Community online intelligent analysis system based on health big data

Abstract

The present application relates to the technical field of big data, and more particularly to a community online intelligent analysis system based on health big data, which comprises an information collection module, an analysis module, a level determination module, a decision-making module and a dynamic adjustment module; the information collection module is responsible for collecting health indicators, lifestyle and environmental data of community members, and obtaining historical data; the analysis module predicts disease risk index, calculates green coverage rate, and analyzes the influence coefficient of environmental factors on risk index; the level determination module calculates the risk score level accordingly; the decision-making module formulates an initial prevention strategy according to the risk level; the dynamic adjustment module monitors health indicators and environmental data in real time, and adjusts the initial prevention strategy according to real-time data. Through intelligent analysis and management, the present application improves the accuracy of community health risk assessment and the effectiveness of response measures, and helps to improve the health level and disease prevention ability of community members.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a community online intelligent analysis system based on health big data. Background Technology

[0002] With the rapid development of information technology, the healthcare field has generated a massive amount of data, including electronic medical records, medical images, genomics data, and health monitoring data. This data, known as health big data, offers new possibilities for improving healthcare services and conducting scientific research due to its sheer scale and complexity.

[0003] Healthcare informatization refers to the process of using information technology to improve the quality and efficiency of healthcare services. With the widespread adoption of electronic medical record systems and the continuous advancement of healthcare informatization, medical institutions have begun to accumulate a large amount of health data, which provides the data foundation for community online intelligent analysis systems.

[0004] Patent document CN107731314A discloses a health intelligent monitoring platform and monitoring method based on the Internet of Things (IoT) and big data. The monitoring platform includes an infrastructure layer, an information centralization layer, and a service provision layer. The infrastructure layer includes multiple IoT terminals for collecting, transmitting, and storing medical data. The information centralization layer communicates with the infrastructure layer to perform big data analysis and mining based on the stored medical data. The service provision layer communicates with the information centralization layer to provide services to platform users based on the data analysis and mining results. Multiple IoT terminals share detection information, identity information, and diagnostic and treatment information.

[0005] This reveals the following problem: because different community members may have different health conditions and lifestyles in the existing technology, a single risk assessment model may not be able to meet everyone's personalized needs, thus affecting the accuracy. Summary of the Invention

[0006] To address this issue, the present invention provides a community online intelligent analysis system based on health big data, which overcomes the problem in existing technologies that different community members may have different health conditions and lifestyles, and a single risk assessment model may not be able to meet everyone's personalized needs, thus affecting accuracy.

[0007] To achieve the above objectives, the present invention provides a community online intelligent analysis system based on health big data, comprising:

[0008] The information collection module is used to collect health indicators and lifestyles of community members, and also to collect environmental data of the community. Based on the health indicators, lifestyles and environmental data, it obtains corresponding historical data, including green area, community area, noise level and air quality.

[0009] An analysis module, connected to the acquisition module, is used to predict the disease risk index of community members based on the health indicators and the lifestyle; calculate the green coverage rate of the community based on the green area and the community area; and analyze the influence of the green coverage rate, the noise level, and the air quality on the disease risk index to obtain an influence coefficient.

[0010] A risk rating module, connected to the analysis module, is used to calculate the risk score of the infectious disease based on the disease risk index and the influence coefficient to obtain a target risk score; and to determine the risk rating level based on the target risk score and a preset risk rating threshold.

[0011] The decision-making module, connected to the level determination module, is used to formulate initial prevention strategies for the community members based on the risk score level.

[0012] A dynamic adjustment module, connected to the decision-making module, is used to detect the health indicators of community members and the environmental data of the community in real time to obtain real-time data, and dynamically adjust the initial prevention strategy based on the real-time data.

[0013] Furthermore, the analysis module includes:

[0014] The data processing unit is used to clean and format the health indicators and lifestyles of the community members to obtain processing results.

[0015] A feature extraction unit, connected to the data processing unit, is used to extract the gender, age, exercise frequency, and dietary habits of the processing results to obtain a first feature result;

[0016] The model building unit, connected to the feature extraction unit, is used to take the first feature result as the input parameter of the model and build the prediction model based on the historical data corresponding to the feature result and the input parameter.

[0017] Furthermore, the model building unit includes:

[0018] The feature engineering subunit is used to combine the various feature results to obtain the target feature result;

[0019] The model training subunit is connected to the feature engineering subunit to train the prediction model based on the target feature results and the historical data to obtain the training model;

[0020] The model validation subunit, connected to the model training subunit, is used to use unused data from the historical data as a validation dataset to validate the trained model based on the validation dataset in order to obtain the disease risk index of the community members.

[0021] Furthermore, the analysis module also includes:

[0022] A noise level analysis unit is used to analyze the noise level of the community to obtain a first analysis result;

[0023] An air quality assessment unit is used to detect and assess the air quality of the community to obtain assessment results;

[0024] An influence coefficient calculation unit is connected to the noise level analysis unit and the air quality assessment unit, respectively, and is used to calculate the influence coefficients of the first analysis result, the assessment result and the green coverage rate on the disease risk index.

[0025] Furthermore, the influence coefficient calculation unit includes:

[0026] The data integration subunit is used to integrate the data collected from the noise level analysis unit and the air quality assessment unit, as well as the green coverage rate, into a unified dataset;

[0027] The feature extraction subunit, connected to the data integration subunit, is used to extract the average noise level, peak air quality index, and green coverage rate trend of the dataset to obtain the second feature result.

[0028] A data analysis subunit, connected to the feature extraction subunit, is used to analyze the relationship between the second feature extraction results to obtain a second analysis result;

[0029] An influence coefficient calculation subunit is connected to the data analysis subunit to calculate the influence coefficient based on the second analysis results and the statistical model.

[0030] Furthermore, the level determination module includes:

[0031] A scoring calculation unit is used to calculate a sub-risk score based on the disease risk index and each of the influence coefficients;

[0032] A weighting allocation unit is used to assign a weight value to each of the air quality, the noise level, and the green coverage rate.

[0033] A scoring correction unit is connected to the scoring calculation unit and the weight allocation unit, respectively, to correct the risk score according to the sub-risk score and the weight value to obtain the target risk score.

[0034] Furthermore, the level determination module also includes:

[0035] A threshold setting unit is used to set the risk score threshold;

[0036] A scoring comparison unit, connected to the threshold setting unit, is used to compare the target risk score and the risk score threshold to obtain a comparison result;

[0037] A rating determination unit, connected to the rating comparison unit, is used to determine the risk rating level based on the comparison result.

[0038] Furthermore, the level determination unit includes:

[0039] A threshold parsing subunit is used to parse the risk scoring threshold to obtain the parsing result;

[0040] A level division subunit, connected to the threshold analysis subunit, is used to divide the target risk score into three levels: low risk, medium risk, and high risk based on the comparison result and the analysis result;

[0041] The risk level determination subunit is connected to the risk level division subunit and is used to determine the risk level of the division.

[0042] Furthermore, the dynamic adjustment module includes:

[0043] The data acquisition unit is used to detect the health indicators of the community members and the community environment data in real time to obtain real-time data;

[0044] A data analysis unit, connected to the data acquisition unit, is used to analyze the real-time data to identify the changing trends of the health indicators and the lifestyle in order to obtain a third analysis result;

[0045] A strategy evaluation unit, connected to the data analysis unit, is used to determine whether the initial prevention strategy needs to be adjusted based on the third analysis results. Compared with the prior art, the advantages of this invention are:

[0046] Furthermore, the strategy evaluation unit includes:

[0047] The effect tracking subunit is used to track and record the effect of the initial prevention strategy after its implementation to obtain the initial effect;

[0048] An effect comparison subunit, connected to the effect tracking subunit, is used to compare the initial effect with the preset target effect to obtain a comparison result;

[0049] The strategy adjustment subunit is connected to the effect comparison subunit to determine whether to adjust the initial prevention strategy based on the comparison results.

[0050] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention uses the analysis module to predict disease risk based on data provided by the collection module, which helps to detect health problems early and thus take preventative measures. The risk assessment module calculates a risk score using the disease risk index and impact coefficient provided by the analysis module, making prevention strategies more targeted and practical. The initial prevention strategy formulated by the decision-making module can be optimized and adjusted by the dynamic adjustment module based on real-time data. The dynamic adjustment module ensures that the prevention strategy remains consistent with the health status of community members and environmental changes, improving the system's flexibility and adaptability.

[0051] In particular, the data processing unit cleans and formats health indicator and lifestyle data, ensuring the accuracy and consistency of subsequent analyses. By removing erroneous and redundant data, data quality is improved, reducing the impact of misleading information on the analysis results. The feature extraction unit extracts key features, such as gender, age, exercise frequency, and dietary habits, enabling the model to focus more on factors closely related to health risks, thus improving the model's predictive efficiency and accuracy. The model building unit uses the extracted features and historical data to construct the predictive model, ensuring that the model can capture the complex relationship between health indicators and lifestyles and disease risk.

[0052] In particular, by processing and combining the first feature results through the feature engineering subunit, more informative features can be extracted, thereby improving the model's predictive accuracy. The model training subunit uses unseen data as a validation set, which can evaluate the model's generalization ability, avoid overfitting, and ensure good performance in practical applications. The final model validated by the model validation subunit can be used to predict the disease risk index of community members, helping medical institutions to more accurately carry out disease prevention and resource allocation, and improve the efficiency of medical resource utilization.

[0053] In particular, the noise level analysis unit and the air quality assessment unit enable a comprehensive assessment of the community's environmental health risks. The impact coefficient calculation unit, by evaluating the influence coefficients of different factors on health risks, allows the community to allocate limited health resources more effectively.

[0054] In particular, the data integration subunit ensures data integrity and consistency by integrating data from different sources into a unified dataset, providing accurate foundational data for subsequent analysis. The feature extraction subunit simplifies the data structure by extracting key features such as noise levels, air quality index, and green coverage, making subsequent data analysis more efficient and focused. The data analysis subunit reveals the intrinsic links between different environmental factors and health risks by analyzing the interrelationships between features, providing a scientific basis for developing targeted health interventions.

[0055] In particular, the scoring calculation unit provides a quantitative risk assessment by multiplying the disease risk index by specific environmental impact coefficients, helping to understand the contribution of each factor to health risk. The weighting unit, by assigning different weights to air quality, noise levels, and green coverage, reflects the relative importance of these factors in the health risk assessment. This helps ensure the fairness and accuracy of the assessment results. The scoring correction unit, by combining sub-risk scores with their respective weight values, provides a health risk score that balances the influence of each factor. This helps community members understand how their environment affects their health.

[0056] In particular, the scoring comparison unit compares the risk score threshold set by the threshold setting unit with the target risk score, helping the community accurately identify high-risk groups and thus more effectively implement health interventions. Based on the comparison results, the grading unit can classify residents' risk scores into grades, providing clear health risk level labels. This helps enhance residents' health awareness and encourages them to take appropriate preventative measures.

[0057] In particular, the threshold parsing subunit ensures that the risk score thresholds are accurately understood and applied. The grading subunit provides a clear framework for quickly identifying and responding to risks of varying degrees by dividing the risk score into low, medium, and high levels. The grading determination subunit performs the final judgment based on the information provided by the grading subunit and determines the risk level of the target. This helps ensure that the system's output is reliable and can serve as the basis for developing risk response strategies.

[0058] In particular, through real-time monitoring by the data acquisition unit and data analysis by the data analysis unit, communities can manage health risks more effectively and take timely measures to reduce them. The strategy evaluation unit can assess the effectiveness of existing prevention strategies and adjust them as needed, helping to ensure that prevention strategies are aligned with current health risks and lifestyle changes, thereby improving the targeting and effectiveness of interventions.

[0059] In particular, the effect tracking subunit ensures that prevention strategies are truly implemented by tracking data and monitoring changes in participants' health indicators, providing objective data for subsequent evaluation. The results from the effect comparison subunit avoid wasting resources, focusing resources and attention on the most effective interventions. The strategy adjustment subunit's method of adjusting strategies based on actual effects ensures effective resource utilization, improves the targeting and effectiveness of prevention strategies, and thus better protects the health of community members. Attached Figure Description

[0060] Figure 1 A schematic diagram of the structure of a community online intelligent analysis system based on health big data provided in an embodiment of the present invention;

[0061] Figure 2 A schematic diagram of the structure of a community online intelligent analysis system based on health big data provided in an embodiment of the present invention;

[0062] Figure 3 A schematic diagram of the structure of a community online intelligent analysis system based on health big data provided in an embodiment of the present invention;

[0063] Figure 4 This is a schematic diagram of the structure of a community online intelligent analysis system based on health big data, provided in an embodiment of the present invention. Detailed Implementation

[0064] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0065] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0066] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0067] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0068] Please see Figure 1 As shown in the embodiment of the present invention, the community online intelligent analysis system based on health big data includes:

[0069] The information collection module 10 is used to collect health indicators and lifestyles of community members, and also to collect environmental data of the community. Based on the health indicators, lifestyles and environmental data, it obtains corresponding historical data, including green area, community area, noise level and air quality.

[0070] Analysis module 20, connected to the acquisition module 10, is used to predict the disease risk index of community members based on the health indicators and the lifestyle; calculate the green coverage rate of the community based on the green area and the community area; and analyze the influence of the green coverage rate, the noise level, and the air quality on the disease risk index to obtain the influence coefficient.

[0071] The risk assessment module 30, connected to the analysis module 20, is used to calculate the risk score of the infectious disease based on the disease risk index and the influence coefficient to obtain a target risk score; and to determine the risk score level based on the target risk score and a preset risk score threshold.

[0072] The decision-making module 40 is connected to the level determination module 30 and is used to formulate initial prevention strategies for the community members based on the risk score level.

[0073] The dynamic adjustment module 50 is connected to the decision-making module 40 and is used to detect the health indicators of the community members and the environmental data of the community in real time to obtain real-time data, and dynamically adjust the initial prevention strategy based on the real-time data.

[0074] Specifically, health indicators (such as blood pressure, blood sugar, and weight), lifestyle data (such as diet and exercise frequency), and community environmental data (green area, community area, noise level, and air quality) of community members are collected through questionnaires, wearable devices, and medical records. The collected data is stored in the cloud or a distributed database, ensuring data security and privacy. Machine learning algorithms are used to analyze health indicators and lifestyle data to predict the disease risk index of community members. Green coverage rate, noise level, and air quality are calculated, and their correlation with the disease risk index is analyzed. The impact of green coverage rate, noise level, and air quality on the disease risk index is calculated using statistical methods, resulting in an impact coefficient. Combining the disease risk index and the impact coefficient, a risk score for infectious diseases is calculated. The calculated risk score is compared with a preset threshold to classify risk levels. Based on the risk level, corresponding prevention strategies are developed for community members, such as health education, vaccination, and environmental improvement. Community members' health indicators and environmental data are continuously monitored. Prevention strategies are adjusted promptly based on real-time data to ensure their effectiveness and adaptability.

[0075] Specifically, the analysis module predicts disease risk by collecting data from the acquisition module, which helps to identify health problems early and take preventative measures. The risk assessment module calculates a risk score using the disease risk index and impact coefficient provided by the analysis module, making prevention strategies more targeted and practical. The initial prevention strategy developed by the decision-making module can be optimized and adjusted by the dynamic adjustment module based on real-time data. The dynamic adjustment module ensures that the prevention strategy remains consistent with the health status of community members and environmental changes, improving the system's flexibility and adaptability.

[0076] Specifically, such as Figure 2 As shown, the analysis module 20 includes:

[0077] The data processing unit 21 is used to clean and format the health indicators and lifestyles of the community members to obtain processing results.

[0078] The feature extraction unit 22 is connected to the data processing unit 21 and is used to extract the gender, age, exercise frequency and dietary habits of the processing results to obtain the first feature result;

[0079] The model building unit 23 is connected to the feature extraction unit 22 and is used to take the first feature result as the input parameter of the model and build the prediction model based on the historical data corresponding to the feature result and the input parameter.

[0080] Specifically, the data processing unit cleans the health indicators and lifestyle data of community members to remove incomplete, erroneous, or redundant data. The cleaned data is then formatted to ensure uniformity and consistency. The processing result should be a clean set of data with a consistent format. The feature extraction unit extracts key features from the results obtained by the data processing unit, such as gender, age, exercise frequency, and dietary habits. These features are crucial for predicting disease risk indices because they are closely related to an individual's health status. The first feature result is the output after preliminary processing and simplification of the raw data, preparing it for model building. The model building unit uses the extracted first feature result as input parameters to build a predictive model. Appropriate machine learning algorithms, such as logistic regression, decision trees, and neural networks, are selected. During model training, historical data is used to adjust the model parameters so that it can accurately predict health risk indices based on given features. The constructed model should be able to process the features provided by the feature extraction unit and output predicted values ​​of disease risk indices.

[0081] Specifically, the data processing unit cleans and formats health indicator and lifestyle data to ensure the accuracy and consistency of subsequent analysis. By removing erroneous and redundant data, data quality is improved, and the impact of misleading information on the analysis results is reduced. The feature extraction unit extracts key features, such as gender, age, exercise frequency, and dietary habits, allowing the model to focus more on factors closely related to health risks, thus improving the model's predictive efficiency and accuracy. The model building unit uses the extracted features and historical data to construct a predictive model, ensuring that the model can capture the complex relationship between health indicators and lifestyles and disease risk.

[0082] Specifically, the model building unit includes:

[0083] The feature engineering subunit is used to combine the various feature results to obtain the target feature result;

[0084] The model training subunit is connected to the feature engineering subunit to train the prediction model based on the target feature results and the historical data to obtain the training model;

[0085] The model validation subunit, connected to the model training subunit, is used to use unused data from the historical data as a validation dataset to validate the trained model based on the validation dataset in order to obtain the disease risk index of the community members.

[0086] In this embodiment, age and exercise frequency can be combined into a single feature to represent the physical activity level of people in different age groups. For example, age can be divided into several intervals (e.g., <40, 40-60, >60) and combined with exercise frequency (e.g., never exercise, <3 times per week, 3-5 times per week, >5 times per week) to create a new feature. The target feature result, such as the physical activity feature, is output. The target feature result and historical data are received. The new feature created by the feature engineering subunit is combined with the original features such as blood pressure, cholesterol levels, and BMI to form a feature matrix. A logistic regression model is selected for training. 70% of the historical data is used as the training set, and 30% as the validation set. Gradient descent optimization algorithms are used to adjust model parameters, such as learning rate and regularization strength. After training, the model performance is evaluated using the validation set, such as calculating accuracy and recall. Unused data is separated from the historical data to serve as the validation dataset, ensuring the independence and impartiality of the validation. The trained model is then evaluated using the validation dataset. It is assumed that the trained model achieves 80% accuracy on the validation dataset. Based on the validation results, further adjustments to the model parameters or selection of different models are needed, such as attempting to train and validate using Support Vector Machines (SVM) or decision trees. Finally, the validated final model is output, which is used to predict the disease risk index of community members.

[0087] Specifically, by processing and combining the first feature results through the feature engineering subunit, more informative features can be extracted, thereby improving the model's predictive accuracy. The model training subunit uses unseen data as a validation set to evaluate the model's generalization ability, avoid overfitting, and ensure good performance in practical applications. The final model validated by the model validation subunit can be used to predict the disease risk index of community members, helping medical institutions to more accurately carry out disease prevention and resource allocation, and improve the efficiency of medical resource utilization.

[0088] Specifically, the analysis module also includes:

[0089] A noise level analysis unit is used to analyze the noise level of the community to obtain a first analysis result;

[0090] An air quality assessment unit is used to detect and assess the air quality of the community to obtain assessment results;

[0091] An influence coefficient calculation unit is connected to the noise level analysis unit and the air quality assessment unit, respectively, and is used to calculate the influence coefficients of the first analysis result, the assessment result and the green coverage rate on the disease risk index.

[0092] Specifically, the noise level analysis unit uses a noise meter or sound analysis software to measure and analyze the noise level within the community, obtaining a noise level score. The air quality assessment unit uses environmental sensors to monitor air quality indicators such as PM2.5, PM10, sulfur dioxide (SO2), and nitrogen oxides (NOx), and calculates the AQI based on these indicators. The influence coefficient calculation unit uses multivariate statistical analysis methods, such as regression analysis, to determine the relationship between noise levels, air quality, and other factors (such as green coverage) and the disease risk index, and calculates their influence coefficients.

[0093] Specifically, the noise level analysis unit and the air quality assessment unit can be used to comprehensively assess the environmental health risks of a community. The impact coefficient calculation unit, by evaluating the impact coefficients of different factors on health risks, allows the community to allocate limited health resources more effectively.

[0094] Specifically, the influence coefficient calculation unit includes:

[0095] The data integration subunit is used to integrate the data collected from the noise level analysis unit and the air quality assessment unit, as well as the green coverage rate, into a unified dataset;

[0096] The feature extraction subunit, connected to the data integration subunit, is used to extract the average noise level, peak air quality index, and green coverage rate trend of the dataset to obtain the second feature result.

[0097] A data analysis subunit, connected to the feature extraction subunit, is used to analyze the relationship between the second feature extraction results to obtain a second analysis result;

[0098] An influence coefficient calculation subunit is connected to the data analysis subunit to calculate the influence coefficient based on the second analysis results and the statistical model.

[0099] Specifically, noise and air quality data are collected from the noise level analysis unit and the air quality assessment unit. Community green coverage data is also collected, including changes in green coverage at different time points. Data cleaning and preprocessing techniques are used, such as removing missing values ​​and outliers, and normalizing or standardizing the data. The processed data are then integrated into a unified dataset. The feature extraction subunit analyzes the noise data, extracting features such as the average or peak noise level. It analyzes the air quality data, extracting the peak value or other relevant features of the Air Quality Index (AQI). It analyzes the green coverage data, extracting features such as the trend or average value of green coverage. The data analysis subunit analyzes the relationships between the second feature extraction results, which may include the relationship between noise level and AQI, green coverage, or the interaction between these factors. Statistical analysis methods, such as correlation analysis and principal component analysis (PCA), are used to explore the relationships between features. The second analysis results are output for use by subsequent units. The influence coefficient calculation subunit calculates the influence coefficients of noise level, AQI, and green coverage on the disease risk index using appropriate statistical models (such as regression models) based on the second analysis results. The impact coefficient represents the relative contribution of these factors to health risk. Output the calculated impact coefficient.

[0100] Specifically, the data integration subunit ensures data integrity and consistency by integrating data from different sources into a unified dataset, providing accurate foundational data for subsequent analysis. The feature extraction subunit simplifies the data structure by extracting key features such as noise levels, air quality index, and green coverage, making subsequent data analysis more efficient and focused. The data analysis subunit reveals the intrinsic links between different environmental factors and health risks by analyzing the interrelationships between features, providing a scientific basis for developing targeted health interventions.

[0101] Specifically, the level determination module 30 includes:

[0102] The scoring calculation unit 31 is used to calculate a sub-risk score based on the disease risk index and each of the influence coefficients.

[0103] The weighting allocation unit 32 is used to assign a weight value to each of the air quality, the noise level and the green coverage rate;

[0104] The scoring correction unit 33 is connected to the scoring calculation unit 31 and the weight allocation unit 32 respectively, and is used to correct the risk score according to the sub-risk score and the weight value to obtain the target risk score.

[0105] In this embodiment, a scenario is assumed with three factors: Air Quality (AQI), noise level, and green coverage. An integrated risk score is calculated using the influence coefficients of these factors and preset weights. Assume a Disease Risk Index (DRI) of 50 (this is a hypothetical value representing a moderate level of health risk). The influence coefficient for AQI is assumed to be 1.2, meaning that for every 1 unit increase in AQI, the health risk increases by 1.2%. The influence coefficient for noise level is assumed to be 0.8, meaning that for every 1 unit increase in noise level, the health risk increases by 0.8%. The influence coefficient for green coverage is assumed to be 0.5, meaning that for every 1 unit increase in green coverage, the health risk decreases by 0.5%. Using the formula Sub-risk Score = DRI × Influence Coefficient, the sub-risk score for AQI is calculated to be 60 (50 × 1.2), the sub-risk score for noise level is 40 (50 × 0.8), and the sub-risk score for green coverage is -25 (50 × -0.5). Assign a weight of 33.3% each to AQI, noise level, and green coverage (assuming they are equally important). Therefore, the weight of AQI is 19.8 (60 × 0.333), the weight of noise level is 13.3 (40 × 0.333), and the weight of green coverage is -8.3 (-25 × 0.333). Combine the sub-risk scores and weights to obtain the corrected risk score. Corrected risk score = (AQI sub-risk score + noise level sub-risk score + green coverage sub-risk score) / 3 Corrected risk score = (60 + 40 - 25) / 3 = 25.

[0106] In this example, the adjusted risk score is a comprehensive score that takes into account the weights and influence coefficients of all three factors. This score can be used to assess the health risks of community members and guide the development of health interventions.

[0107] Specifically, the scoring calculation unit provides a quantitative risk assessment by multiplying a disease risk index by a specific environmental impact coefficient, helping to understand the contribution of each factor to health risk. The weighting unit, by assigning different weights to air quality, noise levels, and green coverage, reflects the relative importance of these factors in the health risk assessment. This helps ensure the fairness and accuracy of the assessment results. The scoring correction unit, by combining sub-risk scores with their respective weight values, provides a health risk score that balances the influence of each factor. This helps community members understand how their environment affects their health.

[0108] Specifically, the level determination module also includes:

[0109] A threshold setting unit is used to set the risk score threshold;

[0110] A scoring comparison unit, connected to the threshold setting unit, is used to compare the target risk score and the risk score threshold to obtain a comparison result;

[0111] A rating determination unit, connected to the rating comparison unit, is used to determine the risk rating level based on the comparison result.

[0112] Specifically, the threshold setting unit is responsible for determining the thresholds for the risk score. These thresholds are typically based on public health standards, historical data analysis, and expert opinions. For example, a community might set a threshold, such as 80 points, as a cutoff point for health risk; exceeding this score is considered high risk. The scoring comparison unit receives the target risk score and compares it to the threshold. A comparison operation (such as greater than, less than, or equal to) is used to determine the target risk score's position relative to the threshold. For example, if the target risk score is 90 points and the threshold is 80 points, the comparison result would be "greater than". The grading unit determines the risk score grading based on the comparison result. It uses a predefined grading system, such as low risk (0-50 points), medium risk (51-80 points), and high risk (81-100 points). For example, if the comparison result is "greater than", the target risk score is classified as high risk.

[0113] Specifically, the scoring comparison unit compares the risk score threshold set by the threshold setting unit with the target risk score, helping the community accurately identify high-risk groups and thus more effectively implement health interventions. Based on the comparison results, the grading unit can classify residents' risk scores into grades, providing clear health risk level labels. This helps enhance residents' health awareness and encourages them to take appropriate preventative measures.

[0114] Specifically, the level determination unit includes:

[0115] A threshold parsing subunit is used to parse the risk scoring threshold to obtain the parsing result;

[0116] A level division subunit, connected to the threshold analysis subunit, is used to divide the target risk score into three levels: low risk, medium risk, and high risk based on the comparison result and the analysis result;

[0117] The risk level determination subunit is connected to the risk level division subunit and is used to determine the risk level of the division.

[0118] Specifically, the threshold parsing subunit parses the set risk score threshold for subsequent use.

[0119] For example, it might convert the threshold into a percentage or compare it with historical data to determine the appropriateness of the threshold. The grading subunit categorizes the target risk score into three levels: low risk, medium risk, and high risk, based on the comparison results and the analysis results of the threshold analysis subunit. For example, if the threshold is 80%, then a risk score of 80% or less is classified as low risk, greater than 80% but less than or equal to 90% as medium risk, and greater than 90% as high risk. The grading determination subunit finalizes the risk level classification and takes corresponding actions. For example, for low-risk individuals, regular monitoring might be recommended; for medium-risk individuals, enhanced personal protective measures might be recommended; and for high-risk individuals, immediate vaccination and isolation measures might be recommended to prevent virus transmission.

[0120] Specifically, the threshold parsing subunit ensures that the risk score thresholds are accurately understood and applied. The grading subunit provides a clear framework for quickly identifying and responding to risks of varying degrees by dividing the risk score into low, medium, and high levels. The grading determination subunit performs the final judgment based on the information provided by the grading subunit and determines the risk level of the target. This helps ensure the reliability of the system's output and can serve as the basis for developing risk response strategies.

[0121] Specifically, such as Figure 4 As shown, the dynamic adjustment module 50 includes:

[0122] Data acquisition unit 51 is used to detect the health indicators of the community members and community environmental data in real time to obtain real-time data;

[0123] The data analysis unit 52 is connected to the data acquisition unit 51 and is used to analyze the real-time data to identify the changing trends of the health indicators and the lifestyle to obtain a third analysis result.

[0124] The strategy evaluation unit 53 is connected to the data analysis unit 52 and is used to determine whether the initial prevention strategy needs to be adjusted based on the third analysis result.

[0125] Specifically, the data acquisition unit includes various sensors, health monitoring devices, and community environmental monitoring systems. For example, wearable devices can be used to monitor health indicators such as heart rate, blood pressure, and step count of community members. Environmental data can come from air quality monitors, noise level recorders, and green coverage survey tools. The data analysis unit is a data processing and analysis software program responsible for processing the collected real-time data. For example, statistical analysis and machine learning algorithms can be used to analyze trends in health indicators and environmental data. Analysis results can include trend charts, statistical reports, and predictive models to help the community understand changes in risk. The strategy evaluation unit can assess the effectiveness of existing prevention strategies based on the analysis results. For example, decision trees or logical judgment rules can be used to determine whether adjustments to prevention strategies are needed. If the analysis shows that trends in health indicators or lifestyle require new or modified strategies, the strategy evaluation unit will provide recommendations.

[0126] Specifically, through real-time monitoring by the data acquisition unit and data analysis by the data analysis unit, communities can more effectively manage health risks and take timely measures to reduce them. The strategy evaluation unit can assess the effectiveness of existing prevention strategies and adjust them as needed, helping to ensure that prevention strategies are aligned with current health risks and lifestyle changes, thereby improving the targeting and effectiveness of interventions.

[0127] Specifically, the strategy evaluation unit includes:

[0128] The effect tracking subunit is used to track and record the effect of the initial prevention strategy after its implementation to obtain the initial effect;

[0129] An effect comparison subunit, connected to the effect tracking subunit, is used to compare the initial effect with the preset target effect to obtain a comparison result;

[0130] The strategy adjustment subunit is connected to the effect comparison subunit to determine whether to adjust the initial prevention strategy based on the comparison results.

[0131] Specifically, the effect tracking subunit collects data on the effectiveness of the prevention strategy through regular health checks, questionnaires, and wearable device data. For example, regular health checks can be set up to monitor changes in specific health indicators (such as weight and blood sugar levels), and this data can be recorded to evaluate the effectiveness of the strategy. The effect comparison subunit compares the initial effect with the pre-set target effect. For example, charts or reports can be used to show the difference between the initial effect and the target effect, and to calculate the percentage or absolute value of the improvement. The comparison results can help the community understand the short-term and long-term effects of the strategy implementation. The strategy adjustment subunit determines whether the initial prevention strategy needs to be adjusted based on the comparison results. For example, if the comparison results show that the strategy has not achieved the expected goal, the strategy adjustment subunit can make modification suggestions, such as changing the intensity, duration, or target population of the intervention. If the effect exceeds expectations, the strategy adjustment subunit can recommend maintaining or enhancing the current strategy, and may recommend expanding the scope of implementation.

[0132] In this embodiment, the community launched an obesity prevention program, which included providing healthy eating guidance and increasing physical activity. After the program was implemented, the community health center began tracking participants' weight changes. At the start of the program, the average weight of the 100 participants was 70 kg. After six months of program implementation, data collected showed that the average weight had decreased to 68 kg. The pre-set target effect was to reduce the participants' average weight by 2 kg through the program. The results showed that the participants' average weight actually decreased by 2 kg, achieving the pre-set target effect. Since the participants' average weight decreased by 2 kg, achieving the pre-set target, the strategy adjustment subunit might recommend maintaining the current prevention strategy and considering extending the successful experience to more community members. If the average weight loss is less than 2 kg, the strategy adjustment subunit might recommend enhancing the personalization of dietary guidance or increasing the frequency and intensity of physical activity to improve weight loss results.

[0133] Specifically, the effect tracking subunit ensures that prevention strategies are truly implemented by tracking data and monitors changes in participants' health indicators, providing objective data for subsequent evaluation. The results from the effect comparison subunit prevent resource waste, focusing resources and attention on the most effective interventions. The strategy adjustment subunit's method of adjusting strategies based on actual effects ensures effective resource utilization, improves the targeting and effectiveness of prevention strategies, and thus better protects the health of community members.

[0134] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0135] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A community online intelligent analysis system based on health big data, characterized in that, include: The information collection module is used to collect health indicators and lifestyles of community members, as well as environmental data of the community. Based on the health indicators, lifestyles, and environmental data, it obtains corresponding historical data, including green area, community area, noise level, and air quality. An analysis module, connected to the acquisition module, is used to predict the disease risk index of community members based on the health indicators and the lifestyle; calculate the green coverage rate of the community based on the green area and the community area; and analyze the influence of the green coverage rate, the noise level, and the air quality on the disease risk index to obtain an influence coefficient. The risk rating module, connected to the analysis module, is used to calculate the risk score of the infectious disease based on the disease risk index and the influence coefficient to obtain the target risk score. The risk score level is determined based on the target risk score and the preset risk score threshold. The decision-making module, connected to the level determination module, is used to formulate initial prevention strategies for the community members based on the risk score level. A dynamic adjustment module, connected to the decision-making module, is used to detect the health indicators of community members and the environmental data of the community in real time to obtain real-time data, and dynamically adjust the initial prevention strategy based on the real-time data. The analysis module also includes: A noise level analysis unit is used to analyze the noise level of the community to obtain a first analysis result; An air quality assessment unit is used to detect and assess the air quality of the community to obtain assessment results; An influence coefficient calculation unit is connected to the noise level analysis unit and the air quality assessment unit respectively, and is used to calculate the influence coefficients of the first analysis result, the assessment result and the green coverage rate on the disease risk index. The level determination module includes: A scoring calculation unit is used to calculate a sub-risk score based on the disease risk index and each of the influence coefficients; A weighting allocation unit is used to assign a weight value to each of the air quality, the noise level, and the green coverage rate. A scoring correction unit, connected to the scoring calculation unit and the weight allocation unit respectively, is used to correct the risk score according to the sub-risk score and the weight value to obtain a target risk score; the dynamic adjustment module includes: The data acquisition unit is used to detect the health indicators of the community members and the community environment data in real time to obtain real-time data; A data analysis unit, connected to the data acquisition unit, is used to analyze the real-time data to identify the changing trends of the health indicators and the lifestyle in order to obtain a third analysis result; The strategy evaluation unit, connected to the data analysis unit, is used to determine whether the initial prevention strategy needs to be adjusted based on the third analysis results.

2. The community online intelligent analysis system based on health big data according to claim 1, characterized in that, The analysis module includes: The data processing unit is used to clean and format the health indicators and lifestyles of the community members to obtain processing results. A feature extraction unit, connected to the data processing unit, is used to extract the gender, age, exercise frequency, and dietary habits of the processing results to obtain a first feature result; The model building unit, connected to the feature extraction unit, is used to take the first feature result as the input parameter of the model and build the prediction model based on the historical data corresponding to the feature result and the input parameter.

3. The community online intelligent analysis system based on health big data according to claim 2, characterized in that, The model building unit includes: The feature engineering subunit is used to combine the various feature results to obtain the target feature result; The model training subunit is connected to the feature engineering subunit to train the prediction model based on the target feature results and the historical data to obtain the training model; The model validation subunit, connected to the model training subunit, is used to use unused data from the historical data as a validation dataset to validate the trained model based on the validation dataset in order to obtain the disease risk index of the community members.

4. The community online intelligent analysis system based on health big data according to claim 1, characterized in that, The influence coefficient calculation unit includes: The data integration subunit is used to integrate the data collected from the noise level analysis unit and the air quality assessment unit, as well as the green coverage rate, into a unified dataset; The feature extraction subunit, connected to the data integration subunit, is used to extract the average noise level, peak air quality index, and green coverage rate trend of the dataset to obtain the second feature result. A data analysis subunit, connected to the feature extraction subunit, is used to analyze the relationship between the second feature extraction results to obtain a second analysis result; An influence coefficient calculation subunit is connected to the data analysis subunit to calculate the influence coefficient based on the second analysis results and the statistical model.

5. The community online intelligent analysis system based on health big data according to claim 1, characterized in that, The level determination module also includes: A threshold setting unit is used to set the risk score threshold; A scoring comparison unit, connected to the threshold setting unit, is used to compare the target risk score and the risk score threshold to obtain a comparison result; A rating determination unit, connected to the rating comparison unit, is used to determine the risk rating level based on the comparison result.

6. The community online intelligent analysis system based on health big data according to claim 5, characterized in that, The level determination unit includes: A threshold parsing subunit is used to parse the risk scoring threshold to obtain the parsing result; A level division subunit, connected to the threshold analysis subunit, is used to divide the target risk score into three levels: low risk, medium risk, and high risk based on the comparison result and the analysis result; The risk level determination subunit is connected to the risk level division subunit and is used to determine the risk level of the division.

7. The community online intelligent analysis system based on health big data according to claim 1, characterized in that, The strategy evaluation unit includes: The effect tracking subunit is used to track and record the effect of the initial prevention strategy after its implementation to obtain the initial effect; An effect comparison subunit, connected to the effect tracking subunit, is used to compare the initial effect with the preset target effect to obtain a comparison result; The strategy adjustment subunit is connected to the effect comparison subunit to determine whether to adjust the initial prevention strategy based on the comparison results.

Images