Personalized digital health suggestion method based on digital twinning and generative AI

Abstract

The invention discloses a personalized digital health suggestion method based on digital twinning and generative AI, and relates to the technical field of digital health. The method comprises the following steps: collecting state data of a user through a multi-source data collection channel, carrying out preprocessing including cleaning, denoising and standardization on the collected multi-dimensional data, and constructing a personalized digital twinborn model for reflecting the physiological structure, function and health state of the user by utilizing the collected multi-dimensional state data. Based on the current health state of the user, the health risk of the user is comprehensively evaluated by utilizing a generative AI model, the health risk possibly faced by the user is identified by comparing industry standards, medical research results and big data analysis, and the health risk of the user is evaluated according to the health state of the user and a risk evaluation result in combination with professional medical knowledge and latest research results. And generating personalized health suggestions covering one or a combination of more of diet adjustment, exercise plans, psychological adjustment, drug therapy and periodic physical examination.

Description

Technical Field

[0001] The present invention relates to the field of digital health technologies, and in particular to a personalized digital health recommendation method based on digital twins and generative AI. Background Art

[0002] With rising health awareness and the rapid development of medical technology, personalized health management has become an important means of improving public health. In recent years, digital twin technology and generative AI have been widely applied in various fields, bringing new opportunities for personalized health management.

[0003] Digital twin technology dynamically simulates and optimizes physical entities by creating virtual digital models of them and using real-time data to drive model updates. In healthcare, digital twin technology can be used to build digital twin models of patients, which comprehensively reflect multi-dimensional information such as their physiological status, medical history, and lifestyle habits, providing strong support for precision medicine and personalized health management. Generative AI technology has powerful data processing and content generation capabilities, and can generate text, images, and other content that meets specific needs based on input data. In the health field, generative AI can generate personalized health recommendations based on patients' health data, providing users with more accurate and scientific health guidance.

[0004] However, current personalized health management approaches still have some shortcomings. Traditional health recommendations are often based on universal health guidelines, lacking sufficient consideration for individual differences and failing to meet the personalized needs of different users. Furthermore, existing health management methods have limitations in integrating multi-source health data, monitoring user health status in real time, and dynamically adjusting health recommendations. To address this, we propose a personalized digital health recommendation approach based on digital twins and generative AI. Summary of the Invention

[0005] The main purpose of the present invention is to provide a personalized digital health advice method based on digital twins and generative AI, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above purpose, the technical solution adopted by the present invention is: A personalized digital health recommendation approach based on digital twins and generative AI, including: Step 1: Collect user status data through multi-source data collection channels, where the collection channels include health monitoring devices, mobile apps, and electronic medical records. The status data includes physiological indicator data, lifestyle data, and genetic information data. The collected multi-dimensional data is pre-processed by cleaning, denoising, and standardization to remove invalid and erroneous data, and converted to a unified format and standard. Step 2: Using the collected multi-dimensional status data, construct a personalized digital twin model that reflects the user's physiological structure, function, and health status, wherein the personalized digital twin model is dynamically updated according to the user's status data collected in real time; Step 3: Based on the user's current health status, a generative AI model is used to conduct a comprehensive assessment of the user's health risks. By comparing industry standards, medical research results, and big data analysis, the user's potential health risks are identified. Step 4: Based on the user's health status and risk assessment results, combined with professional medical knowledge and the latest research results, generate personalized health recommendations covering one or more combinations of diet adjustments, exercise plans, psychological adjustments, drug treatments and regular physical examinations.

[0007] Furthermore, the method further comprises: Step 5: The generative AI model receives feedback information in real time after the user adopts the personalized health advice. The feedback information includes the user's execution status and changes in health status, and dynamically adjusts the formulated personalized health advice based on the feedback information obtained.

[0008] Furthermore, the method further comprises: Step 6: Dynamically update the status data according to the changes in the user's health status, and synchronously feed it back to the personalized digital twin model. Adjust the personalized digital twin model parameters based on the feedback information to optimize the model's evaluation performance of the user's physiological structure, function and health status.

[0009] Furthermore, in step five, the specific process of dynamically adjusting the personalized health recommendations based on the obtained feedback information includes the following steps: Obtaining personalized health advice information for the user, including a first personalized health advice, a second personalized health advice, ..., an nth personalized health advice; Classify the execution status of the i-th personalized health advice into two categories: executed and not executed, and obtain the user's execution status of all personalized health advice, where i=1,...,n; Classify the changes in health risks into three categories: increased health risks, unchanged health risks, and decreased health risks, and determine the changes in the user's health risks based on the feedback information obtained; Classify the personalized health advice based on the implementation status of the obtained personalized health advice and the change in health risks, wherein the types of personalized health advice include type 1 advice that is implemented and the health risk is reduced, type 2 advice that is implemented and the health risk is increased or remains unchanged, type 3 advice that is not implemented and the health risk is reduced, and type 4 advice that is not implemented and the health risk is increased or remains unchanged; According to the classification results of personalized health recommendations, they are adjusted to generate recommended adjustment strategies.

[0010] Furthermore, the specific content of the adjustment strategy is: For recommendations that have been implemented and have reduced health risks, the adjustment strategy is to continue to retain and strengthen their specific content while further optimizing the details of the content; For Category II recommendations that have been implemented and where health risks have increased or remained unchanged, the adjustment strategy is: reassess the scientific nature and feasibility of the recommendations and adjust the recommendations; For the three types of recommendations that were not implemented and whose health risks were reduced, the adjustment strategy was: analyze the reasons why users did not implement them and adjust the wording of the recommendation content and implementation steps; For the four types of recommendations that were not implemented and whose health risks increased or remained unchanged, the adjustment strategy was to change the content of the recommendations or add incentives to increase users' willingness to implement them.

[0011] Furthermore, in step three, the specific assessment process of the health risks that users may face includes the following steps: Determine the target disease that the user needs to evaluate, obtain the status data of patients with the target disease, and extract risk characteristics related to the target disease from the massive status data of patients with the target disease through data mining technology; Constructing a risk assessment model for the target disease, using the acquired risk characteristic data as input data for the risk assessment model, and training the model until its prediction accuracy meets a set expected value, thereby obtaining a trained risk assessment model; The user's status data is input into the trained risk assessment model, and the acquired risk assessment model is used to assess the user's health risk for the target disease.

[0012] Furthermore, the risk characteristics include uncontrollable factor characteristics, controllable factor characteristics, environmental factor characteristics, medical history characteristics and socioeconomic factors; wherein, The uncontrollable factor characteristics include at least one of age, gender, family medical history and genes; The controllable factor characteristics include at least one of lifestyle habits, physiological indicators, sleep and psychological factors; The environmental factor characteristics include at least one of occupational exposure and environmental pollution; The medical history characteristics include at least one of previous illness and medication use; The socioeconomic factor includes at least one of education level and income level.

[0013] The present invention has the following beneficial effects: Compared with the existing technology, the user's status data is collected through multi-source data collection channels, and the collected multi-dimensional data is preprocessed including cleaning, denoising and standardization. The collected multi-dimensional status data is used to construct a personalized digital twin model reflecting the user's physiological structure, function and health status. Based on the user's current health status, a generative AI model is used to comprehensively assess the user's health risks. By comparing industry standards, medical research results and big data analysis, the health risks that the user may face are identified. According to the user's health status and risk assessment results, combined with professional medical knowledge and the latest research results, personalized health recommendations covering one or more combinations of diet adjustments, exercise plans, psychological adjustments, drug treatments and regular physical examinations are generated. It can integrate multi-source health data and, based on full consideration of individual differences, formulate health recommendations that meet the personalized needs of different users, so as to achieve real-time monitoring and dynamic adjustment of the user's health status. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of the personalized digital health recommendation method based on digital twins and generative AI of the present invention. DETAILED DESCRIPTION

[0015] The present invention will be further described below in conjunction with specific embodiments. The accompanying drawings are for illustrative purposes only and represent only schematic diagrams rather than actual drawings. They should not be understood as limiting the present invention. In order to better illustrate the specific embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0016] The specific implementation process of the technical solution of the present invention includes the following steps: Step 1: Collect user status data through multi-source data collection channels, pre-process the collected multi-dimensional data including cleaning, denoising and standardization, remove invalid and erroneous data, and convert it into a unified format and standard.

[0017] Among them, collection channels include health monitoring devices, mobile apps, and electronic medical records, such as wearable devices and home medical devices; Status data includes physiological indicator data (such as heart rate, blood pressure, blood sugar, etc.), lifestyle habit data (such as diet, exercise, sleep, etc.) and genetic information data.

[0018] Step 2: Use the collected multi-dimensional status data to build a personalized digital twin model that reflects the user's physiological structure, function, and health status. The personalized digital twin model is dynamically updated based on the user's status data collected in real time.

[0019] Step 3: Based on the user's current health status, use the generative AI model to comprehensively assess the user's health risks. By comparing industry standards, medical research results and big data analysis, identify the health risks the user may face.

[0020] The specific assessment process for health risks that users may face includes the following steps: Determine the target disease that the user needs to evaluate, obtain the status data of patients with the target disease, and use data mining technology to extract risk features related to the target disease from the massive status data of patients with the target disease. Use feature selection algorithms (such as principal component analysis (PCA)) to reduce data dimensions and improve model processing efficiency. Build a risk assessment model for the target disease. The risk assessment model can be selected from the following options: Machine learning model: Select an appropriate machine learning algorithm based on the specific application scenario, such as logistic regression, decision tree, random forest, support vector machine (SVM), etc. Deep learning model: For complex data patterns, deep learning models such as convolutional neural network (CNN) and recurrent neural network (RNN) can be used. The acquired risk feature data is used as the input data of the risk assessment model. When it is trained until its prediction accuracy meets the set expected value, a trained risk assessment model is obtained. The specific training process is as follows: a. Dataset division: the data set is divided into a training set and a test set, usually in an 8:2 or 7:3 ratio; b. Model training: the selected model is trained using the training set to optimize the model parameters; c. Model validation: the model performance is evaluated through the test set. Common evaluation indicators include accuracy, recall rate, precision, F1 value and AUC value.

[0021] Input the user's status data into the trained risk assessment model, and use the acquired risk assessment model to assess the user's health risk for the target disease. Specifically, the following steps can be taken: Data collection and integration Electronic health record (EHR) analysis: Utilizes detailed information in electronic health records, including medical history, diagnosis, treatment process, medication use, etc., to identify potential health risks through big data analysis technology.

[0022] Wearable device data: Analyzing data from wearable devices, such as activity levels, sleep patterns, heart rate, etc., can help identify chronic disease risks or early signs of illness.

[0023] Genomic data: By analyzing genomic data, we can identify genetically related disease risks, such as certain cancers and cardiovascular diseases.

[0024] Industry standard comparison Clinical Guidelines and Standards: Compare your health data to industry standards and clinical guidelines. For example, use standards published by organizations such as the World Health Organization (WHO) or the American Heart Association (AHA) to assess your cardiovascular disease risk.

[0025] Risk Assessment Model: Apply validated risk assessment models, such as the Framingham Cardiovascular Risk Score, to quantify a user's risk of cardiovascular disease.

[0026] Application of medical research results Latest research results: Refer to the latest medical research results, such as those on diabetes complication prediction and mental health intervention, to identify specific health risks that users may face.

[0027] Clinical trial data: Use clinical trial data to assess a user's response to a specific drug or treatment regimen, thereby predicting potential health risks.

[0028] Big Data Analysis Predictive analytics: Using big data analytics techniques, such as machine learning and data mining, to identify patterns and trends from large amounts of patient data and predict the health risks a user may face.

[0029] Real-time monitoring and early warning: Utilize real-time big data analysis to continuously monitor users’ health status, detect abnormal situations in a timely manner and issue early warnings.

[0030] Comprehensive assessment and personalized recommendations Multi-dimensional assessment: Combining the analysis results of the above methods, a comprehensive assessment of the user's health risks is conducted to identify high-risk areas.

[0031] Personalized recommendations: Based on the assessment results, users are provided with personalized health recommendations, including lifestyle adjustments, drug treatment, psychological intervention, etc., to reduce health risks.

[0032] Through the above methods, we can more accurately identify the health risks that users may face and provide them with targeted health management recommendations.

[0033] It should be noted that the characteristics related to health risks can be classified and identified from multiple dimensions, mainly including characteristics of uncontrollable factors, controllable factors, environmental factors, medical history characteristics and socioeconomic factors. The following are specific descriptions of risk characteristics: Characteristics of uncontrollable factors Age: Age is a significant risk factor for many diseases. For example, the risk of cardiovascular disease, cancer, and diabetes generally increases with age.

[0034] Gender: Certain diseases are more common in certain sexes. For example, women are more likely to develop breast cancer, and men are more likely to develop prostate cancer.

[0035] Family history: Having certain diseases in your family can increase your risk of developing the same disease. For example, having cardiovascular disease or diabetes in your family can increase your risk.

[0036] Genes: Certain gene mutations or inherited traits can increase the risk of specific diseases. For example, mutations in the BRCA genes are associated with an increased risk of breast and ovarian cancer.

[0037] Controllable factor characteristics Lifestyle, specifically: Diet: Unhealthy eating habits, such as a diet high in sugar, salt, and fat, increase the risk of obesity, cardiovascular disease, and diabetes.

[0038] Exercise: Physical inactivity is a risk factor for several chronic diseases. Regular aerobic exercise and strength training can reduce the risk of cardiovascular disease, diabetes, and certain cancers.

[0039] Sleep: Insufficient sleep or poor sleep quality can affect mental health and physiological function, and increase the risk of cardiovascular disease, diabetes and obesity.

[0040] Smoking and drinking: Smoking is a major risk factor for several cancers, cardiovascular disease, and respiratory diseases. Excessive alcohol consumption also increases the risk of liver disease, cardiovascular disease, and certain cancers.

[0041] Physiological indicators may include: Blood pressure: High blood pressure is a significant risk factor for cardiovascular disease and stroke.

[0042] Blood sugar: High blood sugar is the main risk factor for diabetes. Long-term high blood sugar also increases the risk of cardiovascular disease and kidney disease.

[0043] Blood lipids: High cholesterol and high triglyceride levels increase the risk of cardiovascular disease.

[0044] Body mass index (BMI): Obesity is a risk factor for several chronic diseases, including cardiovascular disease, diabetes, and certain cancers.

[0045] Psychological factors can include: Psychological stress: Long-term psychological stress can affect mental health and increase the risk of cardiovascular disease, diabetes and certain mental illnesses.

[0046] Emotional states: Emotional issues such as depression and anxiety can affect lifestyle and health behaviors, increasing the risk of chronic diseases.

[0047] Environmental factors characteristics Occupational exposure: Long-term exposure to hazardous chemicals or dust in occupational environments increases the risk of certain diseases, such as occupational cancer.

[0048] Environmental pollution: Environmental factors such as air pollution, water pollution and soil pollution can affect health and increase the risk of cardiovascular disease, respiratory diseases and certain cancers.

[0049] Medical history characteristics Pre-existing medical conditions: Having certain medical conditions before increases the risk of complications or recurrence. For example, people with a history of cardiovascular disease are at higher risk of developing another condition.

[0050] Drug use: Long-term use of certain drugs may increase the risk of certain diseases. For example, long-term use of glucocorticoids increases the risk of osteoporosis and diabetes.

[0051] Socioeconomic characteristics Education level: Lower education levels may be associated with unhealthy lifestyles and poorer health.

[0052] Income level: Lower income levels may limit access to health resources and increase the risk of chronic diseases.

[0053] By comprehensively considering these characteristics, it is possible to more comprehensively identify the health risks that users may face and develop personalized health management plans.

[0054] Step 4: Based on the user's health status and risk assessment results, combined with professional medical knowledge and the latest research results, generate personalized health recommendations covering one or more combinations of diet adjustments, exercise plans, psychological adjustments, drug treatments and regular physical examinations.

[0055] Among them, personalized health recommendations can be: Dietary adjustment suggestions Personalized diet plans: Develop personalized diet plans based on the user's health status and risk assessment results, combined with nutritional research. For example, a low-sugar, high-fiber diet is recommended for users at risk of diabetes; for obese users, calorie control and increased intake of vegetables and whole grains are recommended.

[0056] Precision Nutrition Support: Drawing on the latest research, such as the National Institutes of Health's Precision Nutrition for Health program, uses machine learning and statistical models to identify the personal characteristics most relevant to dietary choices and predict which foods and eating patterns are most beneficial for individuals.

[0057] Exercise plan recommendations Exercise goal setting: Set specific exercise goals based on the user's health status and lifestyle habits. For example, it is recommended to perform aerobic exercise at least three times a week, each lasting more than 30 minutes, to improve cardiopulmonary function.

[0058] Personalized exercise plan: Based on the user's interests and physical conditions, it recommends suitable exercise types, such as swimming, yoga, running, etc., and provides suggestions on exercise intensity and frequency.

[0059] Psychological adjustment suggestions Psychological state assessment: Assess the user's psychological state through psychological tests and questionnaires to identify potential psychological stress and emotional problems.

[0060] Psychological adjustment strategies: Provide targeted psychological adjustment suggestions, such as stress management techniques, emotion regulation methods, relaxation training, etc., to help users maintain a good mental state.

[0061] Drug treatment recommendations Medication treatment plans: Based on the user's health status and risk assessment results and the latest medical research results, personalized medication treatment plans are provided for users who require medication intervention. For example, for patients with high cholesterol, new PCSK9 inhibitors such as ricasimab are recommended due to their long half-life and good compliance.

[0062] Drug use instructions: Provide detailed instructions for drug use, including dosage, medication time, precautions, etc., to ensure that users use the drugs correctly.

[0063] Regular medical checkup plan recommendations Customized physical examination items: We can customize personalized physical examination items based on the user's health status and risk assessment results. For example, for women at risk of breast cancer, we recommend personalized screening based on their risk.

[0064] Physical examination frequency recommendations: Based on the user's specific situation, appropriate physical examination frequency is recommended to ensure that potential health problems are discovered in a timely manner.

[0065] Step 5: The generative AI model receives feedback in real time after the user adopts personalized health advice. The feedback information includes the user's execution status and changes in health status. The personalized health advice is dynamically adjusted based on the feedback information obtained.

[0066] The specific process of dynamically adjusting and formulating personalized health recommendations based on the feedback information obtained includes the following steps: Obtaining personalized health advice information for the user, including a first personalized health advice, a second personalized health advice, ..., an nth personalized health advice; Classify the execution status of the i-th personalized health advice into two categories: executed and not executed, and obtain the user's execution status of all personalized health advice, where i=1,...,n; Classify the changes in health risks into three categories: increased health risks, unchanged health risks, and decreased health risks, and determine the changes in the user's health risks based on the feedback information obtained; Classify the personalized health advice based on the implementation of the obtained personalized health advice and the changes in health risks, where the types of personalized health advice include type 1 advice that is implemented and the health risk is reduced, type 2 advice that is implemented and the health risk is increased or remains unchanged, type 3 advice that is not implemented and the health risk is reduced, and type 4 advice that is not implemented and the health risk is increased or remains unchanged; Based on the classification results of personalized health recommendations, adjustments are made to generate recommended adjustment strategies. The specific contents are as follows: For recommendations that have been implemented and have reduced health risks, the adjustment strategy is to continue to retain and strengthen their specific content, while further optimizing the details of the content to improve user compliance and effectiveness; For Category II recommendations that have been implemented and where health risks have increased or remained unchanged, the adjustment strategy is: re-evaluate the scientific nature and feasibility of the recommendations and adjust the recommendations based on the latest medical research and expert opinions; For the three types of suggestions that were not implemented and whose health risks were reduced, the adjustment strategy was as follows: Analyze the reasons why users did not implement them (such as excessive difficulty, lack of motivation, etc.), and adjust the wording of the suggestions and implementation steps to make them easier to understand and implement; For the four types of recommendations that were not implemented and whose health risks increased or remained unchanged, the adjustment strategy was to change the content of the recommendations or add incentives to increase users' willingness to implement them.

[0067] Step 6: Dynamically update the status data according to the changes in the user's health status and synchronously feed it back to the personalized digital twin model. Adjust the personalized digital twin model parameters based on the feedback information to optimize the model's assessment performance of the user's physiological structure, function, and health status.

[0068] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A personalized digital health recommendation method based on digital twins and generative AI, characterized by: include: Step 1: Collect user status data through multi-source data collection channels, where the collection channels include health monitoring devices, mobile apps, and electronic medical records. The status data includes physiological indicator data, lifestyle data, and genetic information data. The collected multi-dimensional data is pre-processed by cleaning, denoising, and standardization to remove invalid and erroneous data, and converted to a unified format and standard. Step 2: Using the collected multi-dimensional status data, construct a personalized digital twin model that reflects the user's physiological structure, function, and health status, wherein the personalized digital twin model is dynamically updated according to the user's status data collected in real time; Step 3: Based on the user's current health status, a generative AI model is used to conduct a comprehensive assessment of the user's health risks. By comparing industry standards, medical research results, and big data analysis, the user's potential health risks are identified. Step 4: Based on the user's health status and risk assessment results, combined with professional medical knowledge and the latest research results, generate personalized health recommendations covering one or more combinations of diet adjustments, exercise plans, psychological adjustments, drug treatments and regular physical examinations.

2. The personalized digital health advice method based on digital twins and generative AI according to claim 1, characterized in that The method further comprises: Step 5: The generative AI model receives feedback information in real time after the user adopts the personalized health advice. The feedback information includes the user's execution status and changes in health status, and dynamically adjusts the formulated personalized health advice based on the feedback information obtained.

3. The personalized digital health advice method based on digital twins and generative AI according to claim 2, characterized in that The method further comprises: Step 6: Dynamically update the status data according to the changes in the user's health status, and synchronously feed it back to the personalized digital twin model. Adjust the personalized digital twin model parameters based on the feedback information to optimize the model's evaluation performance of the user's physiological structure, function and health status.

4. The personalized digital health advice method based on digital twins and generative AI according to claim 2, characterized in that In step five, the specific process of dynamically adjusting the personalized health recommendations based on the feedback information obtained includes the following steps: Obtaining personalized health advice information for the user, including a first personalized health advice, a second personalized health advice, ..., an nth personalized health advice; Classify the execution status of the i-th personalized health advice into two categories: executed and not executed, and obtain the user's execution status of all personalized health advice, where i=1,...,n; Classify the changes in health risks into three categories: increased health risks, unchanged health risks, and decreased health risks, and determine the changes in the user's health risks based on the feedback information obtained; Classify the personalized health advice based on the implementation status of the obtained personalized health advice and the change in health risks, wherein the types of personalized health advice include type 1 advice that is implemented and the health risk is reduced, type 2 advice that is implemented and the health risk is increased or remains unchanged, type 3 advice that is not implemented and the health risk is reduced, and type 4 advice that is not implemented and the health risk is increased or remains unchanged; According to the classification results of personalized health recommendations, they are adjusted to generate recommended adjustment strategies.

5. The personalized digital health advice method based on digital twins and generative AI according to claim 4, characterized in that The specific content of the adjustment strategy is: For recommendations that have been implemented and have reduced health risks, the adjustment strategy is to continue to retain and strengthen their specific content while further optimizing the details of the content; For Category II recommendations that have been implemented and where health risks have increased or remained unchanged, the adjustment strategy is: reassess the scientific nature and feasibility of the recommendations and adjust the recommendations; For the three types of recommendations that were not implemented and whose health risks were reduced, the adjustment strategy was: analyze the reasons why users did not implement them and adjust the wording of the recommendation content and implementation steps; For the four types of recommendations that were not implemented and whose health risks increased or remained unchanged, the adjustment strategy was to change the content of the recommendations or add incentives to increase users' willingness to implement them.

6. The personalized digital health advice method based on digital twins and generative AI according to claim 1, characterized in that In step three, the specific assessment process of the health risks that users may face includes the following steps: Determine the target disease that the user needs to evaluate, obtain the status data of patients with the target disease, and extract risk characteristics related to the target disease from the massive status data of patients with the target disease through data mining technology; Constructing a risk assessment model for the target disease, using the acquired risk characteristic data as input data for the risk assessment model, and training the model until its prediction accuracy meets a set expected value, thereby obtaining a trained risk assessment model; The user's status data is input into the trained risk assessment model, and the acquired risk assessment model is used to assess the user's health risk for the target disease.

7. The personalized digital health advice method based on digital twins and generative AI according to claim 6, characterized in that The risk characteristics include uncontrollable factor characteristics, controllable factor characteristics, environmental factor characteristics, medical history characteristics and socioeconomic factors; among them, The uncontrollable factor characteristics include at least one of age, gender, family medical history and genes; The controllable factor characteristics include at least one of lifestyle habits, physiological indicators, sleep and psychological factors; The environmental factor characteristics include at least one of occupational exposure and environmental pollution; The medical history characteristics include at least one of previous illness and medication use; The socioeconomic factor includes at least one of education level and income level.

Images