Method, apparatus, device and readable medium for predicting the epidemic transmission cycle

Abstract

The present application discloses a method, apparatus, device and readable medium for predicting the propagation period of an epidemic. The method includes: obtaining epidemic time series data of a specified epidemic within a preset time period; performing waveform decomposition on the epidemic time series data to determine corresponding frequency data; determining a first candidate period set of the epidemic according to the frequency data; performing autocorrelation analysis on the epidemic time series data to determine autocorrelation coefficients corresponding to different phase differences; determining a second candidate period set according to multiple autocorrelation coefficients; analyzing the first candidate period set and the second candidate period set to determine the propagation period corresponding to the specified epidemic, so as to predict the epidemic based on the propagation period. By applying the method provided in the embodiments of the present application, the epidemic prevalence period can be accurately and objectively predicted.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a method, apparatus, device, and readable medium for predicting the transmission cycle of an epidemic disease. Background Art

[0002] Diseases that occur epidemically at regular time intervals are called periodicity. Some epidemics occur due to an increase in the susceptible population and often show periodic epidemics. Analyzing the transmission law of an epidemic or infectious disease also plays an important guiding role in the construction and parameter adjustment of the model in the modeling and prediction of an epidemic or infectious disease, and can promote the further analysis of epidemic data.

[0003] Currently, estimating the transmission cycle law of an epidemic mainly relies on historical experience or subjective judgment through drawing and viewing. However, the regularity of many epidemics or syndromes is not obvious enough. Subjective viewing has a high degree of human factors and requires strong professional knowledge, making it difficult to accurately determine the transmission cycle of an epidemic or infectious disease. Summary of the Invention

[0004] Embodiments of this application creatively provide a method, apparatus, device, and readable medium for predicting the transmission cycle of an epidemic disease to solve the above-mentioned existing problems.

[0005] According to the first aspect of the embodiments of this application, a method for predicting the transmission cycle of an epidemic disease is provided. The method includes: obtaining epidemic time series data of a specified epidemic disease within a preset time period; performing waveform decomposition on the epidemic time series data to determine corresponding frequency data; determining a first candidate cycle set of the epidemic disease according to the frequency data; performing autocorrelation analysis on the epidemic time series data to determine autocorrelation coefficients corresponding to different phase differences; determining a second candidate cycle set according to multiple autocorrelation coefficients; and analyzing the first candidate cycle set and the second candidate cycle set to determine the transmission cycle corresponding to the specified epidemic disease, so as to predict the epidemic disease based on the transmission cycle.

[0006] According to an embodiment of this application, the obtaining of the epidemic time series data of a specified epidemic disease within a preset time period includes: obtaining the original time series data corresponding to the specified epidemic disease; filling in missing values of the original time series data to obtain filled time series data; and performing smoothing processing on the filled time series data to obtain epidemic time series data.

[0007] According to an embodiment of this application, performing waveform decomposition on the epidemic time series data to determine corresponding frequency data includes: performing a time-domain to frequency-domain conversion on the epidemic time series data through Fourier transform to obtain a frequency-domain waveform; and determining frequency data corresponding to each wave peak according to the frequency-domain waveform.

[0008] According to an embodiment of the present application, determining a first candidate period set of the epidemic based on the frequency data includes: converting the frequency data according to the time interval corresponding to the epidemic time series data to obtain a first candidate period set.

[0009] According to an embodiment of the present application, the determining a second candidate period set according to a plurality of the autocorrelation coefficients includes: determining a corresponding autocorrelation waveform according to the autocorrelation coefficient and the preset phase difference interval; determining phase difference data corresponding to each wave peak according to the autocorrelation waveform; and determining the phase difference data as the second candidate period set.

[0010] According to an embodiment of the present application, analyzing the first candidate period set and the second candidate period set to determine the propagation period corresponding to the specified epidemic includes: if there are the same candidate periods in the first candidate period set and the second candidate period set, determining the same candidate periods as the propagation period corresponding to the specified epidemic.

[0011] According to an embodiment of the present application, the analyzing the first candidate period set and the second candidate period set to determine the propagation period corresponding to the specified epidemic includes: if there are no same candidate periods in the first candidate period set and the second candidate period set, determining the period interval between each first candidate period and each second candidate period; sorting the period intervals to determine the minimum period interval; and determining the propagation period corresponding to the specified epidemic according to the first candidate period and the second candidate period corresponding to the minimum period interval.

[0012] According to an embodiment of the present application, the determining the propagation period corresponding to the specified epidemic according to the first candidate period and the second candidate period corresponding to the minimum period interval includes: judging whether the minimum period interval meets a preset period threshold; and if the minimum period interval meets the preset period threshold, integrating the first candidate period and the second candidate period to determine the propagation period corresponding to the specified epidemic.

[0013] According to a second aspect of the embodiments of the present application, a device for predicting the transmission cycle of an epidemic is provided. The device includes: an acquisition module configured to acquire epidemic time series data of a specified epidemic within a preset time period; a decomposition module configured to perform waveform decomposition on the epidemic time series data to determine corresponding frequency data; a determination module configured to determine a first candidate cycle set of the epidemic according to the frequency data; an analysis module configured to perform autocorrelation analysis on the epidemic time series data to determine autocorrelation coefficients corresponding to different phase differences; the determination module is further configured to determine a second candidate cycle set according to multiple autocorrelation coefficients; the analysis module is further configured to analyze the first candidate cycle set and the second candidate cycle set to determine the transmission cycle corresponding to the specified epidemic, so as to predict the epidemic based on the transmission cycle.

[0014] According to an embodiment of the present application, the acquisition module includes: an obtaining sub-module configured to obtain the original time series data corresponding to the specified epidemic; a filling sub-module configured to fill missing values in the original time series data to obtain filled time series data; a smoothing sub-module configured to perform smoothing processing on the filled time series data to obtain epidemic time series data.

[0015] According to an embodiment of the present application, the decomposition module includes: a transformation sub-module configured to perform a time-domain to frequency-domain transformation on the epidemic time series data through Fourier transform to obtain a frequency-domain waveform; a determination sub-module configured to determine frequency data corresponding to each wave peak according to the frequency-domain waveform.

[0016] According to an embodiment of the present application, the determination module is further configured to convert the frequency data according to the time interval corresponding to the epidemic time series data to obtain a first candidate cycle set.

[0017] According to an embodiment of the present application, the determination module is further configured to determine a corresponding autocorrelation waveform according to the autocorrelation coefficient and the preset phase difference interval; determine phase difference data corresponding to each wave peak according to the autocorrelation waveform; and determine the phase difference data as a second candidate cycle set.

[0018] According to an embodiment of the present application, the analysis module is further configured to, if there are identical candidate cycles in the first candidate cycle set and the second candidate cycle set, determine the identical candidate cycle as the transmission cycle corresponding to the specified epidemic.

[0019] According to an embodiment of the present application, the analysis module is further configured to, if there is no same candidate period in the first candidate period set and the second candidate period set, determine the period interval between each first candidate period and each second candidate period; sort the period intervals to determine the minimum period interval; and determine the transmission period of the specified epidemic disease according to the first candidate period and the second candidate period corresponding to the minimum period interval.

[0020] According to an embodiment of the present application, the analysis module is further configured to determine whether the minimum period interval meets a preset period threshold; if the minimum period interval meets the preset period threshold, integrate the first candidate period and the second candidate period to determine the transmission period of the specified epidemic disease.

[0021] According to a third aspect of the present application, there is also provided an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the program, implements the method according to any one of the above-mentioned feasible embodiments.

[0022] According to a fourth aspect of the present application, there is also provided a storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the method according to any one of the above-mentioned feasible embodiments when executed by a computer processor.

[0023] The method, device, equipment, and readable medium for predicting the transmission period of an epidemic disease provided by the embodiments of the present application determine a first candidate period set by performing waveform decomposition on epidemic disease time series data, determine a second candidate period set by calculating the autocorrelation coefficient of the epidemic disease time series data, and then analyze the first candidate period set and the second candidate period set to determine the transmission period of the specified epidemic disease. Applying this method can objectively and accurately predict the transmission period of the specified epidemic disease based on the epidemic disease time series data, determine the transmission period of the epidemic disease, and further provide more accurate information for the construction and parameter adjustment of the epidemic disease model based on the transmission period of the epidemic disease, which is of great significance for the prevention and control of the epidemic disease.

[0024] It should be understood that the teachings of the present application do not need to achieve all the beneficial effects described above. Instead, specific technical solutions can achieve specific technical effects, and other embodiments of the present application can also achieve the beneficial effects not mentioned above. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present application will become readily understandable. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, where:

[0026] In the accompanying drawings, the same or corresponding reference numerals denote the same or corresponding parts.

[0027] Figure 1 Fig. shows a schematic implementation flowchart of a method for predicting the epidemic transmission cycle according to an embodiment of the present application;

[0028] Figure 2 Fig. shows a waveform diagram of the corresponding time domain of a method for predicting the epidemic transmission cycle according to an embodiment of the present application;

[0029] Figure 3 Fig. shows a spectrogram of a method for predicting the epidemic transmission cycle according to an embodiment of the present application;

[0030] Figure 4 Fig. shows a schematic diagram of the autocorrelation coefficient waveform of a method for predicting the epidemic transmission cycle according to an embodiment of the present application;

[0031] Figure 5 Fig. shows a schematic diagram of the implementation modules of a device for predicting the epidemic transmission cycle according to an embodiment of the present application;

[0032] Figure 6 Fig. shows a schematic implementation structure diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0033] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and then implement the present application, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to convey the scope of the present application fully to those skilled in the art.

[0034] The technical solutions of the present application will be further elaborated in detail below with reference to the accompanying drawings and specific embodiments.

[0035] Figure 1 Fig. shows a schematic implementation flowchart of a method for predicting the epidemic transmission cycle according to an embodiment of the present application.

[0036] See Figure 1, according to the first aspect of the embodiments of the present application, a method for predicting the transmission cycle of an epidemic is provided. The method includes: Operation 101, obtaining the epidemic time series data of a specified epidemic within a preset time period; Operation 102, performing waveform decomposition on the epidemic time series data to determine the corresponding frequency data; Operation 103, determining the first candidate cycle set of the epidemic according to the frequency data; Operation 104, performing autocorrelation analysis on the epidemic time series data to determine the autocorrelation coefficients corresponding to different phase differences; Operation 105, determining the second candidate cycle set according to multiple autocorrelation coefficients; Operation 106, analyzing the first candidate cycle set and the second candidate cycle set to determine the transmission cycle corresponding to the specified epidemic, so as to predict the epidemic based on the transmission cycle.

[0037] The method for predicting the transmission cycle of an epidemic provided by the embodiments of the present application determines the first candidate cycle set by performing waveform decomposition on the epidemic time series data, determines the second candidate cycle set by calculating the autocorrelation coefficients of the epidemic time series data, and then determines the transmission cycle corresponding to the specified epidemic by analyzing the first candidate cycle set and the second candidate cycle set. Applying this method can objectively and accurately predict the transmission cycle of a specified epidemic with an unknown transmission cycle or verify and supplement the transmission cycle of a specified epidemic with a known transmission cycle based on the epidemic time series data. Using the transmission cycle can analyze the transmission law of an epidemic or an infectious disease, know its transmission cycle law, and play an important guiding role in the construction and parameter adjustment of the epidemic model in the modeling prediction of an epidemic, which can promote the further analysis of epidemic data and is of great significance for the prevention and control of an epidemic.

[0038] In Operation 101 of this method, the specified epidemic is the epidemic for which cycle prediction is required, such as measles, epidemic cerebrospinal meningitis, "whooping cough", influenza A, influenza B, etc. The epidemic time series data can be the syndrome data corresponding to the specified epidemic or the confirmed data corresponding to the specified epidemic. It should be added that since the specified epidemic has a transmission area, the epidemic time series data specifically refers to the epidemic time series data of the area to be predicted. For example, if the specified epidemic is scarlet fever and the area to be predicted is the transmission cycle of scarlet fever in a certain city, then the epidemic time series data is the epidemic time series data related to scarlet fever in this city. According to needs, the area to be predicted includes but is not limited to: streets, cities, provinces, states, countries, etc. According to needs, the preset time period is the time range corresponding to the epidemic time series data, and the time unit corresponding to the epidemic time series data can be selected from any one of units such as days, weeks, months, years, etc. For example, the epidemic time series data within the preset time period can be the number of confirmed cases of the specified epidemic per day in the area to be predicted in the past several years. It can be understood that the more precise the time unit, the more precise the range of the predicted cycle can be.

[0039] In operations 102 and 103 of this method, in the epidemic time series data, there may be multiple overlapping epidemic cycles. Taking the epidemic time series data as an example of the number of daily confirmed cases of a specified epidemic in the area to be predicted in the past few years, this method can draw a waveform diagram of the corresponding time domain with time information as the abscissa and epidemic characteristic parameters as the ordinate. This waveform diagram is actually formed by the overlap of multiple different wave peaks and basic waveforms with different frequencies. Based on this, this method decomposes the waveform of the corresponding time domain waveform diagram to obtain multiple basic waveforms, and obtains the frequency spectrum diagram of the corresponding frequency domain, so as to determine the amplitude data and frequency data of each sine wave. By converting according to the frequency data and the total time length corresponding to the epidemic time series data, the first candidate period set can be determined. The first candidate period set contains at least one first candidate period, and one first candidate period corresponds to one frequency data. Among them, the epidemic characteristic parameters include but are not limited to the number of daily confirmed cases corresponding to the specified epidemic. As Figure 2 shown, Figure 2 is the waveform diagram of the corresponding time information and epidemic characteristic parameters. After Figure 2 performing waveform decomposition, Figure 3 the frequency spectrum diagram shown can be obtained.

[0040] In operation 104 of this method, the autocorrelation coefficient of the epidemic time series data is also calculated to measure the correlation degree of the epidemic time series data at different times. The preset phase difference interval contains multiple preset phase differences with different values. The preset phase difference is used to determine two sets of epidemic time series data for autocorrelation coefficient measurement. For example, if the preset phase difference is +1 unit, the autocorrelation coefficient between the epidemic time series data and the data after the time information of the epidemic time series data is +1 unit is compared. The preset autocorrelation difference interval of this method does not exceed the total time length of the epidemic time series data. Further, the preset autocorrelation difference interval of this method can be determined according to the first candidate period set. For example, the preset autocorrelation difference interval is determined according to the largest first candidate period and the smallest first candidate period in the first candidate period set. Further, the time unit of the phase difference can be the same or different from the time unit of the first candidate period.

[0041] The specific calculation formula of the autocorrelation coefficient is as follows:

[0042]

[0043] Among them, refers to the mean value corresponding to the epidemic time series data sequence, h is the phase difference, X i is the original sequence of the epidemic time series data; X i+h is the phase difference sequence corresponding to the epidemic time series data, and ρ is the autocorrelation coefficient.

[0044] AsFigure 4 As shown, a corresponding autocorrelation waveform diagram can be plotted with the autocorrelation coefficient as the vertical axis and the phase difference as the horizontal axis. It should be understood that the higher the autocorrelation coefficient in the figure, the higher the correlation.

[0045] In operation 105 of this method, the peak phase difference corresponding to the peak is determined according to the autocorrelation waveform diagram, and the second candidate period set is determined according to the peak phase difference. The second candidate period set includes at least one second candidate period, and one second candidate period corresponds to one peak phase difference.

[0046] In operation 106 of this method, by comparing the first candidate period set and the second candidate period set, the transmission period corresponding to the specified epidemic is determined according to whether the first candidate period set and the second candidate period set contain the same candidate period. It can be understood that if there is the same candidate period in the first candidate period set and the second candidate period set, that is, both cycle determination methods consider this candidate period as the transmission period. Therefore, this candidate period can be determined as the transmission period. It should be added that if the time unit of the first candidate period can be consistent with the time unit of the second candidate period, the first candidate period set and the second candidate period set can be directly compared; if the time unit of the first candidate period is inconsistent with the time unit of the second candidate period, the time units need to be unified first, and then the first candidate period set and the second candidate period set are compared.

[0047] According to an embodiment of the present application, in operation 101, epidemic time series data of a specified epidemic in a preset time period is obtained, including: First, the original time series data corresponding to the specified epidemic is obtained; then, the missing values in the original time series data are filled to obtain the filled time series data; and then, the filled time series data is smoothed to obtain the epidemic time series data.

[0048] In operation 101, the original time series data used to determine the epidemic time series data usually easily has problems such as missing values and high fluctuation frequencies. Based on this, this method needs to preprocess the original time series data to reduce the problem of false positive fluctuations in the data and improve the credibility of the data while retaining the time series information.

[0049] The original time series data of this method refers to the historical medical data of the area to be predicted for the specified epidemic, such as: the daily confirmed number of the specified epidemic in a certain city in the past ten years, the number of syndrome diagnoses of the specified epidemic in a certain hospital in the past twenty years, etc. The original time series data can be presented in the form of a data table, and the data table can include information such as date, confirmed number, and current newly confirmed cases.

[0050] Then, since the original time-series data for a specified epidemic has a certain fluctuating trend, to avoid losing time-series information, this method uses a forward and backward weighted filling method to supplement missing values. Taking the missing value as the number of daily confirmed cases as an example, the data of the N days before and after the missing number of daily confirmed cases is taken for weighted filling to determine the missing value. Taking the data of the 3 days before and after the missing number of daily confirmed cases for weighted filling as an example, the specific formula is as follows:

[0051] x i = 0.25 * x i-1 + 0.15 * x i-2 + 0.1 * x i-3 + 0.25 * x i+1 + 0.15 * x i+2 + 0.1 * x i+3

[0052] Among them, x i is the number of daily confirmed cases on the i-th day, that is, the number of daily confirmed cases on the missing day. 0.25, 0.15, and 0.1 are the weight values corresponding to the number of daily confirmed cases in the 3 days before and after respectively. It should be understood that the weight values can be allocated according to the specific value of N, and the weight values of this method are not limited to 0.25, 0.15, and 0.1. And the sum of all weight values is 1. The weight value for each day is determined according to the time distance between the number of days before and after and the i-th day, that is, the farther away from the i-th day, the smaller the corresponding weight value.

[0053] After filling all missing values using the above formula, the filled time-series data is obtained. Since the filling of missing values uses forward and backward weighted filling, time-series information will not be lost.

[0054] Then, the filled time-series data is smoothed to reduce the situation of false positive fluctuations and make subsequent data processing more accurate. Specifically, combining the weighted filling method and the moving average algorithm, this method uses the moving weighted average method to smooth the filled time-series data, specifically referring to weighted smoothing of the data of the N days before and after the data to be smoothed to determine the epidemic time-series data. Taking the filled number of daily confirmed cases as an example again, assuming N is 3 days, the specific formula is as follows:

[0055]

[0056] Among them, x′ iis the epidemic time-series data for the i-th day, i.e., the daily confirmed cases on the i-th day after smoothing. 0.25, 0.15, and 0.1 are the weights corresponding to the daily confirmed cases in the previous and next 3 days respectively. It should be understood that the weights can be allocated according to the specific value of N. The weights of this method are not limited to 0.25, 0.15, and 0.1, and according to the actual needs of this method, the weights used for smoothing can be the same as or different from the weights used for filling. The denominator 2 is the sum of all weights. It should be added that during the smoothing process, the sum of the weights corresponding to the daily confirmed cases in the previous and next 3 days may not be 1. The denominator 2 is the sum of all weights in the numerator. If the sum of all weights in the numerator is not 2, the denominator is not 2.

[0057] According to an embodiment of the present application, in operation 102, waveform decomposition is performed on the epidemic time-series data to determine the corresponding frequency data, including: First, the epidemic time-series data is transformed from the time domain to the frequency domain through Fourier transform to obtain a frequency-domain waveform; then, the frequency data corresponding to each wave peak is determined according to the frequency-domain waveform.

[0058] The waveform decomposition of this method can be implemented by Fourier transform. Fourier transform is a method of transforming time-domain data into frequency-domain data. Through Fourier transform, any time-domain waveform can be transformed into a spectrogram composed of sine waves with different amplitudes and different phases.

[0059] This method generates a corresponding time-domain waveform by converting the epidemic time-series data with time information as the horizontal axis and epidemic characteristic parameters as the vertical axis. Then, the time-domain waveform is transformed through Fourier transform to obtain a corresponding spectrogram, realizing the decomposition of the waveform diagram. The horizontal axis of the transformed spectrogram is the frequency, and the vertical axis is the amplitude. According to the waveform diagram, the wave peaks corresponding to the epidemic time-series data can be determined. It should be understood that there are usually multiple wave peaks. According to the wave peaks, the frequency data corresponding to each wave peak can be determined.

[0060] According to an embodiment of the present application, in operation 103, the first candidate period set of the epidemic is determined according to the frequency data, including: The frequency data is converted according to the time interval corresponding to the epidemic time-series data to obtain the first candidate period set.

[0061] In operation 103, by determining the time interval corresponding to the epidemic time-series data, the frequency data can be converted according to the time interval, that is, the time data corresponding to each frequency data can be determined, and the time data is determined as the first candidate period. For example, if the time interval is 10 years, that is, the total time length of the data corresponding to the epidemic time-series data is 10 years, and the frequency data is 2, the first candidate period is the total time length of the data divided by the frequency data, and the first candidate period is 5 years. Based on the characteristic that there are usually multiple wave peaks, there are also multiple first candidate periods. For example, Figure 3It is the spectrogram corresponding to the first candidate period set, and each peak of the spectrogram corresponds to a first candidate period.

[0062] In another specific implementation scenario, there can also be multiple first candidate period sets. When the epidemic time series data contains multiple regions, there is corresponding epidemic time series data for each region. The corresponding first candidate period sets can also be multiple. For example, there are three hospitals in a certain city. This method can respectively determine the epidemic time series data corresponding to each hospital and obtain three epidemic time series data. Perform waveform decomposition on the three epidemic time series data respectively to obtain the corresponding spectrograms. Then, determine one or more first candidate periods corresponding to each hospital according to the corresponding spectrograms. By operating in this way, the first candidate periods corresponding to each hospital can be obtained. This method can have higher accuracy of the first candidate period data, which is beneficial to the subsequent processing of the data. Specifically, after obtaining multiple first candidate period sets, this method can integrate the multiple first candidate period sets to determine the target first candidate period set for comparison with the second candidate period set. The integration method of the multiple first candidate period sets can be any one of intersection integration, union integration, or average integration or other integration methods according to needs.

[0063] According to an embodiment of the present application, in operation 104, determining the second candidate period set according to multiple autocorrelation coefficients includes: First, determining the corresponding autocorrelation waveform according to the autocorrelation coefficient and the preset phase difference interval; then, determining the phase difference data corresponding to each peak according to the autocorrelation waveform; and then, determining the phase difference data as the second candidate period set.

[0064] This method determines each peak in the autocorrelation waveform according to the autocorrelation waveform diagram, and then determines the phase difference data corresponding to the peak according to the peak corresponding to the horizontal axis, and determines the phase difference data as the second candidate period. Among them, if there are multiple peaks, there are also multiple second candidate periods included in the second candidate period set of this method. It should be added that this method can also set a peak threshold interval. If the autocorrelation coefficient corresponding to the peak is lower than the peak threshold interval, the phase difference data corresponding to the peak is not determined as the second candidate period. If the autocorrelation coefficient corresponding to the peak satisfies the peak threshold interval, the phase difference data corresponding to the peak is determined as the second candidate period.

[0065] Correspondingly, there can also be multiple second candidate period sets. When the epidemic time series data contains multiple regions, there is corresponding epidemic time series data for each region. Correspondingly, there are also multiple second candidate period sets. For example, if there are three hospitals in a certain city, this method can respectively determine the epidemic time series data corresponding to each hospital and obtain three epidemic time series data. Analyze the autocorrelation coefficients of the three epidemic time series data respectively to obtain the second candidate period sets corresponding to each hospital. This method can achieve higher accuracy of the data of the second candidate period sets, which is beneficial to the subsequent processing of the data. After obtaining multiple second candidate period sets, this method can integrate the multiple second candidate period sets to determine the target second candidate period set for comparison with the first candidate period set. The integration method of the multiple second candidate period sets can be any one of intersection integration, union integration or average integration or other integration methods according to needs.

[0066] According to an embodiment of the present application, in operation 106, analyze the first candidate period set and the second candidate period set to determine the transmission period corresponding to the specified epidemic, including: if there are the same candidate periods in the first candidate period set and the second candidate period set, determine the same candidate periods as the transmission period corresponding to the specified epidemic.

[0067] In an analysis scenario, determine the intersection of the first candidate period set and the second candidate period set, and the candidate periods included in this intersection are the transmission periods. For example: the first candidate period set is {2, 5, 8, 10}, the second candidate period set is {5, 9, 20}, the intersection is {5}, and the transmission period is 5. If there are multiple elements in the intersection, it can be considered that the specified epidemic has multiple transmission periods. Further, this method can determine the importance degree of each transmission period according to the amplitude data and autocorrelation parameters corresponding to the transmission period. That is, determine the credibility degree of the transmission period according to the autocorrelation coefficient corresponding to the transmission period, and determine the severity degree of the transmission period through the amplitude data corresponding to the transmission period. The importance degree, credibility degree and severity degree can also be compared with the autocorrelation coefficient and amplitude data by setting corresponding thresholds to realize the quantification of degree judgment.

[0068] According to an embodiment of the present application, in operation 106, analyze the first candidate period set and the second candidate period set to determine the transmission period corresponding to the specified epidemic, including: First, if there are no same candidate periods in the first candidate period set and the second candidate period set, determine the period interval between each first candidate period and each second candidate period; then, sort the period intervals to determine the minimum period interval; then, determine the transmission period corresponding to the specified epidemic according to the first candidate period and the second candidate period corresponding to the minimum period interval.

[0069] In another analysis scenario, the intersection of the first candidate period set and the second candidate period set is determined. If the intersection is an empty set, further analysis of the first candidate period set and the second candidate period set is required. Specifically, the method can compare each first candidate period in the first candidate period set with each candidate period in the second candidate period set to determine the period interval. For example, if the first candidate period set is {2, 7} and the second candidate period set is {1, 4}, the corresponding period intervals are: 2 - 1 = 1, 4 - 2 = 2, 7 - 1 = 6, 7 - 4 = 3. Among them, the minimum period interval is 2 - 1 = 1, and the corresponding first candidate period and second candidate period are 2 and 1 respectively. If the first candidate period and the second candidate period are integrated by taking the mean, the propagation period can be determined as (2 + 1) / 2 = 1.5. Further, the method can also compare the corresponding autocorrelation coefficient and amplitude data. For example, if the autocorrelation coefficient and amplitude data of the first candidate period are both smaller than those of the second candidate period, the candidate period is determined to be 1. The corresponding weights can also be determined according to the autocorrelation coefficient and amplitude data, and then the first candidate period and the second candidate period are weighted by the weights to determine the propagation period.

[0070] According to an embodiment of the present application, in operation 105, determining the propagation period of a specified epidemic disease according to the first candidate period and the second candidate period corresponding to the minimum period interval includes: determining whether the minimum period interval meets a preset period threshold; if the minimum period interval meets the preset period threshold, integrating the first candidate period and the second candidate period to determine the propagation period of the specified epidemic disease.

[0071] If the minimum period interval is too large, the correlation between the first candidate period and the second candidate period is smaller. Based on this, the method also sets a preset period threshold. If the minimum period interval does not exceed the preset period threshold, the first candidate period and the second candidate period can be integrated according to the above integration method or other methods to determine the propagation period of the specified epidemic disease. By determining the propagation period of the specified epidemic disease, it is helpful for epidemic prediction modeling and provides a reference for public health work.

[0072] It should be added that if the minimum period interval does not meet the preset period threshold, it is determined that the propagation period of the specified epidemic disease cannot be determined. Specifically, if the minimum period interval exceeds the preset period threshold, it is considered that the current epidemic time series data provided is insufficient to determine the propagation period.

[0073] Figure 5 The schematic diagram of the implementation module of a device for predicting the propagation period of an epidemic disease according to an embodiment of the present application is shown.

[0074] See Figure 5, according to the second aspect of the embodiments of the present application, a device for predicting the epidemic transmission cycle is provided. The device includes: an acquisition module 501, configured to acquire the epidemic time-series data of a specified epidemic within a preset time period; a decomposition module 502, configured to perform waveform decomposition on the epidemic time-series data to determine the corresponding frequency data; a determination module 503, configured to determine the first candidate cycle set of the epidemic according to the frequency data; an analysis module 504, configured to perform autocorrelation analysis on the epidemic time-series data to determine the autocorrelation coefficients corresponding to different phase differences; the determination module 503 is further configured to determine the second candidate cycle set according to multiple autocorrelation coefficients; the analysis module 504 is further configured to analyze the first candidate cycle set and the second candidate cycle set to determine the transmission cycle corresponding to the specified epidemic, so as to predict the epidemic based on the transmission cycle.

[0075] According to an embodiment of the present application, the acquisition module 501 includes: an obtaining sub-module 5011, configured to obtain the original time-series data corresponding to the specified epidemic; a filling sub-module 5012, configured to fill the missing values in the original time-series data to obtain the filled time-series data; a smoothing sub-module 5013, configured to perform smoothing processing on the filled time-series data to obtain the epidemic time-series data.

[0076] According to an embodiment of the present application, the decomposition module 502 includes: a transformation sub-module 5021, configured to perform the transformation from the time domain to the frequency domain on the epidemic time-series data through Fourier transform to obtain the frequency-domain waveform; a determination sub-module 5022, configured to determine the frequency data corresponding to each wave peak according to the frequency-domain waveform.

[0077] According to an embodiment of the present application, the determination module 503 is further configured to convert the frequency data according to the time interval corresponding to the epidemic time-series data to obtain the first candidate cycle set.

[0078] According to an embodiment of the present application, the determination module 503 is further configured to determine the corresponding autocorrelation waveform according to the autocorrelation coefficient and the preset phase difference interval; determine the phase difference data corresponding to each wave peak according to the autocorrelation waveform; and determine the phase difference data as the second candidate cycle set.

[0079] According to an embodiment of the present application, the analysis module 504 is further configured to, if there are the same candidate cycles in the first candidate cycle set and the second candidate cycle set, determine the same candidate cycles as the transmission cycle corresponding to the specified epidemic.

[0080] According to an embodiment of the present application, the analysis module 504 is further configured to, if there is no same candidate period between the first candidate period set and the second candidate period set, determine the period interval between each first candidate period and each second candidate period; sort the period intervals to determine the minimum period interval; and determine the transmission period of the specified epidemic disease according to the first candidate period and the second candidate period corresponding to the minimum period interval.

[0081] According to an embodiment of the present application, the analysis module 504 is further configured to determine whether the minimum period interval meets a preset period threshold; if the minimum period interval meets the preset period threshold, integrate the first candidate period and the second candidate period to determine the transmission period of the specified epidemic disease.

[0082] It should be noted here that the description of the embodiment of the apparatus for predicting the transmission period of an epidemic disease above is similar to the description of the method embodiment shown above, and has the same beneficial effects as the method embodiment shown above. Therefore, it will not be elaborated. For the technical details not disclosed in the embodiment of the apparatus for predicting the transmission period of an epidemic disease of the present application, please refer to the description of the method embodiment shown above in the present application. For the sake of saving space, it will not be elaborated here. Figures 1 to 4 shown above Figures 1 to 4 shown above Figures 1 to 4 shown above

[0083] According to a third aspect of the present application, there is also provided an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method according to any one of the above-mentioned embodiments when executing the program.

[0084] According to a fourth aspect of the present application, there is also provided a storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the method according to any one of the above-mentioned embodiments when executed by a computer processor.

[0085] Figure 6 The figure shows a schematic implementation structure diagram of an electronic device according to an embodiment of the present application.

[0086] See Figure 6 , according to the embodiments of the present application, the present application also provides an electronic device and a readable storage medium.

[0087] The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present application described herein and / or claimed.

[0088] Device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0089] A plurality of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0090] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 executes the various methods and processes described above, such as a method for predicting the epidemic propagation cycle. For example, in some embodiments, a method for predicting the epidemic propagation cycle can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for predicting the epidemic propagation cycle described above can be executed. Alternatively, in other embodiments, the computing unit 601 can be configured to execute a method for predicting the epidemic propagation cycle in any other suitable manner (e.g., by means of firmware).

[0091] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0093] In the context of this application, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0094] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0095] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of a communication network include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0096] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0097] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and no limitations are imposed herein.

[0098] In addition, the terms "first" and "second" are used only for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "a plurality of" means two or more, unless otherwise specifically defined.

[0099] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting the propagation cycle of an epidemic disease, characterized in that, the method includes: obtaining epidemic time series data of a specified epidemic disease within a preset time period; the epidemic time series data is the epidemic time series data of the area to be predicted; performing waveform decomposition on the epidemic time series data to determine corresponding frequency data; determining a first candidate cycle set of the epidemic disease according to the frequency data; performing autocorrelation analysis on the epidemic time series data to determine autocorrelation coefficients corresponding to different phase differences; the autocorrelation coefficient is used to measure the correlation degree of the epidemic time series data at different times; determining a second candidate cycle set according to multiple said autocorrelation coefficients; analyzing the first candidate cycle set and the second candidate cycle set to determine the propagation cycle corresponding to the specified epidemic disease, so as to predict the epidemic disease based on the propagation cycle; wherein, analyzing the first candidate cycle set and the second candidate cycle set to determine the propagation cycle corresponding to the specified epidemic disease includes: if there are the same candidate cycles in the first candidate cycle set and the second candidate cycle set, determining the same candidate cycles as the propagation cycle corresponding to the specified epidemic disease; if there are no same candidate cycles in the first candidate cycle set and the second candidate cycle set, determining the cycle intervals between each first candidate cycle and each second candidate cycle; sorting the cycle intervals to determine the minimum cycle interval; determining the propagation cycle corresponding to the specified epidemic disease according to the first candidate cycle and the second candidate cycle corresponding to the minimum cycle interval; wherein, determining the propagation cycle corresponding to the specified epidemic disease according to the first candidate cycle and the second candidate cycle corresponding to the minimum cycle interval includes: determining the propagation cycle corresponding to the specified epidemic disease by any one of the methods of taking the mean, comparing the autocorrelation coefficient and the amplitude data, and weighting the first candidate cycle and the second candidate cycle by combining the weights of the autocorrelation coefficient and the amplitude data according to the first candidate cycle and the second candidate cycle corresponding to the minimum cycle interval.

2. The method according to claim 1, characterized in that, the obtaining of the epidemic time series data of a specified epidemic disease within a preset time period includes: obtaining the original time series data corresponding to the specified epidemic disease; performing missing value filling on the original time series data to obtain the filled time series data; performing smoothing processing on the filled time series data to obtain the epidemic time series data.

3. The method according to claim 1, characterized in that, performing waveform decomposition on the epidemic time series data to determine corresponding frequency data includes: performing transformation from the time domain to the frequency domain on the epidemic time series data through Fourier transform to obtain a frequency domain waveform; determining the frequency data corresponding to each wave peak according to the frequency domain waveform.

4. The method according to claim 1, characterized in that, determining a first candidate cycle set of the epidemic disease according to the frequency data includes: converting the frequency data according to the time interval corresponding to the epidemic time series data to obtain a first candidate cycle set.

5. The method according to claim 1, characterized in that, Determining the second candidate period set according to the multiple autocorrelation coefficients includes: Determining a corresponding autocorrelation waveform according to the autocorrelation coefficient and the preset phase difference interval; Determining phase difference data corresponding to each wave peak according to the autocorrelation waveform; Determining the phase difference data as the second candidate period set.

6. The method according to claim 1, wherein, Determining the propagation period of the specified epidemic according to the first candidate period and the second candidate period corresponding to the minimum period interval includes: Judging whether the minimum period interval meets a preset period threshold; If the minimum period interval meets the preset period threshold, integrating the first candidate period and the second candidate period to determine the propagation period of the specified epidemic.

7. An apparatus for predicting the propagation period of an epidemic, wherein, The apparatus includes: An acquisition module, configured to acquire epidemic time series data of a specified epidemic within a preset time period; the epidemic time series data is epidemic time series data of a region to be predicted; A decomposition module, configured to perform waveform decomposition on the epidemic time series data to determine corresponding frequency data; A determination module, configured to determine a first candidate period set of the epidemic according to the frequency data; An analysis module, configured to perform autocorrelation analysis on the epidemic time series data to determine autocorrelation coefficients corresponding to different phase differences; the autocorrelation coefficient is used to measure the correlation degree of the epidemic time series data at different times; The determination module is further configured to determine a second candidate period set according to the multiple autocorrelation coefficients; The analysis module is further configured to analyze the first candidate period set and the second candidate period set to determine the propagation period of the specified epidemic, so as to predict the epidemic based on the propagation period; wherein, analyzing the first candidate period set and the second candidate period set to determine the propagation period of the specified epidemic includes: If there are identical candidate periods in the first candidate period set and the second candidate period set, determining the identical candidate periods as the propagation period of the specified epidemic; If there are no identical candidate periods in the first candidate period set and the second candidate period set, determining the period interval between each first candidate period and each second candidate period; sorting the period intervals to determine the minimum period interval; determining the propagation period of the specified epidemic according to the first candidate period and the second candidate period corresponding to the minimum period interval; wherein, determining the propagation period of the specified epidemic according to the first candidate period and the second candidate period corresponding to the minimum period interval includes: Determining the propagation period of the specified epidemic according to any one of the methods of taking the average value, comparing the autocorrelation coefficient and the amplitude data, and weighting the first candidate period and the second candidate period by combining the weights of the autocorrelation coefficient and the amplitude data according to the first candidate period and the second candidate period corresponding to the minimum period interval.

8. An electronic device, including: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of claims 1-6 is implemented.

9. A storage medium containing computer-executable instructions that, when executed by a computer processor, are used to execute the method described in any one of claims 1-6.

Images