Urban epidemic risk prediction method and device

Abstract

The application provides a city epidemic risk prediction method and device, the method comprises the following steps: obtaining internal epidemic data of multiple types of people in a preset area and external epidemic data of other areas outside the preset area; obtaining an internal transmission risk prediction curve according to the internal epidemic data and a first prediction model; obtaining an external inflow risk prediction curve according to the external epidemic data and a second prediction model; obtaining a weight vector of a first preset index in the preset area; weighting and integrating the internal transmission risk prediction curve and the external inflow risk prediction curve according to the weight vector of the first preset index to obtain an epidemic risk prediction curve; by predicting the internal transmission risk and the external transmission risk respectively and considering the isolation of the latent population under the actual epidemic prevention and control measures, the accuracy of the epidemic risk prediction can be effectively improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of urban epidemic risk prediction, and particularly relates to an urban epidemic risk prediction method and device. BACKGROUND

[0002] Epidemic risk prediction is one of the key topics in the field of public health safety. Predicting epidemic spatial risk data can make urban epidemic risk more intuitive and make people more clear about the risk degree of the region they are in, which is helpful for decision-making of epidemic supervision and resumption of work and school.

[0003] In the prior art, the SEIR (Susceptible-Exposed-Infected-Removed) dynamic model is usually used for prediction, which considers four kinds of populations, i.e. susceptible, exposed, infected and removed, to predict the risk of infectious diseases. However, this prediction method does not take into account the actual epidemic prevention situation, and the accuracy of epidemic risk prediction is low. SUMMARY

[0004] Therefore, the application provides an urban epidemic risk prediction method and device, aiming to solve the problem of low safety of epidemic risk prediction.

[0005] The first aspect of the embodiment of the application provides an urban epidemic risk prediction method, comprising:

[0006] obtaining internal epidemic data of multiple types of populations in a preset area and external epidemic data of other areas outside the preset area;

[0007] obtaining an internal transmission risk prediction curve according to the internal epidemic data and a first prediction model;

[0008] obtaining an external inflow risk prediction curve according to the external epidemic data and a second prediction model;

[0009] obtaining a weight vector of a first preset index in the preset area;

[0010] integrating the internal transmission risk prediction curve and the external inflow risk prediction curve by weighting according to the weight vector of the first preset index to obtain an epidemic risk prediction curve;

[0011] The multiple types of populations include susceptible, exposed, infected, removed, dead and isolated latent populations; the first preset index includes an urban internal transmission risk index and an urban external inflow risk index; the first prediction model represents the relationship between the change rate of the number of each type of population and the epidemic data; and the second prediction model represents the relationship between the number of infected persons flowing into the preset area per unit time from other areas and the number of infected persons in other areas.

[0012] The second aspect of the embodiment of the present application provides a city epidemic risk prediction device, comprising:

[0013] a first acquisition module configured to acquire internal epidemic data of a plurality of types of people in a preset area and external epidemic data of other areas outside the preset area;

[0014] a processing module configured to obtain an internal transmission risk prediction curve according to the internal epidemic data and a first prediction model, and obtain an external inflow risk prediction curve according to the external epidemic data and a second prediction model;

[0015] a second acquisition module configured to acquire a weight vector of a first preset index in the preset area;

[0016] an integration module configured to perform weighted integration on the internal transmission risk prediction curve and the external inflow risk prediction curve according to the weight vector of the first preset index to obtain an epidemic risk prediction curve;

[0017] The plurality of types of people include susceptible people, latent people, infected people, recovered people, dead people and isolated latent people; the first preset index includes a city internal transmission risk index and a city external inflow risk index; the first prediction model represents a relationship between a change rate of the number of people of each type and the epidemic data; and the second prediction model represents a relationship between the number of infected people flowing into the preset area per unit time from other areas and the number of infected people in other areas.

[0018] The third aspect of the embodiment of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to realize the steps of the city epidemic risk prediction method according to the first aspect.

[0019] The fourth aspect of the embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the city epidemic risk prediction method according to the first aspect.

[0020] The urban epidemic risk prediction method and device provided in this invention acquire internal epidemic data of multiple population groups in a preset area and external epidemic data of other areas outside the preset area; obtain an internal transmission risk prediction curve based on the internal epidemic data and a first prediction model; obtain an external inflow risk prediction curve based on the external epidemic data and a second prediction model; acquire the weight vector of a first preset indicator within the preset area; and weight and integrate the internal transmission risk prediction curve and the external inflow risk prediction curve based on the weight vector of the first preset indicator to obtain the epidemic risk prediction curve. By predicting internal transmission risk and external transmission risk separately, and considering the isolation of potential carriers under actual epidemic prevention and control measures, the accuracy of epidemic risk prediction can be effectively improved. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is an application environment diagram of an urban epidemic risk prediction method provided in one embodiment of the present invention;

[0023] Figure 2 This is a flowchart illustrating the implementation of an urban epidemic risk prediction method according to an embodiment of the present invention;

[0024] Figure 3 This is a transformation relationship diagram between various groups of people provided in one embodiment of the present invention;

[0025] Figure 4 This is a flowchart illustrating the implementation of an urban epidemic risk prediction method provided in an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of an urban epidemic risk prediction device provided in one embodiment of the present invention;

[0027] Figure 6 This is a schematic diagram of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0028] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0029] The current outbreaks of infectious pneumonias, such as COVID-19, can easily lead to rapid spread of the epidemic within a short period of time, posing a significant and sudden public health emergency. Predicting spatial risk data for epidemics can make urban epidemic risks more intuitive, allowing people to better understand the risk level of their area, and assisting local governments in making decisions regarding epidemic control and the resumption of work and school.

[0030] Taking into account multiple factors such as the current state of the epidemic, population size, population mobility, and the characteristics of epidemic risk, and combining relevant epidemic risk theories, this study concludes that the main sources of urban epidemic risk lie in the risk of transmission within the city and the risk of inflow from outside the city. It is determined that this invention is suitable for research using the SEIR epidemic dynamics model and the Keyfitz population migration model, and then the curves obtained from the two models are integrated using the analytic hierarchy process (AHP). This invention can specifically predict the risk values ​​of internal transmission and external inflow within a city based on time, which is of great significance for summarizing epidemic risk.

[0031] Currently, the use of dynamics for risk prediction is widely applied in various fields such as mining exploration, forest fire prevention, landslide surveying, and metal pollution control. Corresponding epidemic dynamics models can also be used for epidemic risk prediction. However, existing epidemic risk prediction systems still have shortcomings. Most researchers only assess epidemic risk at the national or provincial level, and risk assessment for small and medium-sized cities remains incomplete. Therefore, this invention uses a modified SEIR epidemic dynamics model and a modified Keyfitz population migration model to calculate risks inside and outside the city, and integrates these risks through the analytic hierarchy process (AHP) to achieve urban epidemic risk prediction.

[0032] Figure 1 This is an application environment diagram of an urban epidemic risk prediction method provided in one embodiment of the present invention. The urban epidemic risk prediction method provided in this embodiment of the present invention can be applied to, but is not limited to, this application environment. Figure 1 As shown, the system includes: database 11, electronic device 12, and terminal device 13.

[0033] The database 11 is configured to store epidemic data and send the epidemic data corresponding to the acquisition instruction sent by the electronic device 12 after receiving the acquisition instruction. The electronic device 12 is configured to obtain the epidemic risk prediction curve and / or the epidemic risk prediction map after obtaining the data from the database 11. The terminal device 13 is configured to send a query instruction to the electronic device 12. The electronic device 12 is further configured to send the epidemic risk prediction curve and / or the epidemic risk prediction map corresponding to the time period queried by the terminal device 13 after receiving the query instruction. The terminal device 13 is further configured to display the epidemic risk prediction curve and / or the epidemic risk prediction map.

[0034] The database 11 can be a relational database or a non-relational database, which is not limited herein. The electronic device 12 can be a server, a terminal, or the like, which is not limited herein. The server can be implemented by an independent server or a server cluster composed of multiple servers. The terminal can include, but is not limited to, a desktop computer, a notebook computer, a tablet computer, and the like. The terminal device 13 can include, but is not limited to, a desktop computer, a notebook computer, and a tablet computer.

[0035] Figure 2 is an implementation flowchart of the urban epidemic risk prediction method provided by an embodiment of the present application. In this embodiment, the method is applied to the electronic device in Figure 1 . As shown in Figure 2 , the method comprises the following steps.

[0036] S201, obtaining internal epidemic data of multiple types of people in a preset area and external epidemic data of other areas outside the preset area.

[0037] S202, obtaining an internal transmission risk prediction curve according to the internal epidemic data and a first prediction model, and obtaining an external inflow risk prediction curve according to the external epidemic data and a second prediction model.

[0038] S203, obtaining a weight vector of a first preset index in the preset area.

[0039] S204, weighting and integrating the internal transmission risk prediction curve and the external inflow risk prediction curve according to the weight vector of the first preset index to obtain an epidemic risk prediction curve.

[0040] The multiple types of people include susceptible people, latent people, infected people, recovered people, dead people, and isolated latent people. The first preset index includes an urban internal transmission risk index and an urban external inflow risk index. The first prediction model represents the relationship between the change rate of the number of people of each type and the epidemic data. The second prediction model represents the relationship between the number of infected people flowing into the preset area per unit time and the number of infected people in other areas.

[0041] In this embodiment, the preset area can be a region of any size, which is specifically set according to actual conditions, for example, can be set according to administrative regions, or can be set according to epidemic situation, which is not limited herein. Other regions outside the preset area are regions that have population migration with the preset area. The first prediction model can be a neural network model, a support vector machine model, a modified SEIR infectious disease dynamics model, etc., which is not limited herein. The second prediction model can be a neural network model, a support vector machine model, a modified Keyfitz population migration model, etc., which is not limited herein. The algorithm for calculating the weight vector of the first preset index can be an analytic hierarchy process algorithm, an entropy method algorithm, a principal component analysis algorithm, etc., which is not limited herein.

[0042] Optionally, the internal epidemic data can include, but is not limited to, at least one of the following: a transmission probability of each contact of an infected person, a number of contacts per unit time of an infected person, a conversion rate between various populations, a transmission ability coefficient of a latent person relative to an infected person, a moving rate of other regions to the preset region, and a number of initial values of each population. Optionally, the external epidemic data can include, but is not limited to, at least one of the following: the number of epidemic cases in other regions, and the migration rate of the population of other regions to the preset region.

[0043] In this embodiment, the internal epidemic data of multiple populations in the preset region and the external epidemic data of other regions outside the preset region are obtained; an internal transmission risk prediction curve is obtained according to the internal epidemic data and the first prediction model; an external inflow risk prediction curve is obtained according to the external epidemic data and the second prediction model; a weight vector of the first preset index in the preset region is obtained; and the internal transmission risk prediction curve and the external inflow risk prediction curve are weighted and integrated according to the weight vector of the first preset index, to obtain an epidemic risk prediction curve. The respective prediction of the internal transmission risk and the external transmission risk, and the consideration of the latent population under actual epidemic prevention and control measures, can effectively improve the accuracy of the epidemic risk prediction.

[0044] In some embodiments, the internal transmission risk prediction curve is obtained according to the internal epidemic data and the first prediction model, including:

[0045] A number change curve corresponding to each population is obtained according to the internal epidemic data and the first prediction model;

[0046] A weight vector of the second preset index in the preset region is obtained;

[0047] The number change curves corresponding to each population are weighted and integrated according to the weight vector of the second preset index, to obtain the internal transmission risk prediction curve; wherein the second preset index includes a susceptible person index, a latent person index, an infected person index, a cured person index, a dead person index, and an isolated latent person index.

[0048] In this embodiment, the algorithm for calculating the weight vector of the second preset index can be an analytic hierarchy process algorithm, an entropy value method algorithm, a principal component analysis algorithm, etc., which is not limited herein.

[0049] Figure 3 is a conversion relationship diagram between various populations provided by an embodiment of the present application. On the basis of any of the above embodiments, the first prediction model comprises a modified SEIR infectious disease dynamics model.

[0050] At present, high-risk susceptible populations are usually concentrated for isolation, and all infected persons are isolated for treatment. Considering the influence of prevention and control measures, new population isolation latent persons (Eq) and dead persons (D) are added to the model, so that it is more suitable for city-level epidemic risk calculation.

[0051] Figure 3 In this embodiment, the types of the population include: susceptible persons, latent persons, infected persons, recovered persons, dead persons and isolated latent persons. The susceptible persons refer to healthy people who have not been infected, i.e. people who are easily infected after contacting the infected persons; the latent persons refer to people who carry the infection source but have not shown clinical symptoms, and can transmit the infection to the susceptible persons; the infected persons refer to people who have shown clinical symptoms and have been diagnosed as infectious disease patients, and are isolated for treatment at the same time, and are considered to be unable to infect the susceptible persons; the recovered persons refer to people who have recovered from the disease and have acquired immunity; the dead persons refer to people who have died and cannot serve as infection sources; and the isolated latent persons refer to latent persons who are isolated in designated facilities and cannot serve as infection sources.

[0052] The modified SEIR infectious disease dynamics model is:

[0053]

[0054] wherein S is the number of susceptible persons, E is the number of latent persons, Eq is the number of isolated latent persons, I is the number of infected persons, R is the number of recovered persons, D is the number of dead persons, r is the number of contacts, b is the transmission probability per contact with infected persons, theta is the transmission ability coefficient of latent persons relative to infected persons, q0 and q1 are the conversion rates of susceptible persons and latent persons to isolated latent persons respectively, a0 and a1 are the conversion rates of latent persons and isolated latent persons to infected persons respectively, y0 and y1 are the conversion rates of infected persons to recovered persons and dead persons respectively, and t is time. The transmission probability density beta = rb.

[0055] In some embodiments, the multiple types of population further include: immune persons; and the epidemic data can further include at least one of: an initial value of the number of immune persons, a number of times of vaccination per unit time of susceptible persons, and a decay speed of transmission probability per unit time.

[0056] In this embodiment, as the actual epidemic prevention measures are taken, the immunity of the vaccine injection and the isolation of the latent person due to the isolation measures make the infectious disease risk decrease, and the infection probability density β gradually decays, and the exponential decay equation is as follows:

[0057] N(t)=N0e -kt (2)

[0058] wherein N(t) is the value of the exponential equation N at time t, N0 represents the initial value of N at time 0, and k is the decay constant. It can be seen from the formula that the decay rate of the exponential equation N is e -kt .

[0059] Therefore, it can be concluded that, assuming that the epidemic is always in exponential decay, that is, the decay rate k0 of the transmission probability per unit time is constant, the epidemic decay coefficient is:

[0060]

[0061] wherein C is the epidemic decay coefficient.

[0062] At this time, the infection probability density is:

[0063]

[0064] The modified SEIR infectious disease dynamics model is:

[0065]

[0066] In this embodiment, the effects of the isolated latent person and the immune person generated under the actual epidemic prevention measures on the epidemic risk prediction are considered, and the prediction accuracy can be effectively improved.

[0067] In some embodiments, if the infectious disease virus occurs in the infection enhancement type variation in the infection process, two modified SEIR infectious disease dynamics models are used to predict the virus before and after the variation, respectively. For the virus after the variation, the resistance of the immune person and the recovered person corresponding to the virus before the variation is weakened relative to the virus after the variation, and the conversion rate of the immune person to the infected person and the latent person isolated latent person should be adjusted, and the conversion rate of the recovered person to the infected person and the latent person isolated latent person should be adjusted. Or the immune person and the recovered person can be regarded as susceptible again. And the transmission probability of each contact with the infected person is adjusted, and the conversion rate between the populations should be adjusted according to the actual variation virus, which is not limited here.

[0068] In some embodiments, the second prediction model comprises a modified Keyfitz population migration model, wherein in the modified Keyfitz population migration model, the city is a preset area, the countryside is an area outside the preset area, and the natural growth rate of the preset area is zero.

[0069] The modified Keyfitz population migration model is:

[0070]

[0071] wherein ΔUP(t) is the number of epidemic cases flowing from the other areas to the preset area in a preset period, RP(t) is the number of epidemic cases in the other areas at time t, and g is the migration rate of the population in the other areas to the preset area; wherein the number of epidemic cases is the sum of the number of infected persons, latent persons, and isolated latent persons.

[0072] In this embodiment, the influence of external inflow population on epidemic risk prediction is considered, and the prediction accuracy is effectively improved.

[0073] In some embodiments, S202 comprises:

[0074] When the other areas outside the preset area are multiple, the inflow curves of the respective other areas are determined according to the external epidemic data of the respective other areas and the second prediction model.

[0075] The inflow curves of the respective other areas are weighted and summed according to the proportion of the number of epidemic cases in the respective other areas, to obtain an external inflow risk prediction curve.

[0076] In some embodiments, the weight vector of the first preset indicators in the preset area is obtained, comprising:

[0077] The scale between the respective first preset indicators is obtained.

[0078] The weight vector of the respective first preset indicators in the preset area is determined according to the scale and the chromatography analysis algorithm.

[0079] In this embodiment, the weight vector of the respective first preset indicators in the preset area is determined according to the scale and the chromatography analysis algorithm, and the specific process is as follows:

[0080] (1) Construct a judgment matrix

[0081] The judgment matrix is constructed according to the scale between the respective first preset indicators:

[0082]

[0083] Each row (column) of the judgment matrix corresponds to a first preset indicator.

[0084] (2) Calculate the weight vector

[0085] The eigenvector of the maximum eigenvalue of the judgment matrix is normalized to obtain the weight vector W. Denote the weight vector W = (w1,..., wn), and the calculation formula is as follows: i

[0086]

[0087] where w i is the weight vector corresponding to the first preset index, and n is the number of the first preset indexes.

[0088] (3) Consistency check

[0089] The consistency ratio CR of the matrix and the weight vector is calculated, and when CR < 0.1, it is considered that the judgment matrix has good consistency. The test formula is as follows:

[0090]

[0091] where λ max is the maximum eigenvalue of the judgment matrix, and RI represents the random consistency index. In some embodiments, on the basis of any of the above embodiments, after determining the weight vector of each preset index in the preset area according to the epidemic data and the chromatography analysis algorithm, the following is further included:

[0092] According to the spatial autocorrelation analysis algorithm, the weight vector obtained based on the chromatography analysis algorithm is adjusted.

[0093] In this embodiment, the weight vector calculated by the analytic hierarchy process algorithm generally only considers the whole preset area, and due to the uneven distribution of the number of epidemic people in the preset area, there is a certain deviation. For the area with a large number of epidemic people in the preset area, the internal transmission risk of the epidemic is relatively high; and for the area with a small number of epidemic people and close to the risk area, the epidemic inflow risk is relatively high.

[0094] In this embodiment, the weight vector obtained based on the chromatography analysis algorithm is adjusted as follows:

[0095] 1. Determine whether the city epidemic exists spatial aggregation by Moran's I index, and divide the deviation caused by spatial autocorrelation according to the degree of spatial aggregation of the epidemic.

[0096] 2. Then measure the spatial difference of the epidemic weight by LISA index.

[0097] 3. Weight the weight vector calculated by the analytic hierarchy process algorithm to obtain the adjusted weight vector.

[0098] ​In this embodiment, according to the spatial autocorrelation analysis algorithm, the weight vector obtained based on the tomographic analysis algorithm is adjusted, a more detailed risk weight vector can be obtained, and the accuracy of risk prediction is effectively improved.

[0099] In some embodiments, the internal epidemic data of the plurality of types of people in the preset area and the external epidemic data of other areas outside the preset area are obtained, including:

[0100] Obtaining original data from a database;

[0101] According to the original data and the moment estimation algorithm, the original data is estimated to obtain estimated data;

[0102] According to the estimated data and the original data, internal epidemic data and external epidemic data are obtained.

[0103] In this embodiment, the data in the database can be obtained from official websites or other websites through the network, or can be obtained through literature research, which is not limited here. The data collection tool can be a Python web crawler, the HTTP library is the requests library, and the parsing plug-in is Beautiful Soup.

[0104] In this embodiment, for some data that is difficult to measure and obtain, it can be obtained by estimation. In this embodiment, the moment estimation algorithm is used to calculate the data in the form of a regenerative matrix.

[0105] In some embodiments, after obtaining the internal epidemic data and the external epidemic data, the method further comprises: preprocessing the internal epidemic data and the external epidemic data.

[0106] Among them, preprocessing refers to cleaning the data and selecting sample data.

[0107] In some embodiments, after obtaining the epidemic risk prediction curve, the method further comprises:

[0108] Obtaining actual population data of each type of population in the prediction period;

[0109] Determining actual risk data according to the actual population data;

[0110] According to the correlation algorithm, the correlation coefficient between the actual risk data and the epidemic risk prediction curve corresponding to the prediction period is calculated;

[0111] If the correlation coefficient is greater than a preset threshold, it is determined that the epidemic risk prediction curve is effective.

[0112] In this embodiment, the correlation algorithm can be a Pearson correlation coefficient algorithm, a canonical correlation analysis algorithm, etc., which is not limited here. Optionally, the correlation coefficient greater than the preset threshold is greater than 0.6.

[0113] Optionally, if the correlation coefficient is not greater than the preset threshold, the epidemic risk prediction curve is deleted, the actual population data and the actual risk data of each type of population in the prediction period are taken as a data set, and the weight vector of the first preset index and the weight vector of the second preset index are optimized according to the data set and the optimization algorithm to obtain a more accurate epidemic risk prediction curve.

[0114] Optionally, if the correlation coefficient is not greater than the preset threshold, the epidemic risk prediction curve is deleted, and the actual population data of each type of population and the matrix estimation algorithm are used to obtain new internal epidemic data and new external epidemic data to obtain a new epidemic risk prediction curve. The new epidemic risk prediction curve is used to predict the infectious disease risk value of the next to be predicted period.

[0115] Optionally, the actual estimated risk curve can also be determined according to the reference data, the Pearson correlation coefficient between the actual estimated risk curve and the epidemic risk prediction curve is determined, and the size relationship between the correlation coefficient and the preset threshold is judged. The reference data can include but is not limited to at least one of the following: actual morbidity index, medical resource allocation index, travel intensity index.

[0116] In some embodiments, the preset region is a plurality of;

[0117] The method further comprises:

[0118] obtaining a geographic information system (GIS) map in each preset region and an epidemic risk prediction curve corresponding to each preset region;

[0119] combining the epidemic risk prediction curve with the GIS map corresponding thereto to obtain an epidemic risk prediction map.

[0120] In this embodiment, the epidemic risk prediction curve can be imported into ArcGIS software and combined with a Geographic Information System (GIS) to obtain a city epidemic risk prediction map, which can then be displayed on the front-end webpage using the ArcGIS API interface. Alternatively, the epidemic risk prediction curve can be used to create a time-bound line chart using Echarts charting tools, and mapped onto the city map on the front-end webpage using XY fields to obtain a city epidemic risk prediction map. The city epidemic risk prediction map may include, but is not limited to, at least one of the following: daily epidemic risk prediction maps for each district and county within a week; risk levels for each region during the city's peak and stable periods; and a curve showing the city's epidemic risk change for the coming week.

[0121] The above-mentioned equipment control method is illustrated below with an implementation example, but it is not intended to be limiting. Figure 4 Figure 4 is a flowchart illustrating the implementation of an urban epidemic risk prediction method according to an embodiment of the present invention. As shown in Figure 4, in this embodiment, the urban epidemic risk prediction method can be implemented by the following steps:

[0122] Step 1: Obtain internal and external epidemic data. The specific data types and acquisition methods are shown in the table below:

[0123] Table 1 Data Source Table

[0124]

[0125] Official data refers to epidemic-related data stored in databases or retrieved from official websites, while parameter estimation refers to data estimated based on official data and estimation algorithms.

[0126] Step 2: Obtain the population change curves for each type of population based on internal epidemic data and the first prediction model.

[0127] Step 3: Obtain the internal transmission risk prediction curve based on the hierarchical analysis algorithm and the population change curve.

[0128] Specifically as follows:

[0129] (1) Determine the scale between each of the second preset indicators according to the table below:

[0130] Table 2 Scale Table

[0131]

[0132] (2) Based on the scale between the second preset indicators, a judgment matrix of size 7×7 is obtained.

[0133] wherein each row (column) of the judgment matrix corresponds to a second preset index.

[0134] (3) The eigenvector of the maximum eigenvalue of the judgment matrix is calculated, and after normalization, the weight vector set is obtained. Denote the weight vector set as W = (w1, w2, w3, w4, w5, w6, w7), wherein w i is the weight vector corresponding to each second preset index, and n is the number of first preset indexes.

[0135] (4) According to the spatial autocorrelation analysis algorithm, the weight vector corresponding to each second preset index is adjusted.

[0136] (5) According to the number of people change curve corresponding to each second preset index and the weight vector, the internal transmission risk prediction curve is obtained.

[0137] (6) Consistency test.

[0138] The consistency ratio CR of the matrix and the weight vector is calculated, and when CR < 0.1, it is considered that the judgment matrix has good consistency. The test formula is as follows:

[0139]

[0140] wherein λ max is the maximum eigenvalue of the judgment matrix. RI represents the random consistency index, which is related to the number of first preset indexes, and the specific values are shown in Table 3.

[0141] Table 3 Random consistency index values for different numbers of indexes

[0142]

[0143] There are 7 second preset indexes, and RI = 1.32.

[0144] Step 4, according to the external epidemic data and the second prediction model, the external inflow risk prediction curve is obtained.

[0145] Step 5, according to the analytic hierarchy process algorithm, the internal transmission risk prediction curve and the external inflow risk prediction curve, the epidemic risk prediction curve is obtained, which is as follows:

[0146] (1) According to Table 2, the scale between each first preset index is determined.

[0147] (2) According to the scale between the first preset indexes, a judgment matrix with a size of 2x2 is obtained.

[0148] (3) The eigenvector of the maximum eigenvalue of the judgment matrix is calculated, and after normalization, the weight vector set is obtained. Denote the weight vector set as W = (w1, w2).

[0149] (4) According to the spatial autocorrelation analysis algorithm, the weight vector corresponding to each first preset index is adjusted.

[0150] (5) According to the number of people change curve corresponding to each first preset index and the weight vector, the internal propagation risk prediction curve is obtained.

[0151] (6) Consistency test. There are 2 first preset indexes, and RI = 0.

[0152] Step 6, according to the actual number of people data of each type of population and the correlation algorithm, the curve is verified. If the correlation coefficient is greater than 0.6, it is determined that the epidemic risk prediction curve is effective. If the correlation coefficient is not greater than 0.6, the following steps are performed:

[0153] (i) First, check the authenticity of the epidemic data set.

[0154] (ii) If the above data is true and effective, the weight vector of the first preset index and the second preset index is recalculated.

[0155] That is, the judgment matrix of the analytic hierarchy process in the first preset index and the second preset index is reset, the scale weight is calculated, and the correlation coefficient of the obtained result reaches the standard range.

[0156] (iii) Substitute another group of epidemic data set, check whether the modified weight vector reaches the standard range. If it meets the standard, it proves that the model modification is completed; if it does not meet the standard, steps (ii) and (iii) are performed again.

[0157] Step 7, combine the epidemic risk prediction curve with its corresponding GIS map to obtain the epidemic risk prediction map.

[0158] Step 8, after receiving the query instruction, output and display the epidemic risk prediction map corresponding to the query instruction.

[0159] In this embodiment, the city epidemic risk prediction method provided includes: obtaining internal epidemic data of multiple types of populations in a preset area and external epidemic data of other areas outside the preset area; obtaining an internal propagation risk prediction curve according to the internal epidemic data and a first prediction model; obtaining an external inflow risk prediction curve according to the external epidemic data and a second prediction model; obtaining a weight vector of a first preset index in the preset area; weighting and integrating the internal propagation risk prediction curve and the external inflow risk prediction curve according to the weight vector of the first preset index to obtain an epidemic risk prediction curve; and predicting the internal propagation risk and the external propagation risk respectively, and considering the latent population group under the actual epidemic prevention and control measures, which can effectively improve the accuracy of the epidemic risk prediction, and has the advantages of low cost, scalability and the like.

[0160] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0161] Figure 5 FIG. 1 is a structural schematic diagram of an urban epidemic risk prediction device provided by an embodiment of the present application. As shown in FIG. 1, the urban epidemic risk prediction device 5 comprises: Figure 5

[0162] A first acquisition module 510 is configured to acquire internal epidemic data of multiple types of people in a preset region and external epidemic data of other regions outside the preset region.

[0163] A processing module 520 is configured to obtain an internal transmission risk prediction curve according to the internal epidemic data and a first prediction model, and obtain an external inflow risk prediction curve according to the external epidemic data and a second prediction model.

[0164] A second acquisition module 530 is configured to acquire a weight vector of a first preset index in the preset region.

[0165] An integration module 540 is configured to perform weighted integration on the internal transmission risk prediction curve and the external inflow risk prediction curve according to the weight vector of the first preset index, to obtain an epidemic risk prediction curve.

[0166] The multiple types of people include susceptible people, latent people, infected people, recovered people, dead people and isolated latent people; the first preset index includes an urban internal transmission risk index and an urban external inflow risk index; the first prediction model represents the relationship between the change rate of the number of each type of people and the epidemic data; and the second prediction model represents the relationship between the number of infected people flowing into the preset region per unit time from other regions and the number of infected people in other regions.

[0167] Optionally, the processing module 520 is configured to obtain a number change curve corresponding to each type of people according to the internal epidemic data and the first prediction model.

[0168] The weight vector of a second preset index in the preset region is acquired.

[0169] The number change curve corresponding to each type of people is weighted and integrated according to the weight vector of the second preset index, to obtain the internal transmission risk prediction curve; and the second preset index includes a susceptible person index, a latent person index, an infected person index, a recovered person index, a dead person index and an isolated latent person index.

[0170] Optionally, the first prediction model includes a modified SEIR infectious disease dynamics model.

[0171] The modified SEIR infectious disease dynamics model is:​

[0172]

[0173] wherein S is the number of susceptible persons, E is the number of latent persons, Eq is the number of quarantined latent persons, I is the number of infected persons, R is the number of cured persons, D is the number of dead persons, r is the number of contacts, b is the transmission probability per contact with infected persons, theta is the transmission ability coefficient of latent persons relative to infected persons, q0 and q1 are the conversion rates of susceptible persons and latent persons to quarantined latent persons respectively, a0 and a1 are the conversion rates of latent persons and quarantined latent persons to infected persons respectively, y0 and y1 are the conversion rates of infected persons to cured persons and dead persons respectively, and t is time.

[0174] Optionally, the second prediction model comprises a modified Keyfitz population migration model, wherein in the modified Keyfitz population migration model, the city is a preset area, the countryside is other areas outside the preset area, and the natural growth rate of the preset area is zero.

[0175] The modified SEIR infectious disease dynamics model is:

[0176]

[0177] wherein Delta UP(t) is the number of epidemic cases flowing from other areas to the preset area in a preset period, RP(t) is the number of epidemic cases in other areas at time t, and g is the migration rate of the population in other areas to the preset area; wherein the number of epidemic cases is the sum of the number of infected persons, latent persons and quarantined latent persons.

[0178] Optionally, the second acquisition module 530 is configured to acquire scales between the first preset indexes.

[0179] According to the scales and the chromatography analysis algorithm, a weight vector of each preset index in the preset area is determined.

[0180] After the weight vector of each preset index in the preset area is determined according to the epidemic data and the chromatography analysis algorithm, the method further comprises:

[0181] According to the spatial autocorrelation analysis algorithm, the weight vector obtained based on the chromatography analysis algorithm is adjusted.

[0182] Optionally, the first acquisition module 510 is configured to acquire original data from a database.

[0183] According to the original data and the matrix estimation algorithm, original data estimation is performed to obtain estimated data.

[0184] According to the estimated data and the original data, internal epidemic data and external epidemic data are obtained.

[0185] Optionally, the urban epidemic risk prediction device 5 further comprises a verification module 550.

[0186] The verification module 550 is configured to acquire actual population data of each type of population in the prediction period.

[0187] The actual risk data is determined according to the actual population data.

[0188] The correlation coefficient between the actual risk data and the epidemic risk prediction curve corresponding to the prediction period is calculated according to a correlation algorithm.

[0189] If the correlation coefficient is greater than a preset threshold, it is determined that the epidemic risk prediction curve is valid.

[0190] Optionally, the preset region is multiple.

[0191] The urban epidemic risk prediction device 5 further comprises a map module 560.

[0192] The map module 560 is configured to acquire a geographic information system (GIS) map in each preset region and an epidemic risk prediction curve corresponding to each preset region.

[0193] The epidemic risk prediction curve is combined with the GIS map corresponding thereto to obtain an epidemic risk prediction map.

[0194] Optionally, the internal epidemic data comprises at least one of the following: a transmission probability of each contact of an infected person, a number of contacts of an infected person per unit time, a conversion rate between each type of population, a transmission ability coefficient of a latent person relative to an infected person, a moving rate of other regions to the preset region, and a population initial value of each type of population.

[0195] Optionally, the external epidemic data comprises at least one of the following: a number of epidemic cases in other regions, and a migration rate of a population of other regions to the preset region.

[0196] Optionally, the multiple types of population further comprise an immune person, and the epidemic data further comprises at least one of the following: an initial value of the number of immune persons, a number of vaccination times of susceptible persons per unit time, and a decay speed of the transmission probability per unit time.

[0197] The urban epidemic risk prediction device provided in the embodiment can be used to execute the method embodiment, and has similar implementation principles and technical effects, which will not be described here again.

[0198] Figure 6 is a schematic diagram of an electronic device provided in an embodiment of the present application. Figure 6As shown, one embodiment of the electronic device 6 provided by the present application includes a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60. The processor 60 implements the steps of each of the above-mentioned city epidemic risk prediction method embodiments when executing the computer program 62, for example Figure 2 As shown, the processor 60 implements the functions of each of the above-mentioned modules / units in each of the above-mentioned device embodiments when executing the computer program 62, for example Figure 5 As shown, the processor 60 implements the functions of each of the above-mentioned modules / units in each of the above-mentioned device embodiments when executing the computer program 62, for example

[0199] As an example, the computer program 62 can be divided into one or more modules / units, one or more modules / units are stored in the memory 61 and executed by the processor 60 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which is used to describe the execution process of the computer program 62 in the electronic device 6.

[0200] The electronic device 6 can be a desktop computer, a notebook computer, a palm computer, a cloud server, and other computing devices. The terminal can include, but is not limited to, the processor 60, the memory 61. Those skilled in the art can understand that Figure 6 The electronic device 6 is only an example and does not constitute a limitation on the electronic device 6, and can include more or fewer components than shown, or combine certain components, or different components, for example, the terminal can also include an input / output device, a network access device, a bus, etc.

[0201] The processor 60 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0202] The memory 61 can be an internal storage unit of the electronic device 6, for example, a hard disk or an internal memory of the electronic device 6. The memory 61 can also be an external storage device of the electronic device 6, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like equipped on the electronic device 6. Further, the memory 61 can include both the internal storage unit and the external storage device of the electronic device 6. The memory 61 is used to store a computer program and other programs and data required by the terminal. The memory 61 can also be used to temporarily store data that has been output or is to be output.

[0203] The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned city epidemic risk prediction method embodiment.

[0204] The computer readable storage medium stores a computer program 62, and the computer program 62 includes program instructions, which are executed by the processor 60 to implement all or part of the processes in the above-mentioned embodiment method. The computer program 62 can also instruct related hardware to complete through the computer program 62. The computer program 62 can be stored in a computer readable storage medium. When the computer program 62 is executed by the processor 60, the steps of the above-mentioned various method embodiments can be implemented. The computer program 62 includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The computer readable medium can include any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0205] The computer readable storage medium can be an internal storage unit of the terminal of any of the preceding embodiments, for example, a hard disk or a memory of the terminal. The computer readable storage medium can also be an external storage device of the terminal, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, or the like. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the terminal. The computer readable storage medium is used to store computer programs and other programs and data required by the terminal. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0206] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

[0207] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above described functions. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific name of each functional unit and module is only for easy distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can be referred to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0208] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0209] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in combination of computer software and electronic hardware. Whether the functions are realized 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 realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0210] In the embodiments of the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other manners. For example, the apparatus / terminal embodiments described above are merely schematic. For example, the division of the modules or units is merely logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0211] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0212] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0213] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method in the above-mentioned embodiments can also be completed by a computer program instructing relevant hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the various method embodiments described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include appropriate contents according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to the legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0214] The above examples are only used to illustrate the technical solutions of the present application, but not to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand: the technical solutions recorded in the foregoing examples can still be modified, or some technical features therein can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for predicting urban epidemic risk, characterized in that, include: Acquire internal epidemic data of multiple population groups within a preset area and external epidemic data of other areas outside the preset area; An internal transmission risk prediction curve is obtained based on the internal epidemic data and the first prediction model; The external inflow risk prediction curve is obtained based on the external epidemic data and the second prediction model; The internal epidemic data includes at least one of the following: the probability of transmission with each contact with an infected person, the number of people the infected person contacts per unit time, the conversion rate between different population groups, the transmission capacity coefficient of a latent person relative to the infected person, the movement rate from other areas to the preset area, and the initial value of the number of people in each population group. The external epidemic data includes at least one of the following: the number of epidemic cases in other regions, and the migration rate of the population in other regions to the preset region; Obtain the weight vector of the first preset indicator within the preset region; The internal transmission risk prediction curve and the external inflow risk prediction curve are weighted and integrated according to the weight vector of the first preset indicator to obtain the epidemic risk prediction curve. The various population groups include susceptible individuals, latent individuals, infected individuals, recovered individuals, deceased individuals, and isolated latent individuals; the first preset indicators include urban internal transmission risk indicators and external inflow risk indicators; the first prediction model represents the relationship between the rate of change of the number of each population group and the epidemic data; the second prediction model represents the relationship between the number of infected individuals flowing into the preset area from other areas per unit time and the number of infected individuals in other areas; The multi-group population also includes: the immune population; the epidemic data also includes at least one of the following: the initial number of the immune population, the number of vaccinations per unit time for susceptible individuals, and the rate of decay of the transmission probability per unit time; The first prediction model includes a modified SEIR infectious disease dynamics model; The modified SEIR infectious disease dynamics model is as follows: Alternatively, the modified SEIR infectious disease dynamics model is as follows: in, S For the number of susceptible individuals, E For the number of infiltrators, Eq To isolate the number of asymptomatic carriers, I The number of infected people R For the number of cured patients, D For the number of the dead, r For the number of contacts, b The probability of transmission with each contact with an infected person. θ This represents the transmissibility coefficient of asymptomatic individuals relative to infected individuals. q 0 and q 1 represents the conversion rate from susceptible individuals and latent individuals to isolated latent individuals, respectively. a 0 and a 1 represents the conversion rate from latent individuals to infected individuals, and the conversion rate from isolated latent individuals to infected individuals, respectively. y 0 and y 1 represents the conversion rate from infected individuals to recovered individuals and the rate of death, respectively. t For time; where, the probability density of transmission. β = rb ; S i For the immune, i 0 represents the rate of conversion from susceptible to immune individuals; If an infectious disease virus undergoes an enhanced mutation during transmission, two modified SEIR infectious disease dynamics models are used to predict the virus before and after the mutation, respectively. For the mutated virus, the resistance of the immune and recovered individuals corresponding to the virus before the mutation is weakened relative to the mutated virus, and the immune and recovered individuals are re-considered as susceptible individuals. Based on the aforementioned internal epidemic data and the first prediction model, an internal transmission risk prediction curve is obtained, including: Based on the internal epidemic data and the first prediction model, the population change curves for various groups of people are obtained. Obtain the weight vector of the second preset indicator within the preset area; The internal transmission risk prediction curve is obtained by weighting and integrating the population change curves corresponding to various groups according to the weight vector of the second preset indicator; wherein, the second preset indicator includes susceptible person indicator, latent person indicator, infected person indicator, cured person indicator, deceased person indicator and isolated latent person indicator. The second prediction model includes a modified Keyfitz population migration model, wherein the cities in the modified Keyfitz population migration model are the preset areas, the rural areas are other areas outside the preset areas, and the natural growth rate of the preset areas is zero; The modified Keyfitz population migration model is as follows: Where, ∆ UP ( t The number of COVID-19 cases that migrated from other areas to the preset area within a preset time period is [number]. RP ( t )for t The number of COVID-19 cases in other regions as of that time. g The migration rate of the population from other areas to the preset area; wherein, the number of epidemic cases is the sum of the number of infected persons, the number of latent persons, and the number of isolated latent persons.

2. The urban epidemic risk prediction method according to claim 1, characterized in that, The external inflow risk prediction curve is obtained based on the external epidemic data and the second prediction model, including: When there are multiple other regions outside the preset region, the inflow curve of each other region is determined based on the external epidemic data of each other region and the second prediction model; Based on the proportion of COVID-19 cases in each of the other regions, the inflow curves of each of the other regions are weighted and summed to obtain the external inflow risk prediction curve.

3. The urban epidemic risk prediction method according to claim 1, characterized in that, The step of obtaining the weight vector of the first preset index within the preset region includes: Obtain the scale between each of the first preset indicators; Based on the scaling and tomographic analysis algorithm, determine the weight vector of each preset index within the preset region; After determining the weight vectors of each preset indicator within the preset area based on the epidemic data and the stratified analysis algorithm, the method further includes: Adjust the weight vector obtained based on the tomography analysis algorithm according to the spatial autocorrelation analysis algorithm.

4. The urban epidemic risk prediction method according to claim 1, characterized in that, The preset area is multiple; The method further includes: Obtain the geographic information system (GIS) map of each preset area and the corresponding epidemic risk prediction curve for each preset area; By combining the epidemic risk prediction curve with its corresponding GIS map, an epidemic risk prediction map is obtained.

5. The urban epidemic risk prediction method according to any one of claims 1-4, characterized in that, The acquisition of internal epidemic data for multiple population groups within a preset area and external epidemic data for other areas outside the preset area includes: Retrieve raw data from the database; Based on the original data and the moment estimation algorithm, the original data is estimated to obtain the estimated data; The internal epidemic data and the external epidemic data are obtained based on the estimated data and the original data; After obtaining the epidemic risk prediction curve, the method further includes: Obtain actual population data for various groups within the forecast period; The actual risk data is determined based on the actual number of people. The correlation coefficient between the actual risk data and the epidemic risk prediction curve corresponding to the prediction period is calculated based on the correlation algorithm. If the correlation coefficient is greater than a preset threshold, the epidemic risk prediction curve is determined to be valid.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the urban epidemic risk prediction method as described in any one of claims 1 to 5 above.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the urban epidemic risk prediction method as described in any one of claims 1 to 5 above.

Images