Respiratory infectious disease early warning method and system based on new-safety medicine

Abstract

The invention discloses a respiratory infectious disease early warning method and system based on new-safety medicine, and particularly relates to the technical field of infectious disease early warning. The method comprises the following steps: acquiring symptom self-reporting information of a crowd in an incubation period and environmental climate data of an environment in which the crowd is located, and constructing incubation period symptom and climate abnormality associated data; extracting time-space coupling characteristic data of symptoms in the incubation period by establishing a time-space coupling relationship between weak symptoms in the incubation period and regional climate anomalies; identifying an incubation period infection enhancement effect by combining a new-safety medical theory, generating risk judgment data of incubation period infection enhancement, and performing risk threshold judgment on the incubation period infection enhancement effect to obtain incubation period group high-risk judgment data; according to the high-risk judgment data of the incubation period population, the high-risk area of the incubation period population and the spatial distribution of the susceptible population are determined, and finally, the respiratory infectious disease early warning information is generated in combination with the infectious disease early warning grading decision model, so that the accuracy and timeliness of the early warning of the respiratory infectious disease are improved.

Description

Technical Field

[0001] This invention relates to the field of infectious disease early warning technology, and more specifically, to a method and system for early warning of respiratory infectious diseases based on Xin'an Medicine. Background Technology

[0002] Respiratory infectious diseases are characterized by transmission during the incubation period, meaning that although infected individuals do not show clinical symptoms during the incubation period, they already have the ability to transmit the disease, which is closely related to changes in external environmental and climatic factors.

[0003] Existing methods for early warning of respiratory infectious diseases typically rely on monitoring and reporting mechanisms for typical symptoms. They do not fully consider the subtle symptom information of infected individuals during the incubation period, ignore the correlation between subtle symptoms in the population during the incubation period and abnormal environmental climate, and fail to detect the impact of abnormal environmental climate fluctuations on the risk of transmission during the incubation period in a timely manner, thus affecting the accuracy and timeliness of early warning of respiratory infectious diseases. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a respiratory infectious disease early warning method and system based on Xin'an Medicine to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A respiratory infectious disease early warning method based on Xin'an Medicine includes the following steps: S1: Collect symptom self-reporting information and environmental climate data from people during the incubation period, conduct sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generate data on the correlation between incubation period symptoms and climate anomalies. S2: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output the spatiotemporal coupling characteristic data of latent symptoms. S3: Based on the spatiotemporal coupling characteristic data of latent symptoms, the Xin'an Medical Theory is used to identify the latent infection enhancement effect and output the risk assessment data of latent infection enhancement. S4: Based on the risk assessment data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period and output the high-risk assessment data of the incubation period population; S5: Based on the high-risk assessment data of the latent period population, determine the high-risk areas and spatial distribution of susceptible populations during the latent period, and output spatial risk hotspot identification data; S6: Based on spatial risk hotspot identification data and combined with the infectious disease early warning classification decision model, generate early warning information for respiratory infectious diseases.

[0006] In a preferred embodiment, S1 specifically refers to: Collect self-reported symptom information from people during the incubation period and environmental and climate data of the environment in which the people are located; Sensitivity screening of symptom features was performed on the collected self-reported symptom information to obtain sensitive feature data of symptoms in the latent period population; Analyze the characteristics of abnormal fluctuations in environmental and climate data to obtain characteristic data of abnormal fluctuations in environmental and climate. Based on the sensitive characteristic data of latent period symptoms and the characteristic data of abnormal fluctuations in environmental climate, the correlation characteristics between latent period symptoms and abnormal fluctuations in environmental climate are determined, and the correlation data between latent period symptoms and climate anomalies are generated.

[0007] In a preferred embodiment, S2 specifically refers to: Based on the correlation data between latent period symptoms and climate anomalies, the spatiotemporal correspondence between latent period symptom sensitivity characteristics data and environmental climate anomaly fluctuation characteristics data was determined. Based on the spatiotemporal correspondence, and combined with the actual distribution area of ​​the population and the range of environmental and climate change, a spatiotemporal coupling parameter system between weak symptoms during the incubation period and regional climate anomalies is constructed. Based on the spatiotemporal coupling parameter system, the distribution characteristics of latent symptoms in different regions and under different climatic conditions are identified, and spatiotemporal coupling characteristic data of latent symptoms are obtained.

[0008] In a preferred embodiment, the spatiotemporal coupling parameter system includes spatial coupling weight parameters, temporal coupling weight parameters, and symptom-climate correlation strength parameters.

[0009] In a preferred embodiment, S3 specifically refers to: Based on the spatiotemporal coupling characteristic data of latent symptoms, a latent infection enhancement identification model was constructed with reference to the theory of latent pathogenic factors in Xin'an medicine. Threshold discrimination is performed on the symptom sensitivity characteristics data of the latent period population to obtain the symptom sensitivity determination results of the latent period; By weighting the characteristic data of abnormal fluctuations in environmental and climate, the results of measuring the impact of abnormal environmental and climate are obtained. The results of sensitivity assessment of latent symptoms and measurement of the impact of abnormal environmental and climate conditions are corrected by physical fitness categories to obtain the coupled results of latent physical fitness correction. Based on the results of latent period constitution correction coupling, the infection enhancement determination of the latent period infection enhancement identification model is carried out, and the latent period infection enhancement risk determination data is generated.

[0010] In a preferred embodiment, the parameters of the latent period infection enhancement identification model of the Xin'an Medical theory of latent pathogenicity include latent period symptom sensitivity threshold parameters, environmental climate anomaly weight parameters, and population constitution category correction parameters.

[0011] In a preferred embodiment, S4 specifically refers to: Based on the data on the risk of enhanced transmission during the incubation period, a risk threshold for enhanced transmission during the incubation period is set. By comparing the data on the risk of enhanced transmission during the incubation period with the risk threshold for enhanced transmission during the incubation period, it can be determined whether the population during the incubation period is in a high-risk state, and the high-risk determination result of the population during the incubation period can be obtained. The results of high-risk group assessment during the incubation period are matched with the geographic distribution information of the population to generate high-risk group assessment data during the incubation period.

[0012] In a preferred embodiment, S5 specifically refers to: By identifying spatial hotspots, areas with dense distribution of high-risk populations in the data on high-risk groups during the incubation period can be determined. Based on the densely populated areas of high-risk populations, determine the geographical distribution characteristics of high-risk populations; Based on population symptom sensitivity data and environmental climate abnormal fluctuation data, spatial correlation feature analysis is conducted to obtain correlation feature data between high-risk populations and environmental climate abnormalities. Based on the geographical distribution characteristics of high-risk groups and the correlation characteristics between high-risk groups and environmental and climate anomalies, high-risk areas of the incubation period and the spatial distribution range of susceptible groups are determined, generating spatial risk hotspot identification data.

[0013] In a preferred embodiment, S6 specifically refers to: Based on spatial risk hotspot identification data, an infectious disease early warning classification decision model is established, including regional risk level classification rules, risk level determination criteria, and early warning information classification rules. Based on spatial risk hotspot identification data, and according to regional risk level classification rules, high-risk areas are divided into different warning levels; Based on the risk level assessment criteria, the risk level of susceptible populations in each high-risk area is determined; Based on the rules for classifying early warning information, respiratory infectious disease early warning information is generated for each high-risk area and the susceptible population at the corresponding risk level.

[0014] On the other hand, the present invention provides a respiratory infectious disease early warning system based on Xin'an Medicine, comprising: Symptom association module: Collects self-reported symptom information and environmental climate data from people during the incubation period, performs sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generates data on the association between incubation period symptoms and climate anomalies. Spatiotemporal coupling module: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output spatiotemporal coupling characteristic data of latent symptoms; Latent Symptom Identification Module: Based on the spatiotemporal coupling characteristic data of latent symptoms, the module uses the Xin'an Medical Theory to identify the enhanced infectivity effect during the latent period and outputs risk assessment data for enhanced infectivity during the latent period. Threshold determination module: Based on the risk determination data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period and output the high-risk determination data of the incubation period population; Spatial Hotspot Module: Based on the high-risk assessment data of the incubation period population, determine the high-risk areas of the incubation period population and the spatial distribution of susceptible populations, and output spatial risk hotspot identification data; Tiered early warning module: Based on spatial risk hotspot identification data and combined with the infectious disease early warning tiered decision model, it generates early warning information for respiratory infectious diseases.

[0015] The technical effects and advantages of the respiratory infectious disease early warning method and system based on Xin'an Medicine of this invention are as follows: By jointly collecting self-reported symptom information and environmental climate data from individuals during the incubation period, and conducting sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, representative data on the correlation between incubation period symptoms and climate anomalies can be extracted from the incubation period. Through the spatiotemporal coupling relationship between weak incubation period symptoms and regional climate anomalies, spatiotemporal coupling characteristic data of incubation period symptoms reflecting the evolution trend of transmission risk during the incubation period can be obtained. The theory of latent pathogenic factors in Xin'an Medicine is used to identify the enhanced infectivity effect during the incubation period, obtaining risk assessment data for enhanced incubation period infection, thus quantifying the infection risk during the incubation period. By judging the risk threshold of the enhanced incubation period infection effect, high-risk assessment data for the incubation period population is determined, and the spatial distribution of high-risk areas and susceptible populations during the incubation period is identified, generating spatial risk hotspot identification data. Based on the spatial risk hotspot identification data and combined with the infectious disease early warning grading decision model, graded respiratory infectious disease early warning information is output, thereby achieving forward identification and early warning of infection risk during the incubation period, which is beneficial to improving the sensitivity and targeting of respiratory infectious disease early warning. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of a respiratory infectious disease early warning method based on Xin'an Medicine according to the present invention; Figure 2 This is a schematic diagram of the structure of a respiratory infectious disease early warning system based on Xin'an Medicine according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1 Figure 1 This invention provides a respiratory infectious disease early warning method based on Xin'an Medicine, which includes the following steps: S1: Collect symptom self-reporting information and environmental climate data from people during the incubation period, conduct sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generate data on the correlation between incubation period symptoms and climate anomalies. S2: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output the spatiotemporal coupling characteristic data of latent symptoms. S3: Based on the spatiotemporal coupling characteristic data of latent symptoms, the Xin'an Medical Theory is used to identify the latent infection enhancement effect and output the risk assessment data of latent infection enhancement. S4: Based on the risk assessment data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period and output the high-risk assessment data of the incubation period population; S5: Based on the high-risk assessment data of the latent period population, determine the high-risk areas and spatial distribution of susceptible populations during the latent period, and output spatial risk hotspot identification data; S6: Based on spatial risk hotspot identification data and combined with the infectious disease early warning classification decision model, generate early warning information for respiratory infectious diseases.

[0019] S1: Collect self-reported symptom information and environmental climate data from individuals during the incubation period, perform sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generate correlation data between incubation period symptoms and climate anomalies, including: Collect self-reported symptom information from people during the incubation period and environmental and climate data of the environment in which the people are located; Symptom self-reporting information is obtained through self-reporting. Symptoms include fever, cough, sore throat, fatigue, nasal congestion, and muscle aches. Each symptom is recorded as a binary variable, with 0 indicating absence and 1 indicating presence. Symptom self-reporting information is collected daily for 30 consecutive days. Environmental climate data is obtained from meteorological monitoring stations covering residential areas. These stations provide data on daily average temperature, daily average relative humidity, daily precipitation, and daily average wind speed. Environmental climate data is collected daily for 30 consecutive days, synchronized with the symptom self-reporting information collection period. The collected symptom self-reporting information and environmental climate data undergo data cleaning, including removing missing values, correcting formatting errors, and standardizing timestamps. Missing values ​​are filled using linear interpolation, which calculates the average value based on data from consecutive time points to replace missing values. Formatting errors are corrected by standardizing temperature units to degrees Celsius, humidity units to percentages, precipitation units to millimeters, and wind speed units to meters per second. A unified timestamp involves aligning the time of all data records to midnight each day.

[0020] Sensitivity screening of symptom features was performed on the collected self-reported symptom information to obtain sensitive feature data of symptoms in the latent period population; Sensitivity screening of symptom characteristics employs statistical frequency analysis to calculate the frequency of each symptom in the population; the frequency equals the number of symptom occurrences divided by the total number of reports. Frequency calculation is based on all self-reported symptom information within a 30-day collection period. A frequency threshold is set for sensitivity screening, calculated based on historical epidemiological data. This historical epidemiological data is a database of symptom reports from the same season and region over the past five years, with the frequency threshold set at the 90th percentile of the historical frequency distribution. For example, if the 90th percentile of the historical frequency distribution for fever is 0.15, then the frequency threshold is set to 0.15. Symptoms with a frequency greater than or equal to the frequency threshold are marked as sensitive symptoms. Sensitive symptoms constitute the symptom sensitivity feature data for the incubation period population; this data is in vector form, with the vector dimension equal to the number of symptoms, and each dimension representing the symptom's frequency.

[0021] Analyze the characteristics of abnormal fluctuations in environmental and climate data to obtain characteristic data of abnormal fluctuations in environmental and climate. The analysis of abnormal fluctuations in environmental climate employs a time-series deviation calculation method to calculate the deviation of each climate parameter from its historical average for the same period. The historical average is calculated based on climate data from the same date and region over the past ten years, including average daily temperature, average daily relative humidity, average daily precipitation, and average daily wind speed. The deviation is equal to the current climate parameter value minus the historical average. Anomaly detection uses a deviation threshold, calculated based on the standard deviation of historical climate data. The standard deviation is calculated from the climate data series from the same date and region over the past ten years, and the deviation threshold is set to twice the standard deviation. For example, if the historical standard deviation of daily average temperature is 2 degrees Celsius, the deviation threshold is set to 4 degrees Celsius. When the absolute value of a climate parameter's deviation is greater than or equal to the deviation threshold, the climate parameter is marked as exhibiting abnormal fluctuations. These abnormally fluctuating climate parameters constitute the environmental climate abnormal fluctuation characteristic data; this data is in matrix form, with rows corresponding to dates and columns corresponding to climate parameters. Each matrix element represents the deviation of the climate parameter for the corresponding date.

[0022] Based on the sensitive characteristic data of latent period symptoms and the characteristic data of abnormal fluctuations in environmental climate, the correlation characteristic relationship between latent period symptoms and abnormal fluctuations in environmental climate is determined, and the correlation data between latent period symptoms and climate anomalies is generated. The correlation characteristics were determined using the Pearson correlation coefficient method, calculating the correlation coefficient between each sensitive symptom and each anomalous climate parameter. The Pearson correlation coefficient formula is: the correlation coefficient equals the covariance divided by the product of the standard deviations of the two variables. The covariance calculation is based on 30-day time series data, with the two variables being the frequency sequence of sensitive symptoms and the deviation value sequence of anomalous climate parameters. A correlation coefficient with an absolute value greater than or equal to 0.5 is considered a strong correlation. Strongly correlated pairs constitute the correlation characteristic relationship, represented as an association rule table. The association rule table includes symptom name, climate parameter type, correlation coefficient, and association strength label. The association strength label is a binary variable, with 0 indicating a weak association and 1 indicating a strong association. Based on the association rule table, latent symptom and climate anomaly correlation data are generated. This data is in graph form, where graph nodes represent symptoms or climate parameters, graph edges represent correlation relationships, and edge weights are the correlation coefficients.

[0023] S2: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output the spatiotemporal coupling characteristic data of latent symptoms, including: Based on the correlation data between latent period symptoms and climate anomalies, the spatiotemporal correspondence between latent period symptom sensitivity characteristics data and environmental climate anomaly fluctuation characteristics data was determined. The determination of spatiotemporal correspondence employs a geospatial grid division and time series alignment method. Geospatial grid division divides the population distribution area into multiple spatial units, each a rectangular grid. Grid size is set based on population density distribution data, obtained from a census database. The grid size is determined using an equal-interval division method, with the grid side length calculated as the square root of the total area divided by the number of grids. The number of grids is determined based on the area size and resolution requirements. For example, for an area of ​​1000 square kilometers, if the number of grids is set to 1000, the grid side length is calculated as the square root of 1000 square kilometers divided by 1000, which equals 1 kilometer. Each spatial unit is assigned a unique grid identifier containing latitude and longitude information. The time series alignment method aligns the data daily, with each day as the time unit and a time series length of 30 days, consistent with the collection cycle of symptom self-reporting information and environmental climate data. Raw records of symptom sensitivity features and climate anomaly fluctuation features were extracted from the correlation data between latent symptoms and climate anomalies. These raw records included user geographic location data from self-reported symptom information and meteorological station geographic location data from environmental climate data. User geographic location data was obtained through self-reporting and recorded as latitude and longitude coordinates. Meteorological station geographic location data was obtained from meteorological monitoring station metadata and recorded as station latitude and longitude coordinates. For each spatial cell, all self-reported symptom records and environmental climate records within that cell were extracted. The method for assigning self-reported symptom records to spatial cells was based on the ray casting method, determining whether the user's latitude and longitude coordinates fell within the grid polygon. The method for assigning environmental climate data to spatial cells was the nearest neighbor interpolation method, selecting the meteorological station data closest to the grid center point as the grid's climate data; the distance was calculated using the Havesing formula. Time series alignment ensured that each grid had a unique daily symptom and climate feature value. Symptom characteristic values ​​are obtained from symptom sensitivity characteristic data of the latent period population. This data is in vector form, with the vector dimension equal to the number of symptoms. Each dimension's value is the symptom occurrence frequency, calculated based on all self-reported symptom records within the grid. The symptom occurrence frequency equals the number of symptom occurrences divided by the total number of reports. The symptom characteristic value is the symptom occurrence frequency. Climate characteristic values ​​are obtained from environmental climate anomaly fluctuation characteristic data, which is in matrix form. Rows correspond to dates, columns to climate parameters, and each matrix element is a deviation value. The spatiotemporal correspondence is represented by a spatiotemporal data cube, a three-dimensional array structure. The first dimension is the spatial unit index, the second is the time point index, and the third is the feature index, which includes both symptom characteristic values ​​and climate characteristic values.

[0024] Based on the spatiotemporal correspondence, and combined with the actual distribution area of ​​the population and the range of environmental and climate change, a spatiotemporal coupling parameter system between weak symptoms during the incubation period and regional climate anomalies is constructed. The spatiotemporal coupling parameter system includes spatial coupling weight parameters, temporal coupling weight parameters, and symptom-climate association strength parameters. Spatial coupling weight parameters characterize the degree of mutual influence between symptom and climate associations between different spatial units. The calculation of spatial coupling weight parameters is based on a spatial distance attenuation function, which employs the inverse distance weighting method. The formula for the inverse distance weighting method is: spatial coupling weight equals 1 divided by the square of the distance, where the distance is the Havesing distance between the center points of the two spatial units. The spatial coupling weight parameters are a symmetric matrix, with rows and columns corresponding to spatial unit indices, and matrix elements representing the weight values ​​between corresponding unit pairs. The time-coupling weight parameter characterizes the temporal influence of the symptom-climate association between different time points. The calculation of the time-coupling weight parameter is based on the time autocorrelation function, which employs partial autocorrelation analysis (PAutocorrelation Analysis). PAutocorrelation Analysis calculates the partial autocorrelation coefficient of the time series, which is calculated as: the partial autocorrelation coefficient equals the correlation coefficient of the residual series, where the residual series is the series after removing the influence of previous periods. The PAutocorrelation coefficient calculation is based on 30-day time series data. The time lag order is set based on the Bayesian information criterion, which is calculated as: the Bayesian information criterion equals -2 multiplied by the log-likelihood value plus the logarithm of the number of parameters multiplied by the sample size. The log-likelihood value is calculated based on the time series model, the number of parameters is the lag order, and the sample size is the number of time points. For example, if the minimum value of the Bayesian information criterion is a lag order of 3, then the time lag order is set to 3. The time-coupling weight parameter is a symmetric matrix, where the matrix rows and columns correspond to time point indices, and the matrix element values ​​are the weight values ​​between corresponding time point pairs. The symptom-climate correlation strength parameter characterizes the degree of coupling between symptoms and climate anomalies. The calculation of this parameter is based on the spatiotemporally extended Pearson correlation coefficient. The formula for the spatiotemporally extended Pearson correlation coefficient is: the correlation coefficient equals the product of the spatiotemporally weighted covariance divided by the spatiotemporally weighted standard deviation. The spatiotemporally weighted covariance is calculated based on the spatiotemporal data cube. The formula for the spatiotemporally weighted covariance is: the spatiotemporally weighted covariance equals the sum of all weight parameters multiplied by the symptom value minus the symptom mean multiplied by the climate value minus the climate mean. The weight parameters are the product of the spatial coupling weight and the temporal coupling weight. The symptom mean is the spatial-temporal average of the symptom occurrence frequency. For example, first calculate the symptom occurrence frequency for each day in each grid, sum the symptom occurrence frequencies of all grids over all days, and then divide by the total number of data points (total number of grids × total number of days) to obtain the spatial-temporal average of the symptom occurrence frequency. The climate mean is the spatial-temporal average of the climate deviation value. The symptom-climate association strength parameter is a parameter vector, the dimension of which is equal to the number of symptom-climate pairs, and the value of each dimension is the association strength value; a symptom-climate pair refers to a pairing combination of a symptom and a climate parameter.

[0025] Based on the spatiotemporal coupling parameter system, the distribution characteristics of latent symptoms in different regions and under different climatic conditions are identified, and spatiotemporal coupling characteristic data of latent symptoms are obtained. Distribution feature identification employs spatiotemporal clustering analysis, combining spatial clustering and time-series clustering. Spatial clustering utilizes the DBSCAN algorithm, based on density clustering. Input data consists of symptom and climate feature values ​​from a spatiotemporal data cube. DBSCAN algorithm parameters include neighborhood radius and minimum number of points. The neighborhood radius is set based on the k-distance graph method, calculating the distance from each point to its k-th nearest neighbor. The value of k is set to the square root of the number of data points; for example, if the number of data points is 1000, the k value is set to 31. The neighborhood radius is set to the inflection point value of the k-distance graph, determined through visual observation or gradient changes; for example, if the inflection point value is 5, the neighborhood radius is set to 5. The minimum number of points is set based on data density. The formula for calculating the minimum number of points is: minimum number of points equals the number of data points multiplied by a density threshold, set to 0.01; for example, if the number of data points is 1000, the minimum number of points is set to 10. The DBSCAN algorithm outputs spatial cluster labels, assigning a cluster identifier to each spatial unit. The cluster identifier is an integer representing the cluster category to which the spatial unit belongs. Time series clustering uses the K-means algorithm, based on Euclidean distance. The input data consists of time series features from a spatiotemporal data cube. These features are the 30-day symptom frequency sequence and climate deviation value sequence for each spatial unit. K-means algorithm parameters include the number of clusters, set based on the elbow rule. The elbow rule calculates the sum of squares for different cluster numbers. The formula for the sum of squares is: the sum of squares equals the sum of the squares of the distances from all points to their cluster centers. The elbow is determined through visual observation or gradient changes. For example, if the elbow is a cluster number of 5, then the cluster number is set to 5. The K-means algorithm outputs temporal cluster labels, assigning a cluster identifier to each time series. Spatiotemporal clustering fusion combines spatial and temporal clustering labels. The fusion method employs cross-tabulation analysis, which calculates the joint frequency of spatial and temporal clusters. Regions with a joint frequency greater than a preset threshold are marked as spatiotemporal hotspots. The preset threshold is based on historical data distribution and is calculated as the 95th percentile of the historical joint frequency distribution. For example, if the 95th percentile of the historical joint frequency distribution is 0.1, then the preset threshold is set to 0.1. The output of spatiotemporal hotspots is spatiotemporal coupled feature data, presented as a graph. Graph nodes represent spatial units or time points, graph edges represent clustering relationships, and edge weights are the joint frequencies.

[0026] S3: Based on the spatiotemporal coupling characteristics of latent symptoms, the Xin'an Medical Theory is used to identify the latent period infection enhancement effect, and the risk assessment data for latent period infection enhancement is output, including: Based on the spatiotemporal coupling characteristic data of latent symptoms, a latent infection enhancement identification model was constructed with reference to the theory of latent pathogenic factors in Xin'an medicine. The model parameters include a sensitivity threshold parameter for latent symptoms, a weight parameter for environmental and climatic anomalies, and a population constitution category correction parameter. The Xin'an Medical theory of latent pathogenic factors posits that latent pathogenic factors within the body are activated by abnormal changes in external climate, leading to disease. The theory's application includes identifying the coupling pattern between symptoms and climate anomalies as an indicator of the outward manifestation of latent pathogenic factors. The model is constructed using a parametric modeling method, which optimizes model parameters based on historical training data. This historical training data comprises records of epidemic outbreaks in the same region and season over the past five years, along with corresponding symptoms and climate data. The historical training data includes time series of confirmed cases, symptom reporting sequences, and climate anomaly sequences. The method for setting the sensitivity threshold parameter for incubation period symptoms uses receiver operating characteristic curve analysis to calculate the true positive rate and false positive rate under different thresholds. The true positive rate is the proportion of correctly identified high-risk cases, and the false positive rate is the proportion of incorrectly identified low-risk cases as high-risk. The threshold selection is based on the principle of maximizing the Youden index, which is equal to the true positive rate plus the true negative rate minus 1. The true negative rate is the proportion of correctly identified low-risk cases. For example, by analyzing historical training data, the receiver operating characteristic curve for fever symptoms shows that the threshold corresponding to the maximum Youden index is 0.12. Therefore, the threshold for fever symptoms in the sensitivity threshold parameter for incubation period symptoms is set to 0.12. The method for setting the weight parameters of environmental and climate anomalies adopts the entropy weight method. The weight of each climate parameter is calculated based on information entropy. The formula for calculating information entropy is: entropy equals the negative summation probability multiplied by the natural logarithm of the probability. The probability is the frequency of occurrence of each climate parameter in historical anomaly events. The smaller the entropy value, the higher the parameter discrimination. The formula for calculating the weight is: weight equals 1 minus the entropy value divided by the sum of 1 minus the entropy value. For example, the entropy value of the daily average temperature deviation is 0.2, and the entropy value of the daily average relative humidity deviation is 0.3. Then the weight of the daily average temperature deviation is calculated as (1-0.2) / ((1-0.2)+(1-0.3)) equals 0.47, and the weight of the daily average relative humidity deviation is 0.53. The method for setting the population constitution category correction parameters is based on the TCM constitution classification theory, which divides the population into nine basic constitution types, including balanced constitution, qi deficiency constitution, yang deficiency constitution, yin deficiency constitution, phlegm-dampness constitution, damp-heat constitution, blood stasis constitution, qi stagnation constitution, and special constitution. Constitution classification data is obtained through questionnaires, including a constitution identification scale containing 60 questions, each scored from 1 to 5 points. The constitution score is calculated as the sum of scores across all dimensions. Constitution category determination is based on a score threshold, which is set according to the TCM constitution classification and determination criteria. The population constitution category correction parameters are the correction coefficients for each constitution's sensitivity to symptoms and climate. The correction coefficients are set based on historical regression analysis, which establishes a linear regression model linking constitution type with symptoms and climate. The regression coefficients serve as correction coefficients. For example, the correction coefficient for fever symptoms in qi deficiency constitution is 1.2, indicating that the weight of fever symptoms increases by 20% under qi deficiency constitution.

[0027] Based on the sensitivity threshold parameter of latent period symptoms, threshold discrimination is performed on the symptom sensitivity characteristic data of the latent period population to obtain the symptom sensitivity judgment result of the latent period; Each symptom is compared with its frequency to the corresponding threshold in the incubation period symptom sensitivity threshold parameters. A symptom is considered sensitive if its frequency is greater than or equal to the corresponding threshold, and insensitive if its frequency is less than the threshold. The result is output as a binary vector, where the dimension equals the number of symptoms, and each dimension has a value of 0 or 1, where 0 indicates insensitive and 1 indicates sensitive. For example, if the symptoms include fever, cough, and sore throat, the incubation period symptom sensitivity threshold parameters would have a fever threshold of 0.12, a cough threshold of 0.10, and a sore throat threshold of 0.08.

[0028] Based on the environmental and climate anomaly weight parameters, the environmental and climate anomaly fluctuation characteristic data are weighted to obtain the environmental and climate anomaly impact measurement results; The deviation value of each climate parameter is multiplied by its corresponding weight in the environmental climate anomaly weighting parameters. Then, the weighted deviation values ​​of all climate parameters are summed to obtain the daily environmental climate anomaly impact measurement. The impact measurement value equals the sum of the weights multiplied by the deviation values, and the sum covers all climate parameters. For example, climate parameters include daily average temperature deviation and daily average relative humidity deviation. In the environmental climate anomaly weighting parameters, the daily average temperature deviation has a weight of 0.47, and the daily average relative humidity deviation has a weight of 0.53. The environmental climate anomaly impact measurement result is a time series vector, where the dimension of the time series vector equals the number of time points, and each dimension value is the impact measurement value.

[0029] Based on the population physical category correction parameters, the results of sensitivity determination of latent symptoms and measurement of the impact of abnormal environmental climate are corrected by physical category to obtain the coupled results of latent physical correction. Constitutional category correction first assigns a constitution category to each individual based on the constitution classification in the population constitutional category correction parameters. For each individual, a corresponding correction coefficient is obtained from the population constitutional category correction parameters, combining the individual's constitution category. The correction coefficients include symptom correction coefficients and climate correction coefficients. Symptom correction is applied to the sensitivity determination results of latent symptoms. The symptom correction method multiplies each value in the binary vector by the corresponding symptom correction coefficient. If the original determination value is 0 (insensitive), it remains 0 after correction; if the original determination value is 1 (sensitive), the corrected value becomes the correction coefficient. Climate correction is applied to the measurement results of the impact of environmental climate anomalies. The climate correction method multiplies the impact measurement value by the climate correction coefficient. For example, if an individual's constitution is Qi deficiency, the correction coefficient for fever symptoms in the constitution category correction parameters is 1.2, and the correction coefficient for climate influence is 1.1. If the individual's latent period symptom sensitivity judgment result is 1 (sensitive), then the corrected fever value becomes 1.2. If the environmental climate abnormality influence measurement result is 4.06, then the corrected influence measurement value becomes 4.06 multiplied by 1.1, which equals 4.466. After correction, the symptom correction value and the climate correction value are coupled for calculation. The coupling calculation uses a weighted summation formula: the coupling result equals the weighted sum of symptoms plus the climate weighted value. The weighted sum of symptoms is the sum of all symptom correction values, and the climate weighted value is the climate correction value multiplied by a climate weight set to 0.5. For example, if the symptoms include fever, cough, and sore throat, with corrected values ​​of 1.2, 0, and 1.0 respectively, then the weighted sum of symptoms is 1.2 + 0 + 1.0 = 2.2. The climate correction value is 4.466, and the climate weight is 0.5. Therefore, the coupling result is 2.2 plus 4.466 multiplied by 0.5, which equals 4.433. The coupling result of the latent period constitution correction is in vector form, with the vector dimension equal to the number of individuals, and each dimension value being the coupling result value.

[0030] Based on the results of latent period constitution correction coupling, the infection enhancement determination of the latent period infection enhancement identification model is carried out, and latent period infection enhancement risk determination data is generated; The determination of enhanced infectivity employs a logistic regression model. The input is the coupling result of latent period constitution correction, and the output is the probability of enhanced infectivity. The probability of enhanced infectivity is equal to 1 divided by 1 plus e raised to the power of -z, where z equals the linear combination value. The linear combination value is equal to the coefficient multiplied by the coupling result plus the intercept. The coefficient and intercept are obtained through training on historical training data, which includes labels of past outbreak events. The labels are binary variables, with 1 indicating an outbreak and 0 indicating no outbreak. The model is trained using maximum likelihood estimation, which optimizes the parameters to maximize the likelihood function, which is the product of the probabilities of all samples. The determination threshold is set to 0.5. When the probability of enhanced infectivity is greater than or equal to 0.5, it is considered high-risk; when the probability is less than 0.5, it is considered low-risk. The data for determining the risk of enhanced infectivity during the latent period is a risk label vector. The dimension of the risk label vector equals the number of individuals, and each dimension has a value of 0 or 1, where 0 represents low risk and 1 represents high risk.

[0031] S4: Based on the risk assessment data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period, and output high-risk assessment data for the incubation period population, including: Based on the data on the risk of enhanced transmission during the incubation period, a risk threshold for enhanced transmission during the incubation period is set. The threshold for enhanced transmission risk during the incubation period was set using a population-level risk assessment method, based on aggregate analysis of historical epidemic outbreak data and corresponding individual risk labels. Historical epidemic outbreak data consisted of records of infectious disease outbreaks in the same region and season over the past five years, including outbreak time, location, and outbreak intensity index. The outbreak intensity index was calculated by dividing the number of confirmed cases by the total population. The aggregate analysis first summarized historical individual risk labels by geospatial grid, using the same grid division method as in step S2, with each spatial unit being a rectangular grid. The grid identifier included latitude and longitude information. For each historical time point and each spatial unit, the proportion of high-risk individuals within the unit was calculated, equal to the number of individuals with a risk label of 1 divided by the total number of individuals within the unit. A correlation analysis was then performed between the proportion of high-risk individuals and the actual outbreak intensity index of the corresponding spatial unit. This correlation analysis employed receiver operating characteristic (ROC) curve analysis, which calculated the true positive rate and false positive rate under different high-risk individual proportion thresholds. For example, by analyzing historical data, the receiver operating characteristic curve shows that the highest Youden index corresponds to a high-risk individual proportion threshold of 0.25, so the enhanced risk threshold for transmission during the incubation period is set at 0.25.

[0032] By comparing the data on the risk of enhanced transmission during the incubation period with the risk threshold for enhanced transmission during the incubation period, it can be determined whether the population during the incubation period is in a high-risk state, and the high-risk determination result of the population during the incubation period can be obtained. The comparison process is based on a geospatial grid, and the geospatial grid division method is consistent with that in step S2. Each spatial unit is assigned a unique grid identifier. For each spatial unit, risk labels for all individuals within the unit are extracted from the latent period infection enhancement risk assessment data. Risk labels are either 0 or 1. The proportion of high-risk individuals in the spatial unit is calculated, which is equal to the number of individuals with a risk label of 1 divided by the total number of individuals in the unit. The proportion of high-risk individuals in the spatial unit is compared with the latent period infection enhancement risk threshold. If the proportion of high-risk individuals is greater than or equal to the latent period infection enhancement risk threshold, the spatial unit is determined to be in a high-risk state; if the proportion of high-risk individuals is less than the latent period infection enhancement risk threshold, the spatial unit is determined to be in a low-risk state. The high-risk assessment result for the latent period population is a spatial unit risk state vector. The dimension of the spatial unit risk state vector is equal to the number of spatial units, and each dimension has a value of 0 or 1, where 0 represents a low-risk state and 1 represents a high-risk state.

[0033] The results of high-risk group assessment during the incubation period are matched with the geographic distribution information of the population to generate high-risk group assessment data during the incubation period. First, the spatial unit risk status vectors from the high-risk assessment results of the latent period population are associated with the spatial unit geographic coordinates from the population geographic distribution information. The association method is based on grid identifier matching, where each grid identifier corresponds to a unique geographic coordinate range. A geospatial risk distribution map is generated. The geospatial risk distribution map is in vector map form, containing multiple polygonal features. Each polygonal feature corresponds to a spatial unit, and its attribute table includes the grid identifier, latitude and longitude range, and risk status value. The risk status value is obtained from the spatial unit risk status vector and is either 0 or 1. For example, if the spatial unit with grid identifier A001 in the spatial unit risk status vector has a risk status of 1, and the latitude and longitude range corresponding to grid identifier A001 in the population geographic distribution information is 120.1°E to 120.2°E and 30.1°N to 30.2°N, then the risk status value of the polygonal feature in the geospatial risk distribution map is set to 1. The high-risk assessment data for the latent period population is output as a geospatial risk distribution map file in Shapefile format.

[0034] S5: Based on the high-risk assessment data of the incubation period population, determine the high-risk areas and spatial distribution of susceptible populations during the incubation period, and output spatial risk hotspot identification data, including: By identifying spatial hotspots, areas with dense distribution of high-risk populations in the data on high-risk groups during the incubation period can be determined. Spatial hotspot identification employs local spatial autocorrelation analysis to calculate the similarity of risk status between each spatial unit and its neighboring units. Input data consists of the spatial unit risk status vector and geographic coordinates from the high-risk assessment data for latent populations. The dimension of the spatial unit risk status vector equals the number of spatial units, with each dimension representing a risk status value. The geographic coordinates of the spatial units are extracted from the geometric attributes of a Shapefile file, which is a list of polygon vertex coordinates. Local spatial autocorrelation analysis uses the local Moran index, calculated as follows: the local Moran index equals the spatial unit's risk status value minus the global mean multiplied by the neighboring unit's risk status value minus the global mean, then divided by the global variance. The global mean is the average of all spatial unit risk status values, and the global variance is the variance of all spatial unit risk status values. The summation covers all neighboring units. Neighboring units are defined based on a spatial weight matrix, which uses the Queen adjacency rule. The Queen adjacency rule defines two spatial units as neighboring when they share a boundary or vertex. Elements in the spatial weight matrix are 1 for neighborliness and 0 for non-neighborliness. A local Moran's index value greater than 0 indicates positive spatial autocorrelation, i.e., high-risk clustering; a value less than 0 indicates negative spatial autocorrelation, i.e., low-risk clustering; and a value close to 0 indicates random distribution. A significance threshold is set for determining densely populated high-risk areas. This threshold is based on Monte Carlo simulation, where the risk state value is randomly permuted 1000 times. The local Moran's index distribution is calculated for each iteration. The significance level is set to 0.05. When the local Moran's index p-value is less than 0.05 and the local Moran's index value is greater than 0, the spatial unit is determined to be a hotspot area.

[0035] Based on the densely populated areas of high-risk populations, determine the geographical distribution characteristics of high-risk populations; Geographic location distribution features are extracted using spatial statistical methods, including calculating the spatial center point, spatial distribution range, and spatial density of hotspot regions. The spatial center point is calculated as the geometric center of the hotspot region polygon. The formula for calculating the geometric center is: the longitude of the center point equals the average longitude of all vertices of the hotspot polygons, and the latitude of the center point equals the average latitude of all vertices of the hotspot polygons. The spatial distribution range is calculated as the minimum bounding rectangle of the hotspot region. The minimum bounding rectangle is formed by traversing all vertices of the hotspot polygons and finding the minimum and maximum latitude and longitude values. The spatial density is calculated as the ratio of the area of ​​the hotspot region to the total area. The area of ​​the hotspot region is obtained by summing the areas of all hotspot polygons. The polygon area calculation uses the shoelace formula, summing to cover all vertices. For example, if the center point of a hotspot area has a longitude of 120.5 degrees and a latitude of 30.2 degrees, and its smallest circumscribed rectangle extends from 120.4 degrees east longitude to 120.6 degrees east longitude and from 30.1 degrees north latitude to 30.3 degrees north latitude, with a hotspot area of ​​10 square kilometers and a total area of ​​1000 square kilometers, then the spatial density is 10 divided by 1000, which equals 0.01. The geographical distribution characteristics of high-risk populations include the coordinates of the center point, the coordinates of the distribution boundary, and the spatial density.

[0036] Based on population symptom sensitivity data and environmental climate abnormal fluctuation data, spatial correlation feature analysis is conducted to obtain correlation feature data between high-risk populations and environmental climate abnormalities. Spatial correlation feature analysis employs a geographically weighted regression method to model the spatially non-stationary relationship between high-risk populations and symptom-related climate variables. Input data includes hotspot label vectors for densely distributed high-risk populations, symptom sensitivity data, and environmental climate anomaly fluctuation data. All data are aligned to the same spatial unit and time point. The geographically weighted regression model formula is: hotspot label equals intercept plus a summed coefficient multiplied by symptom frequency plus a summed coefficient multiplied by climate bias. The intercept and coefficient are spatially variable parameters, calculated based on a spatial kernel function. A Gaussian kernel function is used, with the formula: weight equals the square of the negative distance e divided by the square of the bandwidth. The distance is the Havesing distance between the center points of the spatial units. The bandwidth is set based on cross-validation, which minimizes the prediction error, which is the root mean square error between the actual hotspot label and the predicted value. For example, the bandwidth is determined to be 5 kilometers through cross-validation. The geographically weighted regression coefficient output is a coefficient plot, which includes the intercept value for each spatial unit and the coefficient values ​​for each symptom-related climate variable. The correlation feature data is represented as a coefficient vector, with the dimension of the coefficient vector equal to the number of symptom climate variables. Each dimension's value is the average coefficient, calculated as the average of the coefficients across all spatial units. For example, the average coefficient for fever symptoms is 0.8, and the average coefficient for daily average temperature deviation is 0.5, indicating a positive correlation between fever symptoms and daily average temperature deviation and high-risk populations.

[0037] Based on the geographical distribution characteristics of high-risk groups and the correlation characteristics between high-risk groups and environmental and climate anomalies, high-risk areas of latent populations and the spatial distribution range of susceptible populations are determined, and spatial risk hotspot identification data are generated. The determination of high-risk areas is based on spatial density and correlation strength. The spatial density threshold is set at the 75th percentile of the historical spatial density distribution, which is calculated based on data from the same region over the past five years. The correlation strength threshold is set at the 75th percentile of the absolute value of the average coefficient. For example, the 75th percentile of the historical spatial density distribution is 0.02, and the 75th percentile of the average coefficient is 0.6. The determination of the spatial distribution range of susceptible populations is based on symptom sensitivity feature data, which is in vector form. The vector dimension equals the number of symptoms, and each dimension value is the frequency of symptom occurrence. A frequency threshold is set for susceptible population determination, based on the 90th percentile of the historical symptom frequency distribution. For example, the frequency threshold for fever is 0.15. Spatial distribution range generation uses spatial overlay analysis, combining high-risk areas and susceptible population areas. High-risk areas are regions with spatial density greater than or equal to the spatial density threshold and correlation strength greater than or equal to the correlation strength threshold. Susceptible population areas are spatial units with symptom occurrence frequencies greater than or equal to the frequency threshold. The overlay analysis method uses the intersection operation in the geographic information system, and the intersection operation outputs the overlapping area. Spatial risk hotspot identification data is output as a risk hotspot map in vector format. Each element represents a hotspot area, and the element attribute table includes an area identifier, risk level, and the proportion of susceptible population. The risk level is calculated based on a weighted sum of spatial density and average coefficient, with a weighting of 0.5 to 0.5. For example, if a hotspot area has a spatial density of 0.03 and an average coefficient of 1.2, its risk level is calculated to be 0.5. 0.03 + 0.5 1.2 = 0.615.

[0038] S6: Based on spatial risk hotspot identification data and combined with the infectious disease early warning grading decision model, generate respiratory infectious disease early warning information, including: Based on spatial risk hotspot identification data, an infectious disease early warning and grading decision-making model was established. The infectious disease early warning and grading decision-making model includes regional risk level classification rules, risk level determination criteria, and early warning information grading rules. The regional risk level classification rules define the early warning level classification for high-risk areas, with four levels: red, orange, yellow, and blue. Red indicates the highest risk level, and blue indicates the lowest. The regional risk level classification rules are based on risk levels identified in spatial risk hotspot identification data. Three risk level thresholds are set for the early warning level classification. The threshold setting method combines historical outbreak analysis with the quantile method. Historical outbreak analysis is based on infectious disease outbreak records from the same region and season over the past five years. Outbreak records include outbreak time, location, and outbreak intensity index, which is the number of confirmed cases divided by the total population. The quantile method calculates the risk level distribution corresponding to historical outbreaks, selecting three quantile points as thresholds. The selection of quantile points is based on the principle of balancing early warning sensitivity and specificity. Sensitivity is the proportion of correctly identified high-risk events, and specificity is the proportion of correctly identified low-risk events. For example, by analyzing historical data, if the 25th percentile of the risk level distribution is 0.3, the 50th percentile is 0.5, and the 75th percentile is 0.7, then the risk level thresholds are set to 0.3, 0.5, and 0.7. The risk level classification rules are as follows: a risk level less than 0.3 is classified as a blue alert; a risk level greater than or equal to 0.3 and less than 0.5 is classified as a yellow alert; a risk level greater than or equal to 0.5 and less than 0.7 is classified as an orange alert; and a risk level greater than or equal to 0.7 is classified as a red alert. The risk level determination criteria define the risk level classification of susceptible populations, with three levels: high risk, medium risk, and low risk. High risk indicates that the susceptible population is in the highest risk state, and low risk indicates that the susceptible population is in the lowest risk state. The risk level determination criteria are based on the proportion of susceptible populations in the spatial risk hotspot identification data. The risk level determination uses two thresholds for the proportion of susceptible populations. These thresholds are set using historical susceptible population data distribution analysis, which calculates the quantiles of the susceptible population proportion distribution based on the past five years' data on the proportion of susceptible populations in the same region and season. For example, if the 33rd percentile of the historical susceptible population proportion distribution is 0.2 and the 67th percentile is 0.4, then the thresholds are set at 0.2 and 0.4. The risk level determination criteria are: a susceptible population proportion less than 0.2 indicates low risk; a susceptible population proportion greater than or equal to 0.2 and less than 0.4 indicates medium risk; and a susceptible population proportion greater than or equal to 0.4 indicates high risk. The warning information grading rules define the warning information content corresponding to each warning level and risk level. The warning information content includes the warning level, scope of impact, recommended measures, and dissemination channels. The warning information grading rules are in the form of a rule table, a two-dimensional table where rows correspond to combinations of warning and risk levels, and columns correspond to the warning information.The warning level uses the warning grade and risk level name, such as Red Alert (High Risk). The scope of impact describes the geographical area and population size covered by the warning. The geographical area is obtained from the area identifier of the spatial risk hotspot identification data, and the population size is calculated based on the proportion of susceptible individuals and the total population of the area, which is obtained from a census database. Recommended measures provide prevention and control recommendations based on the warning level and risk level. For example, recommended measures for a Red Alert (High Risk) include restricting the movement of people, strengthening the allocation of medical resources, and issuing health advisories. The dissemination channels define how the warning information is disseminated, including SMS notifications, mobile application push notifications, and public media broadcasts.

[0039] Based on spatial risk hotspot identification data, and according to regional risk level classification rules, high-risk areas are divided into different warning levels; The regional risk level classification rules include risk level thresholds and warning level categories. Risk level thresholds are 0.3, 0.5, and 0.7, and warning levels are divided into red, orange, yellow, and blue warnings. According to the regional risk level classification rules, the warning level is determined by comparing the risk level with the risk level thresholds. If the risk level value is less than 0.3, the warning level is set to blue; if the risk level is greater than or equal to 0.3 and less than 0.5, the warning level is set to yellow; if the risk level is greater than or equal to 0.5 and less than 0.7, the warning level is set to orange; and if the risk level is greater than or equal to 0.7, the warning level is set to red.

[0040] Based on the risk level assessment criteria, the risk level of susceptible populations in each high-risk area is determined; For each high-risk area, the proportion of susceptible individuals is retrieved from the spatial risk hotspot identification data. Based on the risk level determination criteria, the proportion of susceptible individuals is compared with a threshold to determine the risk level. If the proportion of susceptible individuals is less than 0.2, the risk level is set to low; if the proportion is greater than or equal to 0.2 and less than 0.4, the risk level is set to medium; and if the proportion is greater than or equal to 0.4, the risk level is set to high.

[0041] Based on the rules for classifying early warning information, respiratory infectious disease early warning information is generated for each high-risk area and the susceptible population at the corresponding risk level. Based on the combination of warning level and risk level, corresponding warning information content is matched to generate respiratory infectious disease warning information. For example, if the warning level is orange, the risk level is medium risk, the affected area is region A, the population size is 3500, the recommended measures are to strengthen monitoring and issue health tips, and the dissemination channels are SMS notifications and mobile application push notifications.

[0042] Example 2 The difference between Embodiment 2 and Embodiment 1 is that this embodiment introduces a respiratory infectious disease early warning system based on Xin'an Medicine.

[0043] Figure 2 A schematic diagram of a respiratory infectious disease early warning system based on Xin'an Medicine is provided. The system includes: Symptom association module: Collects self-reported symptom information and environmental climate data from people during the incubation period, performs sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generates data on the association between incubation period symptoms and climate anomalies. Spatiotemporal coupling module: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output spatiotemporal coupling characteristic data of latent symptoms; Latent Symptom Identification Module: Based on the spatiotemporal coupling characteristic data of latent symptoms, the module uses the Xin'an Medical Theory to identify the enhanced infectivity effect during the latent period and outputs risk assessment data for enhanced infectivity during the latent period. Threshold determination module: Based on the risk determination data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period and output the high-risk determination data of the incubation period population; Spatial Hotspot Module: Based on the high-risk assessment data of the incubation period population, determine the high-risk areas of the incubation period population and the spatial distribution of susceptible populations, and output spatial risk hotspot identification data; Tiered early warning module: Based on spatial risk hotspot identification data and combined with the infectious disease early warning tiered decision model, it generates early warning information for respiratory infectious diseases.

[0044] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0045] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0046] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0047] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0048] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0049] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0050] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0051] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0052] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for early warning of respiratory infectious diseases based on Xin'an Medicine, characterized in that, Includes the following steps: S1: Collect symptom self-reporting information and environmental climate data from people during the incubation period, conduct sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generate data on the correlation between incubation period symptoms and climate anomalies. S2: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output the spatiotemporal coupling characteristic data of latent symptoms. S3: Based on the spatiotemporal coupling characteristic data of latent symptoms, the Xin'an Medical Theory is used to identify the latent infection enhancement effect and output the risk assessment data of latent infection enhancement. S4: Based on the risk assessment data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period and output the high-risk assessment data of the incubation period population; S5: Based on the high-risk assessment data of the latent period population, determine the high-risk areas and spatial distribution of susceptible populations during the latent period, and output spatial risk hotspot identification data; S6: Based on spatial risk hotspot identification data and combined with the infectious disease early warning classification decision model, generate early warning information for respiratory infectious diseases.

2. The respiratory infectious disease early warning method based on Xin'an Medicine according to claim 1, characterized in that, S1, specifically: Collect self-reported symptom information from people during the incubation period and environmental and climate data of the environment in which the people are located; Sensitivity screening of symptom features was performed on the collected self-reported symptom information to obtain sensitive feature data of symptoms in the latent period population; Analyze the characteristics of abnormal fluctuations in environmental and climate data to obtain characteristic data of abnormal fluctuations in environmental and climate. Based on the sensitive characteristic data of latent period symptoms and the characteristic data of abnormal fluctuations in environmental climate, the correlation characteristics between latent period symptoms and abnormal fluctuations in environmental climate are determined, and the correlation data between latent period symptoms and climate anomalies are generated.

3. The respiratory infectious disease early warning method based on Xin'an Medicine according to claim 2, characterized in that, S2, specifically: Based on the correlation data between latent period symptoms and climate anomalies, the spatiotemporal correspondence between latent period symptom sensitivity characteristics data and environmental climate anomaly fluctuation characteristics data was determined. Based on the spatiotemporal correspondence, and combined with the actual distribution area of ​​the population and the range of environmental and climate change, a spatiotemporal coupling parameter system between weak symptoms during the incubation period and regional climate anomalies is constructed. Based on the spatiotemporal coupling parameter system, the distribution characteristics of latent symptoms in different regions and under different climatic conditions are identified, and spatiotemporal coupling characteristic data of latent symptoms are obtained.

4. The respiratory infectious disease early warning method based on Xin'an Medicine according to claim 3, characterized in that, The spatiotemporal coupling parameter system includes spatial coupling weight parameters, temporal coupling weight parameters, and symptom-climate correlation strength parameters.

5. A respiratory infectious disease early warning method based on Xin'an Medicine according to claim 4, characterized in that, S3, specifically: Based on the spatiotemporal coupling characteristic data of latent symptoms, a latent infection enhancement identification model was constructed with reference to the theory of latent pathogenic factors in Xin'an medicine. Threshold discrimination is performed on the symptom sensitivity characteristics data of the latent period population to obtain the symptom sensitivity determination results of the latent period; By weighting the characteristic data of abnormal fluctuations in environmental and climate, the results of measuring the impact of abnormal environmental and climate are obtained. The results of sensitivity assessment of latent symptoms and measurement of the impact of abnormal environmental and climate conditions are corrected by physical fitness categories to obtain the coupled results of latent physical fitness correction. Based on the results of latent period constitution correction coupling, the infection enhancement determination of the latent period infection enhancement identification model is carried out, and the latent period infection enhancement risk determination data is generated.

6. A method for early warning of respiratory infectious diseases based on Xin'an Medicine according to claim 5, characterized in that, The parameters of the latent period infection enhancement identification model based on the theory of latent pathogenic factors in Xin'an Medicine include the sensitivity threshold parameter for latent period symptoms, the weight parameter for environmental and climatic anomalies, and the correction parameter for population constitution category.

7. A respiratory infectious disease early warning method based on Xin'an Medicine according to claim 6, characterized in that, S4, specifically: Based on the data on the risk of enhanced transmission during the incubation period, a risk threshold for enhanced transmission during the incubation period is set. By comparing the data on the risk of enhanced transmission during the incubation period with the risk threshold for enhanced transmission during the incubation period, it can be determined whether the population during the incubation period is in a high-risk state, and the high-risk determination result of the population during the incubation period can be obtained. The results of high-risk group assessment during the incubation period are matched with the geographic distribution information of the population to generate high-risk group assessment data during the incubation period.

8. A respiratory infectious disease early warning method based on Xin'an Medicine according to claim 7, characterized in that, S5, specifically: By identifying spatial hotspots, areas with dense distribution of high-risk populations in the data on high-risk groups during the incubation period can be determined. Based on the densely populated areas of high-risk populations, determine the geographical distribution characteristics of high-risk populations; Based on population symptom sensitivity data and environmental climate abnormal fluctuation data, spatial correlation feature analysis is conducted to obtain correlation feature data between high-risk populations and environmental climate abnormalities. Based on the geographical distribution characteristics of high-risk groups and the correlation characteristics between high-risk groups and environmental and climate anomalies, high-risk areas of the incubation period and the spatial distribution range of susceptible groups are determined, generating spatial risk hotspot identification data.

9. A respiratory infectious disease early warning method based on Xin'an Medicine according to claim 8, characterized in that, S6, specifically: Based on spatial risk hotspot identification data, an infectious disease early warning classification decision model is established, including regional risk level classification rules, risk level determination criteria, and early warning information classification rules. Based on spatial risk hotspot identification data, and according to regional risk level classification rules, high-risk areas are divided into different warning levels; Based on the risk level assessment criteria, the risk level of susceptible populations in each high-risk area is determined; Based on the rules for classifying early warning information, respiratory infectious disease early warning information is generated for each high-risk area and the susceptible population at the corresponding risk level.

10. A respiratory infectious disease early warning system based on Xin'an Medicine, used to implement the respiratory infectious disease early warning method based on Xin'an Medicine as described in any one of claims 1-9, characterized in that, include: Symptom association module: Collects self-reported symptom information and environmental climate data from people during the incubation period, performs sensitivity screening of symptom characteristics and analysis of abnormal fluctuations in environmental climate, and generates data on the association between incubation period symptoms and climate anomalies. Spatiotemporal coupling module: Based on the correlation data between latent symptoms and climate anomalies, establish the spatiotemporal coupling relationship between weak latent symptoms and regional climate anomalies, and output spatiotemporal coupling characteristic data of latent symptoms; Latent Symptom Identification Module: Based on the spatiotemporal coupling characteristic data of latent symptoms, the module uses the Xin'an Medical Theory to identify the enhanced infectivity effect during the latent period and outputs risk assessment data for enhanced infectivity during the latent period. Threshold determination module: Based on the risk determination data of enhanced transmission during the incubation period, determine the risk threshold of the enhanced transmission effect during the incubation period and output the high-risk determination data of the incubation period population; Spatial Hotspot Module: Based on the high-risk assessment data of the incubation period population, determine the high-risk areas of the incubation period population and the spatial distribution of susceptible populations, and output spatial risk hotspot identification data; Tiered early warning module: Based on spatial risk hotspot identification data and combined with the infectious disease early warning tiered decision model, it generates early warning information for respiratory infectious diseases.

Images