Public health epidemic situation prevention and control system based on big data analysis

Abstract

The invention discloses a public health epidemic situation prevention and control system based on big data analysis, relates to the technical field of public health epidemic situation prevention and control, can collect and fuse epidemic situation related information in real time by integrating data sources of hospitals, social media and meteorological departments, and reduces the problem of data lag in a traditional monitoring system. Through fusion of social media data and weather and environment data, early warning of the epidemic situation is more accurate, so that the risk of potential epidemic situation outbreak can be predicted in advance, and the response time is greatly shortened. According to the system, through the data acquisition and preprocessing module and the data fusion and feature extraction module, useful features can be extracted from original data from different sources, and intelligent analysis is carried out. And the risk assessment and hotspot region identification module generates a comprehensive risk index RI based on a prediction result of epidemic situation propagation in combination with various factors such as an environmental pollution index EPI and population flow data Rk, and provides decision support for government departments.

Description

Technical Field

[0001] The present invention relates to the technical field of public health epidemic prevention and control, and specifically to a public health epidemic prevention and control system based on big data analysis. Background Art

[0002] With the acceleration of the globalization process and the increase in population mobility, the risk of infectious disease transmission is increasing day by day, and timely and effective epidemic prevention and control is particularly important. In this context, the application of big data technology provides a new solution for epidemic prevention and control. By integrating various data sources such as hospitals, social media, weather, and environmental monitoring, an epidemic monitoring platform can be effectively constructed, which can use big data analysis technology to track and predict the spread trend of the epidemic in real time.

[0003] Currently, traditional epidemic prevention and control systems usually rely on data from a single source, mainly relying on hospital case reports, investigation reports of public health institutions, and epidemic bulletins released by some governments. The biggest problem with this model lies in the timeliness and comprehensiveness of the data. The case information reported by hospitals is often lagged, while the epidemic-related information on social media and the Internet is often ignored, but these data can actually provide early warning signals.

[0004] With the popularization of social media, smartphones, and other Internet of Things devices, the public's epidemic-related dynamics are updated in real time, often exposing the spread trend of the epidemic earlier than traditional epidemic bulletin systems. When dealing with the epidemic, due to the lag and incompleteness of the data, it often leads to decision-making mistakes or slow responses, missing the best prevention and control opportunities. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a public health epidemic prevention and control system based on big data analysis, which solves the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A public health epidemic prevention and control system based on big data analysis includes a data collection and preprocessing module, a data fusion and feature extraction module, an epidemic spread prediction module, a risk assessment and hot spot area identification module, a decision support and emergency response module, and a dynamic feedback and optimization module;

[0007] The data collection and preprocessing module is responsible for collecting raw data from hospitals, social media, and meteorological departments and performing preprocessing to obtain an epidemic prevention data set FYW;

[0008] The feature extraction module extracts features from the epidemic prevention data set FYW, including the emotional fluctuation features related to the epidemic in social media and the association features between air pollution and respiratory diseases, to form a health feature set F;

[0009] The epidemic transmission prediction module uses the susceptible-infected-recovered model to predict the trend of epidemic transmission through the epidemic prevention data set FYW and the health feature set F, analyzes the impacts of population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on epidemic spread, and obtains the prediction results.

[0010] Based on the prediction results, the risk assessment and hotspot area identification module combines the epidemic density Iden, population mobility data Rk, and environmental pollution index EPI to identify the risk areas of the current epidemic and evaluate them to obtain the comprehensive risk index RI.

[0011] The decision support and emergency response module provides decision support for public health institutions according to the comprehensive risk index RI and formulates prevention and control measures.

[0012] During the epidemic prevention and control process, the dynamic feedback and optimization module monitors the effects of prevention and control measures in real time and adjusts strategies through data feedback.

[0013] Preferably, the data collection and preprocessing module includes a data collection unit and a data cleaning and standardization unit.

[0014] The collection unit collects raw data from multiple data sources such as hospitals, social media, and meteorological departments, including electronic health records EHR, population mobility data Rk, sentiment analysis data SQ, temperature data TE, humidity data HU, and air quality data AQ.

[0015] Among them, the electronic health records EHR are obtained through the hospital information management system and include the incidence of respiratory diseases DiseaseRate; the population mobility data Rk is obtained by the ratio of the number of people flowing within the region to the total area of the region.

[0016] The sentiment analysis data SQ includes scraping epidemic-related posts from social media platforms, conducting sentiment analysis, and classifying each post into positive sentiment, negative sentiment, and neutral sentiment through NLP technology, and assigning numerical values to positive sentiment, negative sentiment, and neutral sentiment, specifically: positive sentiment is +1, negative sentiment is -1, and neutral sentiment is 0.

[0017] The sentiment analysis data SQ is obtained through the following formula:

[0018] ;

[0019] In the formula, Si represents the i-th social media post, and n represents the total number of posts analyzed.

[0020] The temperature data TE and humidity data HU are obtained through temperature sensors and humidity sensors respectively.

[0021] The air quality data AQ is obtained through the following formula:

[0022] ;

[0023] Wherein, cPM2.5, cCO and cNO2 respectively represent the concentrations of airborne particulate matter PM2.5, carbon monoxide CO and nitrogen dioxide NO2, IPM2.5, ICO and INO2 respectively represent the pollutant standardization indices of the concentrations of airborne particulate matter PM2.5, carbon monoxide CO and nitrogen dioxide NO2, and max represents taking the peak value in the numerical values;

[0024] The data cleaning and standardization unit cleans and standardizes the raw data collected by the data acquisition unit to obtain the epidemic prevention data set FYW;

[0025] Cleaning includes removing noise and invalid information in the raw data through the use of filters, including missing values and outliers;

[0026] The standardization process unifies the dimension scale of the raw data through the use of the standardization method.

[0027] Preferably, the feature extraction module includes a social media sentiment fluctuation feature extraction unit and an air pollution and respiratory disease association feature extraction unit;

[0028] The social media sentiment fluctuation feature extraction unit extracts sentiment fluctuation features according to the sentiment analysis data SQ, analyzes the change trend of the public opinion related to the epidemic; calculates and obtains the sentiment fluctuation index EVI and the sentiment change trend ET;

[0029] The sentiment fluctuation index EVI is obtained through the following formula:

[0030] ;

[0031] Wherein, N represents the total time period, SQti represents the value of the sentiment analysis data at the time point ti, and PSQ represents the average value of the sentiment analysis data;

[0032] The sentiment change trend ET is obtained through the following formula:

[0033] ;

[0034] Wherein, SQ(qi) represents the value of the sentiment analysis data at the time qi, and SQ(pi) represents the value of the sentiment analysis data at the time pi.

[0035] Preferably, the respiratory disease association feature extraction unit calculates and obtains the pollution and health association index PHI according to the association between the air quality data AQ and the electronic health record EHR, specifically by combining the air quality data AQ and the respiratory disease incidence rate DiseaseRate;

[0036] The pollution and health correlation index PHI is obtained through the following formula:

[0037] ;

[0038] In the formula, ln represents the natural logarithm function;

[0039] The obtained emotional fluctuation index EVI, emotional change trend ET, and pollution and health correlation index PHI are combined to obtain the health feature set F.

[0040] Preferably, the epidemic transmission prediction module includes an SIR model construction and parameter estimation unit and an influencing factor analysis and transmission trend adjustment unit;

[0041] The SIR model construction and parameter estimation unit constructs an epidemic transmission mathematical model based on the epidemic prevention data set FYW and the health feature set F according to the susceptible-infected-recovered model, analyzes the change trends of the number S of susceptible people, the number I of infected people, and the number R of recovered people, predicts the trend of future epidemic transmission, and obtains the number S(t) of susceptible people, the number I(t) of infected people, and the number R(t) of recovered people at the future time point t;

[0042] By analyzing the population flow data Rk, air quality data AQ, and sentiment analysis data SQ, the parameters of the epidemic transmission mathematical model are estimated, including the infection rate β and the recovery rate γ;

[0043] Specifically, the population flow data Rk reflects the movement of people between different regions and affects the transmission speed and range of the virus; high population mobility regions lead to an increase in the infection rate β because more people coming into contact increases the possibility of transmission; by analyzing the population flow frequency, flow pattern, and flow volume, the transmission potential of the region can be deduced, thereby affecting the estimation of the β value.

[0044] Fine particulate matter and air pollutants affect people's respiratory health; when the air quality is poor, people's immune systems are easily affected, thus exacerbating the spread of diseases; regions with higher pollutant concentrations will lead to an increase in the infection rate β, so β can be deduced by analyzing the correlation between the air quality index and the infection rate.

[0045] The sentiment analysis data SQ in social media can reveal people's emotional reactions to the epidemic. When people are panicked about the epidemic, it leads to more frequent social contacts and unnecessary gatherings, thus increasing the chance of virus transmission; by analyzing the relationship between emotional fluctuations and the infection rate, the β value can be further adjusted.

[0046] The speed and frequency of population movement affect the speed of epidemic recovery; in places with less population movement, prevention and control measures are easier to implement, which may lead to a faster recovery; while in areas with frequent population movement, infected individuals may not be isolated in a timely manner, and the recovery speed may slow down; therefore, the population movement situation can help estimate the recovery rate γ.

[0047] The impact of air quality on the health status of the population will affect the recovery process. Poor air quality makes patients with chronic diseases more susceptible and prolongs the recovery time; areas with severe air pollution may affect the recovery rate γ and cause it to decrease.

[0048] Sentiment analysis data SQ reflects the public's perception and response to the epidemic; when the mood tends to be negative, people will ignore prevention and control measures and delay treatment, which will affect the recovery speed; therefore, emotional fluctuations can also have a certain impact on the recovery rate γ.

[0049] The number of susceptible individuals S(t) at the time point t is obtained through the following formula:

[0050] ;

[0051] In the formula, represents the influence coefficient of temperature data TE and humidity data HU on the spread of the epidemic, represents the influence coefficient of the j-th feature in the health feature set F on the spread of the epidemic, Fj represents the j-th feature in the health feature set F, and m represents the total number of features in the health feature set F;

[0052] The number of infected individuals I(t) at the time point t is obtained through the following formula:

[0053] ;

[0054] The number of recovered individuals R(t) at the time point t is obtained through the following formula:

[0055] .

[0056] Preferably, the influence factor analysis and transmission trend adjustment unit analyzes the influence of population movement data Rk, air quality data AQ, and sentiment analysis data SQ on the spread of the epidemic, and substitutes them into the epidemic transmission mathematical model to adjust the epidemic transmission trend, obtains the adjusted infection rate βadj and the adjusted recovery rate γadj, substitutes them into the epidemic transmission mathematical model, and re-predicts the number of susceptible individuals S(t), the number of infected individuals I(t), and the number of recovered individuals R(t) at the future time point t;

[0057] The adjusted infection rate βadj is obtained through the following formula;

[0058] ;

[0059] In the formula, respectively represent the influence coefficients of the population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on the infection rate β;

[0060] The adjusted recovery rate γadj is obtained through the following formula;

[0061] ;

[0062] In the formula, respectively represent the influence coefficients of the population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on the recovery rate γ.

[0063] Preferably, the risk assessment and hot spot area identification module includes a risk assessment unit and a hot spot area identification and dynamic update unit;

[0064] The risk assessment unit calculates and obtains the comprehensive risk index RI based on the number of infected people I(t) at the future time point t provided by the epidemic transmission prediction module, combined with the epidemic density Iden, population mobility data Rk, and environmental pollution index EPI, and compares it with the preset risk threshold TRI to evaluate the epidemic risk of the region;

[0065] The severity of the epidemic in the region is estimated by calculating the epidemic density Iden of the infected population;

[0066] The epidemic density Iden is obtained through the following formula:

[0067] ;

[0068] In the formula, mA represents the area of the region;

[0069] The environmental pollution index EPI is calculated through the air quality data AQ;

[0070] The environmental pollution index EPI is obtained through the following formula:

[0071] ;

[0072] In the formula, M represents the total number of pollutants, represents the weight coefficient of the ia-th pollutant, and AQia represents the air quality data of the ia-th pollutant;

[0073] The comprehensive risk index RI is obtained through the following formula:

[0074] ;

[0075] In the formula, respectively represent the preset weight values of the epidemic density Iden, the population mobility data Rk, and the environmental pollution index EPI, and ;

[0076] The epidemic risk of the area is obtained through the following matching method:

[0077] When the comprehensive risk index RI ≤ the risk threshold TRI, it means that the epidemic risk in the area is normal;

[0078] When the comprehensive risk index RI > the risk threshold TRI, it means that the epidemic risk in the area is abnormal.

[0079] Preferably, the hot spot area identification and dynamic update unit identifies the epidemic hot spot areas according to the comprehensive risk index RI of the area, and updates the comprehensive risk index RI of each area in real time, and dynamically adjusts the identification of the epidemic hot spots;

[0080] Sort the comprehensive risk index RI of each obtained area, and mark the area with the comprehensive risk index RI > the risk threshold TRI as the hot spot area K, indicating that the risk of this area is abnormal;

[0081] Fit all the hot spot areas K to form a hot spot set HArea = {Area(K)|RI(K) > TRI};

[0082] In the formula, RI(K) represents the comprehensive risk index of the Kth hot spot area, and Area(K) represents the Kth hot spot area, specifically indicating the area with abnormal risk;

[0083] Update the comprehensive risk index RI of the hot spot area K at a fixed period to track the trend of the epidemic change; ensure the timely response of the identification of the hot spot area and the prevention and control measures.

[0084] Preferably, the decision-making support and emergency response module includes a decision-making support unit and an emergency response unit;

[0085] The decision-making support unit divides the epidemic risk of the area into a first level and a second level according to the preset risk threshold TRI, and provides prevention and control measures for each hot spot area K;

[0086] When the comprehensive risk index RI ≤ the risk threshold TRI, it is marked as the first level, which means that the area does not belong to the hot spot area K, and the epidemic risk in the area is normal, maintaining the normal prevention and control measures, and conducting regular monitoring and reporting;

[0087] When the comprehensive risk index RI > the risk threshold TRI, it is marked as the second level, which means that the epidemic risk in the hot spot area K is abnormal, and prevention and control measures are provided, including implementing lockdown measures, isolating the infected, and adjusting the allocation of medical resources;

[0088] The emergency response unit formulates an emergency response plan according to the prevention and control measures provided by the decision support unit, including resource allocation, personnel scheduling, and emergency measures;

[0089] Among them, resource allocation includes hospital bed allocation, ambulance allocation, testing equipment allocation, and personal protective equipment allocation;

[0090] Personnel scheduling includes assigning relevant personnel to areas with abnormal epidemic risks for epidemic monitoring and prevention and control;

[0091] Emergency measures include temporarily setting up epidemic prevention and control points, strengthening the dissemination of epidemic information, and health education for residents.

[0092] Preferably, the dynamic feedback and optimization module includes a prevention and control effect monitoring unit and a strategy adjustment unit;

[0093] The prevention and control effect monitoring unit obtains real-time epidemic data and the implementation status of prevention and control measures, including the number of infected people I, the number of recovered people R, the number of deceased people, and the implementation intensity of prevention and control measures, including the implementation degree of lockdown, testing, and isolation, and measures the prevention and control effect through the infection rate β and the recovery rate γ to determine whether the prevention and control measures are effective; if the infection rate does not decrease significantly or the cure rate does not increase significantly, it indicates that there may be problems with the prevention and control measures and need to be adjusted.

[0094] The strategy adjustment unit calculates and identifies whether the current prevention and control measures achieve the expected effect based on the feedback provided by the prevention and control effect monitoring unit, obtains the epidemic control index YZ, and compares it with the preset epidemic control threshold TYZ to determine the effect of the prevention and control measures;

[0095] The epidemic control index YZ is obtained by using a weighted algorithm for the infection rate β and the recovery rate γ;

[0096] The effect of the prevention and control measures is obtained by matching in the following way:

[0097] When the epidemic control index YZ ≥ the epidemic control threshold TYZ, it indicates that the prevention and control measures are effective;

[0098] When the epidemic control index YZ < the epidemic control threshold TYZ, it indicates that the prevention and control measures are ineffective, readjust the prevention and control measures, and formulate a new emergency response plan.

[0099] The present invention provides a public health epidemic prevention and control system based on big data analysis, having the following beneficial effects:

[0100] (1)When the system is running, by integrating data sources from hospitals, social media, and meteorological departments, the system can collect and fuse epidemic-related information in real time, reducing the problem of data lag in traditional monitoring systems. The integration of social media data with weather and environmental data makes early epidemic warnings more accurate, enabling the prediction of the risk of potential epidemic outbreaks in advance and greatly shortening the response time. Through the data collection and preprocessing module and the data fusion and feature extraction module, this system can extract useful features from raw data from different sources and conduct intelligent analysis. This approach helps prevention and control agencies comprehensively understand the development trend of the epidemic, while identifying potential factors triggering the epidemic, providing strong support for formulating more precise and flexible prevention and control measures.

[0101] Based on the prediction results of epidemic spread, the risk assessment and hotspot area identification module combines various factors such as the environmental pollution index EPI and population flow data Rk to accurately identify high-risk areas of the epidemic and generate a comprehensive risk index RI, providing decision-making support for government departments.

[0102] (2)Through the air pollution and respiratory disease association feature extraction unit, combined with the pollution and health association index PHI, the system analyzes the relationship between air quality and the occurrence of respiratory diseases. Through regression analysis, the system can reveal the correlation between pollutant concentration and respiratory diseases, thus providing a more accurate health risk assessment for epidemic prevention and control. Especially in the case of increased population mobility and aggravated environmental pollution, the system can predict the potential threats of environmental factors to health and timely adjust prevention and control strategies to reduce the epidemic risk caused by aggravated pollution.

[0103] Through the epidemic spread prediction module and the risk assessment and hotspot area identification module, the system combines multi-dimensional data such as sentiment analysis, air quality, and population flow to accurately predict the epidemic spread trend and identify high-risk areas.

[0104] (3)By constructing an SIR model and combining the epidemic prevention data set FYW and the health feature set F, this module can accurately predict the number of susceptible, infected, and recovered populations at different time points, providing detailed data on the epidemic spread trend. This prediction method based on the SIR model can more scientifically reflect the dynamic changes of epidemic spread compared with traditional empirical prediction methods, avoiding the errors brought by overly simple linear models. By predicting the number of susceptible, infected, and recovered populations at future time points, the government and public health agencies can timely adjust prevention and control strategies to ensure the accuracy and timeliness of prevention and control measures.

[0105] (4) Through the calculated comprehensive risk index RI, this module can identify and mark in real time areas with relatively high epidemic risks. When the RI value exceeds the preset risk threshold TRI, it indicates that there is a relatively high risk of epidemic transmission in this area, and prevention and control measures must be taken as a priority. The risk assessment process combines multi-dimensional factors such as epidemic transmission data, population mobility, and environmental pollution, improving the accuracy of risk assessment. The introduction of the environmental pollution index EPI, especially the impact of air quality on the epidemic, provides a quantitative analysis of the potential environmental factors for epidemic transmission. Through such comprehensive analysis, the system can better evaluate areas with heavy pollution and dense population mobility, which are often prone to becoming high-risk areas for epidemic spread. By deeply integrating environmental and epidemic data, the spread of the epidemic can be predicted and prevented more accurately. Description of the Drawings

[0106] Figure 1 It is a schematic diagram of the block diagram process of a public health epidemic prevention and control system based on big data analysis according to the present invention. Detailed Embodiments

[0107] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0108] Embodiment 1

[0109] The present invention provides a public health epidemic prevention and control system based on big data analysis. Please refer to Figure 1 , which includes a data collection and preprocessing module, a data fusion and feature extraction module, an epidemic transmission prediction module, a risk assessment and hotspot area identification module, a decision support and emergency response module, and a dynamic feedback and optimization module;

[0110] The data collection and preprocessing module is responsible for collecting raw data from hospitals, social media, and meteorological departments and performing preprocessing to obtain the epidemic prevention data set FYW;

[0111] The feature extraction module extracts features from the epidemic prevention data set FYW, including the emotional fluctuation features related to the epidemic in social media and the correlation features between air pollution and respiratory diseases, to form the health feature set F;

[0112] The epidemic transmission prediction module uses the epidemic prevention data set FYW and the health feature set F to predict the trend of epidemic transmission using the susceptible-infected-recovered model, analyzes the impact of population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on epidemic spread, and obtains the prediction result;

[0113] The risk assessment and hot spot area identification module, based on the prediction results, combines the epidemic density Iden, population flow data Rk, and environmental pollution index EPI to identify the risk areas of the current epidemic and evaluate them to obtain the comprehensive risk index RI.

[0114] The decision-making support and emergency response module provides decision-making support for public health institutions according to the comprehensive risk index RI and formulates prevention and control measures.

[0115] The dynamic feedback and optimization module monitors the effectiveness of the prevention and control measures in real time during the epidemic prevention and control process and adjusts the strategy through data feedback.

[0116] In this embodiment, by integrating data sources from hospitals, social media, and meteorological departments, the system can collect and fuse epidemic-related information in real time, reducing the problem of data lag in traditional monitoring systems. The integration of social media data with weather and environmental data makes the early warning of the epidemic more accurate, enabling the prediction of the risk of potential epidemic outbreaks in advance and greatly shortening the response time. Through the data acquisition and preprocessing module and the data fusion and feature extraction module, the system can extract useful features from the raw data of different sources and perform intelligent analysis. This approach helps the prevention and control agencies comprehensively understand the development trend of the epidemic, identify potential epidemic triggering factors, and provide strong support for formulating more accurate and flexible prevention and control measures.

[0117] Based on the prediction results of the epidemic spread, the risk assessment and hot spot area identification module combines various factors such as the environmental pollution index EPI and population flow data Rk to accurately identify the high-risk areas of the epidemic and generate the comprehensive risk index RI, providing decision-making support for government departments. Through this refined risk assessment, prevention and control measures can be more precisely deployed, avoiding resource waste and over-prevention. At the same time, real-time risk assessment and hot spot area identification help public health institutions efficiently allocate resources in the face of the epidemic, focusing medical resources and testing resources on the most urgent areas, further improving the epidemic response effect.

[0118] Through the dynamic feedback and optimization module, the system can monitor the effectiveness of the prevention and control measures in real time and adjust the strategy based on real-time data feedback. This mechanism can timely identify problems in the prevention and control measures, avoid the lag of prevention and control strategies, and ensure the effectiveness of the prevention and control measures at different epidemic stages. According to different data feedback, the prevention and control measures can be flexibly adjusted to improve the accuracy and timeliness of the prevention and control response and reduce the risk of epidemic spread.

[0119] Through the feature extraction module and the epidemic transmission prediction model, the system can dynamically adjust the prevention and control strategies and resource allocation according to different epidemic development trends and characteristics. This strategy optimization based on big data analysis enables the prevention and control measures to adapt to different stages and emergencies of the epidemic, improves the adaptability and sustainability of the prevention and control measures, and ensures the long-term effective implementation of the prevention and control work.

[0120] Example 2

[0121] This example is an explanatory note based on Example 1. Please refer to Figure 1 , specifically: The data collection and preprocessing module includes a data collection unit and a data cleaning and standardization unit;

[0122] The collection unit collects raw data from multiple data sources such as hospitals, social media, and meteorological departments, including electronic health records EHR, population mobility data Rk, sentiment analysis data SQ, temperature data TE, humidity data HU, and air quality data AQ;

[0123] Among them, the electronic health record EHR is obtained through the hospital information management system and includes the incidence of respiratory diseases DiseaseRate; the population mobility data Rk is obtained by the ratio of the number of people flowing in the region to the total area of the region;

[0124] The sentiment analysis data SQ includes scraping epidemic-related posts from social media platforms, conducting sentiment analysis, and classifying each post into positive sentiment, negative sentiment, and neutral sentiment through NLP technology, and assigning values to positive sentiment, negative sentiment, and neutral sentiment. Specifically: positive sentiment is +1, negative sentiment is -1, and neutral sentiment is 0;

[0125] The sentiment analysis data SQ is obtained through the following formula:

[0126] ;

[0127] In the formula, Si represents the i-th social media post, and n represents the total number of posts analyzed;

[0128] The temperature data TE and the humidity data HU are obtained through a temperature sensor and a humidity sensor respectively;

[0129] The air quality data AQ is obtained through the following formula:

[0130] ;

[0131] Wherein, cPM2.5, cCO, and cNO2 respectively represent the air particulate matter concentration PM2.5, carbon monoxide CO, and nitrogen dioxide NO2, IPM2.5, ICO, and INO2 respectively represent the pollutant standardization indices of the air particulate matter concentration PM2.5, carbon monoxide CO, and nitrogen dioxide NO2, and max represents taking the peak value in the numerical values;

[0132] The data cleaning and standardization unit cleans and standardizes the raw data collected by the data acquisition unit to obtain the epidemic prevention data group FYW;

[0133] Cleaning includes removing noise and invalid information in the raw data through the use of a filter, including missing values and outliers;

[0134] The standardization process uniformly scales the dimensions of the raw data through the use of the standardization method.

[0135] The feature extraction module includes a social media sentiment fluctuation feature extraction unit and an air pollution and respiratory disease association feature extraction unit;

[0136] The social media sentiment fluctuation feature extraction unit extracts sentiment fluctuation features according to the sentiment analysis data SQ, analyzes the change trend of the public opinion related to the epidemic; calculates and obtains the sentiment fluctuation index EVI and the sentiment change trend ET;

[0137] The sentiment fluctuation index EVI is obtained through the following formula:

[0138] ;

[0139] Wherein, N represents the total time period, SQti represents the value of the sentiment analysis data at the time point ti, and PSQ represents the average value of the sentiment analysis data;

[0140] The sentiment change trend ET is obtained through the following formula:

[0141] ;

[0142] Wherein, SQ(qi) represents the value of the sentiment analysis data at the time qi, and SQ(pi) represents the value of the sentiment analysis data at the time pi.

[0143] The respiratory disease association feature extraction unit calculates and obtains the pollution and health association index PHI according to the association between the air quality data AQ and the electronic health record EHR, specifically by combining the air quality data AQ and the respiratory disease incidence rate DiseaseRate;

[0144] The pollution and health association index PHI is obtained through the following formula:

[0145] ;

[0146] In the formula, ln represents the natural logarithm function;

[0147] Combine the obtained Emotional Fluctuation Index EVI, Emotional Change Trend ET, and Pollution-Health Association Index PHI to obtain the health feature set F.

[0148] In this embodiment, the system collects multi-source data, including Electronic Health Records EHR, Population Mobility Data Rk, Sentiment Analysis Data SQ, Temperature Data TE, Humidity Data HU, and Air Quality Data AQ, integrating data sources from different fields, so that epidemic prevention and control no longer rely solely on a single data source. By timely collecting sentiment analysis data in social media and real-time meteorological and environmental data, the system can capture abnormal fluctuations and potential risks of the epidemic earlier, overcoming the problems of single data and lagging updates in traditional prevention and control systems, and improving the timeliness and response ability of prevention and control decisions.

[0149] Under the action of the data cleaning and standardization unit, the system can effectively remove noise and invalid information in the collected data, process missing values and outliers, ensuring the accuracy and reliability of the data. At the same time, the standardization process unifies data of different scales, avoiding analysis errors caused by scale differences between different data sources and ensuring the accuracy of subsequent analysis and modeling. Compared with traditional data processing methods, this automated and systematic data cleaning and standardization process not only improves the data quality but also provides reliable data support for subsequent intelligent analysis and prediction.

[0150] Through the social media emotional fluctuation feature extraction unit, the system can extract the Emotional Fluctuation Index EVI and Emotional Change Trend ET according to the Sentiment Analysis Data SQ, and analyze the public's emotional reaction to the epidemic in real time. This feature extraction mechanism can deeply mine social media content related to the epidemic, timely capture the trend of public emotional fluctuations, and provide important references for prevention and control decisions. By monitoring emotional fluctuations in real time, prevention and control agencies can detect public opinion risks early, avoid the spread of epidemic panic, and improve public emotional management and prevention and control effects.

[0151] The system analyzes the relationship between air quality and the occurrence of respiratory diseases through the air pollution-respiratory disease association feature extraction unit, in combination with the Pollution-Health Association Index PHI. Through regression analysis, the system can reveal the correlation between pollutant concentration and respiratory diseases, thereby providing a more accurate health risk assessment for epidemic prevention and control. Especially in the case of increased population mobility and aggravated environmental pollution, the system can predict the potential threats of environmental factors to health and timely adjust prevention and control strategies to reduce the epidemic risk caused by aggravated pollution.

[0152] The system, through the epidemic transmission prediction module and the risk assessment and hot spot area identification module, combines multi-dimensional data such as sentiment analysis, air quality, and population mobility to accurately predict the epidemic transmission trend and identify high-risk areas. By comprehensively analyzing the impacts of sentiment fluctuations, environmental pollution, and population mobility, the system can identify potential hot spots in the development of the epidemic, providing decision-making support for the government and public health institutions to take timely countermeasures. The improvement of prediction and risk assessment enables the government to take effective prevention and control measures before the outbreak of the epidemic, avoiding the lag problem in traditional emergency responses.

[0153] Embodiment 3

[0154] This embodiment is an explanatory description carried out in Embodiment 2. Please refer to Figure 1 , specifically: The epidemic transmission prediction module includes an SIR model construction and parameter estimation unit and an influencing factor analysis and transmission trend adjustment unit;

[0155] The SIR model construction and parameter estimation unit constructs a mathematical model of epidemic transmission based on the epidemic prevention data set FYW and the health feature set F according to the susceptible-infected-recovered model, analyzes the changing trends of the number S of susceptible people, the number I of infected people, and the number R of recovered people, predicts the trend of future epidemic transmission, and obtains the number S(t) of susceptible people, the number I(t) of infected people, and the number R(t) of recovered people at the future time point t;

[0156] By analyzing the population mobility data Rk, the air quality data AQ, and the sentiment analysis data SQ, estimate the parameters of the epidemic transmission mathematical model, including the infection rate β and the recovery rate γ;

[0157] The number S(t) of susceptible people at the time point t is obtained through the following formula:

[0158] ;

[0159] In the formula, represents the influence coefficient of temperature data TE and humidity data HU on epidemic transmission, represents the influence coefficient of the j-th feature in the health feature set F on epidemic transmission, Fj represents the j-th feature in the health feature set F, and m represents the total number of features in the health feature set F;

[0160] The number I(t) of infected people at the time point t is obtained through the following formula:

[0161] ;

[0162] The number R(t) of recovered people at the time point t is obtained through the following formula:

[0163] .

[0164] The influencing factor analysis and transmission trend adjustment unit analyzes the impacts of population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on the spread of the epidemic, and substitutes them into the epidemic transmission mathematical model to adjust the epidemic transmission trend, obtaining the adjusted infection rate βadj and the adjusted recovery rate γadj, and substituting them into the epidemic transmission mathematical model to re-predict the susceptible population quantity S(t), the infected population quantity I(t), and the recovered population quantity R(t) at the future time point t;

[0165] The adjusted infection rate βadj is obtained through the following formula;

[0166] ;

[0167] In the formula, respectively represent the influence coefficients of the population mobility data Rk, the air quality data AQ, and the sentiment analysis data SQ on the infection rate β;

[0168] The adjusted recovery rate γadj is obtained through the following formula;

[0169] ;

[0170] In the formula, respectively represent the influence coefficients of the population mobility data Rk, the air quality data AQ, and the sentiment analysis data SQ on the recovery rate γ.

[0171] In this embodiment, by constructing the SIR model and combining the epidemic prevention data set FYW and the health feature set F, this module can accurately predict the quantities of susceptible, infected, and recovered populations at different time points, providing detailed data on the epidemic transmission trend. This prediction method based on the SIR model can more scientifically reflect the dynamic changes of the epidemic transmission compared with the traditional empirical prediction method, avoiding the errors brought by the overly simple linear model. By predicting the quantities of susceptible, infected, and recovered populations at future time points, the government and public health institutions can timely adjust the prevention and control strategies to ensure the accuracy and timeliness of the prevention and control measures.

[0172] The influencing factor analysis and transmission trend adjustment unit combines multi-dimensional data such as population mobility data Rk, air quality data AQ, and sentiment analysis data SQ with SIR model parameters including the infection rate β and the recovery rate γ, so as to achieve the adjustment of the epidemic transmission trend. By dynamically adjusting the infection rate β and the recovery rate γ, the system can optimize the epidemic transmission trend in real time according to the actual situation, improving the flexibility of prediction. This is particularly important in the case of a rapidly changing epidemic. By introducing the adjusted infection rate βadj and the adjusted recovery rate γadj, the prediction results can better reflect the epidemic transmission trend under different environmental and social factors. This adjustment not only improves the adaptability of the model, but also optimizes the effect of prevention and control measures, ensuring the efficient allocation of resources. Through the comprehensive analysis of factors such as temperature data TE, humidity data HU, sentiment analysis data SQ, and air quality data AQ, the system can comprehensively evaluate the potential impact of different environmental and social factors on the epidemic transmission.

[0173] By comprehensively using the SIR model and the analysis of various influencing factors, the system can provide more accurate epidemic prediction data and risk assessment results for decision-makers. This enables the government and public health institutions to take timely response measures. The spread of the epidemic is often affected by various factors, such as climatic conditions, population density, social behavior, public sentiment, etc. In different social environments and epidemic development stages, the parameters of the epidemic transmission model may change significantly. Therefore, the dynamic adjustment mechanism enables the system to respond flexibly to these changes and make rapid adjustments according to the new transmission trend. This flexibility makes the system not only applicable to the current epidemic, but also able to adapt to different types of infectious disease transmissions that may occur in the future, providing continuous support for public health institutions.

[0174] Example 4

[0175] This example is an explanatory description carried out in Example 3. Please refer to Figure 1 , specifically: The risk assessment and hot spot area identification module includes a risk assessment unit and a hot spot area identification and dynamic update unit;

[0176] The risk assessment unit calculates and obtains the comprehensive risk index RI according to the number of infected people I(t) at the future time point t provided by the epidemic transmission prediction module, combined with the epidemic density Iden, population mobility data Rk, and environmental pollution index EPI, and compares it with the preset risk threshold TRI to evaluate the epidemic risk of the region;

[0177] The epidemic severity of the region is estimated by calculating the epidemic density Iden of the infected population;

[0178] The epidemic density Iden is obtained through the following formula:

[0179] ;

[0180] Wherein, mA represents the area of the region;

[0181] Calculate the environmental pollution index EPI through the air quality data AQ;

[0182] The environmental pollution index EPI is obtained through the following formula:

[0183] ;

[0184] Wherein, M represents the total number of pollutants, represents the weight coefficient of the ia-th pollutant, and AQia represents the air quality data of the ia-th pollutant;

[0185] The comprehensive risk index RI is obtained through the following formula:

[0186] ;

[0187] Wherein, respectively represent the preset weight values of the epidemic density Iden, the population mobility data Rk and the environmental pollution index EPI, and ;

[0188] The epidemic risk of the region is obtained by matching in the following way:

[0189] When the comprehensive risk index RI ≤ the risk threshold TRI, it means that the epidemic risk in the region is normal;

[0190] When the comprehensive risk index RI > the risk threshold TRI, it means that the epidemic risk in the region is abnormal.

[0191] The hot spot area identification and dynamic update unit identifies the epidemic hot spot areas according to the comprehensive risk index RI of the region, and updates the comprehensive risk index RI of each region in real time, and dynamically adjusts the identification of the epidemic hot spots;

[0192] Sort the obtained comprehensive risk index RI of each region, and mark the region with the comprehensive risk index RI > the risk threshold TRI as the hot spot area K, indicating that the risk of this region is abnormal;

[0193] Fit all the hot spot areas K to form a hot spot set HArea = {Area(K)|RI(K) > TRI};

[0194] Wherein, RI(K) represents the comprehensive risk index of the K-th hot spot area, and Area(K) represents the K-th hot spot area, specifically indicating the area with abnormal risk;

[0195] Update the comprehensive risk index RI of the hotspot area K at fixed intervals to track the trend of the epidemic situation.

[0196] In this embodiment, by calculating the comprehensive risk index RI, the epidemic risk of each region is quantitatively evaluated. This risk assessment method considering multiple factors can more accurately reflect the complexity of the epidemic development compared with the traditional single-factor assessment, especially in the context of different environments, social behaviors, and population flows. The comprehensive risk index RI provides a dynamic and quantifiable risk value for each region, which can help decision-makers quickly identify potential high-risk regions and thus take more targeted prevention and control measures.

[0197] Through the calculated comprehensive risk index RI, this module can identify and mark regions with relatively high epidemic risks in real time. When the RI value exceeds the preset risk threshold TRI, it indicates that there is a relatively high risk of epidemic transmission in this region, and prevention and control measures must be taken as a priority. The risk assessment process combines multi-dimensional factors such as epidemic transmission data, population flow, and environmental pollution, improving the accuracy of risk assessment. The introduction of the environmental pollution index EPI, especially the impact of air quality on the epidemic, provides a quantitative analysis of the potential environmental factors for epidemic transmission. Through such comprehensive analysis, the system can better evaluate those regions with heavy pollution and dense population flow, which are often prone to becoming high-risk areas for epidemic spread. By deeply integrating environmental and epidemic data, the spread of the epidemic can be predicted and prevented more accurately.

[0198] Through the timely assessment and rapid response to regional risks, the module can reduce the spread of the epidemic caused by information lag. Dynamically adjusting the identification of hotspot areas can effectively ensure the timeliness of public health decision-making, seize key areas for effective control at the initial stage of the epidemic, and prevent the spread of the epidemic. Real-time monitoring of the changes in the risk index of each region provides timely and accurate decision-making support for decision-makers, ensuring that prevention and control measures can be adjusted within the shortest time and avoiding unnecessary delays.

[0199] Embodiment 5

[0200] This embodiment is an explanatory description carried out in Embodiment 4. Please refer to Figure 1 , specifically: The decision support and emergency response module includes a decision support unit and an emergency response unit;

[0201] The decision support unit classifies the epidemic risks of regions into the first level and the second level according to the preset risk threshold TRI, and provides prevention and control measures for each hotspot area K;

[0202] When the comprehensive risk index RI ≤ the risk threshold TRI, it is marked as the first level, which means that the region does not belong to the hotspot area K, and the epidemic risk within the region is normal. Maintain normal prevention and control measures and conduct regular monitoring and reporting;

[0203] When the comprehensive risk index RI > the risk threshold TRI, it is marked as the second level, indicating that the epidemic risk in the hot spot area K is abnormal, and prevention and control measures are provided, including implementing lockdown measures, isolating the infected, and adjusting the allocation of medical resources; among them, the adjustment of the allocation of medical resources is specifically to execute the preset plan for increasing the allocation of medical resources, including proportionally magnifying the quantity of medical resource allocation.

[0204] The emergency response unit formulates an emergency response plan according to the prevention and control measures provided by the decision support unit, including resource allocation, personnel scheduling, and emergency measures.

[0205] Among them, resource allocation includes the allocation of hospital beds, ambulances, testing equipment, and personal protective equipment.

[0206] Personnel scheduling includes assigning relevant personnel to areas with abnormal epidemic risks for epidemic monitoring and prevention and control.

[0207] Emergency measures include temporarily setting up epidemic prevention and control points, strengthening the dissemination of epidemic information, and health education for residents.

[0208] The dynamic feedback and optimization module includes a prevention and control effect monitoring unit and a strategy adjustment unit.

[0209] The prevention and control effect monitoring unit obtains real-time epidemic data and the implementation status of prevention and control measures, including the number of infected people I, the number of recovered people R, the number of deceased people, and the implementation intensity of prevention and control measures, and measures the prevention and control effect through the infection rate β and the recovery rate γ to determine whether the prevention and control measures are effective; the strategy adjustment unit calculates and identifies whether the current prevention and control measures have achieved the expected effect based on the feedback provided by the prevention and control effect monitoring unit, obtains the epidemic control index YZ, and compares it with the preset epidemic control threshold TYZ to judge the effect of the prevention and control measures.

[0210] The epidemic control index YZ is obtained by using a weighted algorithm for the infection rate β and the recovery rate γ.

[0211] The effect of the prevention and control measures is obtained by matching in the following way:

[0212] When the epidemic control index YZ ≥ the epidemic control threshold TYZ, it indicates that the prevention and control measures are effective.

[0213] When the epidemic control index YZ < the epidemic control threshold TYZ, it indicates that the prevention and control measures are ineffective, readjust the prevention and control measures, and formulate a new emergency response plan.

[0214] In this embodiment, the decision support unit compares the comprehensive risk index RI with the preset risk threshold TRI to accurately divide the epidemic areas into different risk levels. Such a grading system can help the public health department adopt different levels of prevention and control measures according to the actual situation:

[0215] Low-risk areas (RI≤TRI): Maintain normal prevention and control measures, conduct regular monitoring and reporting, and avoid excessive intervention and resource waste. High-risk areas (RI>TRI): Adopt more stringent measures, such as lockdowns, isolation of infected individuals, and expansion of medical resource allocation, to effectively control the spread of the epidemic. This data-driven hierarchical prevention and control method avoids excessive or insufficient prevention and control measures under a unified standard, can be flexibly adjusted according to the actual risk situation of different regions, and maximizes the prevention and control efficiency.

[0216] The emergency response unit formulates a targeted and flexible emergency response plan based on the prevention and control measures provided by the decision support unit. Through resource allocation, personnel scheduling, and dynamic adjustment of emergency measures, the system can quickly respond to changes in the epidemic: flexibly allocate medical resources according to the regional risk level, including hospital beds, ambulances, and personal protective equipment, to avoid resource waste and ensure the medical needs of key areas. Dispatch medical staff and relevant workers to high-risk areas in a timely manner to ensure the timeliness and effectiveness of epidemic monitoring and prevention and control. Such as temporarily setting up epidemic prevention and control points, increasing the dissemination of epidemic information and health education for residents, to ensure that the public responds to the epidemic in a timely and effective manner. This strategy of dynamic adjustment and flexible response ensures that public health institutions can respond to sudden changes in the epidemic, reduce the risk of epidemic spread, and safeguard social public safety.

[0217] The prevention and control effect monitoring unit can quickly evaluate the actual effect of the prevention and control measures by obtaining real-time epidemic data and the implementation situation of the prevention and control measures, including the number of infected, recovered, and deceased people and the implementation intensity of the prevention and control measures. Evaluate the prevention and control effect by calculating the infection rate β and the recovery rate γ to help decision-makers judge whether the prevention and control measures have achieved the expected goals. Such a real-time monitoring system:

[0218] The strategy adjustment unit can, based on the feedback from the prevention and control effect monitoring unit, judge the effect of the prevention and control measures in real time and optimize the prevention and control strategy according to the change of the epidemic control index YZ. Such an optimization mechanism includes:

[0219] Data-driven adjustment: Through real-time feedback, the system can quickly identify the deficiencies of the prevention and control measures and make adjustments.

[0220] Avoidance of strategy lag: This real-time adjustment ability ensures that the epidemic prevention and control is not affected by outdated strategies and avoids the adverse effects of lagged responses on the spread of the epidemic.

[0221] By combining real-time data feedback and a dynamic adjustment mechanism, the system can provide accurate and timely decision-making support for decision-makers. The decision support unit provides precise prevention and control measures for each region, ensuring that the decision-making basis is built on reliable data and avoiding the limitations of over-relying on traditional experience-based judgments. The real-time nature and precision of this decision-making process make the epidemic response more efficient and flexible. Through the joint operation of the decision support and emergency response modules, the system can form a multi-level and multi-angle response strategy from the macroscopic epidemic risk assessment to the microscopic implementation of emergency responses. For the epidemics in different regions, different levels of prevention and control strategies are adopted, avoiding the limitations of a single prevention and control measure and enabling timely adjustment of the emergency response plan.

[0222] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A public health epidemic prevention and control system based on big data analysis, characterized in that: It includes a data collection and preprocessing module, a data fusion and feature extraction module, an epidemic transmission prediction module, a risk assessment and hot spot area identification module, a decision-making support and emergency response module, and a dynamic feedback and optimization module; The data collection and preprocessing module is responsible for collecting raw data from hospitals, social media, and meteorological departments and performing preprocessing to obtain the epidemic prevention data set FYW; The feature extraction module extracts features from the epidemic prevention data set FYW, including the emotional fluctuation features related to the epidemic in social media and the correlation features between air pollution and respiratory diseases, to form the health feature set F; The epidemic transmission prediction module uses the susceptible-infected-recovered model to predict the trend of epidemic transmission through the epidemic prevention data set FYW and the health feature set F, analyzes the impact of population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on the spread of the epidemic, and obtains the prediction result; The risk assessment and hot spot area identification module, based on the prediction result, combines the epidemic density Iden, population mobility data Rk, and environmental pollution index EPI to identify the risk areas of the current epidemic and conduct an assessment to obtain the comprehensive risk index RI; The decision-making support and emergency response module provides decision-making support for public health institutions according to the comprehensive risk index RI and formulates prevention and control measures; The dynamic feedback and optimization module monitors the effectiveness of prevention and control measures in real time during the epidemic prevention and control process and adjusts the strategy through data feedback.

2. The public health epidemic prevention and control system based on big data analysis according to claim 1, characterized in that: The data collection and preprocessing module includes a data collection unit and a data cleaning and standardization unit; The collection unit collects raw data from multiple data sources such as hospitals, social media, and meteorological departments, including electronic health records EHR, population mobility data Rk, sentiment analysis data SQ, temperature data TE, humidity data HU, and air quality data AQ; Among them, the electronic health record EHR is obtained through the hospital information management system and includes the incidence of respiratory diseases DiseaseRate; the population mobility data Rk is obtained by the ratio of the number of people flowing in the region to the total area of the region; The sentiment analysis data SQ includes scraping epidemic-related posts from social media platforms, performing sentiment analysis, and classifying each post into positive sentiment, negative sentiment, and neutral sentiment through NLP technology, and assigning values to positive sentiment, negative sentiment, and neutral sentiment, specifically: positive sentiment is +1, negative sentiment is -1, and neutral sentiment is 0; The sentiment analysis data SQ is obtained through the following formula: ； In the formula, Si represents the i-th social media post, and n represents the total number of posts analyzed; The temperature data TE and humidity data HU are obtained through temperature sensors and humidity sensors respectively; The air quality data AQ is obtained through the following formula: ； In the formula, cPM2.5, cCO, and cNO2 respectively represent the concentrations of air particulate matter PM2.5, carbon monoxide CO, and nitrogen dioxide NO2, IPM2.5, ICO, and INO2 respectively represent the pollutant standardization indices of the concentrations of air particulate matter PM2.5, carbon monoxide CO, and nitrogen dioxide NO2, and max represents taking the peak value in the numerical values; The data cleaning and standardization unit cleans and standardizes the raw data collected by the data collection unit to obtain the epidemic prevention data set FYW; Cleaning includes removing noise and invalid information in the raw data through the use of filters, including missing values and outliers; The standardization process unifies the dimension scale of the raw data by using the standardization method.

3. The public health epidemic prevention and control system based on big data analysis according to claim 2, characterized in that: The feature extraction module includes a social media sentiment fluctuation feature extraction unit and an air pollution and respiratory disease association feature extraction unit; The social media sentiment fluctuation feature extraction unit extracts sentiment fluctuation features according to the sentiment analysis data SQ, analyzes the change trend of public opinion related to the epidemic; calculates and obtains the sentiment fluctuation index EVI and the sentiment change trend ET; The sentiment fluctuation index EVI is obtained through the following formula: ； In the formula, N represents the total time period, SQti represents the value of the sentiment analysis data at time point ti, and PSQ represents the average value of the sentiment analysis data; The sentiment change trend ET is obtained through the following formula: ； In the formula, SQ(qi) represents the value of the sentiment analysis data at time qi, and SQ(pi) represents the value of the sentiment analysis data at time pi.

4. The public health epidemic prevention and control system based on big data analysis according to claim 3, characterized in that: The respiratory disease association feature extraction unit calculates and obtains the pollution and health association index PHI according to the association between the air quality data AQ and the electronic health record EHR, specifically by combining the air quality data AQ and the respiratory disease incidence rate DiseaseRate; The pollution and health association index PHI is obtained through the following formula: ； In the formula, ln represents the natural logarithm function; The obtained sentiment fluctuation index EVI, sentiment change trend ET, and pollution and health association index PHI are combined to obtain the health feature set F.

5. The public health epidemic prevention and control system based on big data analysis according to claim 4, characterized in that: The epidemic transmission prediction module includes an SIR model construction and parameter estimation unit and an influencing factor analysis and transmission trend adjustment unit; The SIR model construction and parameter estimation unit constructs an epidemic transmission mathematical model based on the epidemic prevention data set FYW and the health feature set F, based on the susceptible-infected-recovered model, analyzes the change trends of the number of susceptible people S, the number of infected people I, and the number of recovered people R, predicts the trend of future epidemic transmission, and obtains the number of susceptible people S(t), the number of infected people I(t), and the number of recovered people R(t) at the future time point t; By analyzing the population flow data Rk, the air quality data AQ, and the sentiment analysis data SQ, the parameters of the epidemic transmission mathematical model are estimated, including the infection rate β and the recovery rate γ; The number of susceptible people S(t) at the time point t is obtained through the following formula: ； In the formula, represents the influence coefficient of temperature data TE and humidity data HU on the spread of the epidemic, represents the influence coefficient of the j-th feature in the health feature set F on the spread of the epidemic, Fj represents the j-th feature in the health feature set F, and m represents the total number of features in the health feature set F; The number of infected people I(t) at the time point t is obtained through the following formula: ； The number of recovered people R(t) at the time point t is obtained through the following formula: 。 6. A public health epidemic prevention and control system based on big data analysis according to claim 5, characterized in that: The influencing factor analysis and transmission trend adjustment unit analyzes the impact of population mobility data Rk, air quality data AQ, and sentiment analysis data SQ on the spread of the epidemic, and substitutes them into the epidemic transmission mathematical model to adjust the epidemic transmission trend, obtaining the adjusted infection rate βadj and the adjusted recovery rate γadj, and substituting them into the epidemic transmission mathematical model to re-predict the number of susceptible people S(t), the number of infected people I(t), and the number of recovered people R(t) at the future time point t; The adjusted infection rate βadj is obtained through the following formula; ； wherein, respectively represent the influence coefficients of the population mobility data Rk, the air quality data AQ, and the sentiment analysis data SQ on the infection rate β; The adjusted recovery rate γadj is obtained through the following formula; ； In the formula, respectively represent the influence coefficients of the population mobility data Rk, the air quality data AQ, and the sentiment analysis data SQ on the recovery rate γ.

7. A public health epidemic prevention and control system based on big data analysis according to claim 6, characterized in that: The risk assessment and hot spot area identification module includes a risk assessment unit and a hot spot area identification and dynamic update unit; The risk assessment unit calculates and obtains the comprehensive risk index RI according to the number of infected people I(t) at the future time point t provided by the epidemic transmission prediction module, combined with the epidemic density Iden, population mobility data Rk, and environmental pollution index EPI, and compares it with the preset risk threshold TRI to evaluate the epidemic risk of the region; The epidemic severity of the region is estimated by calculating the epidemic density Iden of the infected people; The epidemic density Iden is obtained through the following formula: ； In the formula, mA represents the area of the region; The environmental pollution index EPI is calculated through the air quality data AQ; The environmental pollution index EPI is obtained through the following formula: ； where M represents the total quantity of pollutants, represents the weight coefficient of the ia-th pollutant, and AQia represents the air quality data of the ia-th pollutant; The comprehensive risk index RI is obtained through the following formula: ； In the formula, respectively represent the preset weight values of the epidemic density Iden, the population mobility data Rk, and the environmental pollution index EPI, and ; The epidemic risk of the region is obtained through the following matching method: When the comprehensive risk index RI ≤ risk threshold TRI, it means that the epidemic risk in the region is normal; When the comprehensive risk index RI > risk threshold TRI, it means that the epidemic risk in the region is abnormal.

8. The public health epidemic prevention and control system based on big data analysis according to claim 7, characterized in that: The hot spot area identification and dynamic update unit identifies the epidemic hot spot areas according to the comprehensive risk index RI of the region, and real-time updates the comprehensive risk index RI of each region to dynamically adjust the identification of the epidemic hot spots; Sort the obtained comprehensive risk index RI of each region, and mark the regions with comprehensive risk index RI > risk threshold TRI as hot spot areas K, indicating that the risk of the region is abnormal; Fit all hot spot areas K to form a hot spot set HArea={Area(K)|RI(K)>TRI}; In the formula, RI(K) represents the comprehensive risk index of the Kth hot spot area, and Area(K) represents the Kth hot spot area, specifically representing the area with abnormal risk; Update the comprehensive risk index RI of the hot spot area K at a fixed period to track the changing trend of the epidemic.

9. A public health epidemic prevention and control system based on big data analysis according to claim 7, characterized in that: The decision support and emergency response module includes a decision support unit and an emergency response unit; The decision support unit divides the epidemic risk of the region into the first level and the second level according to the preset risk threshold TRI, and provides prevention and control measures for each hot spot area K; When the comprehensive risk index RI ≤ risk threshold TRI, it is marked as the first level, which means that the area does not belong to the hot spot area K, and the epidemic risk in the region is normal, maintaining normal prevention and control measures, and conducting regular monitoring and reporting; When the comprehensive risk index RI > the risk threshold TRI, it is marked as the second level, indicating that the epidemic risk in the hotspot area K is abnormal, and prevention and control measures are provided, including implementing lockdown measures, isolating the infected, and adjusting the allocation of medical resources; The emergency response unit formulates an emergency response plan based on the prevention and control measures provided by the decision support unit, including resource allocation, personnel scheduling, and emergency measures; Among them, resource allocation includes the allocation of hospital beds, ambulances, testing equipment, and personal protective equipment; Personnel scheduling includes assigning relevant personnel to areas with abnormal epidemic risks for epidemic monitoring and prevention and control; Emergency measures include temporarily setting up epidemic prevention and control points, strengthening the dissemination of epidemic information, and health education for residents.

10. A public health epidemic prevention and control system based on big data analysis according to claim 5, wherein: The dynamic feedback and optimization module includes a prevention and control effect monitoring unit and a strategy adjustment unit; The prevention and control effect monitoring unit obtains real-time epidemic data and the implementation of prevention and control measures, including the number of infected people I, the number of recovered people R, the number of deaths, and the implementation intensity of prevention and control measures, and measures the prevention and control effect through the infection rate β and the recovery rate γ to determine whether the prevention and control measures are effective; The strategy adjustment unit calculates and identifies whether the current prevention and control measures have achieved the expected effect based on the feedback provided by the prevention and control effect monitoring unit, obtains the epidemic control index YZ, and compares it with the preset epidemic control threshold TYZ to judge the effect of the prevention and control measures; The epidemic control index YZ is obtained by using a weighted algorithm for the infection rate β and the recovery rate γ; The effect of the prevention and control measures is obtained by matching in the following way: When the epidemic control index YZ ≥ the epidemic control threshold TYZ, it indicates that the prevention and control measures are effective; When the epidemic control index YZ < the epidemic control threshold TYZ, it indicates that the prevention and control measures are ineffective, re-adjust the prevention and control measures, and formulate a new emergency response plan.

Images