A method, apparatus, device, and medium for constructing user health profiles.

Abstract

This application discloses a method, apparatus, device, and medium for constructing a user health profile. In the method, user data is first collected and preprocessed to obtain user indicator data; based on the user indicator data and disease risk level rules, a user disease risk level label is obtained; the user indicator data is input into a data trend prediction model to predict the trend of the user's indicator data; the user indicator data is then input into a disease risk prediction model to predict the user's disease risk; finally, the user's disease risk level label, the user's health indicator trend, and the disease risk are combined to construct a user health profile. In this process, by collecting and comprehensively analyzing user health data from multiple perspectives, a large-scale model is accurately used to assess the user's health status and predict disease risk, thus constructing a user health profile with multi-information capabilities.

Description

Technical Field

[0001] This application relates to the field of medical and health management technology, and in particular to a method, apparatus, device and medium for constructing a user health profile. Background Technology

[0002] With the development of medical informatization, personal medical and health data is growing exponentially. The accumulation of data such as electronic medical records, medical records and physical examination reports provides a wealth of information sources for personal health management.

[0003] Therefore, user health profiles can be built based on various data information to more intuitively understand the health status of different individual users and meet the needs of personalized health management.

[0004] Current methods for constructing user health profiles focus on the analysis of single health indicators, resulting in incomplete profiles, insufficient personalization, and a lack of comprehensive evaluation models. This prevents the dynamic prediction of future health trends and thus fails to meet the needs of personalized health management. Therefore, this application proposes a method to address these issues. Summary of the Invention

[0005] This application provides a method, apparatus, device, and medium for constructing a user health profile. By collecting user data from multiple aspects and analyzing and evaluating the user data to predict the user's future health trends, a user health profile with multiple information is constructed.

[0006] Firstly, this application provides a method for constructing a user health profile, the method comprising:

[0007] User data is collected and preprocessed to obtain user indicator data. The user data includes basic user information and behavioral information. The basic information is user identity and health status data, and the behavioral information is activity or behavior data related to the user's health status.

[0008] Based on user indicator data and disease risk level rules, obtain the user's disease risk level label;

[0009] User indicator data is input into a data trend prediction model to predict the trend of user indicator data. The indicator data prediction model is a trained neural network model, and the training data of the indicator data prediction model is historical indicator data and the trend of the historical indicator data over time.

[0010] User indicator data is input into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores.

[0011] By combining user disease risk level tags, user health indicator trends, and disease risk, a user health profile can be constructed.

[0012] Optionally, user data is preprocessed to obtain user metric data, including:

[0013] Multimodal data processing is performed on user data to extract key information;

[0014] Based on the defined indicators, feature extraction is performed on key information to extract basic user indicators from user data. The defined indicators include basic user indicators, basic health indicators, and extended health indicators.

[0015] Data cleaning and standardization are performed on the user basic metrics data to obtain user metric data.

[0016] Optionally, based on user indicator data and disease risk level rules, a user's disease risk level label is obtained, including:

[0017] Based on user indicator data and health topic rules, the user's disease topic is determined. The health topic rules are rules for evaluating various diseases using indicator data.

[0018] By substituting user indicator data into the disease risk level rules of the disease topic, a user's disease risk level label is obtained. The disease risk level rules are rules for evaluating the level of various diseases based on indicator data.

[0019] Optionally, the training process of the data trend prediction model includes:

[0020] Obtain users' historical metrics data and the trends of historical metrics data over time;

[0021] Historical indicator data and the trend of historical indicator data over time are used as training samples to input into the initial trend model for training until the initial trend model reaches the target value, thus obtaining the data trend prediction model.

[0022] Optionally, the training process for the disease risk prediction model includes:

[0023] Obtain users' historical metric data and historical disease risk scores;

[0024] Historical indicator data and historical disease risk scores are used as training samples to input into the initial risk model for training until the initial risk model reaches the target value, thus obtaining a disease risk prediction model.

[0025] Optionally, the method further includes:

[0026] Based on the user's disease risk level label, a large model is used to obtain health and lifestyle guidance suggestions corresponding to the disease risk level label.

[0027] Optionally, the method further includes:

[0028] Users can set their health control goals using parameters;

[0029] Based on the health control objectives, improvement suggestions for the user are determined from the set of improvement suggestions, wherein the set of improvement suggestions corresponds to the health control objectives;

[0030] Based on users' improvement suggestions, a multi-faceted guidance and suggestion plan is generated, including guidance and suggestion plans on lifestyle, dietary structure, and exercise.

[0031] Secondly, embodiments of this application provide an apparatus for constructing a user health profile, the apparatus comprising:

[0032] A preprocessing unit is used to collect user data and preprocess the user data to obtain user indicator data. The user data includes basic information and behavioral information of the user. The basic information is data on the user's identity and health status, and the behavioral information is activity or behavior data related to the user's health status.

[0033] The acquisition unit is used to obtain the user's disease risk level label based on user indicator data and disease risk level rules;

[0034] The prediction unit is used to input user indicator data into the data trend prediction model to predict the trend of user indicator data. The indicator data prediction model is a trained neural network model, and the training data of the indicator data prediction model is historical indicator data and the trend of historical indicator data over time.

[0035] The prediction unit is also used to input user indicator data into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores.

[0036] The building unit is used to combine user disease risk level tags, user health indicator trends, and disease risk to construct a user health profile.

[0037] Optionally, the preprocessing unit is specifically used for:

[0038] Multimodal data processing is performed on user data to extract key information;

[0039] Based on the defined indicators, feature extraction is performed on key information to extract basic user indicators from user data. The defined indicators include basic user indicators, basic health indicators, and extended health indicators.

[0040] Data cleaning and standardization are performed on the user basic metrics data to obtain user metric data.

[0041] Optionally, obtaining the unit is specifically used for:

[0042] Based on user indicator data and health topic rules, the user's disease topic is determined. The health topic rules are rules for evaluating various diseases using indicator data.

[0043] By substituting user indicator data into the disease risk level rules of the disease topic, a user's disease risk level label is obtained. The disease risk level rules are rules for evaluating the level of various diseases based on indicator data.

[0044] Optionally, the device further includes a training unit for:

[0045] Obtain users' historical metrics data and the trends of historical metrics data over time;

[0046] Historical indicator data and the trend of historical indicator data over time are used as training samples to input into the initial trend model for training until the initial trend model reaches the target value, thus obtaining the data trend prediction model.

[0047] Optionally, the device further includes a training unit for:

[0048] Obtain users' historical metric data and historical disease risk scores;

[0049] Historical indicator data and historical disease risk scores are used as training samples to input into the initial risk model for training until the initial risk model reaches the target value, thus obtaining a disease risk prediction model.

[0050] Optionally, the obtaining unit is also used for:

[0051] Based on the user's disease risk level label, a large model is used to obtain health and lifestyle guidance suggestions corresponding to the disease risk level label.

[0052] Optionally, the apparatus further includes a generating unit for:

[0053] Users can set their health control goals using parameters;

[0054] Based on the health control objectives, improvement suggestions for the user are determined from the set of improvement suggestions, wherein the set of improvement suggestions corresponds to the health control objectives;

[0055] Based on users' improvement suggestions, a multi-faceted guidance and suggestion plan is generated, including guidance and suggestion plans on lifestyle, dietary structure, and exercise.

[0056] Thirdly, this application provides an electronic device, which includes a memory and a processor:

[0057] Memory is used to store computer programs;

[0058] The processor is used to execute the method provided in the first aspect above according to the computer program.

[0059] Fourthly, this application also provides a computer-readable storage medium for storing a computer program for performing the method provided in the first aspect above.

[0060] Therefore, this application has the following beneficial effects:

[0061] This application provides a method for constructing a user health profile. First, user data is collected and preprocessed to obtain user indicator data. Based on the user indicator data and disease risk level rules, a user disease risk level label is obtained. The user indicator data is then input into a data trend prediction model to predict the trend of the user's indicator data. Finally, the user indicator data is input into a disease risk prediction model to predict the user's disease risk. Finally, the user's disease risk level label, the user's health indicator trend, and the disease risk are combined to construct a user health profile. In this process, by collecting and comprehensively analyzing user health data from multiple perspectives, a large-scale model is accurately used to assess the user's health status and predict disease risk, thus constructing a multi-information user health profile. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0063] Figure 1 This is a flowchart illustrating one embodiment of a method for constructing a user health profile according to this application.

[0064] Figure 2This is a flowchart illustrating the definition of metrics for a method of constructing a user health profile, as described in an embodiment of this application.

[0065] Figure 3 This is a flowchart illustrating yet another embodiment of a method for constructing a user health profile in this application.

[0066] Figure 4 This is a schematic diagram of the structure of a device for constructing a user health profile according to an embodiment of this application;

[0067] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0069] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0070] Currently, there are several drawbacks in building user health profiles:

[0071] (1) Data source limitations: Many existing methods may rely on a single data source, such as electronic medical records or physical examination reports, without taking into account multi-source data, such as social media, wearable device data, etc., which may result in an incomplete profile.

[0072] (2) Insufficient personalization: Existing methods may not be able to fully consider individual differences, such as living habits and environmental factors, resulting in insufficient personalization of the profile.

[0073] (3) Lack of dynamic prediction capability: Some methods may only provide static health assessments without the ability to dynamically predict users’ future health trends.

[0074] (4) Poor algorithm transparency and interpretability: Some methods that use complex machine learning models may lack transparency and interpretability, making it difficult for users and medical professionals to understand the decision-making logic of the model.

[0075] (5) Lack of interdisciplinary integration: The construction of health profiles often requires knowledge from multiple disciplines such as medicine, psychology, and nutrition. Existing methods may not have integrated this interdisciplinary knowledge well.

[0076] (6) Difficult to scale up: Some methods may perform well in small-scale applications, but face problems such as performance degradation and increased costs when applied on a large scale.

[0077] In this embodiment of the application, by combining big data and big model technology, the above technologies are used to extract features and predict trends from raw data such as electronic medical records, medical records, physical examination reports, and manual data entry, so as to construct a personalized user health profile.

[0078] In specific implementation, the method may include, for example, the following steps: First, collecting user data and preprocessing it to obtain user indicator data, wherein the user data includes basic user information and behavioral information; wherein the basic information is user identity and health status data, and the behavioral information is activity or behavioral data related to the user's health status; obtaining a user's disease risk level label based on the user indicator data and disease risk level rules; inputting the user indicator data into a data trend prediction model to predict the trend of the user's indicator data, wherein the indicator data prediction model is a trained neural network model, and the training data for the indicator data prediction model is historical indicator data and the trend of historical indicator data over time; inputting the user indicator data into a disease risk prediction model to predict the user's disease risk, wherein the disease risk prediction model is a trained neural network model, and the training samples for the disease risk prediction model are historical indicator data and corresponding historical disease risk scores; finally, combining the user's disease risk level label, the user's health indicator trend, and the disease risk to construct a user health profile.

[0079] As can be seen, the method provided in this application comprehensively analyzes user health data by collecting multi-faceted user data, accurately assesses user health status and predicts disease risk, and constructs a user health profile with multiple information.

[0080] To facilitate understanding of the specific implementation of the method for constructing a user health profile provided in the embodiments of this application, the following description will be provided in conjunction with the accompanying drawings.

[0081] It should be noted that the subject implementing the method for constructing a user health profile can be the device for constructing a user health profile provided in the embodiments of this application. This device for constructing a user health profile can be carried in an electronic device or a functional module of an electronic device. The electronic device in the embodiments of this application can be any device capable of implementing the method for constructing a user health profile in the embodiments of this application, such as an Internet of Things (IoT) device.

[0082] Figure 1 This is a flowchart illustrating a method for constructing a user health profile, provided in an embodiment of this application. This method can be applied to an apparatus for constructing a user health profile, which may be, for example, a device... Figure 4 The device 400 shown is for constructing a user health profile; alternatively, the device for constructing a user health profile may be integrated into... Figure 5 Functional modules in the electronic device 500 shown.

[0083] like Figure 1 As shown, the method includes the following steps S101 to S105:

[0084] S101: Collect user data and preprocess the user data to obtain user indicator data. The user data includes the user's basic information and behavioral information. The basic information is data on the user's identity and health status, and the behavioral information is activity or behavioral data related to the user's health status.

[0085] To construct a more comprehensive personalized user health profile, this embodiment first collects user data and preprocesses it to obtain user indicator data. Then, based on the user indicator data and disease risk level rules, it obtains the user's disease risk level label. Next, it inputs the user indicator data into a data trend prediction model to predict the trend of the user's indicator data, and inputs the user indicator data into a disease risk prediction model to predict the user's disease risk. Finally, it combines the user's disease risk level label, the user's health indicator trend, and the disease risk to construct the user's health profile. In this embodiment, obtaining user indicator data through step S101 prepares the way for subsequently obtaining the user's disease risk level label, the user's health indicator trend, and the disease risk.

[0086] As an example, S101 may include: S1011, collecting user data; S1012, preprocessing the user data to obtain user indicator data.

[0087] The user data in S1011 above includes basic user information and behavioral information; the basic information is data on the user's identity and health status, and the behavioral information is activity or behavioral data related to the user's health status. This user data can be obtained through electronic medical records, medical records, physical examination reports, manual data entry, etc., or it can be collected through an app from various dimensions, including but not limited to basic user information (such as gender, age, region, etc.), as well as electronic medical records, physical examination reports, medical data, behavioral habits (such as product usage behavior), health habits (such as exercise, diet, etc.) generated at different time periods, and health device data.

[0088] In step S1012 above, user basic indicators contained in user data can be extracted using methods such as large model feature extraction, optical character recognition (OCR) technology, multimodal processing technology, and system fault tolerance processing. These indicators are then cleaned and standardized (e.g., unit conversion) to ultimately obtain user indicator data. The specific process may include: first, extracting text information from user-uploaded images and scanned documents using OCR technology; combining text, images, and other multimodal data to extract key information; extracting user basic indicators from the user data based on defined indicators, including basic user indicators and basic health indicators; and then cleaning and standardizing the data in the user basic indicators to obtain user indicator data. Data cleaning involves identifying and processing missing values, outliers, and duplicate records, while standardization involves unifying the data format and converting data from different units of measurement to standard units.

[0089] It should be noted that the above-mentioned defined indicators include basic user indicators, basic health indicators, and extended health indicators, specifically including: (1) defining basic user indicators: basic information such as the user's name, gender, and education level. (2) defining health status indicators: user's health status data, describing a certain time (the time point when the data is obtained), user health events and event results. For example: on a certain day of a certain month of a certain year, Zhang San's blood pressure at rest was 190 mmHg systolic and 120 mmHg diastolic. Specifically, it can include: physiological health data: the user's physical symptoms and organ functions, daily living functions, physical activity functions, etc., which can be obtained through physical examination data, such as blood pressure, blood sugar, blood lipids, liver and kidney function indicators, etc.; mental health data: including the user's mental state, including emotional state, stress level, sleep quality, etc., which can be achieved through mental health scales or regular mental health assessments; social health data: including the user's health status in terms of social relationships, social support, and social activities, which may involve social frequency, social participation, and access to social resources. (3) Define extended health indicators: Lifestyle data: including lifestyle habits such as diet, exercise, and sleep, which have a direct impact on health; Past medical history data: understanding the user's past medical history, which helps to assess the risk of certain diseases; Family medical history data: understanding the hereditary diseases in the user's family, which helps to assess the risk of certain diseases; Occupational history data: recording the user's occupational exposure, living environment, and possible health risk factors in lifestyle habits.

[0090] S102: Obtain the user's disease risk level label based on user indicator data and disease risk level rules.

[0091] As an example, S102 may include: determining the user's disease topic based on user indicator data and health topic rules, wherein the health topic rules are rules for assessing various diseases using indicator data; and substituting the user indicator data into the disease risk level rules of the disease topic to obtain the user's disease risk level label, wherein the disease risk level rules are rules for assessing various disease levels based on indicator data.

[0092] The health theme rules in this application embodiment include predefined reference indicators for health themes, specifying which indicators from the aforementioned user basic indicators, basic health indicators, and extended health indicators are required for each health theme. Specific references can be made to national, local, or industry-specific diagnostic and treatment guidelines, such as: *Guidelines for the Prevention and Treatment of Dyslipidemia in Chinese Adults (2016 Revised Edition)*, *Chinese Medical Association Clinical Diagnosis and Treatment Guidelines for Lung Cancer (2023 Edition)*, *Guidelines for the Primary Care Diagnosis and Treatment of Dyslipidemia (Practice Version 2019)*, and *Guidelines for Early Screening, Diagnosis, and Prevention of Chronic Kidney Disease (2022)*. Specific disease themes may include: Hypertension: Long-term elevated blood pressure may not have obvious symptoms but increases the risk of damage to organs such as the heart, blood vessels, and kidneys. Diabetes: Elevated blood sugar levels due to insufficient insulin secretion or inadequate insulin response; long-term presence may lead to various complications. Coronary Artery Disease: Insufficient blood supply to the coronary arteries of the heart may lead to angina pectoris, myocardial infarction, and other heart problems. Chronic Obstructive Pulmonary Disease (COPD): Includes chronic bronchitis and emphysema, leading to persistent respiratory symptoms and decreased exercise tolerance. Cerebrovascular diseases: such as stroke, caused by ruptured or blocked blood vessels in the brain, leading to brain tissue damage. Chronic kidney disease: Gradual loss of kidney function, potentially requiring dialysis or a kidney transplant. Osteoarthritis: Wear and tear on articular cartilage, causing joint pain and limited mobility. Osteoporosis: Decreased bone density, making bones brittle and prone to fractures. Asthma: Chronic respiratory inflammation, leading to airway constriction, increased sputum, and difficulty breathing. Autoimmune diseases: such as rheumatoid arthritis and lupus, where the immune system mistakenly attacks its own tissues. Obesity: Excessive accumulation of body fat, increasing the risk of various chronic diseases. Mental illnesses: such as depression, anxiety, and bipolar disorder, affecting mood and behavior. Parkinson's disease: A neurodegenerative disease causing impaired motor and cognitive function. Liver diseases: including non-alcoholic fatty liver disease, hepatitis B, and hepatitis C, which may develop into cirrhosis or liver cancer. Cancer: Malignant tumors that can affect any part of the body.

[0093] Taking hypertension as an example, the above health-related rules define hypertension as follows: If a patient's systolic blood pressure is 190 mmHg and diastolic blood pressure is 130 mmHg at rest, we can diagnose the patient with hypertension. The formulas for determining hypertension are as follows: Normal blood pressure: Systolic blood pressure (SBP) < 120 mmHg and diastolic blood pressure (DBP) < 80 mmHg; Stage 1 hypertension: SBP 120-139 mmHg or DBP 80-89 mmHg; Stage 2 hypertension: SBP ≥ 140 mmHg or DBP ≥ 90 mmHg.

[0094] The disease risk level rules for disease topics in this application embodiment are divided into six levels based on the trend of chronic disease risk changes: high risk, relatively high risk, moderate risk, low risk, relatively low risk concept, and past history; that is, based on user indicator data, it can be determined that the user belongs to one of these risk stages, and combined with the specific disease topic, a user disease risk level label can be obtained.

[0095] In addition, after obtaining the user's disease risk level label, this application embodiment can also use a large model to obtain health and lifestyle guidance suggestions corresponding to the disease risk level label.

[0096] S103: Input user indicator data into the data trend prediction model to predict the trend of user indicator data. The indicator data prediction model is a trained neural network model. The training data of the indicator data prediction model consists of historical indicator data and the trend of historical indicator data over time.

[0097] As an example, the training process of the data trend prediction model in S103 may include: acquiring the user's historical indicator data and the trend of historical indicator data over time; using the historical indicator data and the trend of historical indicator data over time as training samples to input into the initial trend model for training until the initial trend model reaches the target value, thereby obtaining the data trend prediction model.

[0098] In this application embodiment, time series analysis, statistical models, or machine learning algorithms, such as support vector machine (SVM) and random forest, can be used as initial models to analyze and predict the trend of user indicator data.

[0099] S104: Input user indicator data into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores.

[0100] As an example, the training process of the disease risk prediction model in S104 may include: acquiring the user's historical indicator data and historical disease risk score; inputting the historical indicator data and historical disease risk score as training samples into the initial risk model for training until the initial risk model reaches the target value, thereby obtaining the disease risk prediction model.

[0101] In this application's embodiments, the disease risk prediction model can utilize algorithms such as Support Vector Machine (SVM), Backpropagation Neural Network (BPNN), Random Forest, and Naive Bayes. SVM is a supervised learning algorithm suitable for small-sample, high-dimensional data, capable of solving classification problems in disease monitoring and bioinformatics, and particularly excels in chronic disease prediction. BPNN is a multi-layer feedforward network suitable for large datasets, possessing parallel processing and self-learning capabilities, and widely used in cardiovascular disease prediction. Random Forest is suitable for handling high-dimensional, feature-missing, and imbalanced data, providing unbiased estimates, and is commonly used for predicting chronic diseases such as diabetes and cardiovascular diseases. Naive Bayes, based on Bayesian decision theory, is suitable for situations where attributes are independent, is less sensitive to missing data, and is suitable for text classification and natural language processing, as well as for predicting liver disease and TCM syndrome risks. In specific disease risk prediction, appropriate machine learning algorithms can be selected based on the characteristics and needs of the data to conduct in-depth analysis and prediction of the user's health status.

[0102] In this embodiment of the application, the historical indicator data for training the disease risk prediction model may also include biochemical indicators: measurements of biochemical components in blood and urine; imaging data: medical imaging data such as X-ray, CT, and MRI; and gene expression data: expression levels of relevant genes.

[0103] S105: Combine user disease risk level tags, user health indicator trends, and disease risk to construct a user health profile.

[0104] After obtaining user disease risk level labels, user health indicator trends, and disease risk, these can be combined to construct a user health profile. The user health profile information in this embodiment is comprehensive, and it analyzes, evaluates, and predicts future user health trends based on user data, possessing the ability to dynamically predict future user health trends.

[0105] After obtaining a user's health image, scientific health guidance suggestions can be proposed from multiple relevant perspectives based on the information in the user's health image, including lifestyle, dietary structure, and exercise recommendations. The specific process may include: setting the user's health control goals through parameters; determining the user's improvement suggestions from a set of improvement suggestions based on the health control goals, wherein the set of improvement suggestions corresponds to the health control goals; and finally generating a multi-faceted guidance suggestion plan based on the user's improvement suggestions, including a lifestyle guidance suggestion plan, a dietary structure guidance suggestion plan, and an exercise guidance suggestion plan.

[0106] The guidance and advice plan in this application embodiment needs to be customized according to the user's specific circumstances to ensure the practicality and effectiveness of the advice. At the same time, the guidance and advice plan also needs to be easy to understand and implement so that the user can adhere to it in the long term.

[0107] As can be seen, this application's embodiments obtain user data from multiple sources, preprocess it to obtain user indicator data, and then obtain the user's disease risk level label based on the user indicator data. Furthermore, it obtains the user's health indicator trends and disease risk based on the model. Finally, it combines the user's disease risk level label, health indicator trends, and disease risk to construct a multi-information user health profile. Based on the user's health profile, it provides comprehensive health guidance, ultimately achieving personalized healthy living guidance and disease prevention suggestions.

[0108] To make the methods provided in the embodiments of this application clearer and easier to understand, the following is combined with... Figure 2 Let me illustrate this with a specific example.

[0109] like Figure 2 As shown, this implementation may include, for example:

[0110] S201: Define basic user metrics, basic health metrics, and extended health metrics as reference metrics for defining metrics and defining health topics.

[0111] like Figure 3 As shown in the flowchart of the defined indicators, this embodiment of the application aims to construct a user health profile to assess the user's health indicator trends and disease risk. This requires collecting data from multiple dimensions and obtaining user indicator data based on defined basic user information, basic health indicators, and extended health indicators. The specific definitions are as described in the above embodiment and will not be repeated here. Furthermore, it is necessary to predefine which of the aforementioned basic user indicators, basic health indicators, and extended health indicators are required as reference indicators for each health topic. For example, the hypertension topic requires reference to family medical history data from the extended health indicators and blood pressure data from the basic health indicators.

[0112] S202: Collect user data.

[0113] In this application embodiment, user data is collected through multiple methods. By increasing the data sources for user health profiles, the accuracy of user health profile data can be improved. User data can be collected through electronic medical records, medical records, physical examination reports, manual data entry, etc., or through an app to collect user data across different dimensions, including but not limited to basic user information (such as gender, age, and region), as well as electronic medical records, physical examination reports, medical records, behavioral habits (such as product usage behavior), health habits (such as exercise and diet), and health device data generated at different time periods.

[0114] S203: Preprocess user data to obtain user metric data.

[0115] This application requires user indicator data as input data for the model. Therefore, the user data needs to be preprocessed, which mainly includes first performing multimodal data processing on the user data to extract key information; then performing feature extraction on the key information based on the defined indicators obtained in S201 above to extract the basic user indicators from the user data; and finally performing data cleaning and standardization on the data in the basic user indicators to obtain the user indicator data.

[0116] S204: Determine the user's disease theme based on user indicator data and health theme rules, wherein the health theme rules are rules for evaluating various diseases using indicator data.

[0117] After obtaining user indicator data, the user's disease risk level label can be determined based on the user indicator data. First, the user's disease theme needs to be determined based on the user indicator data and health theme rules. Specific health theme rules are as shown in the above example, and will not be elaborated here.

[0118] S205: Substitute user indicator data into the disease risk level rules of the disease topic to obtain the user's disease risk level label. The disease risk level rules are rules for evaluating the levels of various diseases based on indicator data.

[0119] After determining the user's disease topic, the user's current disease risk level can also be determined, and a disease risk level label can be attached to the user. The specific disease risk level rules are as shown in the above example, and will not be repeated here.

[0120] S206: Based on the user's disease risk level label, use a large model to obtain health and lifestyle guidance suggestions corresponding to the disease risk level label.

[0121] After obtaining a user's disease risk level label, a corresponding large model can be used to directly obtain health and lifestyle guidance suggestions based on that disease risk level. For example, if a user's disease risk level is moderate hypertension, the corresponding health and lifestyle guidance suggestions could be to regularly measure blood pressure, blood sugar, and blood lipids, as well as adjust lifestyle habits.

[0122] S207: Input user indicator data into the data trend prediction model to predict the trend of user indicator data. The indicator data prediction model is a trained neural network model. The training data of the indicator data prediction model consists of historical indicator data and the trend of historical indicator data over time.

[0123] This application embodiment can not only obtain the user's disease risk level, but also predict the trend of the user's indicator data based on the user's indicator data, so as to better understand the user's health status.

[0124] S208: Input user indicator data into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores.

[0125] This application embodiment can not only obtain the user's disease risk level, but also predict the user's disease risk based on user indicator data, thus providing a better understanding of the user's health status.

[0126] S209: Combine user disease risk level tags, user health indicator trends, and disease risk to construct a user health profile.

[0127] Finally, to enrich the information content of the user health profile, this application embodiment combines the user's disease risk level label, the user's health indicator trend, and the risk of disease to construct a user health profile.

[0128] S210: Set the user's health control goals through parameters, and determine the user's improvement suggestions from the set of improvement suggestions based on the health control goals.

[0129] In this embodiment, a set of improvement suggestions is pre-stored, and this set of suggestions corresponds to certain health control goals. That is, after a user sets their health control goals through parameters, improvement suggestions can be determined from the set of suggestions based on the health control goals and the corresponding relationships. For example, the user's health control goals might be: Blood pressure control: the goal is to maintain it at 90-139 / 60-89 mmHg; Blood glucose control: the goal is to maintain it at 3.9-6.1 mmol / L; Body mass index (BMI): the goal is to reduce it to 18.5-23.9 kg / m²; Total cholesterol: the goal is below 5.2 mmol / L; Triglycerides: the goal is below 1.70 mmol / L. It is recommended to control fat intake; Smoking: the goal is to not smoke. It is recommended to take measures to quit smoking; Alcohol consumption: the goal is to limit alcohol consumption. It is recommended to reduce alcohol intake; Salt intake: the goal is to reduce it to one teaspoon of salt. It is recommended to reduce salt intake. Improvement suggestions can be determined for different goals. For example, for blood pressure control, suggestions include: regularly measuring blood pressure, blood glucose, and blood lipids, and adjusting lifestyle habits. Recommendations for blood sugar control: Regular monitoring of blood sugar levels is recommended. Recommendations for body mass index (BMI): Weight control through diet and exercise is recommended. Recommendations for total cholesterol: Controlling dietary cholesterol intake is recommended.

[0130] S211: Based on the user's improvement suggestions, generate a multi-faceted guidance and suggestion plan, including a lifestyle guidance and suggestion plan, a dietary structure guidance and suggestion plan, and an exercise guidance and suggestion plan.

[0131] Furthermore, in this embodiment, based on the user's improvement suggestions, a multi-faceted guidance and suggestion plan is generated, such as (1) a lifestyle guidance and suggestion plan: using a health radar chart to visualize the user's health habits and providing personalized suggestions based on the radar chart results. Analyzing the user's current health status, pointing out strengths and areas for improvement. (2) Dietary structure suggestions: pointing out deficient indicators in the diet, such as high salt, high sugar, and high fat. Providing specific dietary improvement suggestions, such as increasing the intake of vegetables and fruits and reducing processed foods. (3) Healthy exercise suggestions: choosing light to moderate aerobic exercises, such as brisk walking, jogging, swimming, and Tai Chi. The purpose of exercise is to enhance metabolism and physical fitness, and it should not be excessive. Strictly follow the exercise plan formulated by the doctor. In this embodiment, comprehensive and personalized healthy living guidance and disease prevention suggestions can be provided, providing users with scientific health guidance, which is efficient, accurate, and practical.

[0132] This embodiment provides a method for constructing user health profiles, which comprehensively analyzes user health data based on big data and big models, accurately assesses users' health status and predicts disease risks, thereby providing personalized health and lifestyle guidance and disease prevention suggestions.

[0133] See Figure 4 This application provides an apparatus 400 for constructing a user health profile, the apparatus comprising:

[0134] The preprocessing unit 401 is used to collect user data and preprocess the user data to obtain user indicator data. The user data includes basic information and behavioral information of the user. The basic information is data on the user's identity and health status, and the behavioral information is activity or behavioral data related to the user's health status.

[0135] Unit 402 is used to obtain the user's disease risk level label based on user indicator data and disease risk level rules;

[0136] The prediction unit 403 is used to input user indicator data into the data trend prediction model to predict the trend of user indicator data. The indicator data prediction model is a trained neural network model, and the training data of the indicator data prediction model is historical indicator data and the trend of historical indicator data over time.

[0137] The prediction unit 403 is also used to input user indicator data into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores.

[0138] Building unit 404 is used to combine user disease risk level tags, user health indicator trends, and disease risk to build a user health profile.

[0139] Optionally, the preprocessing unit 401 is specifically used for:

[0140] Multimodal data processing is performed on user data to extract key information;

[0141] Based on the defined indicators, feature extraction is performed on key information to extract basic user indicators from user data. The defined indicators include basic user indicators, basic health indicators, and extended health indicators.

[0142] Data cleaning and standardization are performed on the user basic metrics data to obtain user metric data.

[0143] Optionally, unit 402 is obtained, specifically for:

[0144] Based on user indicator data and health topic rules, the user's disease topic is determined. The health topic rules are rules for evaluating various diseases using indicator data.

[0145] By substituting user indicator data into the disease risk level rules of the disease topic, a user's disease risk level label is obtained. The disease risk level rules are rules for evaluating the level of various diseases based on indicator data.

[0146] Optionally, the device 400 further includes a training unit for:

[0147] Obtain users' historical metrics data and the trends of historical metrics data over time;

[0148] Historical indicator data and the trend of historical indicator data over time are used as training samples to input into the initial trend model for training until the initial trend model reaches the target value, thus obtaining the data trend prediction model.

[0149] Optionally, the device 400 further includes a training unit for:

[0150] Obtain users' historical metric data and historical disease risk scores;

[0151] Historical indicator data and historical disease risk scores are used as training samples to input into the initial risk model for training until the initial risk model reaches the target value, thus obtaining a disease risk prediction model.

[0152] Optionally, the receiving unit 402 is also used for:

[0153] Based on the user's disease risk level label, a large model is used to obtain health and lifestyle guidance suggestions corresponding to the disease risk level label.

[0154] Optionally, the device 400 further includes a generating unit for:

[0155] Users can set their health control goals using parameters;

[0156] Based on the health control objectives, improvement suggestions for the user are determined from the set of improvement suggestions, wherein the set of improvement suggestions corresponds to the health control objectives;

[0157] Based on users' improvement suggestions, a multi-faceted guidance and suggestion plan is generated, including guidance and suggestion plans on lifestyle, dietary structure, and exercise.

[0158] It should be noted that the specific implementation method and effects of the device 400 for constructing user health profiles can be found in the above description. Figure 1 or Figure 2 The relevant descriptions in the provided methods will not be repeated here.

[0159] This application also provides an electronic device 500, such as... Figure 5As shown, the device 500 includes a memory 501 and a processor 502:

[0160] Memory 501 is used to store computer programs;

[0161] Processor 502 is used to execute the above according to the computer program. Figure 1 or Figure 2 The methods provided.

[0162] In addition, this application also provides a computer-readable storage medium for storing a computer program, the computer program being executed. Figure 1 or Figure 2 The methods provided.

[0163] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus a general-purpose hardware platform. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0164] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate. Components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the objectives of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0165] The above description is merely an exemplary implementation of this application and is not intended to limit the scope of protection of this application.

Claims

1. A method for constructing a user health profile, characterized in that, The method includes: User data is collected and preprocessed to obtain user indicator data. The user data includes basic user information and behavioral information. The basic information is user identity and health status data, and the behavioral information is activity or behavior data related to the user's health status. Based on the user indicator data and disease risk level rules, obtain the user's disease risk level label; The user indicator data is input into the data trend prediction model to predict the trend of the user's indicator data. The data trend prediction model is a trained neural network model. The training data of the data trend prediction model is historical indicator data and the trend of the historical indicator data over time. The user indicator data is input into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores. By combining the user's disease risk level tags, the user's health indicator trends, and the risk of developing diseases, a user health profile is constructed.

2. The method according to claim 1, characterized in that, The preprocessing of the user data to obtain user indicator data includes: Multimodal data processing is performed on the user data to extract key information; Based on the defined indicators, feature extraction is performed on the key information to extract basic user indicators from the user data. The defined indicators include basic user indicators, basic health indicators, and extended health indicators. The user indicator data is obtained by performing data cleaning and standardization on the data in the user basic indicators.

3. The method according to claim 1, characterized in that, The step of obtaining a user's disease risk level label based on the user indicator data and disease risk level rules includes: Based on the user indicator data and health topic rules, the user's disease topic is determined, and the health topic rules are rules for evaluating various diseases using indicator data; The user indicator data is substituted into the disease risk level rules of the disease topic to obtain the user's disease risk level label. The disease risk level rules are rules for evaluating the levels of various diseases based on indicator data.

4. The method according to claim 1, characterized in that, The training process of the data trend prediction model includes: Obtain the user's historical metric data and the trend of historical metric data over time; The historical indicator data and the trend of historical indicator data over time are used as training samples to input into the initial trend model for training until the initial trend model reaches the target value, thereby obtaining the data trend prediction model.

5. The method according to claim 1, characterized in that, The training process of the disease risk prediction model includes: Obtain the user's historical indicator data and historical disease risk score; The historical indicator data and historical disease risk scores are used as training samples and input into the initial risk model for training until the initial risk model reaches the target value, thereby obtaining the disease risk prediction model.

6. The method according to claim 1, characterized in that, The method further includes: Based on the user's disease risk level label, a large model is used to obtain health and lifestyle guidance suggestions corresponding to the disease risk level label.

7. The method according to claim 1, characterized in that, The method further includes: The user's health control goals are set through parameters; Based on the health control objectives, improvement suggestions for the user are determined from the set of improvement suggestions, wherein the set of improvement suggestions corresponds to the health control objectives; Based on the user's improvement suggestions, a multi-faceted guidance and suggestion plan is generated, including a lifestyle guidance and suggestion plan, a dietary structure guidance and suggestion plan, and an exercise guidance and suggestion plan.

8. A method for constructing a user health profile, characterized in that, The method includes: A preprocessing unit is used to collect user data and preprocess the user data to obtain user indicator data. The user data includes basic information and behavioral information of the user. The basic information refers to data representing the user's identity and health status, and the behavioral information refers to activity or behavioral data related to the user's health status. The obtaining unit is used to obtain the user's disease risk level label based on the user indicator data and disease risk level rules; The prediction unit is used to input the user indicator data into the data trend prediction model to predict the trend of the user's indicator data. The data trend prediction model is a trained neural network model, and the training data of the data trend prediction model is historical indicator data and the trend of the historical indicator data over time. The prediction unit is also used to input the user indicator data into the disease risk prediction model to predict the user's disease risk. The disease risk prediction model is a trained neural network model, and the training samples of the disease risk prediction model are historical indicator data and corresponding historical disease risk scores. The construction unit is used to combine the user's disease risk level label, the user's health indicator trend, and the risk of disease to construct a user health profile.

9. An electronic device, characterized in that, The device includes a memory and a processor, the electronic device being configured to execute a program stored in the memory, performing the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method according to any one of claims 1-7.

Images