Health consultation service recommendation system and method based on big data

Abstract

The invention relates to the technical field of health consultation, in particular to a health consultation service recommendation system and method based on big data, and the method comprises the following steps: S1, data collection: collecting health data of a user in real time; s2, data preprocessing: preprocessing the collected health data; s3, health intervention service recommendation: performing health risk assessment on the user based on the preprocessed health data, and providing personalized health management service recommendation for the user according to an assessment result, including an exercise plan, a diet suggestion and a psychological counseling scheme; and S4, health trend change prediction and real-time intervention optimization: performing multi-dimensional analysis on the health data by adopting a graph neural network model, predicting the future health trend of the user, and optimizing health management service recommendation of the user. According to the invention, the compliance and participation degree of the user can be improved, the long-term health management effect is enhanced, and the potential health risk is further reduced.

Description

Technical Field

[0001] The present invention relates to the field of health consultation technology, and in particular to a health consultation service recommendation system and method based on big data. Background Art

[0002] With the advancement of science and technology, health management has gradually become an important topic in modern society. Especially with the development of big data, the Internet of Things and artificial intelligence technologies, more and more health data can be collected in real time through various smart devices and sensors. These devices can monitor users' physiological, psychological, environmental and behavioral data, providing a comprehensive understanding of individual health status. At the same time, health management is gradually developing towards personalization and precision. Health intervention and health service recommendations have gradually become an important means to improve the quality of life and prevent diseases.

[0003] However, existing health management methods often lack accuracy and real-time performance, and are unable to effectively intervene in response to changes in the user's health status in a timely manner. Existing technologies mainly rely on static data analysis and simple risk assessment, and usually only intervene when the health data reaches certain preset thresholds, but fail to respond to dynamic changes in the user's health status in a timely manner. In addition, existing systems often cannot comprehensively consider the user's multi-dimensional health data, resulting in insufficient personalization and targeting of intervention measures. Such health management methods often cannot effectively reduce potential health risks, and it is difficult to provide customized services that meet the actual needs of users.

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and propose a health consultation service recommendation system and method based on big data, which can dynamically adjust health intervention services, accurately identify users' health changes, and provide personalized intervention measures in a timely manner, thereby improving the effectiveness of health management, reducing health risks, and ensuring that users can obtain the most appropriate support and services in different health conditions. Summary of the invention

[0005] The present invention provides a health consultation service recommendation system and method based on big data.

[0006] The health consultation service recommendation method based on big data includes the following steps:

[0007] S1, data collection: real-time collection of user health data, including physiological data (heart rate, blood pressure, body temperature), psychological data (emotions, stress levels), environmental data (air quality, temperature and humidity) and behavioral data (exercise volume, sleep status);

[0008] S2, data preprocessing: preprocessing the collected health data, including cleaning, denoising, and standardization;

[0009] S3, health intervention service recommendation: Based on the pre-processed health data, the user's health risk assessment is carried out, and personalized health management service recommendations are provided to the user based on the assessment results, including exercise plans, diet suggestions, and psychological counseling plans;

[0010] S4, health trend change prediction and real-time intervention optimization: Use the graph neural network (GNN) model to perform multi-dimensional analysis of health data, predict users' future health trends, and optimize users' health management service recommendations, including:

[0011] S41, health trend prediction: multi-dimensional analysis of health data through the graph neural network (GNN) model to predict the user's future health trend (disease occurrence, improvement or deterioration of health status);

[0012] S42, health status deviation monitoring and anomaly detection: real-time monitoring of the user's health data, and identifying health status deviations by comparing the user's real-time health data with the predicted health trend;

[0013] S43, health intervention optimization and personalized adjustment: Dynamically adjust the user's health management service recommendations based on the identified health status deviations.

[0014] Optionally, the data collection in S1 includes:

[0015] S11, physiological data collection: collect the user's heart rate, blood pressure, and body temperature in real time through physiological monitoring instruments;

[0016] S12, psychological data collection: real-time collection of users’ emotional states and stress levels through smartphones, portable devices or sensors;

[0017] S13, environmental data collection: collect the air quality, temperature and humidity of the user's environment in real time through environmental monitoring sensors (air quality sensors, temperature and humidity sensors);

[0018] S14, behavioral data collection: collect the user's exercise volume and sleep status in real time through sports tracking devices (smart watches, fitness trackers).

[0019] Optionally, the data preprocessing in S2 includes:

[0020] S21, data cleaning: using the statistical method based on Z-score to remove outliers and fill missing values ​​in the collected health data;

[0021] S22, denoising: using wavelet transform to remove noise from health data;

[0022] S23, standardization: Use the maximum-minimum standardization method to standardize the health data.

[0023] Optionally, the health intervention service recommendation in S3 includes:

[0024] S31, health risk assessment: Based on the pre-processed health data, the user's health risk is assessed and the health risk level is divided into low risk, medium risk and high risk.

[0025] S32, Personalized health management service recommendations: Based on the results of health risk assessment, generate personalized health management service recommendations, including customized exercise plans (such as aerobic exercise, strength training, etc.), dietary recommendations (such as low-salt diet, low-sugar diet, etc.) and psychological counseling programs (such as meditation, psychological counseling, etc.).

[0026] Optionally, the health risk assessment in S31 includes:

[0027] S311, calculating risk score: based on the user's health data, assigning a weight to each health indicator, and calculating the user's health risk score R by weighted average method;

[0028] S312, health risk level classification: based on the calculated health risk score R and the preset health risk threshold upper limit T high , health risk threshold lower limit T low Compare and classify the health risk level for users. <T low When T low ≤R <T high When R ≥ T high , it indicates that the user's health risk level is high.

[0029] Optionally, the personalized health management service recommendation in S32 includes:

[0030] S321, exercise plan recommendation: recommend customized exercise plans for users based on their health risk level and personal preferences. For low-risk users, moderate exercise plans are recommended, including aerobic exercise (jogging, swimming) and strength training (light weight training). For medium-risk users, increase the intensity and frequency of exercise, including high-intensity interval training (HIIT) and resistance training. For high-risk users, low-intensity exercise is recommended based on doctor's advice, including walking and yoga.

[0031] S322, dietary recommendations: Provide personalized dietary recommendations based on the user's health risk level and health problems (hypertension, diabetes). For low-risk users, a balanced diet rich in vegetables, fruits, and whole grains is recommended. For medium-risk users, a low-salt, low-fat, and low-sugar diet is recommended, reducing red meat intake and increasing dietary fiber intake. For high-risk users, professional dietary plans are recommended, including a low-salt diet, a low-sugar diet, or a Mediterranean diet.

[0032] S323, psychological counseling program recommendation: Based on the user's health risk level and mental health status, personalized psychological counseling programs are recommended. Emotion management suggestions, including meditation and breathing exercises, are provided to low-risk users. Psychological counseling services, including psychological counseling and group therapy, are recommended to medium-risk users. Psychological treatment programs, including cognitive behavioral therapy (CBT) and psychotherapy, are provided to high-risk users.

[0033] Optionally, the health trend prediction in S41 includes:

[0034] S411, health data graph representation: converting the user's health data into a graph, wherein each node represents a health data, the edges between the nodes represent the relationship between the health data, and the weight of the edge is calculated according to the correlation between different health data;

[0035] S412, feature extraction: A graph convolutional network (GCN) model is used to extract features from the health data graph. The convolution operation is performed on each node through the adjacency matrix A and the node feature matrix H to learn the implicit representation of the node;

[0036] S413, health trend prediction: After extracting features through the graph convolutional network, the time series features of the health data are predicted through the temporal convolutional network (TCN) model to predict the user's future health trend y t , including the occurrence of disease and improvement or deterioration of health status.

[0037] Optionally, the health status deviation monitoring and abnormality detection in S42 includes:

[0038] S421, Deviation calculation: Compare the user's real-time health data X current and predicted health trends t , calculate the health deviation ΔY t ;

[0039] S422, abnormal identification: the health deviation ΔY t With the preset health threshold T threshold For comparison, if ΔY t ≥T threshold , it is considered that the user's health status is abnormal.

[0040] Optionally, the health intervention optimization and personalized adjustment in S43 includes:

[0041] S431, exercise plan adjustment: If the user's health status is abnormal (such as high heart rate, high blood pressure), a conservative exercise plan will be recommended, including reducing exercise intensity or increasing restorative exercise (such as walking, yoga, etc.);

[0042] S432, dietary adjustment: If the user's health status is abnormal (such as high blood sugar, weight gain, etc.), a low-sugar and low-salt diet plan will be recommended;

[0043] S433, psychological counseling adjustment: If the user's health status is abnormal, adjust the psychological counseling plan according to the user's mental health status, including adding meditation, relaxation exercises or providing psychological counseling.

[0044] The health consultation service recommendation system based on big data is used to implement the above-mentioned health consultation service recommendation method based on big data, and includes the following modules:

[0045] Data collection module: collects users’ health data in real time, including physiological data, psychological data, environmental data and behavioral data;

[0046] Data preprocessing module: preprocess the collected health data, including data cleaning, denoising and standardization;

[0047] Health intervention service recommendation module: conducts health risk assessment on users and provides personalized health management service recommendations to users based on the assessment results, including customized exercise plans, dietary advice and psychological counseling programs;

[0048] Health trend change prediction and real-time intervention optimization module: Use graph neural network models to conduct multi-dimensional analysis of health data, predict users' future health trends, optimize users' health management service recommendations based on the prediction results, and achieve real-time adjustment of personalized health interventions.

[0049] Beneficial effects of the present invention:

[0050] The present invention, by real-time monitoring of the user's health data and combining it with big data analysis technology, can comprehensively evaluate the user's health status. In terms of health intervention service recommendations, it can provide personalized exercise plans, dietary recommendations and psychological counseling programs based on the user's health risk level and individual needs. It can dynamically adjust intervention measures in real time according to changes in health status, ensure the accuracy and timeliness of the intervention plan, and greatly improve the personalization of user health management.

[0051] The present invention analyzes user health data through a graph neural network model, which can effectively predict future health trends and identify potential health risks. By comparing with real-time health data, it can promptly discover deviations in health status and perform abnormality detection, accurately distinguish normal fluctuations from abnormal fluctuations, reduce false alarm rates, and ensure that health status monitoring is more sensitive and accurate. Real-time health deviation monitoring and health trend prediction can not only help users identify health problems in advance, but also provide users with personalized prevention and intervention plans to reduce the risk of disease.

[0052] The present invention, through health intervention optimization and personalized adjustment, can automatically adjust health management services according to real-time monitoring data and predicted health trends, including exercise, diet and psychological counseling. The precise adjustment of health intervention can effectively respond to changes in health status and provide personalized support in a timely manner. Through this dynamic optimization process, users can obtain the most appropriate intervention under different health conditions and maximize the health management effect. In addition, the personalized adjustment plan can also improve user compliance and participation, enhance long-term health management effects, and further reduce potential health risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A schematic diagram of a recommended method flow chart of an embodiment of the present invention;

[0055] Figure 2 Schematic diagram of system function modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0057] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0058] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0059] like Figure 1 As shown, the health consultation service recommendation method based on big data includes the following steps:

[0060] S1, data collection: real-time collection of user health data, including physiological data (heart rate, blood pressure, body temperature), psychological data (emotions, stress levels), environmental data (air quality, temperature and humidity) and behavioral data (exercise volume, sleep status);

[0061] S2, data preprocessing: preprocessing the collected health data, including cleaning, denoising, and standardization;

[0062] S3, health intervention service recommendation: Based on the pre-processed health data, the user's health risk assessment is carried out, and personalized health management service recommendations are provided to the user based on the assessment results, including exercise plans, diet suggestions, and psychological counseling plans;

[0063] S4, Prediction of health trend changes and real-time intervention optimization: Use the graph neural network (GNN) model to perform multi-dimensional analysis of health data, predict users' future health trends, and optimize users' health management service recommendations to ensure the accuracy and timeliness of personalized health services, including:

[0064] S41, health trend prediction: multi-dimensional analysis of health data through the graph neural network (GNN) model to predict the user's future health trend (disease occurrence, improvement or deterioration of health status);

[0065] S42, health status deviation monitoring and anomaly detection: real-time monitoring of the user's health data, and identifying health status deviations by comparing the user's real-time health data with the predicted health trend;

[0066] S43, health intervention optimization and personalized adjustment: dynamically adjust the health management service recommendations for users based on the identified health status deviations;

[0067] Through the above content, personalized health intervention service recommendations and dynamic optimization are achieved. By predicting users' future health trends, monitoring health status in real time and detecting deviations, it is possible to accurately identify users' health changes and adjust intervention measures in a timely manner, thereby improving the accuracy, pertinence and timeliness of health services and significantly improving the effectiveness of health management.

[0068] Data collection in S1 includes:

[0069] S11, physiological data collection: collect the user's heart rate, blood pressure, and body temperature in real time through physiological monitoring instruments;

[0070] S12, psychological data collection: real-time collection of users’ emotional states and stress levels through smartphones, portable devices or sensors;

[0071] S13, environmental data collection: collect the air quality, temperature and humidity of the user's environment in real time through environmental monitoring sensors (air quality sensors, temperature and humidity sensors);

[0072] S14, behavioral data collection: real-time collection of user's exercise volume and sleep status through sports tracking devices (smart watches, fitness trackers);

[0073] Through the above content, a variety of smart devices and sensors are used to collect users' physiological, psychological, environmental and behavioral data in real time, which can comprehensively and accurately reflect the user's health status and ensure comprehensive monitoring and dynamic evaluation of user health.

[0074] Data preprocessing in S2 includes:

[0075] S21, data cleaning: Use the statistical method based on Z-score to remove outliers and fill missing values ​​from the collected health data, expressed as:

[0076]

[0077] Among them, Z is the cleaned health data, X is the collected original health data, μ is the mean of the data, σ is the standard deviation of the data, and when the Z-score is greater than the set threshold, the data is regarded as an outlier and is removed or replaced with a suitable estimated value;

[0078] S22, denoising: Use wavelet transform to remove noise in health data, expressed as:

[0079]

[0080] Among them, W -1 is the inverse transform of wavelet transform, represents the coefficients after applying wavelet transform to the original health data D(t), D denoised (t) is the denoised data after wavelet transformation;

[0081] S23, standardization: In order to eliminate the dimensional differences between different data dimensions, the maximum-minimum standardization method is used to standardize the health data, which is expressed as:

[0082]

[0083] Among them, X is a single health data dimension, min(X) and max(X) are the minimum and maximum values ​​of the dimension data, respectively. normalized is the standardized data;

[0084] Through the above content, efficient optimization of health data is achieved. Data cleaning ensures that outliers are identified and processed in a timely manner, avoiding the interference of erroneous data on the analysis results. De-noising effectively removes the noise in the sensor data through wavelet transform, improving the accuracy and stability of the data. Standardization operations eliminate the dimensional differences between different health indicators, allowing various types of data to be analyzed on a unified scale.

[0085] The health intervention service recommendations in S3 include:

[0086] S31, health risk assessment: Based on the pre-processed health data, the user's health risk is assessed and the health risk level is divided into low risk, medium risk and high risk.

[0087] S32, personalized health management service recommendations: Generate personalized health management service recommendations based on the results of health risk assessment, including customized exercise plans (such as aerobic exercise, strength training, etc.), dietary recommendations (such as low-salt diet, low-sugar diet, etc.) and psychological counseling programs (such as meditation, psychological counseling, etc.);

[0088] Through the above content, the user's health risks can be accurately identified based on their health data, and customized intervention plans can be provided according to the risk level. Health risk assessment ensures that users with different risk levels receive intervention suggestions suitable for their health status. Personalized health management service recommendations not only provide customized exercise, diet and psychological counseling plans based on the user's health status, but also fully consider the user's personal needs and preferences, thereby improving user participation and health management effectiveness.

[0089] The health risk assessment in S31 includes:

[0090] S311, calculate risk score: Based on the user's health data, assign a weight to each health indicator, and calculate the user's health risk score R by weighted average method, which is expressed as:

[0091]

[0092] Among them, X i is the i-th health data, w i is the weight of the health data, n is the total number of health data, and R is the health risk score;

[0093] S312, health risk level classification: based on the calculated health risk score R and the preset health risk threshold upper limit T high , health risk threshold lower limit T low Compare and classify the health risk level for users. <T low When T low ≤R <T high When R ≥ T high When , it means the user's health risk level is high risk;

[0094] Upper limit of health risk threshold T high , health risk threshold lower limit T low The settings are based on historical data, including:

[0095] Historical data collection: Collect a large amount of historical user health data, including various health indicators and known health results of users;

[0096] Health risk score calculation: Calculate the risk score of all users in the historical data to obtain the health risk score R of each user. i ;

[0097] Threshold setting: Based on the health risk score R in historical data i , calculate the distribution of health risk scores for low-risk and high-risk users, and select the 20th percentile of the score distribution as the lower limit of the health risk threshold T low , select the 80th percentile of the score distribution as the upper limit of the health risk threshold T high ;

[0098] Through the above content, the user's health data is effectively combined to provide each user with an accurate health risk level classification. The risk score calculated by weighted calculation can comprehensively consider the impact of multiple health indicators and avoid the deviation that may be caused by a single indicator. At the same time, the health results in historical data are used to set thresholds, making the risk assessment more scientific and practical. It can adjust the health management strategy in real time according to the health status of different users, thereby improving the accuracy, personalization and operability of health risk assessment, ensuring the effectiveness and timeliness of health intervention measures, and providing users with more accurate health management plans.

[0099] The personalized health management service recommendations in S32 include:

[0100] S321, exercise plan recommendation: recommend customized exercise plans for users based on their health risk level and personal preferences. For low-risk users, moderate exercise plans are recommended, including aerobic exercise (jogging, swimming) and strength training (light weight training). For medium-risk users, increase the intensity and frequency of exercise, including high-intensity interval training (HIIT) and resistance training. For high-risk users, low-intensity exercise is recommended based on doctor's advice, including walking and yoga.

[0101] S322, dietary recommendations: Provide personalized dietary recommendations based on the user's health risk level and health problems (hypertension, diabetes). For low-risk users, a balanced diet rich in vegetables, fruits, and whole grains is recommended. For medium-risk users, a low-salt, low-fat, and low-sugar diet is recommended, reducing red meat intake and increasing dietary fiber intake. For high-risk users, professional dietary plans are recommended, including a low-salt diet, a low-sugar diet, or a Mediterranean diet.

[0102] S323, psychological counseling program recommendation: recommend personalized psychological counseling programs based on the user's health risk level and mental health status, provide emotional management suggestions for low-risk users, including meditation and breathing exercises, recommend psychological counseling services for medium-risk users, including psychological counseling and group therapy, and provide psychological treatment programs for high-risk users, including cognitive behavioral therapy (CBT) and psychotherapy;

[0103] Through the above content, it is ensured that the user's health management service is both scientific and personalized, thereby improving the effectiveness of the intervention. Low-risk users can stay healthy, medium-risk users can effectively improve their health status, and high-risk users can obtain timely prevention and intervention measures to avoid the deterioration of health problems. It helps to improve the user's overall health level, enhance health risk control, and reduce the probability of potential diseases. In addition, personalized recommendation plans can help users better adhere to health management plans and improve the execution and long-term effects of interventions.

[0104] Health trend forecasts in S41 include:

[0105] S411, health data graph representation: The user's health data is converted into a graph, where each node represents a health data, the edge between the nodes represents the relationship between the health data, and the weight of the edge is calculated according to the correlation between different health data, and is expressed as:

[0106] A ij =Correlation(X i ,X j );

[0107] Among them, A ij is the weight of the edge, Correlation(X i ,X j ) is used to calculate the health data X i and X j Pearson correlation coefficient between ;

[0108] S412, feature extraction: The graph convolutional network (GCN) model is used to extract features from the health data graph. The convolution operation is performed on each node through the adjacency matrix A and the node feature matrix H to learn the implicit representation of the node, which is expressed as:

[0109]

[0110] Among them, H (l) is the node feature representation of the lth layer, is the normalized adjacency matrix, W (l) is the weight matrix of the lth layer, σ is the ReLU activation function, H (l+1) It is the node feature representation of the l+1th layer;

[0111] S413, health trend prediction: After extracting features through the graph convolutional network, the time series features of the health data are predicted through the temporal convolutional network (TCN) model to predict the user's future health trend y t , including the occurrence of disease, improvement or deterioration of health status, expressed as:

[0112]

[0113] Among them, y t is the output at time t, is the i-th weight of the convolution kernel of the l-th layer, K is the size of the convolution kernel (that is, the number of steps of the convolution operation), and d is the expansion factor, which controls the spacing between adjacent weights in the convolution kernel. is the output of the l+1th layer at time step td·i;

[0114] Through the above content, the complex relationships and long-term dependencies between health indicators can be effectively captured. The spatial features in health data are extracted by the graph convolutional network (GCN), and the time series data is processed by the temporal convolutional network (TCN). It can accurately predict the user's future health trends, including the occurrence of diseases, improvement or deterioration of health conditions. In addition, the application of dilated convolution enables the model to capture long-term dependencies with less computational effort, providing more accurate prediction support for personalized health management, helping to timely discover potential health risks and optimize intervention measures, thereby improving the user's health management effect.

[0115] Health status deviation monitoring and anomaly detection in S42 include:

[0116] S421, Deviation calculation: Compare the user's real-time health data X current and predicted health trends t , calculate the health deviation ΔY t , expressed as:

[0117] ΔY t =|X current -y t |;

[0118] Among them, ΔY t is the health deviation calculated at time t;

[0119] S422, abnormal identification: the health deviation ΔY t With the preset health threshold T threshold For comparison, if ΔY t ≥T threshold , then the user's health status is considered abnormal;

[0120] Health threshold T threshold Based on historical data settings, including:

[0121] Historical data collection: Collect a large amount of historical health data, including the user's health indicators (such as heart rate, blood pressure, body temperature, etc.) and their corresponding health status (such as whether a disease has occurred, changes in health status, etc.);

[0122] Calculate the deviation of historical health data: Calculate the distribution of health deviation based on historical data, and calculate the health deviation ΔY for each piece of historical data i , expressed as:

[0123]

[0124] Among them, X i is the actual health data of the i-th record in the historical data, The health trend value predicted by the model;

[0125] Statistical deviation distribution: Calculate the deviation ΔY based on all historical data i The statistical distribution of , including mean and standard deviation, is expressed as:

[0126]

[0127] Where N is the total amount of historical data, μ ΔY is the mean of the deviations, σ ΔY is the standard deviation of the deviation;

[0128] Set threshold: Set the threshold according to the deviation distribution of historical data, expressed as:

[0129] T threshold =μ ΔY +k·σ ΔY ;

[0130] Where k is the coefficient that controls the threshold sensitivity and is set to 2 or 3;

[0131] Through the above content, deviations in health status can be accurately identified. When the deviation between real-time health data and predicted values ​​exceeds the set threshold, the system can detect potential health abnormalities in a timely manner, effectively distinguish normal fluctuations from abnormal fluctuations, and reduce false alarm rates. Secondly, combined with the comparison of real-time data and predicted trends, the system's sensitivity and accuracy to changes in user health are ensured, and health risks can be identified early, such as early signs of disease, thereby providing timely intervention for personalized health management and maximizing the effectiveness of user health management.

[0132] Health intervention optimization and personalized adjustment in S43 include:

[0133] S431, exercise plan adjustment: If the user's health status is abnormal (such as high heart rate, high blood pressure), a conservative exercise plan will be recommended, including reducing exercise intensity or increasing restorative exercise (such as walking, yoga, etc.);

[0134] S432, dietary adjustment: If the user's health status is abnormal (such as high blood sugar, weight gain, etc.), a low-sugar and low-salt diet plan will be recommended;

[0135] S433, psychological counseling adjustment: if the user's health status is abnormal, adjust the psychological counseling plan according to the user's mental health status, including adding meditation, relaxation exercises or providing psychological counseling;

[0136] Through the above content, user health data can be monitored in real time and health trends can be predicted. When the health status is abnormal, dynamic adjustments can be made in a timely and accurate manner. The health management service can be automatically adjusted according to the user's specific health status (such as heart rate, blood pressure, blood sugar, etc.), making it more personalized and targeted. The adjustment of the exercise plan can dynamically optimize the exercise intensity according to the changes in health status. The adjustment of dietary recommendations can accurately respond to health problems (such as blood sugar control, weight management, etc.). The adjustment of the psychological counseling plan can provide psychological support in a timely manner, which can not only improve the effectiveness of health management, but also effectively reduce potential health risks, ensuring that users can get the most appropriate intervention and support in different health conditions, thereby improving the accuracy and long-term effects of health management.

[0137] like Figure 2 As shown, the health consulting service recommendation system based on big data is used to implement the above-mentioned health consulting service recommendation method based on big data, and includes the following modules:

[0138] Data collection module: collects users’ health data in real time, including physiological data, psychological data, environmental data and behavioral data;

[0139] Data preprocessing module: preprocess the collected health data, including data cleaning, denoising and standardization;

[0140] Health intervention service recommendation module: conducts health risk assessment on users and provides personalized health management service recommendations to users based on the assessment results, including customized exercise plans, dietary advice and psychological counseling programs;

[0141] Health trend change prediction and real-time intervention optimization module: Use graph neural network models to conduct multi-dimensional analysis of health data, predict users' future health trends, optimize users' health management service recommendations based on the prediction results, and achieve real-time adjustment of personalized health interventions.

[0142] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0143] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A health consultation service recommendation method based on big data, characterized in that: The following steps are involved: S1, data collection: real-time collection of user health data, including physiological data, psychological data, environmental data and behavioral data; S2, data preprocessing: preprocessing the collected health data, including cleaning, denoising, and standardization; S3, health intervention service recommendation: Based on the pre-processed health data, the user's health risk assessment is carried out, and personalized health management service recommendations are provided to the user based on the assessment results, including exercise plans, diet suggestions, and psychological counseling plans; S4, prediction of health trend changes and real-time intervention optimization: Use graph neural network models to perform multi-dimensional analysis of health data, predict users' future health trends, and optimize users' health management service recommendations, including: S41, health trend prediction: multi-dimensional analysis of health data is performed through the graph neural network model to predict the user's future health trend; S42, health status deviation monitoring and anomaly detection: real-time monitoring of the user's health data, and identifying health status deviations by comparing the user's real-time health data with the predicted health trend; S43, health intervention optimization and personalized adjustment: Dynamically adjust the user's health management service recommendations based on the identified health status deviations.

2. The method for recommending health consulting services based on big data according to claim 1, characterized in that: The data collection in S1 includes: S11, physiological data collection: collect the user's heart rate, blood pressure, and body temperature in real time through physiological monitoring instruments; S12, psychological data collection: real-time collection of users’ emotional states and stress levels through smartphones, portable devices or sensors; S13, environmental data collection: collect the air quality, temperature and humidity of the user's environment in real time through environmental monitoring sensors; S14, behavioral data collection: collect the user's exercise volume and sleep status in real time through sports tracking devices.

3. The method for recommending health consulting services based on big data according to claim 1, characterized in that: The data preprocessing in S2 includes: S21, data cleaning: using the statistical method based on Z-score to remove outliers and fill missing values ​​in the collected health data; S22, denoising: using wavelet transform to remove noise from health data; S23, standardization: Use the maximum-minimum standardization method to standardize the health data.

4. The health consultation service recommendation method based on big data according to claim 1, characterized in that: The health intervention service recommendations in S3 include: S31, health risk assessment: Based on the pre-processed health data, the user's health risk is assessed and the health risk level is divided into low risk, medium risk and high risk. S32, Personalized health management service recommendations: Generate personalized health management service recommendations based on the results of health risk assessment, including customized exercise plans, dietary recommendations, and psychological counseling programs.

5. The method for recommending health consulting services based on big data according to claim 4, characterized in that: The health risk assessment in S31 includes: S311, calculating risk score: based on the user's health data, assigning a weight to each health indicator, and calculating the user's health risk score R by weighted average method; S312, health risk level classification: based on the calculated health risk score R and the preset health risk threshold upper limit T high , health risk threshold lower limit T low Compare and classify the health risk level for users. <T low When T low ≤R <T high When R ≥ T high , it indicates that the user's health risk level is high.

6. The method for recommending health consulting services based on big data according to claim 5, characterized in that: The personalized health management service recommendation in S32 includes: S321, exercise plan recommendation: recommend customized exercise plans for users based on their health risk level and personal preferences. For low-risk users, moderate exercise plans are recommended, including aerobic exercise and strength training. For medium-risk users, increase the intensity and frequency of exercise, including high-intensity interval training and resistance training. For high-risk users, low-intensity exercise is recommended based on doctor's advice, including walking and yoga. S322, Dietary recommendations: Provide personalized dietary recommendations based on the user's health risk level and health problems. For low-risk users, a balanced diet rich in vegetables, fruits, and whole grains is recommended. For medium-risk users, a low-salt, low-fat, and low-sugar diet is recommended, reducing red meat intake and increasing dietary fiber intake. For high-risk users, professional diet plans are recommended, including a low-salt diet, a low-sugar diet, or a Mediterranean diet. S323, psychological counseling program recommendation: Based on the user's health risk level and mental health status, personalized psychological counseling programs are recommended. Emotion management suggestions, including meditation and breathing exercises, are provided to low-risk users. Psychological counseling services, including psychological counseling and group therapy, are recommended to medium-risk users. Psychological treatment programs, including cognitive behavioral therapy and psychotherapy, are provided to high-risk users.

7. The method for recommending health consulting services based on big data according to claim 1, characterized in that: The health trend prediction in S41 includes: S411, health data graph representation: converting the user's health data into a graph, wherein each node represents a health data, the edges between the nodes represent the relationship between the health data, and the weight of the edge is calculated according to the correlation between different health data; S412, feature extraction: Use the graph convolutional network model to extract features from the health data graph, perform convolution operations on each node through the adjacency matrix A and the node feature matrix H, and learn the implicit representation of the node; S413, health trend prediction: After extracting features through the graph convolutional network, the time series features of the health data are predicted through the time series convolutional network model to predict the user's future health trend y t , including the occurrence of disease and improvement or deterioration of health status.

8. The method for recommending health consulting services based on big data according to claim 7, characterized in that: The health status deviation monitoring and abnormality detection in S42 includes: S421, Deviation calculation: Compare the user's real-time health data X current and predicted health trends t , calculate the health deviation ΔY t ; S422, abnormal identification: the health deviation ΔY t With the preset health threshold T threshold For comparison, if ΔY t ≥T threshold , then the user's health status is considered abnormal.

9. The method for recommending health consulting services based on big data according to claim 8, characterized in that: The health intervention optimization and personalized adjustment in S43 include: S431, exercise plan adjustment: if the user's health status is abnormal, a conservative exercise plan will be recommended, including reducing exercise intensity or increasing restorative exercise; S432, Dietary adjustment: If the user's health status is abnormal, a low-sugar and low-salt diet plan will be recommended; S433, psychological counseling adjustment: If the user's health status is abnormal, adjust the psychological counseling plan according to the user's mental health status, including adding meditation, relaxation exercises or providing psychological counseling.

10. A health consulting service recommendation system based on big data, used to implement the health consulting service recommendation method based on big data as described in any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection module: collects users’ health data in real time, including physiological data, psychological data, environmental data and behavioral data; Data preprocessing module: preprocess the collected health data, including data cleaning, denoising and standardization; Health intervention service recommendation module: conducts health risk assessment on users and provides personalized health management service recommendations to users based on the assessment results, including customized exercise plans, dietary advice and psychological counseling programs; Health trend change prediction and real-time intervention optimization module: Use graph neural network models to conduct multi-dimensional analysis of health data, predict users' future health trends, optimize users' health management service recommendations based on the prediction results, and achieve real-time adjustment of personalized health interventions.

Images