Method, device, equipment and medium for predicting the number of epidemic patients based on period

Abstract

The present disclosure relates to a method and apparatus, an electronic device, and a storage medium for predicting the number of epidemic patients based on a cycle, which relate to the field of computer technologies and can be applied to the scenario of predicting the number of patients during the spread of an epidemic. The method includes: determining patient time-series information from initial patient data, and determining a current effective reproduction number corresponding to an existing statistical cycle according to the patient time-series information; determining a target polynomial according to the current effective reproduction number, fitting a change curve of an effective reproduction number sequence by using the target polynomial and the current effective reproduction number, so as to predict a future effective reproduction number of a to-be-measured cycle according to the change curve; determining the number of newly added patients on the first day of the to-be-measured cycle; constructing a number prediction function according to the future effective reproduction number and the number of newly added patients on the first day, and predicting the number of newly added patients per day in the to-be-measured cycle according to the number prediction function. The present disclosure can predict the number of newly added patients per day in a future cycle based on actual data.

Description

[0001] This application is a divisional application of the invention patent application with the application date of April 8, 2020, the application number of CN202010271242.X, and the title of "Method, Device, Equipment and Medium for Predicting the Number of Epidemic Patients Based on Cycles". Background Art

[0003] The classic epidemic transmission model (Susceptible Exposed Infectious Recovered, SEIR) divides the population within the epidemic range into four categories: susceptibles, exposed, infectious, and recovered, and thus establishes a model to analyze the changes in each category of population.

[0004] During a certain epidemic transmission period, in order to estimate the growth trend of new patients, researchers measure the basic reproduction number of the epidemic to determine the transmission ability of the epidemic, that is, the change trend of the number of patients. Nowadays, the calculation of the number of new patients mainly stems from the SEIR model, and the change trend of the number of people in each state is calculated based on the SEIR model. In addition, the maximum likelihood algorithm can also be used to calculate the basic reproduction value using the daily new patient sequence. After obtaining the basic reproduction value, the number of new patients that existing patients can infect within one disease cycle after one cycle can be calculated.

[0005] It should be noted that the information disclosed in the above background art section is only used to strengthen the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present disclosure is to provide a method for predicting the number of epidemic patients based on cycles, a device for predicting the number of epidemic patients based on cycles, an electronic device, and a computer-readable storage medium, so as to at least to some extent overcome the problem that the existing SEIR model cannot be optimized according to the actual change in the number of new patients and cannot obtain the change in the number of new patients every day within one calculation cycle.

[0007] Other features and advantages of the present disclosure will become apparent through the following detailed description, or be learned in part through the practice of the present invention.

[0008] According to a first aspect of the present disclosure, a method for predicting the number of epidemic patients based on a cycle is provided, including: determining patient time series information from initial patient data, and determining a current effective reproduction number corresponding to an existing statistical cycle according to the patient time series information; determining a target polynomial according to the current effective reproduction number, fitting a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of a period to be measured according to the change curve; determining the number of newly added patients on the first day of the period to be measured; constructing a number prediction function according to the future effective reproduction number and the number of newly added patients on the first day, and predicting the number of newly added patients per day in the period to be measured according to the number prediction function.

[0009] Optionally, determining the current effective reproduction number corresponding to the existing statistical cycle according to the patient time series information includes: determining the number of statistical days of the statistical cycle, dividing the initial patient data according to the number of statistical days and the patient time series information to generate corresponding initial patient sequences; obtaining a basic reproduction number, and determining the current effective reproduction number corresponding to the existing statistical cycle according to the basic reproduction number, the initial patient sequences, and through a maximum likelihood algorithm.

[0010] Optionally, constructing a number prediction function based on the future effective reproduction number and the number of newly added patients on the first day includes: determining the total increase in the number of patients in the period to be measured according to the future effective reproduction number and the number of newly added patients on the first day; determining the number of statistical days of the statistical cycle, and determining the base increase in the number of patients according to the number of statistical days and the total increase in the number of patients; determining a plurality of day numbers of the period to be measured, and determining an increment ratio corresponding to each day number according to the base increase and each day number; determining a scaling factor according to the initial patient data, and constructing a number prediction function according to the number of statistical days, the future effective reproduction number, the increment ratio, and the scaling factor.

[0011] Optionally, the number prediction function is: wherein, fir is the number of newly added patients on the first day of the period to be measured, Rt is the future effective reproduction number corresponding to the period to be measured, a is the number of statistical days of the statistical cycle, b is the scaling factor, and n is a plurality of day numbers of the statistical cycle and n = 1, 2,..., a.

[0012] Optionally, the above method further includes: determining the actual number of newly added patients and the actual daily increase in the number of patients in multiple periods before the period to be measured; determining the value range and step size of the scaling factor, and determining the target number of scaling factor values according to the value range and step size; respectively determining the predicted daily increase in the number of patients and the predicted number of newly added patients in multiple periods before the period to be measured according to the target number of scaling factor values and the number prediction function; determining the loss function of the number prediction function according to the actual number of newly added patients corresponding to multiple periods, the actual daily increase in the number of patients corresponding to multiple periods, the predicted number of newly added patients corresponding to multiple periods, and the predicted daily increase in the number of patients corresponding to multiple periods; calculating by substituting each scaling factor value into the loss function one by one to obtain the target number of loss function values; determining the target scaling factor value corresponding to the minimum loss function value from the target number of loss function values, and substituting the target scaling factor value into the number prediction function.

[0013] Optionally, determining the loss function of the number prediction function according to the actual number of newly added patients corresponding to multiple periods, the actual daily increase in the number of patients corresponding to multiple periods, the predicted number of newly added patients corresponding to multiple periods, and the predicted daily increase in the number of patients corresponding to multiple periods includes: determining the total mean square error between the actual number of newly added patients corresponding to multiple periods and the predicted number of newly added patients corresponding to multiple periods; determining the average mean square error between the actual daily increase in the number of patients corresponding to multiple periods and the predicted daily increase in the number of patients corresponding to multiple periods; determining the total number of statistical days, and determining the loss function according to the total mean square error, the average mean square error, and the total number of statistical days.

[0014] Optionally, the loss function loss is: where loss is the loss function, SUM 实际 is the actual number of newly added patients corresponding to multiple periods, SUM 预测 is the predicted number of newly added patients corresponding to multiple periods, DAY 实际 is the actual daily increase in the number of patients corresponding to multiple periods, DAY 预测 is the predicted daily increase in the number of patients corresponding to multiple periods, and T is the total number of statistical days.

[0015] According to a second aspect of the present disclosure, there is provided a device for predicting the number of epidemic patients based on a cycle, including: a first reproduction number determination module, configured to determine patient time series information from initial patient data, and determine the current effective reproduction number corresponding to the existing statistical cycle according to the patient time series information; a second reproduction number determination module, configured to determine a target polynomial according to the current effective reproduction number, fit a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured according to the change curve; a patient number determination module, configured to determine the number of newly added patients on the first day of the period to be measured; a number prediction module, configured to construct a number prediction function according to the future effective reproduction number and the number of newly added patients on the first day, and predict the number of newly added patients per day in the period to be measured according to the number prediction function.

[0016] Optionally, the first reproduction number determination module includes a first reproduction number determination unit, configured to determine the number of statistical days of the statistical cycle, divide the initial patient data according to the number of statistical days and the patient time series information, so as to generate a corresponding initial patient sequence; obtain the basic reproduction number, and determine the current effective reproduction number corresponding to the existing statistical cycle according to the basic reproduction number and the initial patient sequence through the maximum likelihood algorithm.

[0017] Optionally, the number prediction module includes a function construction unit, configured to determine the total patient increment of the period to be measured according to the future effective reproduction number and the number of newly added patients on the first day; determine the number of statistical days of the statistical cycle, and determine the base increment of the patients according to the number of statistical days and the total patient increment; determine a plurality of day numbers of the period to be measured, and determine the increment ratio corresponding to each day number according to the base increment and each day number; determine a scaling coefficient according to the initial patient data, and construct a number prediction function according to the number of statistical days, the future effective reproduction number, the increment ratio and the scaling coefficient.

[0018] Optionally, the device for predicting the number of epidemic patients based on a cycle further includes a scaling coefficient determination module, configured to determine the actual number of newly added patients and the actual daily increase in patients in a plurality of cycles before the period to be measured; determine the value range and step size of the scaling coefficient, and determine a target number of scaling coefficient values according to the value range and the step size; determine the predicted daily increase in patients and the predicted number of newly added patients in a plurality of cycles before the period to be measured according to the target data volume of scaling coefficient values and the number prediction function; determine the loss function of the number prediction function according to the actual number of newly added patients corresponding to the plurality of cycles, the actual daily increase in patients corresponding to the plurality of cycles, the predicted number of newly added patients corresponding to the plurality of cycles, and the predicted daily increase in patients corresponding to the plurality of cycles; calculate each scaling coefficient value one by one into the loss function to obtain a target number of loss function values; determine the target scaling coefficient value corresponding to the minimum loss function value from the target number of loss function values, and substitute the target scaling coefficient value into the number prediction function.

[0019] Optionally, the scaling factor determination module includes a loss function determination unit configured to determine the total mean square error between the actual number of newly added patients corresponding to multiple periods and the predicted number of newly added patients corresponding to multiple periods; determine the average mean square error between the actual number of daily added patients corresponding to multiple periods and the predicted number of daily added patients corresponding to multiple periods; determine the total number of statistical days, and determine the loss function based on the total mean square error, the average mean square error, and the total number of statistical days.

[0020] According to a third aspect of the present disclosure, there is provided an electronic device, including: a processor; and a memory having computer-readable instructions stored thereon, the computer-readable instructions, when executed by the processor, implementing the method for predicting the number of epidemic cases based on a period according to any one of the above.

[0021] According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the method for predicting the number of epidemic cases based on a period according to any one of the above.

[0022] The technical solution provided by the present disclosure may include the following beneficial effects:

[0023] The method for predicting the number of epidemic cases based on a period in the exemplary embodiments of the present disclosure determines patient time series information from initial patient data, and determines the current effective reproduction number corresponding to the existing statistical period according to the patient time series information; determines a target polynomial according to the current effective reproduction number, and fits a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured according to the change curve; determines the number of newly added patients on the first day of the period to be measured; constructs a number prediction function based on the future effective reproduction number and the number of newly added patients on the first day, and predicts the number of daily added patients in the period to be measured according to the number prediction function. On the one hand, by predicting the number of daily added patients in the period to be measured through the number prediction function, it is possible to predict the number of newly added patients every day in the future period based on actual patient data for the change of newly added patients every day, rather than being limited to the number prediction only in terms of periods, that is, the number change of each day is finely fitted. On the other hand, by fitting a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, the future effective reproduction number can be determined according to the change curve, so as to fit different trends of newly added number changes.

[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 THE DRAWINGS

[0025] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0026] Figure 1 Schematically shows a flowchart of a method for predicting the number of epidemic patients based on a cycle according to an exemplary embodiment of the present disclosure;

[0027] Figure 2 Schematically shows an overall flowchart of predicting the number of newly added patients per day according to an exemplary embodiment of the present disclosure;

[0028] Figure 3 Schematically shows a flowchart of determining the current effective reproduction number according to an exemplary embodiment of the present disclosure;

[0029] Figure 4 Schematically shows a flowchart of constructing a population prediction function according to an exemplary embodiment of the present disclosure;

[0030] Figure 5 Schematically shows a flowchart of determining the number of newly added patients per day according to an exemplary embodiment of the present disclosure;

[0031] Figure 6 Schematically shows a flowchart of determining an optimized population prediction function according to an exemplary embodiment of the present disclosure;

[0032] Figure 7 Schematically shows a flowchart of constructing a loss function of a population prediction function according to an exemplary embodiment of the present disclosure;

[0033] Figure 8 Schematically shows a block diagram of an apparatus for predicting the number of epidemic patients based on a cycle according to an exemplary embodiment of the present disclosure;

[0034] Figure 9 Schematically shows a block diagram of an electronic device according to an exemplary embodiment of the present disclosure;

[0035] Figure 10 Schematically shows a schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure. Detailed Embodiments

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various 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 concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar parts, and thus their repetitive description will be omitted.

[0037] In addition, the described features, structures, or characteristics may 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 the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known structures, methods, devices, implementations, materials, or operations are not shown or described in detail to avoid obscuring aspects of the present disclosure.

[0038] The block diagrams shown in the drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more software-hardened modules, or in different networks and / or processor devices and / or microcontroller devices.

[0039] Currently, regarding the estimation of the number of newly added cases during the epidemic spread, it mainly stems from the classical SEIR epidemic spread model. Based on the number of individuals in the infected state, incubation period, infectious period, and isolated state, combined with the duration of the incubation period and the infectious period, a functional relationship is constructed, and these parameters are used to calculate the trend of the number of people in each state. However, the SEIR model's prediction of newly added patients is based on a set of fixed calculation formulas. After providing the initial information, it will not be optimized with the change in the actual number of newly added patients. Therefore, if there are external factor interferences, the model prediction error will become larger and larger. In addition, after obtaining the basic reproduction number, only the total number of people after one cycle can be inferred, and the change in the number of newly added patients every day within one cycle cannot be obtained. For example, when the disease cycle is 10 days, the trend of the number of people within ten days cannot be learned.

[0040] Based on this, in the exemplary embodiment of the present disclosure, first, a method for predicting the number of epidemic patients based on a cycle is provided. The method for predicting the number of epidemic patients based on a cycle in the present disclosure can be implemented by using a server or a terminal device. Among them, the terminals described in the present disclosure may include mobile terminals such as mobile phones, tablet computers, laptop computers, handheld computers, and personal digital assistants (PDAs), as well as fixed terminals such as desktop computers. Figure 1 A schematic diagram schematically shows the flowchart of the method for predicting the number of epidemic patients based on a cycle according to some embodiments of the present disclosure. Refer to Figure 1 The method for predicting the number of epidemic patients based on a cycle may include the following steps:

[0041] Step S110: Determine patient time series information from the initial patient data, and determine the current effective reproduction number corresponding to the existing statistical cycle according to the patient time series information.

[0042] Step S120: Determine a target polynomial according to the current effective reproduction number, fit a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured according to the change curve.

[0043] Step S130: Determine the number of newly added patients on the first day of the period to be measured.

[0044] Step S140: Construct a number prediction function according to the future effective reproduction number and the number of newly added patients on the first day, and predict the number of newly added patients per day in the period to be measured according to the number prediction function.

[0045] According to the method for predicting the number of epidemic patients based on a cycle in the exemplary embodiment of the present disclosure, on the one hand, by predicting the number of newly added patients per day in the period to be measured through the number prediction function, it is possible to predict the number of newly added patients per day in the future period based on the actual patient data, aiming at the change of newly added patients every day, rather than being limited to the number prediction only in terms of the cycle, that is, the number change of each day is finely fitted. On the other hand, by fitting a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, the future effective reproduction number can be determined according to the change curve, so as to fit different trends of the change in the number of newly added patients.

[0046] Next, the method for predicting the number of epidemic patients based on a cycle in the exemplary embodiment of the present disclosure will be further described.

[0047] In step S110, determine patient time series information from the initial patient data, and determine the current effective reproduction number corresponding to the existing statistical cycle according to the patient time series information.

[0048] In some exemplary embodiments of the present disclosure, the initial patients may be all the diagnosed patients of a certain disease determined from existing patient data records. The initial patient data may be data information related to the initial patients, and the initial patient data may include the patient's personal information, the patient's diagnosis time, the patient's condition information, etc. The patient time series information may be the relevant time series information of the diagnosis times corresponding to different patients among the initial patients. For example, if the diagnosed patients within 15 days from the onset of the disease are obtained from the existing patient data, the corresponding time series information 1 may be added to the diagnosed patients on the 1st day, the corresponding time series information 2 may be added to the diagnosed patients on the 2nd day, and so on, and the corresponding time series information 15 may be added to the diagnosed patients on the 15th day. The existing statistical period may be the statistical period in which the initial patients determined according to the patient time series information are located. For example, if the initial patients are distributed in three statistical periods, the number of existing statistical periods is three. The Effective Reproduction Number (Rt) may be the average number of people that a patient who starts showing symptoms at time t can infect during the process of disease transmission and development. In most cases, this t represents a moment, usually in days. In the present disclosure, each statistical period corresponds to an effective reproduction number. The current effective reproduction number may be the effective reproduction number calculated based on the existing actual data.

[0049] Reference Figure 2 , Figure 2 schematically shows the overall flowchart for predicting the number of newly added patients per day. In step S210, the initial patient data is obtained through the network or a pre-established epidemic analysis database, and the patient time series information is determined from the initial patient data; in step S220, the corresponding current effective reproduction number is determined according to the patient time series information.

[0050] According to some exemplary embodiments of the present disclosure, determine the number of statistical days in a statistical period, divide the initial patient data according to the number of statistical days and the patient time series information to generate corresponding initial patient sequences; obtain the basic reproduction number, and determine the current effective reproduction number corresponding to the existing statistical period according to the basic reproduction number and the initial patient sequences through the maximum likelihood algorithm. The statistical period can be a statistical period determined according to the onset situation of a certain disease. For example, if the period from infection to symptom appearance of a certain disease is 10 days, then 10 days can be used as a statistical period. The number of statistical days can be the number of days included in a statistical period. For example, the number of statistical days can be 5 days, 10 days, 14 days, etc. The number of statistical days can be determined according to the onset characteristics of a certain disease, and the present disclosure does not make any special limitations thereto. The initial patient sequence can be a patient sequence obtained by dividing the initial patient data according to the statistical period. The basic reproduction number (Basic Reproduction Number, R0) can refer to the number of people that an average patient can infect during the disease period in an environment full of susceptible people without intervention. The maximum likelihood algorithm, also known as maximum likelihood estimation or maximum a posteriori estimation, is a method of parameter estimation that estimates the parameters of a probability model through sampling. The current effective reproduction number can be the effective reproduction number corresponding to each initial patient sequence determined according to the existing initial patient sequences. The current effective reproduction number can refer to the effective reproduction numbers corresponding to the existing statistical periods respectively, and each statistical period has an effective reproduction number corresponding thereto.

[0051] Reference Figure 3 , Figure 3A flowchart for determining the current effective reproduction number is schematically shown. In step S310, a statistical period corresponding to a certain disease is determined according to the infectious characteristics of the disease, that is, the number of days included in a statistical period. After obtaining the initial patient data, the initial patient data can be divided according to the patient time series information. For example, if the statistical number of days in a statistical period is 5 days, the initial patient data is divided according to a period of 5 days. Patients with patient time series information of 1, 2, 3, 4, and 5 are divided into a sequence, and so on. The initial patient data is divided, and the patient data that is less than one period at the end is also divided into an independent period sequence. For example, when dividing the patient data for 18 days obtained, 4 initial patient sequences are obtained, which are: {x1, x2, x3, x4, x5}, {x6, x7, x8, x9, x10}, {x11, x12, x13, x14, x15}, {x16, x17, x18}; where xn is the number of newly added patients corresponding to that day. In step S320, the basic reproduction number corresponding to the disease is obtained. The R0 package of the R language (The R Programming Language) can be used to generate the corresponding effective reproduction number, that is, the current effective reproduction number, according to the initial patient sequence by using the maximum likelihood algorithm.

[0052] For example, assume that the initial patient sequence conforms to a Poisson distribution, and assume that the initial patient sequence is: N1, N2... N x , N x can represent the number of patients corresponding to the x-th statistical period. Combining the distribution w of the patient generation time (incubation period + time from onset to diagnosis), the maximized log-likelihood function as shown in Formula 1 is obtained.

[0053]

[0054] Among them, By maximizing the likelihood function, the value of the effective reproduction number Rt corresponding to the time series data in this period can be obtained.

[0055] In step S120, a target polynomial is determined according to the current effective reproduction number, and a change curve of the effective reproduction number sequence is fitted through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured according to the change curve.

[0056] In some exemplary embodiments of the present disclosure, the target polynomial may be a polynomial used to fit the trend curve of the effective reproduction number. The effective reproduction number sequence may be an effective reproduction number sequence obtained by fitting the current effective reproduction number. The change curve may be a curve reflecting the change trend of the effective reproduction number. The period to be measured may be a future period for which the number of newly added patients needs to be determined. The future effective reproduction number may be the effective reproduction number corresponding to the future period predicted according to the change curve.

[0057] Reference Figure 2 , in step S230, the future effective reproduction number of the future period may be determined according to the calculated current effective reproduction number. Specifically, after determining the current effective reproduction number according to the initial patient sequence, the target polynomial for fitting the change curve of the effective reproduction number may be determined according to the current effective reproduction number. For example, in order to fit a more complex jitter curve, a third-order polynomial may be selected. The present disclosure may determine the order of the target polynomial according to the calculation scenario, and the present disclosure does not make any special limitations thereto. The current period number is selected as the input value of the target polynomial. For example, if the first period is 1-5 days and the second period is 6-10 days, the input values corresponding to the first period and the second period are 1 and 2 respectively. Taking the actual effective reproduction number Rt of each period as the output value, a third-order polynomial target polynomial is used for fitting to obtain the change curve of the effective reproduction number sequence. For example, the polynomial for fitting Rt is denoted as the expression of fn(n) as shown in Formula 2, where n is the number of the period.

[0058]

[0059] Substituting the actual period number n value and the corresponding Rt value into fn(n) for calculation, the values of the coefficient terms a, b, c and the constant term d can be solved to obtain the polynomial result of Rt fitting. This fitting process can be performed through the polyfit function, and the polyfit function may be a function in Matrix Laboratory (MATLAB) software for curve fitting; wherein, curve fitting may be to construct an analytical function (whose graph is a curve) to be as close as possible to the given values at the original discrete points given the dataset at the discrete points. The future effective reproduction number, that is, the effective reproduction number Rt corresponding to the future period, can be determined according to the fitted change curve.

[0060] In step S130, determine the number of newly added patients on the first day of the period to be measured.

[0061] In some exemplary embodiments of the present disclosure, the number of newly added patients on the first day may be the number of patients newly added on the first day within the period to be measured. The number of newly added patients on the first day of the period to be measured can be determined based on the existing patient data, so as to construct a population prediction function according to the number of newly added patients on the first day.

[0062] In step S140, a population prediction function is constructed based on the future effective reproduction number and the number of newly added patients on the first day, and the daily newly added patient number within the period to be measured is predicted according to the population prediction function.

[0063] In some exemplary embodiments of the present disclosure, the daily newly added patient number may be the number of newly added patients generated each day within a certain period to be measured predicted according to the population prediction function. The daily newly added patient number corresponding to each day within the period to be measured, that is, the daily newly added patient number, can be predicted according to the obtained population prediction function, so as to achieve a fine-grained prediction result on a daily basis. The population prediction function may be a calculation model for predicting the number of newly added patients of a certain disease within a future period.

[0064] Reference Figure 2 After determining the future effective reproduction number according to the change curve of the effective reproduction number in step S240, a population prediction function for predicting the number of newly added patients can be constructed according to the effective reproduction number, and the daily newly added patient number within a certain future period can be predicted according to the population prediction function, so as to estimate when the spread and development of the disease will reach the peak according to the change trend of the daily newly added patient number, and then a decision-making plan for eliminating the disease can be formulated in combination with the maximum carrying capacity of local hospitals.

[0065] According to some exemplary embodiments of the present disclosure, determine the total patient increment of the period to be measured based on the future effective reproduction number and the number of newly added patients on the first day; determine the number of statistical days of the statistical period, and determine the base increment of patients according to the number of statistical days and the total patient increment; determine multiple day numbers of the period to be measured, and determine the increment ratio corresponding to each day number according to the base increment and each day number; determine the scaling coefficient according to the initial patient data, and construct a number prediction function according to the number of statistical days, the future effective reproduction number, the increment ratio, and the scaling coefficient. The total number of newly added patients on the first day of the period to be measured may be the number of newly added patients on the first day within the statistical period. The total patient increment of the period to be measured may be the total number of newly added patients generated within the statistical period, that is, the sum of the newly added patients generated every day within the statistical period. The base increment may be the number of newly added patients determined according to the number of statistical days and the total patient increment. The day number may be the number corresponding to each day within the period to be measured. For example, if a statistical period is 5 days, the day numbers corresponding to each day within the statistical period are "1, 2, 3, 4, 5". The increment ratio may be the ratio of the number of newly added patients generated every day within the period to be measured to the total patient increment. The scaling coefficient may be a scaling / stretching coefficient introduced to control the overall error when predicting the number of newly added patients in the future period, and the scaling coefficient may be represented by b. Currently, it is determined from the existing initial patient data.

[0066] Using the existing SEIR model in the prior art, based on the definition of the basic reproduction number R0, only the change in the number of newly added patients after one statistical period can be estimated, but the number change of each day within the statistical period cannot be determined. To solve this problem, an initial number prediction function f(a, b, Rt, fir) based on an exponential function can be constructed. Refer to Figure 4 , Figure 4 Schematically shows the flowchart of constructing the number prediction function. The specific steps are as follows:

[0067] In step S410, determine the number of newly added patients on the first day within the period to be measured, that is, the number of newly added patients on the first day within the period to be measured, denoted as fir; obtain the future effective reproduction number. In this exemplary embodiment, the future effective reproduction number may be the effective reproduction number Rt corresponding to the period to be measured; determine the total patient increment according to the number of newly added patients fir on the first day and the future effective reproduction number Rt, as shown in formula 3.

[0068] Total increment = fir × Rt (formula 3)

[0069] In step S420, obtain the number of statistical days of the statistical period, denoted as a; determine the base increment according to the number of statistical days and the total patient increment. The base increment may be represented by base, then the base increment is as shown in formula 4.

[0070]

[0071] In step S430, according to the base increment, the increment ratio corresponding to the number of newly added patients per day within the period to be measured can be determined, that is, the increment ratio ratio corresponding to the day number n n As shown in Formula 5.

[0072]

[0073] In step S440, according to the obtained number of newly added patients on the first day fir, the future effective reproduction number Rt, and the increment ratio, the number of newly added patients on the initial day within the period to be measured can be obtained as: fir×Rt×ratio n , that is, an initial number prediction function is constructed.

[0074] According to some exemplary embodiments of the present disclosure, it is defined that the number prediction functions corresponding to different statistical periods are the same. In order to control the overall error, a scaling coefficient is introduced. According to the scaling coefficient and the number of newly added patients on the initial day, the number of newly added patients on the predicted day can be obtained as: Therefore, the expression of the number prediction function can be as shown in Formula 6.

[0075]

[0076] According to some exemplary embodiments of the present disclosure, the number of newly added patients on the initial day corresponding to each day number is predicted based on the total patient increment and each increment ratio; the value range and step size of the scaling coefficient are determined, and an initial scaling coefficient value is determined from the value range according to the step size; the initial scaling coefficient value is calculated one by one with each number of newly added patients on the initial day to determine the number of newly added patients on the day to be measured. The number of newly added patients on the initial day can be the number of newly added patients generated each day within the period to be measured determined according to the above-established number prediction function. The value range of the scaling coefficient can be the value range where the predefined scaling coefficient value is located. The step size can be the numerical value of a certain number added to the scaling coefficient during each operation. The scaling coefficient value can be the specific value corresponding to the scaling coefficient. The initial scaling coefficient value can be a scaling coefficient value determined from the value range of the initial coefficient according to the step size, and is used to calculate the number of newly added patients on the day to be measured within the period to be measured. The number of newly added patients on the day can be the number of newly added patients obtained by scaling and adjusting the number of newly added patients on the initial day according to the scaling coefficient.

[0077] Refer to Figure 5 , Figure 5 schematically shows a flowchart for determining the number of newly added patients on the predicted day. Two methods for determining the scaling coefficient value are provided in the present disclosure, Figure 5Steps S510 to S530 disclose the process of determining the scaling coefficient value according to the data characteristics of existing patient data. In step S510, the initial daily new patient numbers corresponding to each day number are predicted based on the total patient increment and each increment ratio. The initial daily new patient numbers can be determined according to the above-mentioned number prediction function. In step S520, after introducing the scaling coefficient, the value range of the scaling coefficient can be determined, and the step size corresponding to the scaling coefficient can be set. In step S530, a scaling coefficient value can be selected from the value range as the initial scaling coefficient value according to the given step size. After determining the initial scaling coefficient value, the initial scaling coefficient value can be calculated respectively with the initial daily new patient numbers to obtain the to-be-tested daily new patient numbers. For example, for the scaling coefficient b, the value range of b can be limited to [0.1, 20], and the step size of b is determined to be 0.1. Then, 200 b values can be generated. An initial scaling coefficient value (such as 10) can be selected from these 200 b values, and 10 is substituted into the number prediction function. The initial scaling coefficient value is calculated one by one with each initial daily new patient number, and the number of new patients added each day within the to-be-tested period can be obtained, that is, the predicted new daily patient numbers.

[0078] According to some exemplary embodiments of the present disclosure, in order to optimize the scaling coefficient according to the existing patient data, the embodiment of the present invention provides a second method for determining the scaling coefficient, including: determining the actual new patient numbers and the actual daily new patient numbers of multiple periods before the to-be-tested period; determining the value range and the step size of the scaling coefficient, and determining a target number of scaling coefficient values according to the value range and the step size; respectively determining the predicted daily new patient numbers and the predicted new patient numbers of multiple periods before the to-be-tested period according to the target number of scaling coefficient values and the number prediction function; determining the loss function of the number prediction function according to the actual new patient numbers corresponding to multiple periods, the actual daily new patient numbers corresponding to multiple periods, the predicted new patient numbers corresponding to multiple periods, and the predicted daily new patient numbers corresponding to multiple periods; substituting each scaling coefficient value into the loss function for calculation to obtain a target number of loss function values; determining the target scaling coefficient value corresponding to the minimum loss function value from the target number of loss function values, and substituting the target scaling coefficient value into the number prediction function.

[0079] The multiple periods before the to-be-tested period can be the periods corresponding to the actual new patient numbers that already exist before the to-be-tested period. The actual new patient numbers can be the number of new patients actually generated in each period before the to-be-tested period, which can be denoted as SUM 实际 . The actual daily new patient numbers can be the number of new patients actually generated each day in each period before the to-be-tested period, denoted as DAY 实际The predicted number of new patients can be the number of new patients in each period before the period to be measured predicted by the number prediction function. The predicted number of new patients can be the sum of the predicted daily new patient numbers in each period before the period to be measured. The predicted number of new patients can be denoted as SUM 预测 The predicted daily new patient number can be the number of new patients per day in each period before the period to be measured predicted by the number prediction function. The predicted daily new patient number can be denoted as DAY 预测 The target quantity can be the number of scaling coefficient values determined according to the value range and step size. The loss function can be a function reflecting the gap between the predicted number of new patients by the number prediction function and the actual number of new patients. The loss function value can be the function value corresponding to the loss function determined after substituting the scaling coefficient value into the loss function. The minimum loss function value can be the numerically smallest loss function value determined from multiple loss function values. The target scaling coefficient value can be the scaling coefficient value corresponding to the minimum loss function value. The target scaling coefficient value can be the scaling coefficient value corresponding to the minimum loss function value obtained when the number prediction function is optimized after the target polynomial is processed

[0080] Reference Figure 6 , the method for determining the scaling coefficient includes: in step S610, determine the actual number of new patients and the actual daily new patient number in multiple periods before the period to be measured. In step S620, determine the value range and step size of the scaling coefficient, and determine the target quantity of scaling coefficient values according to the value range and step size. In step S630, determine the predicted daily new patient number and the predicted number of new patients in multiple periods before the period to be measured according to the target quantity of scaling coefficient values and the number prediction function respectively; among them, sum the predicted daily new patient numbers to obtain the predicted number of new patients to be measured. In step S640, determine the loss function of the number prediction function according to the actual number of new patients corresponding to multiple periods, the actual daily new patient number corresponding to multiple periods, the predicted number of new patients corresponding to multiple periods, and the predicted daily new patient number corresponding to multiple periods. In step S650, substitute each scaling coefficient value into the loss function for calculation to obtain the target quantity of loss function values; for example, for the scaling coefficient b, the value range of b can be limited to [0.1, 20], and the step size of b is determined to be 0.1, then 200 b values can be generated, and these 200 b values are respectively substituted into the loss function for calculation, and 200 loss function values can be obtained. In step S660, determine the target scaling coefficient value corresponding to the minimum loss function value from the target quantity of loss function values, and substitute the target scaling coefficient value into the number prediction function. Select a minimum loss function value from the obtained 200 loss function values, obtain the target scaling coefficient value corresponding to the minimum loss function value, and substitute the target scaling coefficient value into the number prediction function to optimize the number prediction function

[0081] According to some exemplary embodiments of the present disclosure, determine the total mean square error of the actual number of newly added patients corresponding to multiple periods and the predicted number of newly added patients corresponding to multiple periods; determine the average mean square error of the actual number of newly added patients per day corresponding to multiple periods and the predicted number of newly added patients per day corresponding to multiple periods; determine the total number of statistical days, and determine the loss function according to the total mean square error, the average mean square error, and the total number of statistical days. The total mean square error may be an error determined based on the specific values of the actual number of newly added patients and the predicted number of newly added patients in multiple periods before the period to be measured. The average mean square error may be an error determined based on the specific values of the actual number of newly added patients per day and the predicted number of newly added patients per day in multiple periods before the period to be measured. The total number of statistical days may be denoted as T.

[0082] In steps S250 and S260, the average mean square error and the total mean square error can be calculated to determine the loss function based on the average mean square error and the total mean square error. Refer to Figure 7 , Figure 7 Schematically shows a flowchart for determining the loss function of the number prediction function. Obtain the actual number of newly added patients and the actual number of newly added patients per day in multiple periods before the period to be measured; in step S710, calculate the total mean square error between the actual number of newly added patients and the predicted number of newly added patients in multiple periods before the period to be measured; in step S720, calculate the average mean square error between the actual number of newly added patients per day and the predicted number of newly added patients per day in multiple periods before the period to be measured; in step S730, the corresponding loss function can be determined according to the total mean square error, the average mean square error, and the number of statistical days.

[0083] The loss function loss is shown in Formula 7.

[0084]

[0085] Wherein, ∑(DAY 实际 -DAY 预测 ) 2 is the sum of the average mean square errors of multiple periods before the period to be measured.

[0086] Since it is found in practice that for areas where the number of newly added patients fluctuates greatly, if the number prediction function only optimizes the prediction error of the daily newly added patient number, the cumulative prediction value will deviate greatly from the actual value after accumulating the prediction error of each day. This is because the exponential function curve is smoother relative to the fluctuating data. The more severe the data fluctuation, the larger the deviation after smoothing. Therefore, the optimization direction of the number prediction function in this disclosure is not limited to reducing the prediction error of each day; when dealing with large fluctuations, the cumulative value will also be considered as part of the constraint in the optimization objective, and the total increase in the number of patients within the period to be measured will be used as part of the constraint. This optimization method can make the optimization direction of the number prediction function more macroscopic and not limited to the deviation of each day.

[0087] In step S270, the target scaling coefficient value corresponding to the minimum loss function value of the loss function can be determined; in step S280, the number prediction function can be optimized according to the target scaling coefficient value, so that the number prediction function can be adjusted accordingly according to the actual number change. Specifically, the specific process of optimizing the number prediction function can be as follows: after obtaining the target number of scaling coefficient values, different b values can be substituted into the loss function, and the loss function values corresponding to each b value can be obtained. The b value corresponding to the minimum loss function value selected from the obtained multiple loss function values is used as the b value in the number prediction function f(a, b, Rt, fir), that is, the target scaling coefficient value. The number prediction function is optimized according to the target scaling coefficient value. Since the number prediction function in this disclosure is different from the fixed calculation form of the patient number change in the SEIR model, the fitting trend of the daily newly added patient number change in this disclosure is a dynamically changing scheme, which is more in line with the actual epidemic situation.

[0088] For example, the statistical period corresponding to a certain disease contains 5 statistical days. After determining the target scaling coefficient value (i.e., b value) and combining the Rt value in the future period generated by fn(n), the predicted newly added patient number for each specific day in the future period can be calculated using f(a, b, Rt, fir). Among them, if fir is the actual value, it can be directly substituted; if fir is a value in a certain future period, the fir value of the nearest existing period can be used and calculated backward one period by one period to obtain the fir value of each future period.

[0089] In summary, in the method for predicting the number of epidemic patients based on a period in the exemplary embodiments of the present disclosure, patient time series information is determined from initial patient data, and the current effective reproduction number corresponding to the existing statistical period is determined according to the patient time series information; a target polynomial is determined according to the current effective reproduction number, and a change curve of the effective reproduction number sequence is fitted by the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured according to the change curve; the number of newly added patients on the first day of the period to be measured is determined; a number prediction function is constructed according to the future effective reproduction number and the number of newly added patients on the first day, and the number of newly added patients per day in the period to be measured is predicted according to the number prediction function. On the one hand, the number prediction function constructed in the present disclosure can predict the number of newly added patients per day in the future period based on actual patient data for the change of newly added patients every day, rather than being limited to predicting the number of people only in units of periods, realizing fine-grained fitting of the number change of each day within the period. On the other hand, the change curve of the effective reproduction number sequence is fitted by the target polynomial and the current effective reproduction number, and the future effective reproduction number can be determined according to the change curve, so as to fit different trends of the change of the newly added number of people. On the other hand, when fitting the newly added number of people every day, considering the total increase in the number of patients within the period and constraining the total increase in the number of patients, it is possible to avoid the number prediction function falling into fitting the number of newly added patients per day when fitting data with large jitters, while ignoring the deviation caused by the total increase in the number of patients. On the other hand, the present disclosure can dynamically adjust the prediction result of the number prediction function according to the number of newly added patients per day, so as to reconstruct the number prediction function for number prediction according to the situation to be measured of the disease.

[0090] It should be noted that although the steps of the method in the present invention are described in the order to be measured in the drawings, this does not require or imply that these steps must be executed in this order to be measured, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0091] In addition, in the present exemplary embodiment, an apparatus for predicting the number of epidemic patients based on a period is also provided. Referring to Figure 8 , the apparatus 800 for predicting the number of epidemic patients based on a period may include: a first reproduction number determination module 810, a second reproduction number determination module 820, a patient number determination module 830, and a number prediction module 840.

[0092] Specifically, the first effective reproduction number determination module 810 can be used to determine patient time series information from the initial patient data, and determine the current effective reproduction number corresponding to the existing statistical period according to the patient time series information; the second effective reproduction number determination module 820 can be used to determine a target polynomial according to the current effective reproduction number, fit a change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured; the patient number determination module 830 can be used to determine the number of newly added patients on the first day of the period to be measured; the number prediction module 840 can be used to construct a number prediction function according to the future effective reproduction number and the number of newly added patients on the first day, and predict the number of newly added patients per day in the period to be measured according to the number prediction function.

[0093] In an exemplary embodiment of the present disclosure, the first effective reproduction number determination module includes a first effective reproduction number determination unit, configured to determine the number of statistical days of the statistical period, divide the initial patient data according to the number of statistical days and the patient time series information, so as to generate a corresponding initial patient sequence; obtain the basic effective reproduction number, and determine the current effective reproduction number corresponding to the existing statistical period according to the basic effective reproduction number and the initial patient sequence through the maximum likelihood algorithm.

[0094] In an exemplary embodiment of the present disclosure, the number prediction module includes a function construction unit, configured to determine the total patient increment of the period to be measured according to the future effective reproduction number and the number of newly added patients on the first day; determine the number of statistical days of the statistical period, and determine the base increment of the patients according to the number of statistical days and the total patient increment; determine the numbering of multiple days in the period to be measured, and determine the increment ratio corresponding to each numbering according to the base increment and each numbering; determine a scaling coefficient according to the initial patient data, and construct a number prediction function according to the number of statistical days, the future effective reproduction number, the increment ratio and the scaling coefficient.

[0095] In an exemplary embodiment of the present disclosure, the loss function determination module includes a scaling coefficient determination module, configured to determine the actual number of newly added patients and the actual daily increase in the number of patients in multiple periods before the period to be measured; determine the value range and step size of the scaling coefficient, and determine a target number of scaling coefficient values according to the value range and the step size; determine the predicted daily increase in the number of patients and the predicted number of newly added patients in multiple periods before the period to be measured according to the target number of scaling coefficient values and the number prediction function; determine the loss function of the number prediction function according to the actual number of newly added patients corresponding to multiple periods, the actual daily increase in the number of patients corresponding to multiple periods, the predicted number of newly added patients corresponding to multiple periods, and the predicted daily increase in the number of patients corresponding to multiple periods; calculate by substituting each scaling coefficient value into the loss function one by one to obtain a target number of loss function values; determine the target scaling coefficient value corresponding to the minimum loss function value from the target number of loss function values, and substitute the target scaling coefficient value into the number prediction function.

[0096] In an exemplary embodiment of the present disclosure, the scaling factor determination module includes a loss function determination unit for determining the total mean square error between the actual number of newly added patients corresponding to multiple periods and the predicted number of newly added patients corresponding to multiple periods; determining the average mean square error between the actual number of daily added patients corresponding to multiple periods and the predicted number of daily added patients corresponding to multiple periods; determining the total number of statistical days, and determining the loss function based on the total mean square error, the average mean square error, and the total number of statistical days.

[0097] The specific details of each of the above virtual device modules for predicting the number of epidemic cases based on periods have been described in detail in the corresponding method for predicting the number of epidemic cases based on periods, and thus will not be elaborated here.

[0098] It should be noted that although several modules or units of the device for predicting the number of epidemic cases based on periods are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the 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 and embodied by multiple modules or units.

[0099] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0100] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method, or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: 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 "circuit", "module", or "system" here.

[0101] Next, reference is made to Figure 9 to describe the electronic device 900 according to this embodiment of the present invention. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0102] As Figure 9 shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one of the above processing units 910, at least one of the above storage units 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

[0103] Among them, the storage unit stores program codes, which can be executed by the processing unit 910, so that the processing unit 910 executes the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0104] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 921 and / or a cache storage unit 922, and may further include a read-only storage unit (ROM) 923.

[0105] The storage unit 920 may include a program / utilities 924 having a set (at least one) of program modules 925. Such program modules 925 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0106] The bus 930 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0107] The electronic device 900 can also communicate with one or more external devices 970 (such as a keyboard, a pointing device, a Bluetooth device, etc.), can also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 950. And, the electronic device 900 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 960. As shown in the figure, the network adapter 960 communicates with other modules of the electronic device 900 through the bus 930. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0108] From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software or by a combination of software and 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 (such as a CD-ROM, a USB flash drive, a portable hard disk, etc.) or on a network, including several instructions for causing a computing device (such as a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0109] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having a program product thereon that can implement the above method of this specification. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0110] Referring Figure 10 As shown, a program product 1000 for implementing the above method according to an embodiment of the present invention is described. It can be a portable compact disc read-only memory (CD-ROM) and includes program code and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0111] The program product can adopt any combination of one or more readable media. A readable medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of a readable storage medium include: an electrical connection having 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0112] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0113] The program code contained on the readable medium may 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.

[0114] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0115] In addition, the above drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, and are not for limiting purposes. It is easily understood that the processes shown in the above drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0116] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include well-known knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0117] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes may be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for predicting the number of epidemic patients based on a cycle, characterized in that, include: Determine patient timing information from initial patient data, and determine a current valid regeneration number corresponding to an existing statistical period based on the patient timing information; Determine a target polynomial according to the current effective regeneration number, and fit a change curve of the effective regeneration number sequence through the target polynomial and the current effective regeneration number, so as to predict the future effective regeneration number of the period to be measured according to the change curve; Determine the number of new patients on the first day of the test period; Constructing a population prediction function according to the future effective reproduction number and the number of new patients on the first day, and predicting the number of new patients on the test day of the test period according to the population prediction function; The determining, according to the patient time series information, the current effective regeneration number corresponding to the existing statistical period includes: Determine the statistical days of the statistical period, and divide the initial patients according to the statistical days and the patient time series information to generate a corresponding initial patient sequence; Obtaining a basic reproduction number, and determining a current effective reproduction number corresponding to the existing statistical period by a maximum likelihood algorithm based on the basic reproduction number and the initial patient sequence; The calculation formula for the current effective reproduction number is as follows: ; where LL(R) is the calculation result of the current effective reproduction number; T is the existing statistical period; the initial patient sequence is: N1, N2, …, N x , N x is the number of patients corresponding to the x-th statistical period; , R is the basic reproduction number, and w is the distribution of the patient generation time; The constructing of a population prediction function according to the future effective reproduction number and the number of new patients on the first day includes: Determine the total increase in patients in the test period according to the future effective reproduction number and the number of new patients on the first day; Determine the statistical days of the statistical period, and determine the patient's basal increment according to the statistical days and the patient's total increment; Determine a plurality of day numbers of the period to be tested, and determine an increment ratio corresponding to each day number according to the base increment and each day number; Determine a scaling factor according to the initial patient data, and construct the number of people prediction function according to the statistical days, the future effective reproduction number, the incremental ratio and the scaling factor; The number of people prediction function is: ； Among them, fir is the number of new patients on the first day of the measured period, Rt is the future effective regeneration number corresponding to the measured period, a is the statistical day of the statistical period, b is the scaling factor, n is the number of multiple days of the statistical period and n=1,2,…,a.

2. The method for predicting the number of epidemic patients based on cycles according to claim 1, wherein The scaling factor determination method comprises: Determine the actual number of new patients in multiple cycles before the period to be tested and the actual number of daily new patients; Determine a value range and a step size of the scaling factor, and determine a target number of scaling factor values according to the value range and the step size; Determine the predicted daily number of new patients and the predicted number of new patients for multiple periods before the period to be tested respectively according to the target data volume scaling coefficient value and the number of people prediction function; Determine the loss function of the number of patients prediction function according to the actual number of new patients corresponding to the multiple periods, the actual number of daily patients corresponding to the multiple periods, the predicted number of new patients corresponding to the multiple periods, and the predicted number of daily new patients corresponding to the multiple periods; Substituting each of the scaling coefficient values into the loss function one by one for calculation, to obtain the target number of loss function values; A target scaling factor value corresponding to a minimum loss function value is determined from the target number of loss function values, and the target scaling factor value is brought into the number of people prediction function.

3. The method for predicting the number of epidemic patients based on cycles according to claim 2, wherein Determining the loss function of the number prediction function based on the actual newly added patient numbers corresponding to the multiple periods, the actual daily added patient numbers corresponding to the multiple periods, the predicted newly added patient numbers corresponding to the multiple periods, and the predicted daily added patient numbers corresponding to the multiple periods, includes: Determining the total mean square error between the actual newly added patient numbers corresponding to the multiple periods and the predicted newly added patient numbers corresponding to the multiple periods; Determining the average mean square error between the actual daily added patient numbers corresponding to the multiple periods and the predicted daily added patient numbers corresponding to the multiple periods; Determining the total number of statistical days, and determining the loss function based on the total mean square error, the average mean square error, and the total number of statistical days.

4. The method for predicting the number of epidemic patients based on period according to claim 3, wherein The loss function loss is: ； where loss is the loss function, SUM 实际 is the actual number of newly added patients corresponding to the multiple periods, SUM 预测 is the predicted number of newly added patients corresponding to the multiple periods, DAY 实际 is the actual number of daily increased patients corresponding to the multiple periods, DAY 预测 is the predicted number of daily increased patients corresponding to the multiple periods, and T is the total number of days for statistics.

5. A device for predicting the number of epidemic patients based on a cycle, characterized in that, Including: The first reproduction number determination module is used to determine the patient time series information from the initial patient data, and determine the current effective reproduction number corresponding to the existing statistical period according to the patient time series information; The second reproduction number determination module is used to determine the target polynomial according to the current effective reproduction number, fit the change curve of the effective reproduction number sequence through the target polynomial and the current effective reproduction number, so as to predict the future effective reproduction number of the period to be measured according to the change curve; The patient number determination module is used to determine the number of newly added patients on the first day of the period to be measured; The number prediction module is used to construct a number prediction function according to the future effective reproduction number and the number of newly added patients on the first day, and predict the number of newly added patients to be measured on the day to be measured according to the number prediction function; The first reproduction number determination module is further used to determine the number of statistical days of the statistical period, and divide the initial patients according to the number of statistical days and the patient time series information to generate corresponding initial patient sequences; Obtaining the basic reproduction number, and determining the current effective reproduction number corresponding to the existing statistical period according to the basic reproduction number and the initial patient sequence through the maximum likelihood algorithm; The calculation formula for the currently effective reproduction number is as follows: ; where LL(R) is the calculation result of the current effective reproduction number; T is the existing statistical period; the initial patient sequence is: N1, N2, …, N x , N x is the number of patients corresponding to the x-th statistical period; , R is the basic reproduction number, and w is the distribution of the patient generation time; The number prediction module is further used to determine the total patient increment of the period to be measured according to the future effective reproduction number and the number of newly added patients on the first day; Determining the number of statistical days of the statistical period, and determining the base increment of the patients according to the number of statistical days and the total patient increment; Determining the multiple day numbers of the period to be measured, and determining the increment ratio corresponding to each day number according to the base increment and each day number; Determining the scaling coefficient according to the initial patient data, and constructing the number prediction function according to the number of statistical days, the future effective reproduction number, the increment ratio, and the scaling coefficient; The number prediction function is: ； Wherein, fir is the number of newly added patients on the first day of the period to be measured, Rt is the future effective reproduction number corresponding to the period to be measured, a is the number of statistical days of the statistical period, b is the scaling coefficient, and n is the multiple day numbers of the statistical period and n = 1, 2,..., a.

6. An electronic device, characterized in that, Including: A processor; And A memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the method for predicting the number of epidemic patients based on a period according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, it implements the method for predicting the number of epidemic patients based on cycles according to any one of claims 1 to 4.

Images