Method, device, storage medium and electronic device for predicting new cases of infectious diseases

Abstract

The present invention discloses a method, device, storage medium and electronic device for predicting new cases of infectious diseases. The method comprises: constructing an initial model of the infectious disease, determining target parameters in the initial model, wherein the target parameters include an environmental factor coefficient for characterizing the urgency of infectious disease prevention and control measures and a mobility influence coefficient to be estimated, wherein the mobility influence coefficient characterizes the mobility of a population; collecting multiple first sample data within a historical time period, wherein each first sample data includes the first number of new cases in the corresponding collection time period; determining an estimated value of the mobility influence coefficient based on the first sample data; determining a prediction model based on the estimated value of the mobility influence coefficient, the environmental factor coefficient and the initial model, so as to predict the daily number of new cases of the infectious disease based on the prediction model. The present invention can accurately predict the daily number of new cases of the infectious disease.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to a method, device, storage medium and electronic device for predicting new cases of infectious diseases. Background Art

[0002] Infectious diseases are a type of disease caused by various pathogens that can be transmitted between people, animals, or between people and animals through various transmission routes. If infectious diseases spread on a large scale, human life and health will face a major threat. If the scale of infectious disease transmission can be reasonably predicted, it will be of great significance for controlling the spread of infectious diseases and formulating prevention and control measures.

[0003] Currently, the prediction of infectious diseases, especially the prediction of new cases, is mostly based on transmission dynamics models, which are divided into SI, SIR, SIRS, SEIR models, etc. according to the type of infectious disease. They study the transmission speed, spatial range, transmission pathways, dynamic mechanisms and other issues of infectious diseases, and can play a guiding role in the effective prevention and control of infectious diseases.

[0004] Due to the complexity of the transmission process of infectious diseases, the current methods for predicting new cases of infectious diseases are not very accurate. Summary of the invention

[0005] The present invention provides a method, device, storage medium and electronic device for predicting new cases of infectious diseases, so as to at least solve the above technical problems existing in the prior art.

[0006] In one aspect, the present invention provides a method for predicting new cases of infectious diseases, the method comprising:

[0007] Constructing an initial model of infectious diseases, and determining target parameters in the initial model, wherein the target parameters include an environmental factor coefficient used to characterize the urgency of infectious disease prevention and control measures and a mobility influence coefficient to be estimated, wherein the mobility influence coefficient characterizes the mobility of the population;

[0008] Collecting multiple pieces of first sample data in a historical time period, each piece of the first sample data includes the first number of newly added cases in the corresponding collection time period;

[0009] Determining an estimated value of the movement influence coefficient according to the first sample data;

[0010] A prediction model is determined based on the estimated value of the mobility impact coefficient, the environmental factor coefficient and the initial model to predict daily new cases of the infectious disease based on the prediction model.

[0011] In one possible implementation manner, determining the estimated value of the movement influence coefficient according to the first sample data includes:

[0012] Constructing multiple pieces of second sample data based on the first sample data, each piece of second sample data includes multiple pieces of first sample data with a continuous collection time period, and all first newly added case numbers of each piece of second sample data constitute a basic newly added sequence;

[0013] Determine the estimated value of the movement influence coefficient corresponding to each second sample data and determine the estimated value of the movement influence coefficient that meets the preset conditions.

[0014] In one possible implementation manner, the first sample data further includes mobility data of a corresponding collection time period, and the mobility data includes a plurality of mobility parameters and parameter values.

[0015] In one possible implementation manner, the calculating an estimated value of a movement influence coefficient corresponding to each piece of second sample data includes:

[0016] For each piece of second sample data, calculating a weight corresponding to each mobility parameter in the piece of second sample data and an intercept of a mobility coefficient;

[0017] The estimated value of the mobility influence coefficient is determined according to the parameter value of each mobility parameter in the second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility coefficient.

[0018] In one possible implementation manner, determining an estimated value of a movement influence coefficient that meets a preset condition includes:

[0019] For each piece of second sample data, according to the estimated value of the mobile influence coefficient corresponding to the piece of second sample data, the estimated new sequence corresponding to the piece of second sample data is calculated by the initial model, and the estimated new sequence includes the number of second new cases in all collection time periods corresponding to the piece of second sample data;

[0020] For each second sample data, the similarity between the basic new sequence and the estimated new sequence of the second sample data is calculated. If the similarity is less than a threshold, it is determined that the preset condition is met, and the estimated value of the mobile influence coefficient corresponding to the second sample data is recorded.

[0021] In one possible implementation manner, the calculating the weight corresponding to each mobility parameter in the second sample data and the intercept of the mobility coefficient includes:

[0022] According to the second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility coefficient are calculated by the MCMC algorithm.

[0023] In one embodiment, calculating the number of new cases per day according to the prediction model includes:

[0024] For each estimated value of the recorded movement influence coefficient, substitute the estimated value into the initial model to obtain a corresponding prediction model;

[0025] For each prediction model, the number of new cases in a specified time period is calculated according to the prediction model;

[0026] The predicted number of new cases for the specified time period is determined based on the number of new cases calculated by each prediction model.

[0027] In one possible implementation, for each prediction model, calculating the number of new cases in a specified time period according to the prediction model includes:

[0028] The daily number of new cases in a specified time period is determined based on the proportion of uninfected people in the set area, the number of new cases on the day before the incubation period, the estimated value of the mobility impact coefficient, and the environmental factor coefficient.

[0029] Another aspect of the present invention provides a device for predicting new cases of infectious diseases, the device comprising:

[0030] A construction module is used to construct an initial model of infectious diseases and determine target parameters in the initial model, wherein the target parameters include an environmental factor coefficient used to characterize the urgency of infectious disease prevention and control measures and a mobility influence coefficient to be estimated, wherein the mobility influence coefficient characterizes the mobility of the population;

[0031] A collection module, used for collecting a plurality of first sample data in a historical time period, each of which includes the first number of newly added cases in the corresponding collection time period;

[0032] A determination module, configured to determine an estimated value of the movement influence coefficient according to the first sample data;

[0033] A prediction module is used to determine a prediction model based on the estimated value of the mobility impact coefficient, the environmental factor coefficient and the initial model, so as to predict the daily number of new cases of the infectious disease according to the prediction model.

[0034] Another aspect of the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the prediction method of the present invention.

[0035] Another aspect of the present invention provides an electronic device, comprising:

[0036] processor;

[0037] a memory for storing instructions executable by the processor;

[0038] The processor is used to read the executable instructions from the memory and execute the instructions to implement the prediction method of the present invention.

[0039] The present invention provides a method for predicting new cases of infectious diseases. An initial model different from a kinetic equation is constructed, which comprehensively considers the mobility of the population and the urgency of prevention and control measures, adds an environmental factor coefficient and a mobility influence coefficient to the initial model, and obtains a prediction model by calculating an estimated value of the mobility influence and substituting it into the initial model. The daily number of new cases of the new infectious disease can be estimated based on the prediction model, thereby improving the accuracy of infectious disease prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram showing a flow chart of a method for predicting new cases of infectious diseases according to an embodiment;

[0041] Figure 2 A schematic diagram of the structure of a device for predicting new cases of infectious diseases according to an embodiment is shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0043] In order to improve the accuracy of prediction of new cases of infectious diseases, this application proposes a method for predicting new cases of infectious diseases, such as Figure 1 As shown, the method includes:

[0044] Step S101, construct an initial model of infectious diseases, and determine the target parameters in the initial model, wherein the target parameters include an environmental factor coefficient used to characterize the urgency of infectious disease prevention and control measures and a mobility influence coefficient to be estimated, wherein the mobility influence coefficient characterizes the mobility of the population.

[0045] In this application example, the initial model of the epidemic is as follows:

[0046]

[0047] In the above model:

[0048] X t Indicates: predicted data of new cases of infectious diseases;

[0049] t means: date and time;

[0050] Duration means: the incubation period of an infectious disease;

[0051] α represents: mobile influence coefficient;

[0052] CBE stands for environmental factor coefficient, which is adjusted according to the urgency of infectious disease prevention and control measures;

[0053] NPOP means: the total number of people in a region, regardless of births and deaths, immigration and emigration, the total number of people remains unchanged.

[0054] Based on the initial model of the infectious disease described above, the method further includes:

[0055] Step S102: Collect multiple pieces of first sample data within a historical time period, each piece of the first sample data includes the first number of newly added cases in the corresponding collection time period.

[0056] When predicting new cases of infectious diseases, it is first necessary to collect data for a certain area to be predicted. The time period for data collection can be a historical time period, and the historical time period is divided into multiple sub-time periods, which are recorded as collection time periods. A collection time period can be one day, one week, etc., and this application does not impose any restrictions on this. The data corresponding to each collection time period is a sample data, and each sample data includes the number of new cases corresponding to the collection time period, which is recorded as the first number of new cases. If the collection time period is one day (i.e., once a day), then the first number of new cases is the number of new cases per day.

[0057] For example: Assuming that sample data from region A is collected, the historical time period is set to 2021 / 3 / 1 to 2021 / 3 / 30, and assuming that the collection time period is 1 day, 30 pieces of sample data can be collected, as shown in Table 1 below:

[0058] date The first number of new cases 2021 / 3 / 1 2 2021 / 3 / 2 0 2021 / 3 / 3 0 2021 / 3 / 4 0 2021 / 3 / 5 1 2021 / 3 / 6 1 2021 / 3 / 7 3 2021 / 3 / 8 5 2021 / 3 / 9 7 2021 / 3 / 10 4 … … 2021 / 3 / 30 10

[0059] Table 1

[0060] In Table 1, the first number of new cases indicates the number of new cases of infectious diseases on that day. For example, on 2021 / 3 / 1, there were 2 new cases in area A; and on 2021 / 3 / 2, there were 0 new cases in area A, that is, there were no new cases on that day.

[0061] In one example, in addition to the first number of new cases, each piece of sample data also includes mobility data for the corresponding collection time period, and the mobility data includes multiple mobility parameters and parameter values. Multiple mobility parameters can be obtained by dividing an area according to different places, such as retail and entertainment, grocery stores and pharmacies, parks, transfer stations, workplaces and residences. Mobility parameters can also be obtained by classifying more detailed locations. For example, entertainment and retail can be used as different mobility parameters separately, or transfer stations can be specifically subdivided into mobility parameters such as railway stations, airports, and bus stations. The present invention does not impose specific restrictions on the division of mobility parameters. Taking the historical time period from 2021 / 3 / 1 to 2021 / 3 / 30 as an example, the mobility data is shown in Table 2 below:

[0062]

[0063] Table 2

[0064] In Table 2, the first column of data is the date, and the second column and beyond are different mobility parameters. For ease of representation, each column of mobility parameters can be represented by g1, g2, ..., gn, and n is a positive integer, indicating that there are n mobility parameters. In Table 2, on March 1, 2021, the mobility of the crowd in retail and entertainment venues decreased by 14% compared with the baseline. For example, the average daily crowd movement (i.e., the baseline) of snack and entertainment venues is 10,000 people, and the crowd movement in retail and entertainment venues on March 1, 2021 is 8,600 people. Therefore, on March 1, 2021, the mobility of the crowd in retail and entertainment venues decreased by 14% compared with the baseline. The same applies to the mobility parameters in other columns in Table 2.

[0065] Step S103, determining an estimated value of the movement influence coefficient according to the first sample data, includes:

[0066] Constructing multiple pieces of second sample data based on the first sample data, each piece of second sample data includes multiple pieces of first sample data with a continuous collection time period, and all first newly added case numbers of each piece of second sample data constitute a basic newly added sequence;

[0067] Determine the estimated value of the movement influence coefficient corresponding to each second sample data and determine the estimated value of the movement influence coefficient that meets the preset conditions.

[0068] One piece of second sample data includes multiple pieces of first sample data, and the collection time periods of these multiple pieces of first sample data are continuous. For example, the 10 pieces of first sample data from March 1 to March 10 in Table 1 constitute one piece of second sample data, as shown in Table 3:

[0069] date The first number of new cases 2021 / 3 / 1 2 2021 / 3 / 2 0 2021 / 3 / 3 0 2021 / 3 / 4 0 2021 / 3 / 5 1 2021 / 3 / 6 1 2021 / 3 / 7 3 2021 / 3 / 8 5 2021 / 3 / 9 7 2021 / 3 / 10 4

[0070] Table 3

[0071] The second sample data may also include mobility data. Table 1 and Table 2 are combined to obtain a second sample data as shown in Table 4:

[0072]

[0073] Table 4

[0074] For the convenience of subsequent description, the newly added sequence composed of all the first newly added case numbers of each second sample data is called the basic newly added sequence of the second sample data.

[0075] In one example, determining an estimated value of a movement influence coefficient corresponding to each piece of second sample data includes:

[0076] For each piece of second sample data, calculating a weight corresponding to each mobility parameter in the piece of second sample data and an intercept of a mobility coefficient;

[0077] The estimated value of the mobility influence coefficient is determined according to the parameter value of each mobility parameter in the second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility coefficient.

[0078] For any second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility influence coefficient are calculated. For the convenience of description, the weights corresponding to different mobility parameters (g1, g2, ..., gn) are represented by a21, a22, ..., a2n respectively, and the intercept is represented by a20.

[0079] The estimated value of the mobility influence coefficient is determined according to the parameter value of the mobility parameter, the weight corresponding to the mobility parameter and the intercept, that is:

[0080] α=a20+a21×g1+a22×g2+...+a2n×gn Formula (2)

[0081] Among them, the values ​​of g1, g2, ..., gn are the parameter values ​​corresponding to the last collection time period in the second sample data. For example, in Table 2, in the second sample data consisting of March 1 to March 10, the parameter values ​​of March 10 are selected as the values ​​of g1, g2, ..., gn in formula (2).

[0082] In one example, a Markov Chain Monte Carlo algorithm (MCMC) can be used to calculate the estimated values ​​of a21, a22, ..., a2n and the intercept a20: a first additional sequence consisting of the first additional quantity in a second sample data is taken as the input of the MCMC algorithm, and a set of estimated values ​​of weights (a21, a22, ..., a2n) and an estimated value of the intercept a20 are output.

[0083] Substituting the estimated values ​​of this set of weights and the estimated value of the intercept into the above formula (2), the estimated value α of the movement influence coefficient corresponding to the second sample data can be calculated. For the convenience of subsequent description, it is recorded as α1, α2, and α3 here.

[0084] Based on the first sample data shown in Table 1, assuming that three pieces of second sample data are constructed, then three estimated values ​​of movement influence coefficients are obtained in this step.

[0085] In one example, determining an estimated value of a movement influence coefficient that meets a preset condition includes:

[0086] For each piece of second sample data, according to the estimated value of the mobile influence coefficient corresponding to the piece of second sample data, the estimated new sequence corresponding to the piece of second sample data is calculated by the initial model, and the estimated new sequence includes the number of second new cases in all collection time periods corresponding to the piece of second sample data;

[0087] For each second sample data, the similarity between the basic new sequence and the estimated new sequence of the second sample data is calculated. If the similarity is less than a threshold, it is determined that the preset condition is met, and the estimated value of the mobile influence coefficient corresponding to the second sample data is recorded.

[0088] Taking the first second sample data as an example, the estimated value of its corresponding moving influence coefficient is α1. Substitute α1 into the initial model of formula (1), calculate the number of new cases from March 1 to March 10 in sequence, and record them as the second number of new cases. Then, these 10 groups of second new cases constitute the estimated new sequence of the first second sample data.

[0089] In one example, Poisson distribution is used to calculate the likelihood values ​​of the basic new sequence and the estimated new sequence, and the likelihood values ​​are used to characterize the similarity between the basic new sequence and the estimated new sequence. If the similarity is less than a threshold, it is determined that the preset conditions are met, and the estimated value of the mobile influence coefficient corresponding to the second sample data is recorded; if the similarity is greater than the threshold, the estimated value of the mobile influence coefficient corresponding to the second sample data is rejected.

[0090] For example: The actual daily increase in the first second sample data from 2021 / 3 / 1 to 2021 / 3 / 10 constitutes the basic increase sequence. After substituting the estimated value of the moving influence coefficient α1 into the initial model, a set of estimated increase sequences is output, and the likelihood values ​​of the basic increase sequence and the estimated increase sequence are calculated using the Poisson distribution. Assuming that the threshold is 1, if the likelihood value is less than 1, the estimated value of the moving influence coefficient α1 corresponding to the second sample data is retained; if the likelihood value is greater than 1, the estimated value of the moving influence coefficient corresponding to the sample data is discarded.

[0091] Step S104: determining a prediction model according to the estimated value of the mobility impact coefficient, the environmental factor coefficient and the initial model, so as to predict the daily number of new cases of the infectious disease according to the prediction model.

[0092] In one example, calculating the number of new cases of the infectious disease per day according to the prediction model includes:

[0093] For each estimated value of the recorded movement influence coefficient, substitute the estimated value into the initial model to obtain a corresponding prediction model;

[0094] For each prediction model, the number of new cases in a specified time period is calculated according to the prediction model;

[0095] The predicted number of new cases for the specified time period is determined based on the number of new cases calculated by each prediction model.

[0096] In one example, for each prediction model, calculating the number of new cases in a specified time period according to the prediction model includes:

[0097] The daily number of new cases in a specified time period is determined based on the proportion of uninfected people in the set area, the number of new cases on the day before the incubation period, the estimated value of the mobility impact coefficient, and the environmental factor coefficient.

[0098] Taking Table 1 and Table 2 as examples, assume that three second sample data (1 / 2 / 3) are constructed, and each second sample data corresponds to an estimated value of a mobile influence coefficient, recorded as α1, α2, and α3. Substituting the estimated value of each mobile influence coefficient into the initial model, the corresponding prediction model will be obtained. Taking α1 as an example, after α1 is substituted into the initial model, the prediction model obtained is as follows:

[0099]

[0100] Assuming that the prediction model is used to predict the number of new cases on 2021 / 4 / 1 (a specified time period), then t is April 1, and assuming the incubation period is 7 days, then X t-duration is the number of new cases on the day before the incubation period, that is, the number of new cases on March 25. It is the sum of the number of new cases from the initial time 0 to March 31, 2021. Based on the proportion of uninfected people in a set area, the number of new cases X1 on April 1 can be predicted.

[0101] Then substitute α2 and α3 into the initial model respectively to calculate the corresponding number of new cases on April 1st as X2 and X3.

[0102] The average of X1, X2, and X3 is the predicted number of new cases on April 1.

[0103] If you need to predict the daily new case sequence from 2021 / 4 / 1 to 2021 / 4 / 10, use the above method to predict the new cases every day from 2021 / 4 / 2 to 2021 / 4 / 10. The final model outputs the predicted new case sequence consisting of the new cases every day from 2021 / 4 / 1 to 2021 / 4 / 10.

[0104] In one example, the present invention also provides a device for predicting new cases of infectious diseases, such as Figure 2 As shown, the device comprises:

[0105] A construction module 201 is used to construct an initial model of infectious diseases and determine target parameters in the initial model, wherein the target parameters include an environmental factor coefficient used to characterize the urgency of infectious disease prevention and control measures and a mobility influence coefficient to be estimated, wherein the mobility influence coefficient characterizes the mobility of the population;

[0106] A collection module 202, configured to collect a plurality of first sample data in a historical time period, each of which includes the first number of newly added cases in a corresponding collection time period;

[0107] A determination module 203, configured to determine an estimated value of the movement influence coefficient according to the first sample data;

[0108] A prediction module 204 is used to determine a prediction model based on the estimated value of the mobility impact coefficient, the environmental factor coefficient and the initial model, so as to predict the daily number of new cases of the infectious disease according to the prediction model.

[0109] In one example, the determining module 203 is specifically configured to:

[0110] Constructing multiple pieces of second sample data based on the first sample data, each piece of second sample data includes multiple pieces of first sample data with a continuous collection time period, and all first newly added case numbers of each piece of second sample data constitute a basic newly added sequence;

[0111] Determine the estimated value of the movement influence coefficient corresponding to each second sample data and determine the estimated value of the movement influence coefficient that meets the preset conditions.

[0112] In an example, the first sample data further includes mobility data of a corresponding collection time period, and the mobility data includes a plurality of mobility parameters and parameter values.

[0113] In one example, determining an estimated value of a movement influence coefficient corresponding to each piece of second sample data includes:

[0114] For each piece of second sample data, calculating a weight corresponding to each mobility parameter in the piece of second sample data and an intercept of a mobility coefficient;

[0115] The estimated value of the mobility influence coefficient is determined according to the parameter value of each mobility parameter in the second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility coefficient.

[0116] In one example, determining an estimated value of a movement influence coefficient that meets a preset condition includes:

[0117] For each piece of second sample data, according to the estimated value of the mobile influence coefficient corresponding to the piece of second sample data, the estimated new sequence corresponding to the piece of second sample data is calculated by the initial model, and the estimated new sequence includes the number of second new cases in all collection time periods corresponding to the piece of second sample data;

[0118] For each second sample data, the similarity between the basic new sequence and the estimated new sequence of the second sample data is calculated. If the similarity is less than a threshold, it is determined that the preset condition is met, and the estimated value of the mobile influence coefficient corresponding to the second sample data is recorded.

[0119] In one example, calculating the weight corresponding to each mobility parameter in the second sample data and the intercept of the mobility coefficient includes:

[0120] According to the second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility coefficient are calculated by the MCMC algorithm.

[0121] In one example, the prediction module 204 is specifically configured to:

[0122] For each estimated value of the recorded movement influence coefficient, substitute the estimated value into the initial model to obtain a corresponding prediction model;

[0123] For each prediction model, the number of new cases in a specified time period is calculated according to the prediction model;

[0124] The predicted number of new cases for the specified time period is determined based on the number of new cases calculated by each prediction model.

[0125] In one example, for each prediction model, calculating the number of new cases in a specified time period according to the prediction model includes:

[0126] The daily number of new cases in a specified time period is determined based on the proportion of uninfected people in the set area, the number of new cases on the day before the incubation period, the estimated value of the mobility impact coefficient, and the environmental factor coefficient.

[0127] In one example, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the prediction method described in the present invention.

[0128] In one example, the present invention provides an electronic device, comprising:

[0129] processor;

[0130] a memory for storing instructions executable by the processor;

[0131] The processor is used to read the executable instructions from the memory and execute the instructions to implement the prediction method of the present invention.

[0132] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0133] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0134] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0135] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0136] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0137] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0138] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0139] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0140] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for predicting new cases of infectious diseases, characterized in that: The method includes: Construct an initial model of infectious diseases, wherein the initial model of infectious diseases is: Where X t represents: predicted new cases of infectious diseases; t represents: date and time; duration represents: incubation period of infectious diseases; α represents: mobility impact coefficient; cbe represents: environmental factor coefficient, which is adjusted according to the urgency of infectious disease prevention and control measures; NPOP represents: the total number of people in a certain area, regardless of birth and death, immigration and emigration of the population in the area, the total number of people remains unchanged; determine the target parameters in the initial model, the target parameters include the environmental factor coefficient used to characterize the urgency of infectious disease prevention and control measures and the mobility impact coefficient to be estimated, the mobility impact coefficient characterizes the mobility of the population; Collecting a plurality of first sample data in a historical time period, each of the first sample data includes the first number of newly added cases in the corresponding collection time period and mobility data in the corresponding collection time period, the mobility data including a plurality of mobility parameters and parameter values; Determining an estimated value of the movement influence coefficient according to the first sample data; Determining a prediction model according to the estimated value of the mobility impact coefficient, the environmental factor coefficient and the initial model, so as to predict the daily number of new cases of the infectious disease according to the prediction model; Wherein, determining the estimated value of the movement influence coefficient includes: Constructing multiple pieces of second sample data based on the first sample data, each piece of second sample data includes multiple pieces of first sample data with a continuous collection time period, and all first newly added case numbers of each piece of second sample data constitute a basic newly added sequence; Determine an estimated value of a movement influence coefficient corresponding to each piece of second sample data and determine an estimated value of the movement influence coefficient that meets a preset condition; The step of determining an estimated value of a movement influence coefficient corresponding to each piece of second sample data includes: For each piece of second sample data, calculating a weight corresponding to each mobility parameter in the piece of second sample data and an intercept of a mobility coefficient; Determine an estimated value of a mobility influence coefficient corresponding to each piece of second sample data according to a parameter value of each mobility parameter in the piece of second sample data, a weight corresponding to each mobility parameter, and an intercept of the mobility coefficient; The step of determining an estimated value of a movement influence coefficient that meets a preset condition includes: For each piece of second sample data, according to the estimated value of the mobile influence coefficient corresponding to the piece of second sample data, the estimated new sequence corresponding to the piece of second sample data is calculated by the initial model, and the estimated new sequence includes the number of second new cases in all collection time periods corresponding to the piece of second sample data; For each second sample data, the similarity between the basic new sequence and the estimated new sequence of the second sample data is calculated. If the similarity is less than a threshold, it is determined that the preset condition is met, and the estimated value of the mobile influence coefficient corresponding to the second sample data is recorded.

2. The method according to claim 1, characterized in that The calculating the weight corresponding to each mobility parameter in the second sample data and the intercept of the mobility coefficient includes: According to the second sample data, the weight corresponding to each mobility parameter and the intercept of the mobility coefficient are calculated by the MCMC algorithm.

3. The method according to claim 1, characterized in that Calculating the number of new cases of the infectious disease per day according to the prediction model includes: For each estimated value of the recorded movement influence coefficient, substitute the estimated value into the initial model to obtain a corresponding prediction model; For each prediction model, the number of new cases in a specified time period is calculated according to the prediction model; The predicted number of new cases for the specified time period is determined based on the number of new cases calculated by each prediction model.

4. The method according to claim 3, characterized in that For each prediction model, calculating the number of new cases in a specified time period according to the prediction model includes: The daily number of new cases in a specified time period is determined based on the proportion of uninfected people in the set area, the number of new cases on the day before the incubation period, the estimated value of the mobility impact coefficient, and the environmental factor coefficient.

5. A device for predicting new cases of infectious diseases, characterized in that: The device includes: A construction module is used to construct an initial model of an infectious disease, wherein the initial model of an infectious disease is: Where X t represents: predicted new cases of infectious diseases; t represents: date and time; duration represents: incubation period of infectious diseases; α represents: mobility impact coefficient; cbe represents: environmental factor coefficient, which is adjusted according to the urgency of infectious disease prevention and control measures; NPOP represents: the total number of people in a certain area, regardless of birth and death, immigration and emigration of the population in the area, the total number of people remains unchanged; determine the target parameters in the initial model, the target parameters include the environmental factor coefficient used to characterize the urgency of infectious disease prevention and control measures and the mobility impact coefficient to be estimated, the mobility impact coefficient characterizes the mobility of the population; A collection module, used to collect multiple first sample data in a historical time period, each of which includes the first number of new cases in the corresponding collection time period and mobility data in the corresponding collection time period, and the mobility data includes multiple mobility parameters and parameter values; A determination module, configured to determine an estimated value of the movement influence coefficient according to the first sample data; A prediction module, configured to determine a prediction model according to the estimated value of the mobility impact coefficient, the environmental factor coefficient and the initial model, so as to predict the daily number of new cases of the infectious disease according to the prediction model; The determination module is further used to construct multiple second sample data according to the first sample data, each second sample data includes multiple first sample data with a continuous collection time period, and all first new case numbers of each second sample data constitute a basic new case sequence; determine the estimated value of the mobile influence coefficient corresponding to each second sample data and determine the estimated value of the mobile influence coefficient that meets the preset conditions; The determination module is further configured to calculate, for each piece of second sample data, a weight corresponding to each mobility parameter in the piece of second sample data and an intercept of a mobility coefficient; and determine an estimated value of a mobility influence coefficient corresponding to each piece of second sample data according to a parameter value of each mobility parameter in the piece of second sample data, a weight corresponding to each mobility parameter, and an intercept of the mobility coefficient; The determination module is further used to calculate, for each second sample data, an estimated new sequence corresponding to the second sample data through the initial model according to the estimated value of the mobile influence coefficient corresponding to the second sample data, wherein the estimated new sequence includes the number of second new cases in all collection time periods corresponding to the second sample data; for each second sample data, calculate the degree of similarity between the basic new sequence and the estimated new sequence of the second sample data; if the degree of similarity is less than a threshold value, determine that the preset condition is met, and record the estimated value of the mobile influence coefficient corresponding to the second sample data.

6. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the prediction method according to any one of claims 1 to 4.

7. An electronic device comprising: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the prediction method described in any one of claims 1 to 4.

Images