Epidemic data prediction method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to an epidemic data prediction method and device, equipment and medium, and relates to the technical field of computers, which can be applied to the scene of predicting the number of infectious disease cases. The method comprises the following steps: dividing the infection state of an initial infectious disease model into a first infection state and a second infection state according to the regional risk level; establishing an initial infectious disease case number prediction model according to the first infection state and the second infection state, and determining the to-be-estimated parameters of the initial infectious disease case number prediction model; obtaining the daily increase in the number of cases in the two infection states in the initial infectious disease case number prediction model, and determining the target parameter value of the to-be-estimated parameters according to the daily increase in the number of cases in each infection state; substituting the target parameter value into the initial infectious disease case number prediction model to obtain an infectious disease case number prediction model, and determining the epidemic prediction number according to the infectious disease case number prediction model. The present disclosure can establish an epidemic transmission prediction model suitable for policy hierarchical regulation scenarios, so that the epidemic case number prediction is more accurate.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of computer technology, and in particular, to an epidemic data prediction method, an epidemic data prediction device, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] Epidemic prediction is an important part of the epidemic prevention and control system, and it is of great significance to accurately establish an epidemic evolution dynamics model. Establishing a model that can predict and provide reliable and sufficient information for prevention and control can provide a scientific basis for precise policy-making and public health strategy formulation. Existing mathematical models of epidemics usually include: Susceptible-Exposed-Infectious-Recovered (SEIR) model, Susceptible-Infectious (SI) model, Susceptible-Infectious-Recovered (SIR) model, and Susceptible-Infectious-Recovered-Susceptible (SIRS) model.

[0003] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0004] The purpose of the present disclosure is to provide an epidemic data prediction method, an epidemic data prediction device, an electronic device, and a computer readable storage medium, thereby at least to some extent overcoming the problem that the existing mathematical model of epidemics does not fit the structure of the epidemic number prediction under the policy hierarchical regulation scenario, and the prediction result is not accurate.

[0005] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0006] According to a first aspect of the present disclosure, a method for predicting epidemic data is provided, including: obtaining an initial infectious disease model, and dividing infection states of the initial infectious disease model into a first infection state and a second infection state according to a regional risk level; establishing an initial infectious disease population prediction model according to the first infection state and the second infection state, and determining to-be-estimated parameters of the initial infectious disease population prediction model; obtaining daily new population numbers in each infection state in the initial infectious disease population prediction model, and determining target parameter values of the to-be-estimated parameters according to the daily new population numbers in each infection state; substituting the target parameter values into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and determining an epidemic prediction population according to the infectious disease population prediction model.

[0007] Optionally, dividing the infection states of the initial infectious disease model into the first infection state and the second infection state according to the regional risk level includes: obtaining a regional risk level threshold and regional risk level values of a plurality of to-be-predicted regions; determining a first risk region for a to-be-predicted region whose regional risk level value is greater than or equal to the regional risk level threshold, and determining a first infection state for a population in the infection state in the first risk region; and determining a second risk region for a to-be-predicted region whose regional risk level value is less than the regional risk level threshold, and determining a second infection state for a population in the infection state in the second risk region.

[0008] Optionally, the initial infectious disease model further includes a susceptible state, an exposed state, and a removed state; and establishing the initial infectious disease population prediction model according to the first infection state and the second infection state includes: determining population categories in the initial infectious disease population prediction model; wherein the population categories include a susceptible population, an exposed population, a first infection state population, a second infection state population, and a removed population; determining state transition parameters of state transitions between the population categories; and establishing the initial infectious disease population prediction model according to the population categories and the state transition parameters.

[0009] Optionally, determining the state transition parameters of the state transitions between the population categories includes: determining a first population proportion of a number of the first risk region in a number of all to-be-predicted regions as a first population proportion; determining a proportion of the exposed population converted into the first infection state population as a first transfer proportion; determining a second population proportion and a second transfer proportion according to the first population proportion and the first transfer proportion, respectively; determining a transfer rate of the infection state population converted into the removed population as an infection-removed transfer rate; and determining a transfer rate of the exposed population converted into the infection state population as an exposed-infection transfer rate.

[0010] Optionally, the to-be-estimated parameter includes an infection coefficient, and determining the to-be-estimated parameter of the initial infectious disease person number prediction model includes: determining a transmission period of the to-be-predicted infectious disease and time series data corresponding to the transmission period; obtaining a prevention and control condition corresponding to the infectious disease in the transmission period; dividing the transmission period into a plurality of transmission periods according to the prevention and control condition, and dividing the time series data into a corresponding number of sub-time series data; and determining the to-be-estimated parameter in each transmission period according to the plurality of sub-time series data.

[0011] Optionally, the target parameter value includes a target parameter mean value and a target parameter confidence interval, and determining the target parameter value of the to-be-estimated parameter according to the daily new person number in each infection state includes: obtaining a prior distribution of the to-be-estimated parameter; performing iterative calculation based on the daily new person number in each infection state and the prior distribution and using a parameter estimation method until the iterative result of the iterative calculation converges; and determining the target parameter mean value and the target parameter confidence interval according to the converged iterative result.

[0012] Optionally, determining the epidemic prediction person number according to the infectious disease person number prediction model includes: obtaining a multinomial distribution function of state transition between different states in the infectious disease person number prediction model; calculating a transition probability of each state in the infectious disease person number prediction model according to the multinomial distribution function, and performing state iterative calculation on different population categories in the infectious disease person number prediction model; and determining the epidemic prediction person number according to the calculation result after the state iterative calculation.

[0013] According to a second aspect of the present disclosure, an epidemic data prediction device is provided, which includes: an infection state determination module configured to obtain an initial infectious disease model and divide infection states of the initial infectious disease model into a first infection state and a second infection state according to a regional risk level; a model establishment module configured to establish an initial infectious disease person number prediction model according to the first infection state and the second infection state, and determine a to-be-estimated parameter of the initial infectious disease person number prediction model; a parameter value determination module configured to obtain a daily new person number in each infection state of the initial infectious disease person number prediction model, and determine a target parameter value of the to-be-estimated parameter according to the daily new person number in each infection state; and a person number prediction module configured to substitute the target parameter value into the initial infectious disease person number prediction model to obtain an infectious disease person number prediction model, and determine an epidemic prediction person number according to the infectious disease person number prediction model.

[0014] Optionally, the infection state determination module includes an infection state determination unit configured to obtain a regional risk level threshold value and regional risk level values of a plurality of to-be-predicted regions; determine a to-be-predicted region with a regional risk level value greater than or equal to the regional risk level threshold value as a first risk region, and determine a population in an infection state in the first risk region as a first infection state; and determine a to-be-predicted region with a regional risk level value less than the regional risk level threshold value as a second risk region, and determine a population in an infection state in the second risk region as a second infection state.

[0015] Optionally, the model establishing module comprises a model establishing unit configured to determine population categories in the initial infectious disease population prediction model, wherein the population categories comprise susceptible population, exposed population, first infectious state population, second infectious state population and removed population; determine state transition parameters of state transitions between the population categories; and establish the initial infectious disease population prediction model according to the population categories and the state transition parameters.

[0016] Optionally, the model establishing unit comprises a state parameter determining subunit configured to determine a first population proportion of the number of the first risk area in the number of all to-be-predicted areas as a first population proportion; determine a proportion of the exposed population converted to the first infectious state population as a first transfer proportion; determine a second population proportion and a second transfer proportion according to the first population proportion and the first transfer proportion, respectively; determine a transfer rate of the infectious state population converted to the removed population as an infectious removed transfer rate; and determine a transfer rate of the exposed population converted to the infectious state population as an exposed infectious transfer rate.

[0017] Optionally, the model establishing module further comprises a to-be-estimated parameter determining unit configured to determine a transmission period of the to-be-predicted infectious disease and time series data corresponding to the transmission period; obtain a control condition corresponding to the infectious disease in the transmission period; divide the transmission period into a plurality of transmission periods according to the control condition, and divide the time series data into a corresponding number of sub-time series data; and determine the to-be-estimated parameters in each transmission period according to the plurality of sub-time series data.

[0018] Optionally, the parameter value determining module comprises a parameter value determining unit configured to obtain a prior distribution of the to-be-estimated parameters; perform iterative calculation based on the daily new number of people in each infectious state and the prior distribution, and using a parameter estimation method until the iterative result of the iterative calculation converges; and determine a target parameter mean value and a target parameter confidence interval according to the converged iterative result.

[0019] Optionally, the population prediction module comprises a population prediction unit configured to obtain a multinomial distribution function of state transitions between different states in the infectious disease population prediction model; calculate transition probabilities of each state in the infectious disease population prediction model according to the multinomial distribution function, and perform state iterative calculation on different population categories in the infectious disease population prediction model; and determine an epidemic prediction population according to a calculation result after the state iterative calculation.

[0020] According to a third aspect of the present disclosure, an electronic device is provided, comprising a processor and a memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the epidemic data prediction method according to any one of the above.

[0021] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to implement the epidemic data prediction method according to any one of the above.

[0022] The technical solutions provided by the present disclosure can include the following beneficial effects:

[0023] In the epidemic data prediction method in the exemplary embodiments of the present disclosure, the infection states of the initial infectious disease model are divided into a first infection state and a second infection state according to the regional risk level; the initial infectious disease population prediction model is established according to the first infection state and the second infection state, and the to-be-estimated parameters of the initial infectious disease population prediction model are determined; the daily new number of people in each infection state in the initial infectious disease population prediction model is obtained, and the target parameter value of the to-be-estimated parameters is determined according to the daily new number of people in each infection state; the target parameter value is substituted into the initial infectious disease population prediction model to obtain the infectious disease population prediction model, and the epidemic prediction population is determined according to the infectious disease population prediction model. Through the epidemic data prediction method of the present disclosure, on the one hand, the infectious disease population prediction model suitable for different policy classification regulation scenarios is established according to the regional risk level, and the infectious disease population prediction model is used for epidemic population prediction, which can make the prediction result more accurate. On the other hand, the to-be-estimated parameters are estimated based on the prior distribution and the actual epidemic data, so that the target parameter value of the to-be-estimated parameters is more accurate, and the accuracy of the prediction result can be further improved based on the target parameter value.

[0024] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0025] The drawings incorporated into the specification and forming a part thereof, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. It is apparent that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings:

[0026] Figure 1 A flowchart of an epidemic data prediction method according to an exemplary embodiment of the present disclosure is schematically shown;

[0027] Figure 2 A block diagram of an established initial infectious disease population prediction model according to an exemplary embodiment of the present disclosure is schematically shown;

[0028] Figure 3 A flowchart of establishing an initial infectious disease population prediction model according to an exemplary embodiment of the present disclosure is schematically shown.

[0029] Figure 4 A flowchart illustrating determining a target parameter value of a parameter to be estimated according to an example embodiment of the disclosure is schematically shown;

[0030] Figure 5 A flowchart illustrating determining an epidemic prediction number according to an infectious disease number prediction model according to an example embodiment of the disclosure is schematically shown;

[0031] Figure 6 A block diagram of an epidemic data prediction apparatus according to an example embodiment of the disclosure is schematically shown;

[0032] Figure 7 A block diagram of an electronic device according to an example embodiment of the disclosure is schematically shown;

[0033] Figure 8 A schematic diagram of a computer readable storage medium according to an example embodiment of the disclosure is schematically shown. DETAILED DESCRIPTION

[0034] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the several views.

[0035] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the techniques described herein can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail in order to avoid obscuring aspects of the disclosure.

[0036] The block diagrams in the drawings show functions and functionality as they can be implemented in software rather than in hardware. Describing the software with a block diagram is therefore to be understood as showing a function rather than a structure of the software. Functions can be implemented in software, firmware, hardware, or any combination thereof. The block diagrams of the drawings are therefore to be understood as only showing a logical flow of the software by representing the functions of the software with the corresponding blocks. The software can be implemented in a machine-executable code and can be stored in machine-readable storage medium, for example, in the form of a computer program product.

[0037] Epidemic prediction is an important part of the epidemic prevention and control system, and it is of great significance to accurately establish the epidemic evolution dynamics model. Establishing a model that can predict and provide reliable and sufficient information for prevention and control can provide a scientific basis for precise policy-making and public health strategy formulation. Existing epidemic mathematical models can generally include SI model, SIR model, SIRS model and SEIR model, etc. However, the existing epidemic models have the problems of not fitting the structure under the current policy classification prevention and control scene, and the prediction result is not accurate enough.

[0038] Based on this, in the present example embodiment, first, an epidemic data prediction method is provided, which can be implemented by a server to implement the epidemic data prediction method of the present disclosure, or a terminal device can be used to implement the method described in the present disclosure. The terminal described in the present disclosure can include mobile terminals such as mobile phones, tablet computers, notebook computers, palmtop computers, personal digital assistants (Personal Digital Assistant, PDA), and fixed terminals such as desktop computers. Figure 1 The schematic diagram of the epidemic data prediction method flow according to some embodiments of the present disclosure is schematically shown. Referring to Figure 1 The epidemic data prediction method can include the following steps:

[0039] Step S110, obtaining an initial infectious disease model, and dividing the infection state of the initial infectious disease model into a first infection state and a second infection state according to the regional risk level.

[0040] Step S120, establishing an initial infectious disease population prediction model according to the first infection state and the second infection state, and determining the to-be-estimated parameters of the initial infectious disease population prediction model.

[0041] Step S130, obtaining the daily new number of people in each infection state in the initial infectious disease population prediction model, and determining the target parameter value of the to-be-estimated parameters according to the daily new number of people in each infection state.

[0042] Step S140, substituting the target parameter value into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and determining the epidemic prediction population according to the infectious disease population prediction model.

[0043] According to the epidemic data prediction method in the present example embodiment, on the one hand, the infectious disease population prediction model suitable for different policy classification regulation scenarios is established according to the regional risk level, and the infectious disease population prediction model is used for epidemic population prediction, which can make the prediction result more accurate. On the other hand, the to-be-estimated parameters are estimated based on the prior distribution and the actual epidemic data, so that the target parameter value of the to-be-estimated parameters is more accurate, and the accuracy of the prediction result can be further improved based on the target parameter value.

[0044] In the following, the epidemic data prediction method in the present example embodiment will be further described.

[0045] In step S110, an initial infectious disease model is obtained, and the infection state of the initial infectious disease model is divided into a first infection state and a second infection state according to a regional risk level.

[0046] In some example embodiments of the present disclosure, the initial infectious disease model can be an SEIR model, which can include four groups of people in different states, such as susceptible, exposed, infected, and removed, wherein the infected correspond to the infection state. The regional risk level can be an epidemic risk level determined for different regions according to specific epidemic control measures of the government. For example, in a city, the corresponding regional risk level can be determined for different streets; in a rural area, the corresponding regional risk level can be determined for different villages. The first infection state can be the infection state corresponding to the region with a regional risk level greater than or equal to a regional risk level threshold. The second infection state can be the infection state corresponding to the region with a regional risk level less than the regional risk level threshold.

[0047] The policy hierarchical control measure can be to determine the corresponding risk level for different regions according to the epidemic, so as to implement different prevention and control policies according to different risk categories of the regions. In order to effectively prevent the spread of the epidemic, the policy hierarchical control measure can be adopted. In order to adapt to the policy hierarchical control measure, the present disclosure can divide the infection state in the SEIR model into a first infection state and a second infection state according to the different regional risk levels on the basis of the SEIR model, and represent the first infection state and the second infection state by I_h and I_l, respectively. The first infection state can represent the number of people in the infection state corresponding to the high-risk region. The second infection state can represent the number of people in the infection state corresponding to the low-risk region.

[0048] As can be easily understood by those skilled in the art, in the epidemic prevention and control scene of different regions, the corresponding regions can be divided according to the actual needs of local epidemic prevention and control for epidemic prevention and control, and the present disclosure does not make any special limitation on the specific division method of the region to be predicted.

[0049] According to some example embodiments of the present disclosure, a region risk level threshold value and region risk level values of a plurality of to-be-predicted regions are obtained; a to-be-predicted region with a region risk level value greater than or equal to the region risk level threshold value is determined as a first risk region, and a population in an infectious state in the first risk region is determined as a first infectious state; a to-be-predicted region with a region risk level value less than the region risk level threshold value is determined as a second risk region, and a population in an infectious state in the second risk region is determined as a second infectious state. The region risk level threshold value can be a risk level threshold value determined according to epidemic transmission characteristics and other factors. For example, the region risk level threshold value can be 3. The to-be-predicted region can be a region where an epidemic exists. The region risk level value can be a numerical value of the respective region risk level of the to-be-predicted region. The first risk region can be a to-be-predicted region with a region risk level value greater than or equal to the region risk level threshold value, i.e., a high-risk region. The second risk region can be a to-be-predicted region with a region risk level value less than the region risk level threshold value, i.e., a low-risk region.

[0050] In the present disclosure, the region risk level values of different to-be-predicted regions are determined according to epidemic transmission characteristics and the number of infected persons in different regions. For example, the region risk level values can be divided into five levels: 1, 2, 3, 4, and 5. The region risk level values of a plurality of to-be-predicted regions are obtained, and the region risk level values of the to-be-predicted regions are compared with a region risk level threshold value. A to-be-predicted region with a region risk level value greater than or equal to the region risk level threshold value is determined as a first risk region; a to-be-predicted region with a region risk level value less than the region risk level threshold value is determined as a second risk region. A population in an infectious state in the first risk region is determined as a first infectious state; a population in an infectious state in the second risk region is determined as a second infectious state. For example, to-be-predicted regions with region risk level values of 3, 4, and 5 can be determined as the first risk region, and a population in an infectious state in the first risk region is determined as the first infectious state. To-be-predicted regions with region risk level values of 1 and 2 can be determined as the second risk region, and a population in an infectious state in the second risk region is determined as the second infectious state.

[0051] It is easy for those skilled in the art to understand that in actual application scenarios, other infectious state structures can be set according to epidemic prevention and control needs, such as determining other numbers of infectious states, and the present disclosure does not make any special limitation thereto.

[0052] In step S120, an initial infectious disease population prediction model is established according to the first infectious state and the second infectious state, and to-be-estimated parameters of the initial infectious disease population prediction model are determined.

[0053] In some example embodiments of the present disclosure, the initial infectious disease population prediction model can be a mathematical model of infectious disease including a first infection state and a second infection state, referred to as an SEIIR model. After determining the population categories included in the initial infectious disease population prediction model, the initial infectious disease population prediction model can be established. After the initial infectious disease population prediction model is established, the parameters to be estimated of the model are determined to further determine the parameter values of the parameters to be estimated.

[0054] According to some example embodiments of the present disclosure, population categories in the initial infectious disease population prediction model are determined; wherein the population categories include susceptible population, exposed population, first infection state population, second infection state population, and removed population; state transition parameters of state transitions between each population category are determined; and the initial infectious disease population prediction model is established according to the population categories and the state transition parameters. The population categories can be populations in different state categories in the initial infectious disease population prediction model; wherein the population categories can include susceptible population, exposed population, first infection state population, second infection state population, and removed population. The state transition parameters can be parameters corresponding to state transitions between different population categories, for example, the state transition parameters can include first population proportion, second population proportion, first transition proportion, second transition proportion, and infection removal transition rate, exposed infection transition rate, etc.

[0055] Reference Figure 2 , Figure 2 A block diagram of the established initial infectious disease population prediction model according to example embodiments of the present disclosure is schematically shown. The initial infectious disease population prediction model can include susceptible population (S) 210, exposed population (E) 220, first infection state population (I h ) 231, second infection state population (I l ) 232, and removed population (R) 240. Specifically, the susceptible population 210 can be people who have not yet been infected but lack immunity and are easily infected after contacting the infection state population; the exposed population 220 can be people who have contacted infected people but have no ability to infect others; the infection state population can be people infected with infectious diseases, who can transmit to S members and change them to E members or I members; wherein the first infection state population 231 can be people in a high-risk area, the second infection state population 232 can be people in a low-risk area, and the first infection state population and the second infection state population both belong to the infection state population category; the removed population 240 can be people who are isolated or have immunity due to recovery.

[0056] Reference Figure 3 , Figure 3A flowchart of establishing an initial infectious disease population prediction model according to an example embodiment of the present disclosure is schematically shown. In step S310, population categories included in the initial infectious disease population prediction model can be determined. In step S320, after all population categories are determined, state transition parameters of state transitions between the population categories can be determined. Since the populations in different states exist mutual transitions between states, the state transition parameters of mutual transitions between different population categories in the initial infectious disease population prediction model can be defined.

[0057] According to some example embodiments of the present disclosure, the proportion of the number of people in the first risk area in the number of people in all the areas to be predicted is determined as the first proportion of the number of people; the proportion of the exposed population converted to the first infected state population is determined as the first transfer proportion; the second proportion of the number of people and the second transfer proportion are respectively determined according to the first proportion of the number of people and the first transfer proportion; the transfer rate of the infected state population converted to the removed population is determined as the infected removed transfer rate; and the transfer rate of the exposed population converted to the infected state population is determined as the exposed infected transfer rate. The number of people in all the areas to be predicted can be the total number of people included in the plurality of areas to be detected, which can be denoted as N. The first proportion of the number of people can be the proportion of the total number of people in the first risk area (high-risk area) to the total number of people N in all the areas to be predicted, which can be denoted as p. The first transfer proportion can be the proportion of the infected state population in the high-risk street when the exposed population (E) is transferred to the infected state, which can be denoted as r. The second proportion of the number of people can be the proportion of the total number of people in the second risk area (low-risk area) to the total number of people N in all the areas to be predicted. The second transfer proportion can be the proportion of the infected state population in the low-risk street when the exposed population (E) is transferred to the infected state. The infected removed transfer rate can be the transfer rate of state I (infected state population) to state R (removed population) per day. The exposed infected transfer rate can be the transfer rate of state E (exposed population) to state I (infected state population) per day. The effective contact rate can be obtained based on the number of contacts between the population not infected with the disease and the population infected with the disease per unit time and the probability of being infected per contact.

[0058] After the first proportion of the number of people and the first transfer proportion are determined, the second proportion of the number of people and the second transfer proportion can be determined according to the first proportion of the number of people and the first transfer proportion. Wherein, the second proportion of the number of people can be denoted as 1-p, and the second transfer proportion can be denoted as 1-r. Referring to Figure 3 In step S330, the initial infectious disease population prediction model can be established according to the population categories and the state transition parameters. After the state transition parameters are defined, the initial infectious disease population prediction model can be established according to the population categories and the state transition parameters. Specifically, the partial differential equation set corresponding to the initial infectious disease population prediction model is shown in formulas 1-6.

[0059]

[0060]

[0061]

[0062]

[0063]

[0064] N=S t +E t +I ht +I lt +R t (Formula 6)

[0065] wherein N is the total number of the population, i.e. the total number of all to-be-predicted regions. S t , E t , I ht , I lt , R t are the number of susceptible population, exposed population, high-risk region infection state population, low-risk region infection state population and removed population respectively at time t. Parameter β h may be the effective contact rate corresponding to the high-risk region; parameter β l may be the effective contact rate corresponding to the low-risk region. Parameter p may be the proportion of the total population of the high-risk region in the total population N of all to-be-predicted regions, i.e. the proportion of the first number; 1-p may be the proportion of the total population of the low-risk region in the total population N of all to-be-predicted regions, i.e. the proportion of the second number; here, the basic difference of the contactable susceptible population of two infection states can be simulated. Parameter r may be the proportion of the high-risk region infection state when the exposed population E transfers to the infection state, i.e. the first transfer proportion; parameter 1-r may be the proportion of the low-risk region infection state when the exposed population E transfers to the infection state, i.e. the second transfer proportion. Parameter γ is the transfer rate of state I (infection state population) to state R (removed population) per day, i.e. the infection removal transfer rate; parameter σ is the transfer rate of state E (exposed population) to state I (infection state population) per day, i.e. the exposure infection transfer rate.

[0066] It should be noted that in the actual epidemic prediction scenario, the infection state can be divided into a corresponding number of infection state categories according to specific needs to establish a corresponding infectious disease number prediction model. The disclosure does not make any special limitation on the number of dividing the infection state into multiple different categories of infection state.

[0067] According to some example embodiments of the present disclosure, a propagation period of an infectious disease to be predicted and time series data corresponding to the propagation period are determined; a prevention and control condition corresponding to the infectious disease in the propagation period is obtained; the propagation period is divided into a plurality of propagation periods according to the prevention and control condition, and the time series data is divided into a corresponding number of sub-time series data; and parameters to be estimated in each propagation period are determined according to the plurality of sub-time series data. The propagation period can be a course of a certain infectious disease, for example, according to the analysis of the incidence of the number of infected people of a certain infectious disease, the propagation period of the infectious disease is determined to be 21 days. The time series data can be a sequence data composed of the number of new cases per day in each state in a certain propagation period of the infectious disease. The prevention and control condition can be a disease prevention and control policy formulated by a certain region for the infectious disease. The propagation period can be a plurality of propagation time periods formed by dividing the propagation period according to the prevention and control condition. The sub-time series data can be a sequence data composed of the number of new cases per day in each state in each propagation period. The sub-time series data can be a sequence data formed by dividing the sub-time series. The parameters to be estimated can be the infection coefficients corresponding to different propagation periods, and the proportional relationship of the infection coefficients corresponding to different infection states in each propagation period.

[0068] Since different prevention and control policies (i.e., prevention and control conditions) are formulated in a certain region in a certain propagation period of an infectious disease in the actual prevention and control process, the propagation period can be divided into a plurality of propagation periods according to the different prevention and control conditions corresponding to the propagation period in a certain region. After determining the propagation period of the infectious disease to be predicted, the time series data corresponding to the propagation period can be determined, i.e., the number of new cases per day in each state. After obtaining different prevention and control conditions formulated for the infectious disease in the propagation period, the propagation period can be divided into a plurality of propagation periods according to the different prevention and control conditions formulated, and the time series data can be divided into a plurality of sub-time series data according to the propagation period. The sub-time series data obtained by dividing can determine the parameters to be estimated corresponding to each propagation period.

[0069] For the propagation of an infectious disease in a certain region, the infection coefficient corresponding to different prevention and control conditions is different, for example, when a certain region discovers new infectious cases, the prevention and control measures in the region will be strengthened to prevent the disease from further spreading. In actual scenarios, corresponding prevention and control measures can be formulated according to the disease development situation of a certain region. Therefore, the propagation period can be segmented according to the prevention and control condition of a certain region to form a plurality of propagation periods. The infection coefficient corresponding to each propagation period is the same, and the infection coefficient corresponding to different propagation periods is different.

[0070] For example, in a certain practical application scenario, according to the prevention and control conditions, one propagation period can be divided into three propagation periods, the infection coefficient parameters of the high-risk infection state and the low-risk infection state are the same in the first period, and the infection state parameter in the first period can be denoted as beta0. In the second period and the third period, the infection coefficient of the high-risk infection state can be a proportional multiple of the coefficient of the low-risk infection state in the same period. For example, the infection coefficients of the low-risk area in the second period and the third period are denoted as beta1 and beta2 respectively, and the infection coefficients of the high-risk area in the second period and the third period can be denoted as beta1*alpha and beta2*alpha respectively. Therefore, the to-be-estimated parameters of the initial infectious disease population prediction model include beta0, beta1, beta2 and alpha. After the to-be-estimated parameters are determined, the parameter estimation method can be used to determine the to-be-estimated parameters.

[0071] In addition, for different to-be-predicted areas, the corresponding propagation periods, such as the number of propagation periods and the segmentation time points of the propagation periods, can be determined according to the area characteristics and epidemic transmission characteristics of the to-be-predicted areas, and the present disclosure does not make any special limitation on this.

[0072] In step S130, the daily new number of people in each infection state in the initial infectious disease population prediction model is obtained, and the target parameter value of the to-be-estimated parameter is determined according to the daily new number of people in each infection state.

[0073] In some example embodiments of the present disclosure, the daily new number of people can be the new number of people in each different state of the population category in a certain period in the epidemic transmission period, for example, the daily new number of people can include the daily new number of susceptible population, the daily new number of exposed population, the daily new number of first infection state population, the daily new number of second infection state population and the daily new number of removed population; wherein the daily new number of people in each infection state includes the daily new number of first infection state population and the daily new number of second infection state population. The target parameter value can be the parameter value corresponding to the to-be-estimated parameter.

[0074] After obtaining the daily new number of people in each state, the target parameter value of the to-be-estimated parameter can be determined based on the initial infectious disease population prediction model and the daily new number of people in each infection state, so as to substitute the target parameter value into the initial infectious disease population prediction model to generate the infectious disease population prediction model.

[0075] According to some example embodiments of the present disclosure, a prior distribution of the to-be-estimated parameter is obtained; based on the daily new number of people in each infection state and the prior distribution, a parameter estimation method is used for iterative calculation until the iteration result of the iterative calculation converges; and a target parameter mean and a target parameter confidence interval of the to-be-estimated parameter are determined according to the converged iteration result. The prior distribution of the to-be-estimated parameter can be a distribution obtained according to other related parameters and experience before a statistical experiment is performed on the to-be-estimated parameter. The parameter estimation method can be a method for calculating the target parameter value of the to-be-estimated parameter, for example, the parameter estimation method can include a Markov Chain Monte Carlo (MCMC) method and the like. The target parameter mean can be a mean of the to-be-estimated parameter. The target parameter confidence interval can be a confidence interval of the to-be-estimated parameter.

[0076] Reference Figure 4 , Figure 4 A flowchart for determining the target parameter value of the to-be-estimated parameter according to an example embodiment of the present disclosure is schematically shown. In step S410, when calculating the to-be-estimated parameter, a prior distribution of the to-be-estimated parameter can be obtained first, in this embodiment, based on experience, it can be set that the parameter beta obeys a uniform distribution U(0, 2) with upper and lower bounds of 0 and 2 respectively, the parameter alpha obeys a uniform distribution U(0, 1), and the above distribution is taken as the prior distribution of the to-be-estimated parameter. In step S420, after the prior distribution of the to-be-estimated parameter is determined, the MCMC algorithm can be used to perform iterative calculation on the to-be-estimated parameter in combination with the daily new number of people in each infection state until the iteration result of the iterative calculation converges. In step S430, after the iteration result of the MCMC method converges, the target parameter mean and the target parameter confidence interval corresponding to the to-be-estimated parameters beta0, beta1, beta2 and alpha can be determined, that is, the target parameter value is determined.

[0077] As can be easily understood by those skilled in the art, when calculating the target parameter value of the to-be-estimated parameter, other distribution functions can also be taken as the prior distribution of the parameter beta and the parameter alpha in other application scenarios. For example, the prior distribution of the parameter beta and the parameter alpha can be determined as a Gamma Distribution obeyed by the parameter beta and the parameter alpha respectively. The present disclosure does not make any special limitation on the distribution function obeyed by the parameter beta and the parameter alpha.

[0078] In step S140, the target parameter value is substituted into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and the epidemic prediction population is determined according to the infectious disease population prediction model.

[0079] In some exemplary embodiments of this disclosure, the infectious disease population prediction model can be an infectious disease mathematical model obtained by substituting target parameter values ​​into an initial infectious disease population prediction model. The predicted number of cases can be the daily increase in different population categories included in the infectious disease population model during the period to be predicted.

[0080] Substituting the calculated target parameter values ​​of the parameters to be estimated into the initial infectious disease population prediction model yields the infectious disease population prediction model. Based on this model, the number of people affected by the epidemic can be predicted, resulting in the predicted number of cases. Specifically, the prediction of new cases can be updated and iterated on a daily basis, calculating the number of new cases under various conditions each day.

[0081] According to some exemplary embodiments of this disclosure, a multinomial distribution function for state transitions between different states in an infectious disease population prediction model is obtained; the transition probability of each state in the infectious disease population prediction model is calculated based on the multinomial distribution function; state iterative calculations are performed on different population categories in the infectious disease population prediction model; and the predicted number of people affected by the epidemic is determined based on the calculation results after state iterative calculations. The multinomial distribution function is the distribution function used to calculate the number of people transitioning between states of different population categories during the prediction process. The transition probability can be the probability of mutual transformation between different states in the infectious disease population prediction model. State iterative calculation can be the process of iteratively calculating the number of people in each state of the infectious disease population prediction model. The calculation results after state iterative calculations can be the daily new number of people in each state of the infectious disease population prediction model obtained after one iteration calculation.

[0082] refer to Figure 5 , Figure 5A flowchart of determining epidemic prediction population according to an infectious disease population prediction model according to an example embodiment of the present disclosure is schematically shown. In the process of predicting the epidemic population by using the infectious disease population prediction model, different from the updating process of parameter estimation of the initial infectious disease population prediction model, in the prediction process, a multinomial distribution function can be introduced when calculating the population transfer between different states. In step S510, the multinomial distribution function of state transition between different states in the infectious disease population prediction model is obtained, for example, the multinomial distribution function can be the Multinom distribution function under R language. In step S520, the transition probability between each state in the infectious disease population prediction model is calculated according to the obtained multinomial distribution function, and the state iteration calculation of different population categories in the infectious disease population prediction model is performed according to the transition probability. By calculating the transition probability of each state through the multinomial distribution function, a certain randomness can be introduced into the state iteration calculation process. In step S530, the calculation result after state iteration calculation can be obtained through daily iteration update, and the calculation result after state iteration calculation contains the daily new population in each state. In the process of predicting the epidemic population, the iteration time can be set to a certain time period in the future, the epidemic population in the future time period is predicted, and the epidemic prediction population is obtained.

[0083] It should be noted that the terms "first", "second", "third" and the like used in the present disclosure are only used to distinguish different infection states, different risk areas, different infection state populations, different population proportions, different transition proportions and the like, and should not impose any limitation on the present disclosure.

[0084] In summary, the epidemic data prediction method of the present disclosure obtains an initial infectious disease model, and divides the infection states of the initial infectious disease model into a first infection state and a second infection state according to a regional risk level; establishes an initial infectious disease population prediction model according to the first infection state and the second infection state, and determines to-be-estimated parameters of the initial infectious disease population prediction model; obtains daily new population under each infection state in the initial infectious disease population prediction model, and determines target parameter values of the to-be-estimated parameters according to the daily new population under each infection state; substitutes the target parameter values into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and determines an epidemic prediction population according to the infectious disease population prediction model. On the one hand, the infectious disease population prediction model suitable for different policy classification regulation scenarios is established according to the regional risk level, and the infectious disease population prediction model is used for epidemic population prediction, which can make the prediction result more accurate. On the other hand, the to-be-estimated parameters are estimated based on the prior distribution and the actual epidemic data, so that the target parameter values of the to-be-estimated parameters are more accurate, and the accuracy of the prediction result can be further improved based on the target parameter values. On the other hand, the infectious disease population prediction model in the present disclosure uses a time period segmentation method, which can better fit the population change of different population categories due to policy changes in the real epidemic, and improve the accuracy of the model prediction result.

[0085] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired result. In addition or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps, etc.

[0086] In addition, in the present example embodiment, an epidemic data prediction device is also provided. Referring to Figure 6 The epidemic data prediction device 600 can include an infection state determination module 610, a model establishment module 620, a parameter value determination module 630, and a population prediction module 640.

[0087] Specifically, the infection state determination module 610 is configured to obtain an initial infectious disease model, and divide infection states of the initial infectious disease model into a first infection state and a second infection state according to a regional risk level; the model establishment module 620 is configured to establish an initial infectious disease population prediction model according to the first infection state and the second infection state, and determine to-be-estimated parameters of the initial infectious disease population prediction model; the parameter value determination module 630 is configured to obtain a daily increase in population under each infection state in the initial infectious disease population prediction model, and determine a target parameter value of the to-be-estimated parameters according to the daily increase in population under each infection state; and the population prediction module 640 is configured to substitute the target parameter value into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and determine an epidemic situation prediction population according to the infectious disease population prediction model.

[0088] The epidemic situation data prediction apparatus 600 establishes an infectious disease population prediction model suitable for different policy classification regulation scenarios according to a regional risk level, and uses the established infectious disease population prediction model to predict an epidemic situation population, so that the prediction result obtained is more accurate. In addition, the to-be-estimated parameters are estimated based on a prior distribution and actual epidemic situation data, so that the target parameter value of the to-be-estimated parameters obtained is more accurate, and the accuracy of the prediction result can be further improved based on the target parameter value obtained, and the epidemic situation data prediction apparatus is an effective epidemic situation data prediction apparatus.

[0089] In an exemplary embodiment of the present disclosure, the infection state determination module includes an infection state determination unit configured to obtain a regional risk level threshold value and regional risk level values of a plurality of to-be-predicted regions; determine a to-be-predicted region with a regional risk level value greater than or equal to the regional risk level threshold value as a first risk region, and determine a population in an infection state in the first risk region as a first infection state; and determine a to-be-predicted region with a regional risk level value less than the regional risk level threshold value as a second risk region, and determine a population in an infection state in the second risk region as a second infection state.

[0090] In an exemplary embodiment of the present disclosure, the model establishment module includes a model establishment unit configured to determine population categories in an initial infectious disease population prediction model; wherein the population categories include a susceptible population, an exposed population, a first infection state population, a second infection state population, and a removed population; determine state transition parameters of state transitions between the population categories; and establish the initial infectious disease population prediction model according to the population categories and the state transition parameters.

[0091] In an example embodiment of the present disclosure, the model establishing unit comprises a state parameter determining subunit configured to determine a first proportion of the number of people in the first risk area in the number of people in all the areas to be predicted as a first proportion of the number of people; determine a proportion of the exposed population converted into the first infected state population as a first transition proportion; determine a second proportion of the number of people and a second transition proportion according to the first proportion of the number of people and the first transition proportion respectively; determine a transition rate of the infected state population converted into the removed population as an infected removed transition rate; and determine a transition rate of the exposed population converted into the infected state population as an exposed infected transition rate.

[0092] In an example embodiment of the present disclosure, the model establishing module further comprises a to-be-estimated parameter determining unit configured to determine a transmission period of the infectious disease to be predicted and time series data corresponding to the transmission period; obtain a control condition corresponding to the infectious disease in the transmission period; divide the transmission period into a plurality of transmission periods according to the control condition, and divide the time series data into a corresponding number of sub-time series data; and determine the to-be-estimated parameters in each transmission period according to the plurality of sub-time series data.

[0093] In an example embodiment of the present disclosure, the parameter value determining module comprises a parameter value determining unit configured to obtain a prior distribution of the to-be-estimated parameters; perform iterative calculation based on the daily increase in the number of people in each infected state and the prior distribution, and using a parameter estimation method until the iteration result of the iterative calculation converges; and determine the target parameter mean and the target parameter confidence interval according to the converged iteration result.

[0094] In an example embodiment of the present disclosure, the number of people predicting module comprises a number of people predicting unit configured to obtain a multinomial distribution function of state transition between different states in the infectious disease number of people predicting model; calculate the transition probability of each state in the infectious disease number of people predicting model according to the multinomial distribution function, and perform state iterative calculation on different population categories in the infectious disease number of people predicting model; and determine the epidemic prediction number of people according to the calculation result after the state iterative calculation.

[0095] The specific details of each virtual epidemic data prediction device module in the above have been described in detail in the corresponding epidemic data prediction method, and therefore will not be described here.

[0096] It should be noted that although several modules or units of the epidemic data prediction device are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into a plurality of modules or units.

[0097] In addition, in the exemplary embodiments of the present disclosure, an electronic device capable of implementing the above-described method is also provided.

[0098] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method or a program product. Therefore, various aspects of the present application can be embodied as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" herein.

[0099] The electronic device 700 according to this embodiment of the present application will be described below with reference to Figure 7 Figure 7 The display electronic device 700 is merely an example and should not impose any limitation on the function and use range of the embodiments of the present application.

[0100] As shown in Figure 7 The electronic device 700 is in the form of a general computing device. The components of the electronic device 700 can include, but are not limited to, the at least one processing unit 710 described above, the at least one storage unit 720 described above, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), and a display unit 740.

[0101] The storage unit stores program code that can be executed by the processing unit 710, so that the processing unit 710 performs the steps described in the "Exemplary Method" section of the present specification according to various exemplary embodiments of the present application.

[0102] The storage unit 720 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 721 and / or a cache memory 722, and can further include a read-only memory (ROM) 723.

[0103] The storage unit 720 can include program / utility 724 having a set of (at least one) program modules 725, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof can include implementation of a network environment.

[0104] The bus 730 can represent one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit or a local bus using any of a variety of bus structures.

[0105] ​The electronic device 700 can also communicate with one or more external devices 770 such as a keyboard or pointing devices, a display, a Bluetooth device, a disk drive or other memory device, or the like. Additionally, the electronic device 700 can communicate with one or more devices that enable a user to interact with the electronic device 700, such as a display, a remote control, or the like. The communication can be via Input / Output (I / O) interface(s) 750. Further, the electronic device 700 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), or the Internet via the network adapter 760. As depicted, the network adapter 760 communicates with the other components of the electronic device 700 via bus 730. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with the electronic device 700. These components, for example, include but are not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0106] From the above description of the embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, or the like) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0107] In the example embodiments of the present disclosure, a computer readable storage medium is also provided, on which a program product capable of implementing the above-mentioned method of the present disclosure is stored. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps described in the above-mentioned "example method" section according to various example embodiments of the present disclosure when the program product is run on the terminal device.

[0108] Reference Figure 8 As shown, a program product 800 for implementing the above-mentioned method according to the embodiments of the present disclosure is described, which can adopt a portable compact disc read-only memory (CD-ROM) and include program codes, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used or combined with an instruction execution system, device, or apparatus.

[0109] The program product can employ any combination of one or more computer-readable media. The computer-readable media can be a computer-readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] The computer-readable signal medium can include a computer-readable storage medium that is propagated as a carrier wave. The computer-readable signal medium can further be any computer-readable medium that is not a storage medium. The computer-readable signal medium can be a computer-readable storage medium that is a propagated signal on a computer-readable storage medium.

[0111] The program code embodied on the computer-readable media can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0112] The program code can be executed by one or more programmable processors, which can be implemented in one or more computer devices including any combination of a microprocessor, a microcontroller, a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device. The program code can be written in any form of programming language, including object-oriented programming languages such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can be entirely executed on the user computing device, partially executed on the user device, executed as a standalone software package, partially executed on the user computing device and partially executed on a remote computing device, or entirely executed on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected to the Internet through an Internet service provider).

[0113] In addition, the above-described flowcharts are merely schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to limit the purpose. It is easily understood that the processes shown in the above-described flowcharts do not indicate or limit the time sequence of the processes. In addition, it is also easily understood that the processes can be executed synchronously or asynchronously, for example, in a plurality of modules.

[0114] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

[0115] It should be understood that the present disclosure is not limited to the precise structures as herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the claims that follow.

Claims

1. An epidemic data prediction method, characterized in that, The method comprises the following steps: obtain an initial infectious disease model, and divide the infection states of the initial infectious disease model into a first infection state and a second infection state according to the regional risk levels; the first infection state is the infection state corresponding to the region whose risk level is greater than or equal to the threshold value of the regional risk level; the second infection state is the infection state corresponding to the region whose risk level is less than the threshold value of the regional risk level; establish an initial infectious disease population prediction model according to the first infection state and the second infection state, and determine the parameters to be estimated of the initial infectious disease population prediction model; the parameters to be estimated are determined based on the sub-time series data corresponding to multiple transmission periods in the transmission cycle of the infectious disease to be predicted, and the population categories corresponding to the initial infectious disease population prediction model include susceptible population, exposed population, first infection state population, second infection state population and removed population; obtain the daily new population under each infection state in the initial infectious disease population prediction model, and determine the target parameter value of the parameters to be estimated according to the daily new population under each infection state; substitute the target parameter value into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and determine the epidemic prediction population according to the infectious disease population prediction model; the parameters to be estimated include infection coefficient; the determination of the parameters to be estimated of the initial infectious disease population prediction model comprises: determine the transmission cycle of the infectious disease to be predicted and the time series data corresponding to the transmission cycle; obtain the prevention and control conditions corresponding to the infectious disease in the transmission cycle; divide the transmission cycle into multiple transmission periods and the time series data into corresponding number of sub-time series data according to the prevention and control conditions; determine the parameters to be estimated under each transmission period according to the multiple sub-time series data, and the parameters to be estimated are used to represent the proportional relationship of the infection coefficients corresponding to each transmission period under different infection states.

2. The method of claim 1, wherein, the division of the infection states of the initial infectious disease model into the first infection state and the second infection state according to the regional risk levels comprises: obtain the threshold value of the regional risk level and the regional risk level values of multiple regions to be predicted; determine the regions to be predicted whose regional risk level values are greater than or equal to the threshold value of the regional risk level as the first risk regions, and determine the population in the infection state in the first risk regions as the first infection state; determine the regions to be predicted whose regional risk level values are less than the threshold value of the regional risk level as the second risk regions, and determine the population in the infection state in the second risk regions as the second infection state.

3. The method of claim 1, wherein, the initial infectious disease model further comprises susceptible state, exposed state and removed state; the establishment of the initial infectious disease population prediction model according to the first infection state and the second infection state comprises: determine the population categories in the initial infectious disease population prediction model; wherein the population categories include susceptible population, exposed population, first infection state population, second infection state population and removed population; determine the state transition parameters of the state transition between each population category; establish the initial infectious disease population prediction model according to the population categories and the state transition parameters.

4. The method of claim 3, wherein, The state transition parameter of the determination of the state transition between each population category comprises: The proportion of the number of people in the first risk area in the number of people in all to-be-predicted areas is determined as a first number proportion, the first risk area being a to-be-predicted area with a region risk level value greater than or equal to the region risk level threshold value; The proportion of the conversion of the exposed population into the first infected state population is determined as a first transfer proportion; The second number proportion and the second transfer proportion are respectively determined according to the first number proportion and the first transfer proportion; The transfer rate of the conversion of the infected state population into the removed population is determined as an infected removal transfer rate; The transfer rate of the conversion of the exposed population into the infected state population is determined as an exposed infection transfer rate.

5. The method of claim 1, wherein, The target parameter value comprises a target parameter mean value and a target parameter confidence interval, and the target parameter value of the to-be-estimated parameter is determined according to the daily increase in the number of people in each infected state, comprising: An initial distribution of the to-be-estimated parameter is obtained; Based on the daily increase in the number of people in each infected state and the initial distribution, iterative calculation is performed by using a parameter estimation method until the iterative result of the iterative calculation converges; The target parameter mean value and the target parameter confidence interval are determined according to the converged iterative result.

6. The method of claim 1, wherein, The epidemic prediction population is determined according to the infectious disease population prediction model, comprising: A multinomial distribution function of state transition between different states in the infectious disease population prediction model is obtained; The transfer probability of each state in the infectious disease population prediction model is calculated according to the multinomial distribution function, and state iterative calculation is performed on different population categories in the infectious disease population prediction model according to the transfer probability; The epidemic prediction population is determined according to the calculation result after the state iterative calculation.

7. An epidemic data prediction device, characterized by comprising: Comprise: An infected state determination module is configured to obtain an initial infectious disease model, and divide the infected state of the initial infectious disease model into a first infected state and a second infected state according to a region risk level; the first infected state is an infected state corresponding to a region with a region risk level greater than or equal to a region risk level threshold value; the second infected state is an infected state corresponding to a region with a region risk level less than the region risk level threshold value; A model establishment module is configured to establish an initial infectious disease population prediction model according to the first infected state and the second infected state, and determine a to-be-estimated parameter of the initial infectious disease population prediction model; the to-be-estimated parameter is determined based on sub-time series data corresponding to multiple transmission periods in a transmission period of a to-be-predicted infectious disease, and the population categories corresponding to the initial infectious disease population prediction model comprise susceptible population, exposed population, first infected state population, second infected state population and removed population; A parameter value determination module is configured to obtain the daily increase in the number of people in each infected state of the initial infectious disease population prediction model, and determine a target parameter value of the to-be-estimated parameter according to the daily increase in the number of people in each infected state; A population prediction module is configured to substitute the target parameter value into the initial infectious disease population prediction model to obtain an infectious disease population prediction model, and determine an epidemic prediction population according to the infectious disease population prediction model; The to-be-estimated parameter comprises an infection coefficient; The model establishing module further comprises a to-be-estimated parameter determining unit configured to determine a propagation period of the to-be-predicted infectious disease and time series data corresponding to the propagation period; acquire a prevention and control condition corresponding to the infectious disease in the propagation period; divide the propagation period into a plurality of propagation periods according to the prevention and control condition, and divide the time series data into a corresponding number of sub-time series data; determine to-be-estimated parameters in each propagation period according to the plurality of sub-time series data, the to-be-estimated parameters being used to represent proportional relationships of corresponding infection coefficients in each propagation period under different infection states.

8. An electronic device, comprising: comprise: a processor; and a memory, the memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the epidemic data prediction method according to any one of claims 1 to 6.

9. A computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the epidemic data prediction method according to any one of claims 1 to 6.

Images