodically reassessing health risks based on the latest medical information and new user data and notifying the user of new suggestions and preventive measures. This enables users to grasp their own health risks early and take appropriate preventive measures.

[1174] "Lifestyle habits" refers to the entire range of daily behaviors and habits that affect health, such as diet, exercise, sleep, smoking, and drinking habits.

[1175] "Family medical history" refers to the history of any illnesses or health conditions experienced by a user's family members, past and present, and is important information when assessing genetic risk.

[1176] "Diet" refers to all activities related to eating, including the quality and quantity of food a user consumes on a daily basis, meal frequency, and balanced eating habits.

[1177] "Exercise habits" refers to the pattern of physical exercise and fitness activities that a user regularly engages in, and is an important factor in maintaining and improving health.

[1178] "Smoking and drinking habits" refers to the amount and frequency of smoking that a user does on a daily basis, and the type, amount, and frequency of alcohol that a user drinks.

[1179] A "machine learning algorithm" is a computational method used to learn patterns and rules from data, which can then be used to predict future events and trends.

[1180] "Risk level" is an assessment that classifies a person into low risk, medium risk, or high risk based on the predicted outcome of a disease that may occur in the future.

[1181] "Additional test items" are specific tests or diagnostic procedures suggested to the user based on the risk assessment, and are useful for early detection and follow-up of disease.

[1182] The "report format" refers to a document format that visually summarizes information such as diagnostic results and suggested test items in an easy-to-understand format, and is used to notify users.

[1183] "Latest medical information" refers to the results of medical research and clinical trials, as well as the latest knowledge and data on new treatments and diagnostic techniques.

[1184] "Health risk reassessment" is the process of periodically reassessing a user's health status and risks based on the user's latest data and medical information, and making new predictions and suggestions.

[1185] "Notification" refers to the act of sending messages or alerts to users to inform them of risk assessment results and recommendations.

[1186] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[1187] 1. Data Collection

[1188] User

[1189] Users access a dedicated questionnaire and enter information about their lifestyle, family medical history, diet, exercise habits, smoking and drinking habits, etc. The questionnaire is designed to comprehensively assess the user's health status.

[1190] 2. Data Transmission

[1191] Terminal

[1192] The terminal receives data entered by the user and checks whether the data format is correct. If there are no errors, it formats the data in the specified format and sends it to the server. For example, it validates the input data and sends it to the server as an HTTP request.

[1193] 3. Data storage

[1194] server

[1195] The server receives the data sent from the terminal and stores it in a database. When storing the data, validation is performed to check the completeness and consistency of the data. The received data is temporarily stored in memory, and once the validation is complete, it is stored in the database.

[1196] 4. Data Analysis

[1197] server

[1198] The data stored on the server is passed to an AI model for analysis. Machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to predict future diseases based on the user's data. The necessary data is extracted from the database and fed into the analysis model using a Python script. The analysis results are temporarily stored on the server.

[1199] 5. Risk Assessment

[1200] server

[1201] The server evaluates the risk level of each disease based on the analysis results. The evaluation is classified into three categories: low risk, medium risk, and high risk, and measures are suggested according to each risk level. The evaluation algorithm categorizes the analysis results and also calculates a confidence score within them. The result is added to the user's profile.

[1202] 6. Inspection Proposal

[1203] server

[1204] Based on the risk assessment, the server recommends additional tests that the user may need. If a high risk is detected, detailed tests (e.g., MRI or CT scan) are recommended, while if a medium risk is detected, blood tests or ultrasound examinations are recommended. The recommendations are generated using templates, and a report is created that includes the appropriate tests and the reasons for them.

[1205] 7. Notifications and Feedback

[1206] server

[1207] The server generates a report containing the risk assessment and recommendations, and notifies the user's device. The report is generated in a visually easy-to-understand format such as PDF. The report is generated using a document template engine (e.g., JasperReports or iText), and is notified to the user's email address or a dedicated app.

[1208] User

[1209] Users can review the report received on their device and consider any suggested tests or preventative measures. They will receive an email or in-app notification with a link they can click to download or view the report.

[1210] 8. Follow-up

[1211] server

[1212] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new recommendations and preventative measures as needed. The server periodically runs the reassessment process using a scheduled task (e.g., cron job or cloud scheduler) and updates the report based on the new data.

[1213] Specific examples

[1214] User A's case

[1215] User A

[1216] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[1217] Terminal

[1218] The terminal checks the format of this information before sending it to the server.

[1219] server

[1220] The server stores the received data in a database and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[1221] server

[1222] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[1223] server

[1224] A report including the proposal is sent to User A's terminal.

[1225] User A

[1226] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[1227] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[1228] Example prompt sentence:

[1229] Describe the processing steps and specific behavior of a system that predicts potential future illnesses based on a user's lifestyle and family medical history, performs a risk assessment, and suggests necessary preventative measures or additional testing.

[1230] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1231] Step 1:

[1232] Data collection

[1233] User

[1234] Users access a special questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[1235] Input: The user enters information about lifestyle habits and family medical history into a questionnaire.

[1236] How it works: Using a web browser or mobile application, you enter your answers into each section of the questionnaire and click the "Submit" button.

[1237] Output: Information about lifestyle habits and family medical history entered.

[1238] Step 2:

[1239] Data transmission

[1240] Terminal

[1241] The terminal receives the data entered by the user and checks whether the format of the data is correct. If there are no errors, it formats the data in the specified format and sends it to the server.

[1242] Input: Information about lifestyle habits and family medical history that you enter into your device.

[1243] Operation: The terminal validates the input data and checks whether characters have been entered in fields that should be entered as numbers. The validated data is sent to the server as an HTTP request.

[1244] Output: Formatted lifestyle and family medical history information sent to the server.

[1245] Step 3:

[1246] Data storage

[1247] server

[1248] The server receives the data sent from the terminal and stores it in a database, where it performs validation to check the completeness and consistency of the data.

[1249] Input: Formatted lifestyle and family medical history information sent from your device.

[1250] How it works: The server temporarily stores the received data in memory and validates it against existing rules before storing it in the database. Once validation is complete, it performs an INSERT operation on the database.

[1251] Output: Information about lifestyle habits and family medical history stored in a database.

[1252] Step 4:

[1253] Data analysis

[1254] server

[1255] The data stored on the server is then passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to predict future illnesses based on the user's data.

[1256] Input: Data about the user's lifestyle and family medical history stored in a database.

[1257] How it works: The server extracts the necessary data from the database and feeds the input data into the analytical model using Python scripts. The analytical results are temporarily stored on the server.

[1258] Output: Prediction of future potential illnesses.

[1259] Step 5:

[1260] Risk Assessment

[1261] server

[1262] The server evaluates the risk level of each disease based on the analysis results, categorizing the risk into three categories: low risk, medium risk, and high risk, and suggests countermeasures according to each risk level.

[1263] Input: Predictions of future disease outcomes obtained from a generative AI model.

[1264] How it works: The rating algorithm categorizes the analysis results and also calculates a confidence score within them, which is added to the user profile.

[1265] Output: Assessment results categorized by risk level.

[1266] Step 6:

[1267] Inspection proposal

[1268] server

[1269] Based on the risk assessment, the server recommends additional tests that the user may need: if a high risk is detected, a detailed examination (e.g., MRI or CT scan) is recommended, and if a medium risk is detected, blood tests or ultrasound examinations are recommended.

[1270] Input: Assessment results categorized by risk level.

[1271] How it works: Recommendations are generated using templates, and a report is created with the appropriate tests and their reasons.

[1272] Output: A report with suggested additional tests for the user.

[1273] Step 7:

[1274] Notifications and Feedback

[1275] server

[1276] The server generates a report containing the risk assessment and recommendations, and sends it to the user's device in a visually easy-to-understand format such as PDF.

[1277] Input: Report with additional tests.

[1278] How it works: Reports are generated using a document template engine (e.g. JasperReports or iText) and then notified to the user via email or a dedicated app.

[1279] Output: A report of risk assessment and inspection suggestions that is communicated to the user.

[1280] User

[1281] The user reviews the report received on the device and considers any suggested tests or preventative measures.

[1282] Input: Risk assessment and inspection suggestion report posted to the terminal.

[1283] How it works: Users receive an email or in-app notification with a link they click to download or view the report.

[1284] Output: User action (getting tested, taking preventative measures, etc.).

[1285] Step 8:

[1286] Follow-up

[1287] server

[1288] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new suggestions and preventative measures as needed.

[1289] Input: Latest medical data and new user data.

[1290] How it works: The server periodically runs the re-evaluation process using a scheduled task (e.g. cron job or cloud scheduler) and updates the reports with new data.

[1291] Output: Notification with reassessment results and new suggestions and preventative measures.

[1292] (Application example 1)

[1293] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1294] Existing health risk assessment systems have the problem that users have to enter information about their lifestyle habits and family medical history, which requires a lot of time and effort. Furthermore, risk assessment results and test recommendations are not notified in real time, which hinders users' ability to respond quickly. Furthermore, the low accuracy of analysis and the low reliability of prediction results make effective health management difficult.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1296] In this invention, the server includes means for collecting information on lifestyle habits and family medical history from a user, means for predicting future diseases based on the collected information, means for assessing risk levels based on the disease prediction results, means for providing an interface that is easy for users to input via a smart device, and means for analyzing data using a generative AI model and performing risk assessment and recommendations in real time, thereby enabling users to easily input information and receive accurate health risk assessments and appropriate test recommendations in real time.

[1297] "Lifestyle habits" refers to the user's daily activities and habits, specifically behavioral patterns such as eating, drinking, exercise, smoking, and alcohol consumption.

[1298] "Family medical history" refers to the history of illnesses experienced by the user's blood relatives, past or present.

[1299] "Means for collecting information" refers to devices and systems for obtaining data such as lifestyle habits and family medical history from users.

[1300] "Means for predicting diseases that may occur in the future" refers to a device or system that predicts diseases that a user may suffer from in the future based on collected data.

[1301] "Means for assessing risk level" refers to a device or system for classifying the likelihood of developing a predicted disease into categories such as low risk, medium risk, or high risk.

[1302] "Means for suggesting additional examination items" refers to a device or system for recommending further examination or diagnostic items that a user should undergo based on the evaluation results.

[1303] "Means for notifying the proposed contents in the form of a report" refers to a device or system for documenting the evaluation results and proposed inspection items and notifying the user.

[1304] "Smart device" refers to an electronic device with internet connectivity that a user uses to enter information and view results.

[1305] "Interface" refers to operation screens, input forms, dialogue systems, etc. that make it easier for users to input information via smart devices.

[1306] A "generative AI model" refers to an artificial intelligence model that uses machine learning and data analysis techniques to analyze collected data and assess health risks.

[1307] "Real-time means" refers to devices or systems that analyze and evaluate information within an extremely short time from the time it is entered by the user, and immediately notify the results.

[1308] This invention is a system that predicts future illnesses based on information such as lifestyle habits and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[1309] 1. Data Collection

[1310] User

[1311] Using a smart device interface, users input information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[1312] Terminal

[1313] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[1314] server

[1315] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[1316] 2. Data Analysis

[1317] server

[1318] The data stored on the server is passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[1319] 3. Risk Assessment

[1320] server

[1321] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[1322] 4. Inspection proposal

[1323] server

[1324] Based on the risk assessment, the server suggests additional tests to the user: if the risk is high, more in-depth tests are suggested, and if the risk is medium, simpler tests are recommended.

[1325] 5. Notifications and Feedback

[1326] server

[1327] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[1328] User

[1329] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[1330] 6. Follow-up

[1331] server

[1332] The server periodically reassess the user's health risk based on the latest medical information and new user data, and sends the user new suggestions and notifications to take preventative measures as needed.

[1333] Specific examples

[1334] For example, if a 45-year-old male user enters information such as "family history of diabetes," "drinks alcohol 1-2 times a week," and "does moderate exercise" into a medical questionnaire, this data is sent to the server via the smart device. The server analyzes the data using a generative AI model and evaluates the user as being at medium risk for diabetes and alcoholic liver disease. Based on this evaluation, the server recommends a "blood sugar test" and an "abdominal ultrasound test," and notifies the user of the results in the form of a report. This system allows users to understand their health risks early and take appropriate preventive measures.

[1335] Prompt Sentence Examples

[1336] "What are the health risks for a 45-year-old man with a family history of diabetes, who consumes alcohol 1-2 times a week, and engages in moderate exercise?"

[1337] "Please make a list of diseases that the user is at high risk of developing based on their family history and lifestyle habits, and suggest the necessary tests."

[1338] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1339] Step 1:

[1340] User data entry

[1341] Users use the interface of a smart device (e.g., smart glasses) to input information such as lifestyle habits and family medical history. Specifically, they answer a questionnaire in the form of questions, and the data is entered into the terminal.

[1342] Input: Lifestyle and family medical history data (e.g., drinking habits, smoking habits, exercise habits, family history, etc.)

[1343] Output: Formatted user data

[1344] Step 2:

[1345] Data transmission and format check

[1346] The terminal checks the format of the collected data, formats it into the specified format, and then sends it to the server.

[1347] Specifically, it validates whether the data input format is correct and transfers the formatted data to the server.

[1348] Input: Data entered by the user

[1349] Output: Formatted data sent to the server

[1350] Step 3:

[1351] Data Storage and Validation

[1352] The server receives the data sent from the terminal and stores it in a database. When storing the data, it checks its integrity and consistency.

[1353] Specifically, it checks whether the data is accurate and consistent before saving and approves it for writing to the database.

[1354] Input: Formatted data

[1355] Output: Saved user data

[1356] Step 4:

[1357] Disease prediction through data analysis

[1358] The server passes the stored data to a generative AI model to predict future diseases.

[1359] Specifically, data analysis is performed using machine learning algorithms (e.g., deep learning models) to create a list of diseases at risk of developing.

[1360] Input: Saved user data

[1361] Output: Disease prediction results

[1362] Step 5:

[1363] Risk Level Assessment

[1364] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[1365] Specifically, the likelihood of developing each predicted disease is calculated and a risk level is defined.

[1366] Input: Disease prediction results

[1367] Output: Risk level classification results

[1368] Step 6:

[1369] Proposal of test items

[1370] Based on the results of the risk assessment, the server suggests to the user what additional tests are required.

[1371] Specifically, in high-risk cases, detailed examinations (e.g., MRI or CT scans) are recommended, and in medium-risk cases, blood tests and ultrasound examinations are recommended.

[1372] Input: Risk level classification results

[1373] Output: Suggested tests

[1374] Step 7:

[1375] Reporting and Notifications

[1376] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the recommended tests.

[1377] Specifically, the prediction results and proposals are compiled into a text report and sent to the terminal.

[1378] Input: Proposed test items, risk assessment details

[1379] Output: Report sent to the user

[1380] Step 8:

[1381] User report review and action

[1382] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[1383] Specifically, they review the report contents and carry out any tests or preventative measures they deem necessary.

[1384] Input: Report sent to user

[1385] Output: User's health care behavior

[1386] Step 9:

[1387] Regular follow-up

[1388] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures.

[1389] Specifically, the database is updated periodically and the results of the reevaluation are notified to the user.

[1390] Input: Latest medical information, new data from users

[1391] Output: New evaluation results and recommendations

[1392] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1393] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[1394] 1. Data Collection

[1395] User

[1396] Users access a questionnaire and enter information about their lifestyle, family medical history, diet, exercise, smoking and drinking habits, etc. This allows detailed data to be collected about their individual health risks.

[1397] Terminal

[1398] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[1399] server

[1400] The server stores the data received from the terminal in a database. When storing the data, it validates the data to ensure its completeness and consistency. The server also adds the data to a queue for analysis.

[1401] 2. Data analysis and risk assessment

[1402] server

[1403] The server then passes the stored data to a machine learning algorithm for analysis. Using machine learning algorithms (e.g., deep learning or decision tree models), the system predicts future diseases based on the user's lifestyle and family medical history. The system then assesses the risk level of each disease based on the prediction results, categorizing it as low, medium, or high risk. The assessment results also include the accuracy and reliability of the diagnosis.

[1404] 3. Emotion Recognition by Emotion Engine

[1405] Emotion Engine

[1406] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[1407] 4. Testing recommendations and mental health assessment

[1408] server

[1409] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest additional tests that the user needs. If the risk is high, more detailed tests (e.g., MRI or CT scan) will be suggested, and if the risk is medium, blood tests or ultrasound scans will be recommended. It will also suggest psychological support and counseling depending on the user's emotional state.

[1410] 5. Notifications and Feedback

[1411] server

[1412] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[1413] User

[1414] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1415] 6. Follow-up

[1416] server

[1417] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[1418] Specific examples

[1419] User B's case

[1420] User B

[1421] User B inputs the following: "I go to the gym three times a week," "I drink beer on weekends," and "My family has a history of myocardial infarction." User B also inputs that he is in a stressful work environment.

[1422] Terminal

[1423] The terminal transmits this information to the server.

[1424] server

[1425] The server stores the received data and analyzes it using an AI model. The analysis results predict a medium risk of heart disease and a low risk of alcohol-related illness. The emotion engine also recognizes that User B has a high stress level.

[1426] server

[1427] Based on this, the server suggests to User B that he undergo an echocardiogram or electrocardiogram, and also suggests counseling to improve his mental health.

[1428] server

[1429] A report including the proposal is sent to User B's device.

[1430] User B

[1431] User B checks the report on the terminal and decides whether to undergo the recommended tests and counseling.

[1432] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[1433] The processing flow will be explained below.

[1434] Step 1:

[1435] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[1436] Step 2:

[1437] The terminal checks the format of the entered information and transmits it to the server in the specified format.

[1438] Step 3:

[1439] The server stores the data received from the terminal in a database and performs validation to check the completeness and consistency of the data.

[1440] Step 4:

[1441] The server adds the stored data to a processing queue and triggers an AI model that uses machine learning algorithms.

[1442] Step 5:

[1443] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict future illnesses based on the user's lifestyle and family medical history.

[1444] Step 6:

[1445] The server evaluates the risk level of each disease based on the prediction results and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[1446] Step 7:

[1447] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[1448] Step 8:

[1449] Based on the risk assessment results and the analysis results of the emotion engine, the server will suggest additional examinations to the user, recommending detailed examinations (e.g., MRI or CT scan) for high-risk patients and blood tests or ultrasound scans for medium-risk patients, and will also suggest psychological support or counseling depending on the user's emotional state.

[1450] Step 9:

[1451] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[1452] Step 10:

[1453] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1454] Step 11:

[1455] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[1456] Example 2

[1457] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1458] In modern society, the development of lifestyle-related diseases and diseases based on genetic risk is a major issue. While it is important to identify these risks early and take appropriate preventive measures, it is difficult for users to accurately assess these risks themselves. There is also a need for comprehensive health management that takes into account the user's mental health status. The present invention aims to achieve comprehensive health management by assessing the risk of disease based on the user's lifestyle and family medical history, and by analyzing the user's emotional state.

[1459] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting diseases that may occur in the future based on the collected information, means for evaluating the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the evaluation, means for notifying the user of the suggestions in the form of a report, means for analyzing the user's emotional state and evaluating the user's mental health state, and means for suggesting psychological support based on the user's emotional state. This enables the user to manage their health comprehensively, including not only physical health risks but also mental health state.

[1460] "Lifestyle habits" refers to the user's daily actions and habits, and specifically includes patterns of eating, exercise, sleeping, smoking, drinking, and the like.

[1461] "Family medical history" refers to information about the illnesses and medical history of the user's relatives in the past.

[1462] "Means for collecting information" refers to methods and devices for obtaining data from users, and specifically includes web applications and mobile applications.

[1463] "Disease prediction methods" refer to algorithms and models that analyze collected data to predict the likelihood of future disease development.

[1464] "Means for assessing risk level" refers to a method for classifying the predicted probability of developing a disease based on certain criteria and assessing it as low risk, medium risk, or high risk.

[1465] "Means for suggesting additional examination items" refers to a method or device for suggesting detailed health examinations to be recommended to a user based on a risk assessment.

[1466] "Means for notifying the user in the form of a report" refers to methods and techniques for notifying the user of a report summarizing the evaluation results and inspection proposals.

[1467] "Emotional state" refers to the user's current psychological and emotional state, and specifically includes emotions such as stress, anxiety, joy, and sadness.

[1468] "Means for analyzing emotional state" refers to methods or algorithms for determining a user's emotions using text analysis, facial recognition technology, etc.

[1469] "Means for assessing mental health status" refers to a method for measuring and assessing the psychological health of a user based on the analyzed emotional state.

[1470] "Means for suggesting psychological support" refers to methods and techniques for suggesting appropriate counseling, psychotherapy, etc. depending on the user's mental health condition.

[1471] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional testing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[1472] 1. Data Collection

[1473] Users access a questionnaire using a dedicated web or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels, which allows detailed data to be collected about individual health risks.

[1474] The terminal checks the format and content of the input information in real time and transmits it to the server in the correct format. The terminal used here is a general computing device such as a smartphone or PC.

[1475] 2. Receipt and storage of data

[1476] The server receives the data sent from the terminal. Upon receiving the data, it validates it to ensure its completeness and consistency, and if there are no problems, it stores it in the database. The stored data is also added to the queue for analysis.

[1477] 3. Perform risk prediction

[1478] The server inputs the user information stored in the database into machine learning algorithms, including deep learning and decision tree models. The algorithms then predict future diseases based on the user's lifestyle and family medical history. The prediction results are categorized into risk levels for each disease (low, medium, or high risk). The risk assessment also includes the accuracy and reliability of the diagnosis.

[1479] 4. Emotion Recognition

[1480] The server uses an emotion engine to analyze the user's input data and reactions, using text analysis and facial recognition technology to identify the user's emotional state, such as stress, anxiety, joy, or sadness.

[1481] 5. Inspection and support proposals

[1482] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations and psychological support that the user may need. For example, an echocardiogram or electrocardiogram may be recommended for a user at high risk of heart disease. Furthermore, if a high stress level is detected, psychological counseling or other support may also be suggested.

[1483] 6. Notification of results and feedback

[1484] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for psychological support.

[1485] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1486] 7. Ongoing follow-up

[1487] The server periodically reassess health risks based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures. The emotion engine also continuously monitors the user's mental state and provides appropriate support.

[1488] Specific examples

[1489] User B's case

[1490] User B enters that he "goes to the gym three times a week," "drinks beer on weekends," and "has a family history of myocardial infarction," and further enters that his work environment is very stressful.

[1491] The terminal checks the format of this information and then sends it to the server.

[1492] The server validates the received data and stores it in a database. The machine learning model then analyzes the data to predict medium risk of heart disease and low risk of alcohol-related diseases. The emotion engine also recognizes User B's high stress level.

[1493] Based on the analysis results, the server suggests that User B undergo an echocardiogram or electrocardiogram, and also recommends counseling to improve his or her mental health.

[1494] The server generates a report containing these suggestions and sends it to User B's device.

[1495] User B checks the report on the terminal and decides whether to undergo the proposed examination and counseling.

[1496] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[1497] Example input to a generative AI model

[1498] You can input the generative AI model using prompt sentences like the following:

[1499] "Based on the user's lifestyle habits and family medical history, predict which diseases the user is at high risk for. Recommend any additional tests the user may need and any measures to address the stress the user is experiencing."

[1500] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1501] Step 1:

[1502] Users access a questionnaire using a dedicated web app or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels. The data entered by the user includes data in text format and checkbox format. This allows detailed data on the user's health risks to be collected. The entered information is temporarily stored on the device.

[1503] Input: lifestyle habits, family medical history, dietary habits, exercise habits, smoking, drinking, stress levels

[1504] Output: Temporarily saved data

[1505] Step 2:

[1506] The terminal checks the format and content of the data entered by the user in real time to ensure that it is in the correct format. If the data format is successfully verified, the data that does not need to be modified is encrypted and sent to the server in the specified format. An API call is made on the terminal to send the data.

[1507] Input: Data entered by the user

[1508] Output: Data sent to the server

[1509] Step 3:

[1510] The server receives data sent from the device. The received data undergoes a validation process to check the data's completeness and consistency, and is then stored in a database. The stored data is then added to a queue for analysis, ensuring the data's format and consistency.

[1511] Input: Data sent from the terminal

[1512] Output: Data stored in the database, data queued for analysis

[1513] Step 4:

[1514] The server inputs the user information stored in the database into a machine learning algorithm (e.g., a deep learning model or a decision tree model). Here, the algorithm predicts future diseases based on the user's lifestyle and family medical history. The risk level (low, medium, or high risk) is also assessed, and the accuracy and reliability of the diagnosis are calculated. The output risk assessment results are then stored back in the database.

[1515] Input: User information stored in the database

[1516] Output: Disease prediction results, risk level, diagnostic accuracy and confidence

[1517] Step 5:

[1518] The server uses an emotion engine to analyze the user's input data and reactions. The emotion engine uses text analysis and facial recognition technology to recognize the user's emotional state, such as stress, anxiety, joy, or sadness. The results of this analysis are stored in a database as the user's emotional state.

[1519] Input: User input data, user response data

[1520] Output: Data parsed as emotional states

[1521] Step 6:

[1522] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations or psychological support to the user. For example, if a user is at high risk of heart disease, an echocardiogram or electrocardiogram will be suggested. If a user shows high stress levels, psychological counseling will be suggested. These suggestions are stored in a database.

[1523] Input: Risk assessment results, emotion engine analysis results

[1524] Output: Suggestions for additional testing items, psychological support

[1525] Step 7:

[1526] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment, the reasons for the proposed tests, and suggestions for psychological support. The report is generated in a dedicated format and sent to the user's device in real time.

[1527] Input: diagnosis results, test item suggestions, psychological support suggestions

[1528] Output: Report sent to user's terminal

[1529] Step 8:

[1530] The user receives a report on their device, which includes details of the risk assessment, reasons for the proposed testing, and suggestions for psychological support, allowing them to make a decision about whether to undergo further testing or take preventative measures.

[1531] Input: Report sent from the server

[1532] Output: User reviews the report and takes necessary action

[1533] Step 9:

[1534] The server periodically reassesses health risks based on the latest medical information and new user data. Based on the risk assessment, new recommendations and preventative measures are generated and notified to the user. Additionally, an emotion engine is used to track changes in mental health status and provide appropriate support.

[1535] Input: Latest medical information, new data from users

[1536] Output: Reassessed health risks, new recommendations and preventative measures

[1537] (Application example 2)

[1538] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1539] In modern society, lifestyle-related diseases and mental stress are on the rise, making it necessary to detect these risks early and take appropriate preventive measures. However, many users lack accurate information about their own health risks and preventive measures, leading to inadequate health management. In addition, there is a problem in that users are not motivated to actively work to maintain their health due to a lack of incentives for health-related expenditures.

[1540] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting future diseases based on the collected information, means for assessing the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the assessment, means for notifying the user of the suggestions in the form of a report, means for awarding points or cash back for health-related expenditures, and means for suggesting to the user a health support plan customized according to the health risk assessment and mental health state. This allows the user to accurately understand their own health risks and take preventive measures, and encourages them to take a proactive approach to health management through incentives.

[1541] "Information about lifestyle habits and family medical history" refers to detailed data about a user's diet, exercise habits, smoking and drinking habits, sleep patterns, stress levels, as well as family health and medical history.

[1542] "Means for predicting future diseases" refers to technology that uses machine learning algorithms and deep learning models based on collected data to predict diseases that a user may develop in the future.

[1543] "Means for assessing risk level" refers to a technique for classifying the predicted disease risk into low risk, medium risk, or high risk, and for assessing the accuracy of the diagnosis, including the reliability.

[1544] The "means for suggesting additional test items to the user" is a technology for individually suggesting necessary additional tests to the user based on the assessed risk level.

[1545] "Means for notifying the user of the proposal content in report format" refers to a technology for compiling the evaluation results and the inspection proposal content into a report and sending the report to the user's terminal.

[1546] "Means for awarding points or cash back for health-related expenditures" refers to technology that awards points or cash back as an incentive to users for purchasing products or using services related to health maintenance or preventive medicine.

[1547] The "means for proposing a customized health support plan to a user" is a technology for proposing an individually optimized health support plan based on the user's health risk assessment and mental health status.

[1548] A specific embodiment of the present invention will be described. This system supports users in managing their health by evaluating their health risks based on their lifestyle habits and family medical history, and by providing an incentive system for health-related expenditures.

[1549] 1. Data Collection

[1550] User

[1551] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns) and family medical history into the device, as well as their mental health status, such as stress levels.

[1552] Terminal

[1553] The terminal receives the data entered by the user, checks the data format, and then transmits it to the server. This terminal can be a smartphone, tablet, or other device.

[1554] server

[1555] The server stores all received data in a database, where it is validated to ensure data integrity and consistency.

[1556] 2. Health Risk Assessment

[1557] server

[1558] The server uses the data stored in the database to predict the user's future potential illnesses based on prediction results obtained using machine learning algorithms (e.g., deep learning models and decision tree models), and also evaluates the risk level (low risk, medium risk, high risk) and considers the reliability of the prediction.

[1559] 3. Mental Health Assessment

[1560] Emotion Engine

[1561] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., increased stress, depression, etc.), which is also sent to the server and used for a comprehensive health risk assessment.

[1562] 4. Inspection proposals and incentives

[1563] server

[1564] Based on the risk assessment and the analysis results of the emotion engine, the server will individually suggest to the user the additional tests that may be required (e.g., MRI, CT scan, blood test, etc.) and also provide a means to reward points and cashback for health-related expenditures.

[1565] 5. Notifications and Reports

[1566] server

[1567] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[1568] User

[1569] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[1570] 6. Follow-up

[1571] server

[1572] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[1573] Specific examples

[1574] User A's case

[1575] User A

[1576] User A enters the following information: "I run every morning," "I drink two cups of green tea a day," "I have a family history of diabetes," and "I feel stressed at work." Based on this, the system determines that User A is at medium risk for diabetes and recognizes that his stress level is high.

[1577] server

[1578] Based on this, the server will suggest a blood glucose test and a stress management program to User A, and will also give points towards the monthly fitness club membership fee.

[1579] Prompt Sentence Examples

[1580] Evaluate the health risks of a user who has entered information such as "running every morning," "two cups of green tea a day," "having a family history of diabetes," and "feeling stressed at work," and suggest the necessary tests and support. Furthermore, calculate cashback on fitness club membership fees.

[1581] This system allows users to clearly understand their health risks, take appropriate preventive measures, and receive incentives for health-related spending.

[1582] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1583] Step 1:

[1584] User

[1585] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns), family medical history, and mental health status (e.g., stress level) into the device. The input data includes specific items such as "I run every morning" and "I drink beer on weekends."

[1586] Input: lifestyle information, family medical history information, mental health status data

[1587] Output: Formatted user data

[1588] Step 2:

[1589] Terminal

[1590] The terminal receives the data entered by the user, checks the data format, and then sends it to the server in the specified format. The data format check checks for missing values ​​and the consistency of the input format.

[1591] Input: formatted user data

[1592] Output: User data with integrity checked

[1593] Step 3:

[1594] server

[1595] The server saves the data sent from the terminal in a database. Validation is performed when saving the data to ensure the data's completeness and consistency. Data is stored separately for each user in the database.

[1596] Input: User data with integrity checked

[1597] Output: User data stored in the database

[1598] Step 4:

[1599] server

[1600] The server uses the data stored in the database to apply machine learning algorithms (e.g., deep learning models or decision tree models) to predict the user's future potential illnesses. Based on the prediction results, the server evaluates the risk level (low risk, medium risk, or high risk) and calculates the reliability.

[1601] Input: User data stored in the database

[1602] Output: Predicted disease risk level and confidence level

[1603] Step 5:

[1604] Emotion Engine

[1605] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., stress, depression, etc.) using facial recognition and text analysis techniques.

[1606] Input: User emotion data

[1607] Output: Parsed emotional state

[1608] Step 6:

[1609] server

[1610] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest to the user which additional tests (e.g., MRI, CT scan, blood test, etc.) are required, and also provide a means to reward points and cashback for health-related expenditures.

[1611] Input: Risk assessment results, analyzed emotional state

[1612] Output: Proposal for additional tests and incentives

[1613] Step 7:

[1614] server

[1615] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[1616] Input: Proposal for additional tests and incentives

[1617] Output: Report format of diagnostic results and recommendations

[1618] Step 8:

[1619] User

[1620] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[1621] Input: Report format diagnostic results and recommendations

[1622] Output: Any additional checks or precautions taken, transaction history

[1623] Step 9:

[1624] server

[1625] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[1626] Input: Latest medical information, new data from users

[1627] Output: Reassessed health risks and new proposed notices

[1628] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1629] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1630] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1631] [Fourth embodiment]

[1632] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1633] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1634] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1635] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1636] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1637] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1638] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1639] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1640] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1641] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1642] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1643] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1644] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1645] This invention is a system that predicts future illnesses based on information about the user's lifestyle and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. The main parts of this system are a server, a terminal, and user interaction.

[1646] 1. Data Collection

[1647] User

[1648] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[1649] Terminal

[1650] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[1651] server

[1652] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[1653] 2. Data Analysis

[1654] server

[1655] The data stored on the server is passed to an AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[1656] 3. Risk Assessment

[1657] server

[1658] Based on the prediction results, the server evaluates the risk level of each disease and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[1659] 4. Inspection proposal

[1660] server

[1661] Based on the risk assessment, the server suggests additional tests the user may need: if the risk is high, it suggests more detailed tests (e.g., MRI or CT scan), and if the risk is medium, it recommends blood tests or ultrasound.

[1662] 5. Notifications and Feedback

[1663] server

[1664] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[1665] User

[1666] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1667] 6. Follow-up

[1668] server

[1669] The server periodically reassess the user's health risk based on the latest medical information and new data about the user, and sends new suggestions and notifications to the user to take preventative measures as needed.

[1670] Specific examples

[1671] User A's case

[1672] User A

[1673] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[1674] Terminal

[1675] The terminal transmits this information to the server.

[1676] server

[1677] The server stores the received data and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[1678] server

[1679] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[1680] server

[1681] A report including the proposal is sent to User A's terminal.

[1682] User A

[1683] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[1684] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[1688] Step 2:

[1689] The terminal validates the entered information, formats it in the specified format, and sends it to the server.

[1690] Step 3:

[1691] The server stores the received data in a database and performs validation to check the completeness and consistency of the data.

[1692] Step 4:

[1693] The server adds the stored data to a processing queue and triggers the AI ​​model to use machine learning algorithms.

[1694] Step 5:

[1695] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict potential future illnesses.

[1696] Step 6:

[1697] The server evaluates the risk level of each disease based on the prediction results and classifies them as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[1698] Step 7:

[1699] The server will suggest additional tests that may be needed depending on the risk assessment: for high risk, further testing (e.g., MRI or CT scan) and for medium risk, blood tests or ultrasound are recommended.

[1700] Step 8:

[1701] The server generates a report containing the diagnosis results and recommended tests and sends it to the user's device, including details of the risk assessment and the reasons for the suggested tests.

[1702] Step 9:

[1703] The user checks the report received on the terminal and decides whether to undergo the proposed examination, if necessary.

[1704] Step 10:

[1705] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures as needed.

[1706] Example 1

[1707] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1708] Conventional health management systems have not adequately predicted or assessed health risks based on users' lifestyle habits and family medical history, making it difficult to recommend effective preventive measures or additional tests. In particular, they lack real-time reassessment based on the latest medical information and individualized support based on user-specific data.

[1709] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1710] In this invention, the server includes: means for collecting information from a user regarding lifestyle habits, family medical history, dietary habits, exercise habits, and smoking and drinking habits; means for checking the format of the collected information and transmitting it to the server in the correct format; means for analyzing the data stored in the server using a machine learning algorithm and predicting future diseases based on the user's data; means for assessing the risk level of each disease based on the prediction results and classifying it as low, medium, or high risk; means for suggesting additional tests to the user based on the risk assessment; means for generating the suggestions in report format and transmitting them to the user's terminal; and means for periodically reassessing health risks based on the latest medical information and new user data and notifying the user of new suggestions and preventive measures. This enables users to grasp their own health risks early and take appropriate preventive measures.

[1711] "Lifestyle habits" refers to the entire range of daily behaviors and habits that affect health, such as diet, exercise, sleep, smoking, and drinking habits.

[1712] "Family medical history" refers to the history of any illnesses or health conditions experienced by a user's family members, past and present, and is important information when assessing genetic risk.

[1713] "Diet" refers to all activities related to eating, including the quality and quantity of food a user consumes on a daily basis, meal frequency, and balanced eating habits.

[1714] "Exercise habits" refers to the pattern of physical exercise and fitness activities that a user regularly engages in, and is an important factor in maintaining and improving health.

[1715] "Smoking and drinking habits" refers to the amount and frequency of smoking that a user does on a daily basis, and the type, amount, and frequency of alcohol that a user drinks.

[1716] A "machine learning algorithm" is a computational method used to learn patterns and rules from data, which can then be used to predict future events and trends.

[1717] "Risk level" is an assessment that classifies a person into low risk, medium risk, or high risk based on the predicted outcome of a disease that may occur in the future.

[1718] "Additional test items" are specific tests or diagnostic procedures suggested to the user based on the risk assessment, and are useful for early detection and follow-up of disease.

[1719] The "report format" refers to a document format that visually summarizes information such as diagnostic results and suggested test items in an easy-to-understand format, and is used to notify users.

[1720] "Latest medical information" refers to the results of medical research and clinical trials, as well as the latest knowledge and data on new treatments and diagnostic techniques.

[1721] "Health risk reassessment" is the process of periodically reassessing a user's health status and risks based on the user's latest data and medical information, and making new predictions and suggestions.

[1722] "Notification" refers to the act of sending messages or alerts to users to inform them of risk assessment results and recommendations.

[1723] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[1724] 1. Data Collection

[1725] User

[1726] Users access a dedicated questionnaire and enter information about their lifestyle, family medical history, diet, exercise habits, smoking and drinking habits, etc. The questionnaire is designed to comprehensively assess the user's health status.

[1727] 2. Data Transmission

[1728] Terminal

[1729] The terminal receives data entered by the user and checks whether the data format is correct. If there are no errors, it formats the data in the specified format and sends it to the server. For example, it validates the input data and sends it to the server as an HTTP request.

[1730] 3. Data storage

[1731] server

[1732] The server receives the data sent from the terminal and stores it in a database. When storing the data, validation is performed to check the completeness and consistency of the data. The received data is temporarily stored in memory, and once the validation is complete, it is stored in the database.

[1733] 4. Data Analysis

[1734] server

[1735] The data stored on the server is passed to an AI model for analysis. Machine learning algorithms (e.g., TensorFlow or Scikit-learn) are used to predict future diseases based on the user's data. The necessary data is extracted from the database and fed into the analysis model using a Python script. The analysis results are temporarily stored on the server.

[1736] 5. Risk Assessment

[1737] server

[1738] The server evaluates the risk level of each disease based on the analysis results. The evaluation is classified into three categories: low risk, medium risk, and high risk, and measures are suggested according to each risk level. The evaluation algorithm categorizes the analysis results and also calculates a confidence score within them. The result is added to the user's profile.

[1739] 6. Inspection Proposal

[1740] server

[1741] Based on the risk assessment, the server recommends additional tests that the user may need. If a high risk is detected, detailed tests (e.g., MRI or CT scan) are recommended, while if a medium risk is detected, blood tests or ultrasound examinations are recommended. The recommendations are generated using templates, and a report is created that includes the appropriate tests and the reasons for them.

[1742] 7. Notifications and Feedback

[1743] server

[1744] The server generates a report containing the risk assessment and recommendations, and notifies the user's device. The report is generated in a visually easy-to-understand format such as PDF. The report is generated using a document template engine (e.g., JasperReports or iText), and is notified to the user's email address or a dedicated app.

[1745] User

[1746] Users can review the report received on their device and consider any suggested tests or preventative measures. They will receive an email or in-app notification with a link they can click to download or view the report.

[1747] 8. Follow-up

[1748] server

[1749] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new recommendations and preventative measures as needed. The server periodically runs the reassessment process using a scheduled task (e.g., cron job or cloud scheduler) and updates the report based on the new data.

[1750] Specific examples

[1751] User A's case

[1752] User A

[1753] User A enters the following information into the questionnaire: "I drink red wine three times a week" and "I have a family history of diabetes."

[1754] Terminal

[1755] The terminal checks the format of this information before sending it to the server.

[1756] server

[1757] The server stores the received data in a database and analyzes it using an AI model, which predicts a moderate risk of diabetes and alcoholic liver disease.

[1758] server

[1759] Based on this, the server suggests to User A that he undergo a blood sugar test and an abdominal ultrasound examination.

[1760] server

[1761] A report including the proposal is sent to User A's terminal.

[1762] User A

[1763] User A checks the report on the terminal and decides whether to undergo the recommended examination.

[1764] The system allows users to identify their health risks early and take appropriate preventative measures, and with medical information regularly updated, the system provides diagnoses and recommendations based on the latest information.

[1765] Example prompt sentence:

[1766] Describe the processing steps and specific behavior of a system that predicts potential future illnesses based on a user's lifestyle and family medical history, performs a risk assessment, and suggests necessary preventative measures or additional testing.

[1767] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1768] Step 1:

[1769] Data collection

[1770] User

[1771] Users access a special questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[1772] Input: The user enters information about lifestyle habits and family medical history into a questionnaire.

[1773] How it works: Using a web browser or mobile application, you enter your answers into each section of the questionnaire and click the "Submit" button.

[1774] Output: Information about lifestyle habits and family medical history entered.

[1775] Step 2:

[1776] Data transmission

[1777] Terminal

[1778] The terminal receives the data entered by the user and checks whether the format of the data is correct. If there are no errors, it formats the data in the specified format and sends it to the server.

[1779] Input: Information about lifestyle habits and family medical history that you enter into your device.

[1780] Operation: The terminal validates the input data and checks whether characters have been entered in fields that should be entered as numbers. The validated data is sent to the server as an HTTP request.

[1781] Output: Formatted lifestyle and family medical history information sent to the server.

[1782] Step 3:

[1783] Data storage

[1784] server

[1785] The server receives the data sent from the terminal and stores it in a database, where it performs validation to check the completeness and consistency of the data.

[1786] Input: Formatted lifestyle and family medical history information sent from your device.

[1787] How it works: The server temporarily stores the received data in memory and validates it against existing rules before storing it in the database. Once validation is complete, it performs an INSERT operation on the database.

[1788] Output: Information about lifestyle habits and family medical history stored in a database.

[1789] Step 4:

[1790] Data analysis

[1791] server

[1792] The data stored on the server is then passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to predict future illnesses based on the user's data.

[1793] Input: Data about the user's lifestyle and family medical history stored in a database.

[1794] How it works: The server extracts the necessary data from the database and feeds the input data into the analytical model using Python scripts. The analytical results are temporarily stored on the server.

[1795] Output: Prediction of future potential illnesses.

[1796] Step 5:

[1797] Risk Assessment

[1798] server

[1799] The server evaluates the risk level of each disease based on the analysis results, categorizing the risk into three categories: low risk, medium risk, and high risk, and suggests countermeasures according to each risk level.

[1800] Input: Predictions of future disease outcomes obtained from a generative AI model.

[1801] How it works: The rating algorithm categorizes the analysis results and also calculates a confidence score within them, which is added to the user profile.

[1802] Output: Assessment results categorized by risk level.

[1803] Step 6:

[1804] Inspection proposal

[1805] server

[1806] Based on the risk assessment, the server recommends additional tests that the user may need: if a high risk is detected, a detailed examination (e.g., MRI or CT scan) is recommended, and if a medium risk is detected, blood tests or ultrasound examinations are recommended.

[1807] Input: Assessment results categorized by risk level.

[1808] How it works: Recommendations are generated using templates, and a report is created with the appropriate tests and their reasons.

[1809] Output: A report with suggested additional tests for the user.

[1810] Step 7:

[1811] Notifications and Feedback

[1812] server

[1813] The server generates a report containing the risk assessment and recommendations, and sends it to the user's device in a visually easy-to-understand format such as PDF.

[1814] Input: Report with additional tests.

[1815] How it works: Reports are generated using a document template engine (e.g. JasperReports or iText) and then notified to the user via email or a dedicated app.

[1816] Output: A report of risk assessment and inspection suggestions that is communicated to the user.

[1817] User

[1818] The user reviews the report received on the device and considers any suggested tests or preventative measures.

[1819] Input: Risk assessment and inspection suggestion report posted to the terminal.

[1820] How it works: Users receive an email or in-app notification with a link they click to download or view the report.

[1821] Output: User action (getting tested, taking preventative measures, etc.).

[1822] Step 8:

[1823] Follow-up

[1824] server

[1825] The server periodically reassess the user's health risk, retrieving the latest medical data and new user data, and notifying the user of new suggestions and preventative measures as needed.

[1826] Input: Latest medical data and new user data.

[1827] How it works: The server periodically runs the re-evaluation process using a scheduled task (e.g. cron job or cloud scheduler) and updates the reports with new data.

[1828] Output: Notification with reassessment results and new suggestions and preventative measures.

[1829] (Application example 1)

[1830] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1831] Existing health risk assessment systems have the problem that users have to enter information about their lifestyle habits and family medical history, which requires a lot of time and effort. Furthermore, risk assessment results and test recommendations are not notified in real time, which hinders users' ability to respond quickly. Furthermore, the low accuracy of analysis and the low reliability of prediction results make effective health management difficult.

[1832] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1833] In this invention, the server includes means for collecting information on lifestyle habits and family medical history from a user, means for predicting future diseases based on the collected information, means for assessing risk levels based on the disease prediction results, means for providing an interface that is easy for users to input via a smart device, and means for analyzing data using a generative AI model and performing risk assessment and recommendations in real time, thereby enabling users to easily input information and receive accurate health risk assessments and appropriate test recommendations in real time.

[1834] "Lifestyle habits" refers to the user's daily activities and habits, specifically behavioral patterns such as eating, drinking, exercise, smoking, and alcohol consumption.

[1835] "Family medical history" refers to the history of illnesses experienced by the user's blood relatives, past or present.

[1836] "Means for collecting information" refers to devices and systems for obtaining data such as lifestyle habits and family medical history from users.

[1837] "Means for predicting diseases that may occur in the future" refers to a device or system that predicts diseases that a user may suffer from in the future based on collected data.

[1838] "Means for assessing risk level" refers to a device or system for classifying the likelihood of developing a predicted disease into categories such as low risk, medium risk, or high risk.

[1839] "Means for suggesting additional examination items" refers to a device or system for recommending further examination or diagnostic items that a user should undergo based on the evaluation results.

[1840] "Means for notifying the proposed contents in the form of a report" refers to a device or system for documenting the evaluation results and proposed inspection items and notifying the user.

[1841] "Smart device" refers to an electronic device with internet connectivity that a user uses to enter information and view results.

[1842] "Interface" refers to operation screens, input forms, dialogue systems, etc. that make it easier for users to input information via smart devices.

[1843] A "generative AI model" refers to an artificial intelligence model that uses machine learning and data analysis techniques to analyze collected data and assess health risks.

[1844] "Real-time means" refers to devices or systems that analyze and evaluate information within an extremely short time from the time it is entered by the user, and immediately notify the results.

[1845] This invention is a system that predicts future illnesses based on information such as lifestyle habits and family medical history, assesses the risk, and suggests necessary preventive measures and additional tests. This system is composed of a server, a terminal, and user interactions.

[1846] 1. Data Collection

[1847] User

[1848] Using a smart device interface, users input information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, etc. This allows detailed data to be collected about individual health risks.

[1849] Terminal

[1850] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[1851] server

[1852] The server stores the data received from the terminal in a database. When storing the data, it performs validation to check the completeness and consistency of the data.

[1853] 2. Data Analysis

[1854] server

[1855] The data stored on the server is passed to a generative AI model for analysis, which uses machine learning algorithms (e.g., deep learning and decision tree models) to predict future illnesses based on the user's lifestyle and family medical history.

[1856] 3. Risk Assessment

[1857] server

[1858] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[1859] 4. Inspection proposal

[1860] server

[1861] Based on the risk assessment, the server suggests additional tests to the user: if the risk is high, more in-depth tests are suggested, and if the risk is medium, simpler tests are recommended.

[1862] 5. Notifications and Feedback

[1863] server

[1864] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the suggested tests.

[1865] User

[1866] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[1867] 6. Follow-up

[1868] server

[1869] The server periodically reassess the user's health risk based on the latest medical information and new user data, and sends the user new suggestions and notifications to take preventative measures as needed.

[1870] Specific examples

[1871] For example, if a 45-year-old male user enters information such as "family history of diabetes," "drinks alcohol 1-2 times a week," and "does moderate exercise" into a medical questionnaire, this data is sent to the server via the smart device. The server analyzes the data using a generative AI model and evaluates the user as being at medium risk for diabetes and alcoholic liver disease. Based on this evaluation, the server recommends a "blood sugar test" and an "abdominal ultrasound test," and notifies the user of the results in the form of a report. This system allows users to understand their health risks early and take appropriate preventive measures.

[1872] Prompt Sentence Examples

[1873] "What are the health risks for a 45-year-old man with a family history of diabetes, who consumes alcohol 1-2 times a week, and engages in moderate exercise?"

[1874] "Please make a list of diseases that the user is at high risk of developing based on their family history and lifestyle habits, and suggest the necessary tests."

[1875] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1876] Step 1:

[1877] User data entry

[1878] Users use the interface of a smart device (e.g., smart glasses) to input information such as lifestyle habits and family medical history. Specifically, they answer a questionnaire in the form of questions, and the data is entered into the terminal.

[1879] Input: Lifestyle and family medical history data (e.g., drinking habits, smoking habits, exercise habits, family history, etc.)

[1880] Output: Formatted user data

[1881] Step 2:

[1882] Data transmission and format check

[1883] The terminal checks the format of the collected data, formats it into the specified format, and then sends it to the server.

[1884] Specifically, it validates whether the data input format is correct and transfers the formatted data to the server.

[1885] Input: Data entered by the user

[1886] Output: Formatted data sent to the server

[1887] Step 3:

[1888] Data Storage and Validation

[1889] The server receives the data sent from the terminal and stores it in a database. When storing the data, it checks its integrity and consistency.

[1890] Specifically, it checks whether the data is accurate and consistent before saving and approves it for writing to the database.

[1891] Input: Formatted data

[1892] Output: Saved user data

[1893] Step 4:

[1894] Disease prediction through data analysis

[1895] The server passes the stored data to a generative AI model to predict future diseases.

[1896] Specifically, data analysis is performed using machine learning algorithms (e.g., deep learning models) to create a list of diseases at risk of developing.

[1897] Input: Saved user data

[1898] Output: Disease prediction results

[1899] Step 5:

[1900] Risk Level Assessment

[1901] Based on the prediction results, the server assesses the risk level of each disease, which is classified as low, medium, or high.

[1902] Specifically, the likelihood of developing each predicted disease is calculated and a risk level is defined.

[1903] Input: Disease prediction results

[1904] Output: Risk level classification results

[1905] Step 6:

[1906] Proposal of test items

[1907] Based on the results of the risk assessment, the server suggests to the user what additional tests are required.

[1908] Specifically, in high-risk cases, detailed examinations (e.g., MRI or CT scans) are recommended, and in medium-risk cases, blood tests and ultrasound examinations are recommended.

[1909] Input: Risk level classification results

[1910] Output: Suggested tests

[1911] Step 7:

[1912] Reporting and Notifications

[1913] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment and the reasons for the recommended tests.

[1914] Specifically, the prediction results and proposals are compiled into a text report and sent to the terminal.

[1915] Input: Proposed test items, risk assessment details

[1916] Output: Report sent to the user

[1917] Step 8:

[1918] User report review and action

[1919] The user reviews the report received on the device and considers any suggested additional tests or preventative measures.

[1920] Specifically, they review the report contents and carry out any tests or preventative measures they deem necessary.

[1921] Input: Report sent to user

[1922] Output: User's health care behavior

[1923] Step 9:

[1924] Regular follow-up

[1925] The server periodically reassess the user's health risks based on the latest medical information and new user data, and notifies them of new suggestions and preventative measures.

[1926] Specifically, the database is updated periodically and the results of the reevaluation are notified to the user.

[1927] Input: Latest medical information, new data from users

[1928] Output: New evaluation results and recommendations

[1929] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1930] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional tests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[1931] 1. Data Collection

[1932] User

[1933] Users access a questionnaire and enter information about their lifestyle, family medical history, diet, exercise, smoking and drinking habits, etc. This allows detailed data to be collected about their individual health risks.

[1934] Terminal

[1935] The user's input data is sent to the server via the terminal, where the terminal checks the format of the input data and sends it to the server in the specified format.

[1936] server

[1937] The server stores the data received from the terminal in a database. When storing the data, it validates the data to ensure its completeness and consistency. The server also adds the data to a queue for analysis.

[1938] 2. Data analysis and risk assessment

[1939] server

[1940] The server then passes the stored data to a machine learning algorithm for analysis. Using machine learning algorithms (e.g., deep learning or decision tree models), the system predicts future diseases based on the user's lifestyle and family medical history. The system then assesses the risk level of each disease based on the prediction results, categorizing it as low, medium, or high risk. The assessment results also include the accuracy and reliability of the diagnosis.

[1941] 3. Emotion Recognition by Emotion Engine

[1942] Emotion Engine

[1943] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[1944] 4. Testing recommendations and mental health assessment

[1945] server

[1946] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest additional tests that the user needs. If the risk is high, more detailed tests (e.g., MRI or CT scan) will be suggested, and if the risk is medium, blood tests or ultrasound scans will be recommended. It will also suggest psychological support and counseling depending on the user's emotional state.

[1947] 5. Notifications and Feedback

[1948] server

[1949] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[1950] User

[1951] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1952] 6. Follow-up

[1953] server

[1954] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[1955] Specific examples

[1956] User B's case

[1957] User B

[1958] User B inputs the following: "I go to the gym three times a week," "I drink beer on weekends," and "My family has a history of myocardial infarction." User B also inputs that he is in a stressful work environment.

[1959] Terminal

[1960] The terminal transmits this information to the server.

[1961] server

[1962] The server stores the received data and analyzes it using an AI model. The analysis results predict a medium risk of heart disease and a low risk of alcohol-related illness. The emotion engine also recognizes that User B has a high stress level.

[1963] server

[1964] Based on this, the server suggests to User B that he undergo an echocardiogram or electrocardiogram, and also suggests counseling to improve his mental health.

[1965] server

[1966] A report including the proposal is sent to User B's device.

[1967] User B

[1968] User B checks the report on the terminal and decides whether to undergo the recommended tests and counseling.

[1969] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[1970] The processing flow will be explained below.

[1971] Step 1:

[1972] Users access a questionnaire and enter information such as lifestyle habits, family medical history, dietary habits, exercise habits, smoking and drinking habits, etc.

[1973] Step 2:

[1974] The terminal checks the format of the entered information and transmits it to the server in the specified format.

[1975] Step 3:

[1976] The server stores the data received from the terminal in a database and performs validation to check the completeness and consistency of the data.

[1977] Step 4:

[1978] The server adds the stored data to a processing queue and triggers an AI model that uses machine learning algorithms.

[1979] Step 5:

[1980] The server uses machine learning algorithms (e.g., deep learning and decision tree models) to analyze the collected data and predict future illnesses based on the user's lifestyle and family medical history.

[1981] Step 6:

[1982] The server evaluates the risk level of each disease based on the prediction results and classifies it as low, medium, or high risk, including the accuracy and reliability of the diagnosis.

[1983] Step 7:

[1984] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state, for example, using the context of text input and facial recognition technology to understand whether the user is stressed, depressed, or in other emotional states.

[1985] Step 8:

[1986] Based on the risk assessment results and the analysis results of the emotion engine, the server will suggest additional examinations to the user, recommending detailed examinations (e.g., MRI or CT scan) for high-risk patients and blood tests or ultrasound scans for medium-risk patients, and will also suggest psychological support or counseling depending on the user's emotional state.

[1987] Step 9:

[1988] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for additional psychological support based on the user's emotional state.

[1989] Step 10:

[1990] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[1991] Step 11:

[1992] The server periodically reassess the user's health risk based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures as needed. It also uses an emotion engine to track changes in the user's mental state and provide ongoing appropriate support.

[1993] Example 2

[1994] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1995] In modern society, the development of lifestyle-related diseases and diseases based on genetic risk is a major issue. While it is important to identify these risks early and take appropriate preventive measures, it is difficult for users to accurately assess these risks themselves. There is also a need for comprehensive health management that takes into account the user's mental health status. The present invention aims to achieve comprehensive health management by assessing the risk of disease based on the user's lifestyle and family medical history, and by analyzing the user's emotional state.

[1996] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting diseases that may occur in the future based on the collected information, means for evaluating the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the evaluation, means for notifying the user of the suggestions in the form of a report, means for analyzing the user's emotional state and evaluating the user's mental health state, and means for suggesting psychological support based on the user's emotional state. This enables the user to manage their health comprehensively, including not only physical health risks but also mental health state.

[1997] "Lifestyle habits" refers to the user's daily actions and habits, and specifically includes patterns of eating, exercise, sleeping, smoking, drinking, and the like.

[1998] "Family medical history" refers to information about the illnesses and medical history of the user's relatives in the past.

[1999] "Means for collecting information" refers to methods and devices for obtaining data from users, and specifically includes web applications and mobile applications.

[2000] "Disease prediction methods" refer to algorithms and models that analyze collected data to predict the likelihood of future disease development.

[2001] "Means for assessing risk level" refers to a method for classifying the predicted probability of developing a disease based on certain criteria and assessing it as low risk, medium risk, or high risk.

[2002] "Means for suggesting additional examination items" refers to a method or device for suggesting detailed health examinations to be recommended to a user based on a risk assessment.

[2003] "Means for notifying the user in the form of a report" refers to methods and techniques for notifying the user of a report summarizing the evaluation results and inspection proposals.

[2004] "Emotional state" refers to the user's current psychological and emotional state, and specifically includes emotions such as stress, anxiety, joy, and sadness.

[2005] "Means for analyzing emotional state" refers to methods or algorithms for determining a user's emotions using text analysis, facial recognition technology, etc.

[2006] "Means for assessing mental health status" refers to a method for measuring and assessing the psychological health of a user based on the analyzed emotional state.

[2007] "Means for suggesting psychological support" refers to methods and techniques for suggesting appropriate counseling, psychotherapy, etc. depending on the user's mental health condition.

[2008] This invention is a system that predicts future illnesses based on information about a user's lifestyle and family medical history, assesses their risk, and suggests necessary preventive measures and additional testing. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides an approach that also takes into account the user's mental health status. The main components of this system are a server, a terminal, an emotion engine, and user interaction.

[2009] 1. Data Collection

[2010] Users access a questionnaire using a dedicated web or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels, which allows detailed data to be collected about individual health risks.

[2011] The terminal checks the format and content of the input information in real time and transmits it to the server in the correct format. The terminal used here is a general computing device such as a smartphone or PC.

[2012] 2. Receipt and storage of data

[2013] The server receives the data sent from the terminal. Upon receiving the data, it validates it to ensure its completeness and consistency, and if there are no problems, it stores it in the database. The stored data is also added to the queue for analysis.

[2014] 3. Perform risk prediction

[2015] The server inputs the user information stored in the database into machine learning algorithms, including deep learning and decision tree models. The algorithms then predict future diseases based on the user's lifestyle and family medical history. The prediction results are categorized into risk levels for each disease (low, medium, or high risk). The risk assessment also includes the accuracy and reliability of the diagnosis.

[2016] 4. Emotion Recognition

[2017] The server uses an emotion engine to analyze the user's input data and reactions, using text analysis and facial recognition technology to identify the user's emotional state, such as stress, anxiety, joy, or sadness.

[2018] 5. Inspection and support proposals

[2019] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations and psychological support that the user may need. For example, an echocardiogram or electrocardiogram may be recommended for a user at high risk of heart disease. Furthermore, if a high stress level is detected, psychological counseling or other support may also be suggested.

[2020] 6. Notification of results and feedback

[2021] The server generates a report containing the diagnosis and recommended tests and sends it to the user's device, including details of the risk assessment, the reasons for the suggested tests, and suggestions for psychological support.

[2022] The user can review the report received on the device and consider any additional testing or preventative measures suggested. The device supports viewing the report and provides information to help the user take necessary actions.

[2023] 7. Ongoing follow-up

[2024] The server periodically reassess health risks based on the latest medical information and new user data, and notifies the user with new suggestions and preventative measures. The emotion engine also continuously monitors the user's mental state and provides appropriate support.

[2025] Specific examples

[2026] User B's case

[2027] User B enters that he "goes to the gym three times a week," "drinks beer on weekends," and "has a family history of myocardial infarction," and further enters that his work environment is very stressful.

[2028] The terminal checks the format of this information and then sends it to the server.

[2029] The server validates the received data and stores it in a database. The machine learning model then analyzes the data to predict medium risk of heart disease and low risk of alcohol-related diseases. The emotion engine also recognizes User B's high stress level.

[2030] Based on the analysis results, the server suggests that User B undergo an echocardiogram or electrocardiogram, and also recommends counseling to improve his or her mental health.

[2031] The server generates a report containing these suggestions and sends it to User B's device.

[2032] User B checks the report on the terminal and decides whether to undergo the proposed examination and counseling.

[2033] This system allows users to comprehensively understand not only their physical health risks but also their mental health status, allowing them to take appropriate preventive measures.

[2034] Example input to a generative AI model

[2035] You can input the generative AI model using prompt sentences like the following:

[2036] "Based on the user's lifestyle habits and family medical history, predict which diseases the user is at high risk for. Recommend any additional tests the user may need and any measures to address the stress the user is experiencing."

[2037] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2038] Step 1:

[2039] Users access a questionnaire using a dedicated web app or mobile app and enter information such as lifestyle habits, family medical history, diet, exercise habits, smoking and drinking habits, and stress levels. The data entered by the user includes data in text format and checkbox format. This allows detailed data on the user's health risks to be collected. The entered information is temporarily stored on the device.

[2040] Input: lifestyle habits, family medical history, dietary habits, exercise habits, smoking, drinking, stress levels

[2041] Output: Temporarily saved data

[2042] Step 2:

[2043] The terminal checks the format and content of the data entered by the user in real time to ensure that it is in the correct format. If the data format is successfully verified, the data that does not need to be modified is encrypted and sent to the server in the specified format. An API call is made on the terminal to send the data.

[2044] Input: Data entered by the user

[2045] Output: Data sent to the server

[2046] Step 3:

[2047] The server receives data sent from the device. The received data undergoes a validation process to check the data's completeness and consistency, and is then stored in a database. The stored data is then added to a queue for analysis, ensuring the data's format and consistency.

[2048] Input: Data sent from the terminal

[2049] Output: Data stored in the database, data queued for analysis

[2050] Step 4:

[2051] The server inputs the user information stored in the database into a machine learning algorithm (e.g., a deep learning model or a decision tree model). Here, the algorithm predicts future diseases based on the user's lifestyle and family medical history. The risk level (low, medium, or high risk) is also assessed, and the accuracy and reliability of the diagnosis are calculated. The output risk assessment results are then stored back in the database.

[2052] Input: User information stored in the database

[2053] Output: Disease prediction results, risk level, diagnostic accuracy and confidence

[2054] Step 5:

[2055] The server uses an emotion engine to analyze the user's input data and reactions. The emotion engine uses text analysis and facial recognition technology to recognize the user's emotional state, such as stress, anxiety, joy, or sadness. The results of this analysis are stored in a database as the user's emotional state.

[2056] Input: User input data, user response data

[2057] Output: Data parsed as emotional states

[2058] Step 6:

[2059] Based on the risk assessment results and the emotion engine's analysis, the server will suggest additional examinations or psychological support to the user. For example, if a user is at high risk of heart disease, an echocardiogram or electrocardiogram will be suggested. If a user shows high stress levels, psychological counseling will be suggested. These suggestions are stored in a database.

[2060] Input: Risk assessment results, emotion engine analysis results

[2061] Output: Suggestions for additional testing items, psychological support

[2062] Step 7:

[2063] The server generates a report containing the diagnosis results and recommended tests, and sends it to the user's device. The report includes details of the risk assessment, the reasons for the proposed tests, and suggestions for psychological support. The report is generated in a dedicated format and sent to the user's device in real time.

[2064] Input: diagnosis results, test item suggestions, psychological support suggestions

[2065] Output: Report sent to user's terminal

[2066] Step 8:

[2067] The user receives a report on their device, which includes details of the risk assessment, reasons for the proposed testing, and suggestions for psychological support, allowing them to make a decision about whether to undergo further testing or take preventative measures.

[2068] Input: Report sent from the server

[2069] Output: User reviews the report and takes necessary action

[2070] Step 9:

[2071] The server periodically reassesses health risks based on the latest medical information and new user data. Based on the risk assessment, new recommendations and preventative measures are generated and notified to the user. Additionally, an emotion engine is used to track changes in mental health status and provide appropriate support.

[2072] Input: Latest medical information, new data from users

[2073] Output: Reassessed health risks, new recommendations and preventative measures

[2074] (Application example 2)

[2075] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2076] In modern society, lifestyle-related diseases and mental stress are on the rise, making it necessary to detect these risks early and take appropriate preventive measures. However, many users lack accurate information about their own health risks and preventive measures, leading to inadequate health management. In addition, there is a problem in that users are not motivated to actively work to maintain their health due to a lack of incentives for health-related expenditures.

[2077] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information on lifestyle habits and family medical history from the user, means for predicting future diseases based on the collected information, means for assessing the risk level based on the disease prediction results, means for suggesting additional test items to the user based on the assessment, means for notifying the user of the suggestions in the form of a report, means for awarding points or cash back for health-related expenditures, and means for suggesting to the user a health support plan customized according to the health risk assessment and mental health state. This allows the user to accurately understand their own health risks and take preventive measures, and encourages them to take a proactive approach to health management through incentives.

[2078] "Information about lifestyle habits and family medical history" refers to detailed data about a user's diet, exercise habits, smoking and drinking habits, sleep patterns, stress levels, as well as family health and medical history.

[2079] "Means for predicting future diseases" refers to technology that uses machine learning algorithms and deep learning models based on collected data to predict diseases that a user may develop in the future.

[2080] "Means for assessing risk level" refers to a technique for classifying the predicted disease risk into low risk, medium risk, or high risk, and for assessing the accuracy of the diagnosis, including the reliability.

[2081] The "means for suggesting additional test items to the user" is a technology for individually suggesting necessary additional tests to the user based on the assessed risk level.

[2082] "Means for notifying the user of the proposal content in report format" refers to a technology for compiling the evaluation results and the inspection proposal content into a report and sending the report to the user's terminal.

[2083] "Means for awarding points or cash back for health-related expenditures" refers to technology that awards points or cash back as an incentive to users for purchasing products or using services related to health maintenance or preventive medicine.

[2084] The "means for proposing a customized health support plan to a user" is a technology for proposing an individually optimized health support plan based on the user's health risk assessment and mental health status.

[2085] A specific embodiment of the present invention will be described. This system supports users in managing their health by evaluating their health risks based on their lifestyle habits and family medical history, and by providing an incentive system for health-related expenditures.

[2086] 1. Data Collection

[2087] User

[2088] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns) and family medical history into the device, as well as their mental health status, such as stress levels.

[2089] Terminal

[2090] The terminal receives the data entered by the user, checks the data format, and then transmits it to the server. This terminal can be a smartphone, tablet, or other device.

[2091] server

[2092] The server stores all received data in a database, where it is validated to ensure data integrity and consistency.

[2093] 2. Health Risk Assessment

[2094] server

[2095] The server uses the data stored in the database to predict the user's future potential illnesses based on prediction results obtained using machine learning algorithms (e.g., deep learning models and decision tree models), and also evaluates the risk level (low risk, medium risk, high risk) and considers the reliability of the prediction.

[2096] 3. Mental Health Assessment

[2097] Emotion Engine

[2098] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., increased stress, depression, etc.), which is also sent to the server and used for a comprehensive health risk assessment.

[2099] 4. Inspection proposals and incentives

[2100] server

[2101] Based on the risk assessment and the analysis results of the emotion engine, the server will individually suggest to the user the additional tests that may be required (e.g., MRI, CT scan, blood test, etc.) and also provide a means to reward points and cashback for health-related expenditures.

[2102] 5. Notifications and Reports

[2103] server

[2104] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[2105] User

[2106] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[2107] 6. Follow-up

[2108] server

[2109] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[2110] Specific examples

[2111] User A's case

[2112] User A

[2113] User A enters the following information: "I run every morning," "I drink two cups of green tea a day," "I have a family history of diabetes," and "I feel stressed at work." Based on this, the system determines that User A is at medium risk for diabetes and recognizes that his stress level is high.

[2114] server

[2115] Based on this, the server will suggest a blood glucose test and a stress management program to User A, and will also give points towards the monthly fitness club membership fee.

[2116] Prompt Sentence Examples

[2117] Evaluate the health risks of a user who has entered information such as "running every morning," "two cups of green tea a day," "having a family history of diabetes," and "feeling stressed at work," and suggest the necessary tests and support. Furthermore, calculate cashback on fitness club membership fees.

[2118] This system allows users to clearly understand their health risks, take appropriate preventive measures, and receive incentives for health-related spending.

[2119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2120] Step 1:

[2121] User

[2122] Users input information about their lifestyle habits (e.g., diet, exercise, smoking and drinking habits, sleep patterns), family medical history, and mental health status (e.g., stress level) into the device. The input data includes specific items such as "I run every morning" and "I drink beer on weekends."

[2123] Input: lifestyle information, family medical history information, mental health status data

[2124] Output: Formatted user data

[2125] Step 2:

[2126] Terminal

[2127] The terminal receives the data entered by the user, checks the data format, and then sends it to the server in the specified format. The data format check checks for missing values ​​and the consistency of the input format.

[2128] Input: formatted user data

[2129] Output: User data with integrity checked

[2130] Step 3:

[2131] server

[2132] The server saves the data sent from the terminal in a database. Validation is performed when saving the data to ensure the data's completeness and consistency. Data is stored separately for each user in the database.

[2133] Input: User data with integrity checked

[2134] Output: User data stored in the database

[2135] Step 4:

[2136] server

[2137] The server uses the data stored in the database to apply machine learning algorithms (e.g., deep learning models or decision tree models) to predict the user's future potential illnesses. Based on the prediction results, the server evaluates the risk level (low risk, medium risk, or high risk) and calculates the reliability.

[2138] Input: User data stored in the database

[2139] Output: Predicted disease risk level and confidence level

[2140] Step 5:

[2141] Emotion Engine

[2142] The emotion engine analyzes the user's input data and reactions to recognize the user's emotional state (e.g., stress, depression, etc.) using facial recognition and text analysis techniques.

[2143] Input: User emotion data

[2144] Output: Parsed emotional state

[2145] Step 6:

[2146] server

[2147] Based on the risk assessment and the analysis results of the emotion engine, the server will suggest to the user which additional tests (e.g., MRI, CT scan, blood test, etc.) are required, and also provide a means to reward points and cashback for health-related expenditures.

[2148] Input: Risk assessment results, analyzed emotional state

[2149] Output: Proposal for additional tests and incentives

[2150] Step 7:

[2151] server

[2152] The server then compiles the diagnostic results and recommendations into a report and sends it to the user's device, which includes details of the risk assessment, the reasons for the proposed tests, and suggestions for additional psychological support based on the user's emotional state.

[2153] Input: Proposal for additional tests and incentives

[2154] Output: Report format of diagnostic results and recommendations

[2155] Step 8:

[2156] User

[2157] Users can review the report on their device, consider and implement any additional tests or preventative measures suggested, as well as any incentives offered. The device also maintains a transaction history of users, recording points and cashback for health-related expenditures.

[2158] Input: Report format diagnostic results and recommendations

[2159] Output: Any additional checks or precautions taken, transaction history

[2160] Step 9:

[2161] server

[2162] The server periodically reassess the user's health risk based on the latest medical information and new user data, notifying them of new suggestions and preventative measures as appropriate, and uses an emotion engine to track changes in the user's mental state and provide ongoing support.

[2163] Input: Latest medical information, new data from users

[2164] Output: Reassessed health risks and new proposed notices

[2165] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2166] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2167] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2168] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2169] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions close...

Claims

1. a means for collecting information from the user regarding lifestyle habits and family medical history; A means for predicting a disease that may occur in the future based on the collected information; A means for assessing a risk level based on the disease prediction result; means for suggesting additional test items to a user based on the evaluation; The system includes a means for notifying the user of the proposed content in the form of a report.

2. 2. The system according to claim 1, further comprising means for allowing the user to check the notified report on a terminal.

3. The system of claim 1 , further comprising means for periodically reassessing the user's health risks based on the latest medical information and notifying the user of new suggestions and preventative measures.

Images