Data-knowledge-driven fine-scale infectious disease prediction model training and infectious disease prediction method, device, medium and program

Abstract

The embodiment of the invention discloses a data-knowledge-driven fine-scale infectious disease prediction model training and infectious disease prediction method, device, medium and program, and the method comprises the steps: obtaining the case monitoring data of a target infectious disease in a target infectious disease related region; according to the case monitoring data of the target infectious disease in the target infectious disease associated area, determining time and space distribution characteristics of the target infectious disease in the target infectious disease associated area; training a target infectious disease prediction model according to the time and space distribution characteristics of the target infectious disease in the target infectious disease associated area; wherein the target infectious disease prediction model is used for predicting a target infectious disease in a to-be-predicted area according to case monitoring data of the target infectious disease in the to-be-predicted area. According to the technical scheme, the space-time prediction precision of the infectious disease risk area can be improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of risk prediction, in particular to a data-knowledge driven fine-scale infectious disease prediction model training and infectious disease prediction method, device, medium and program. BACKGROUND

[0002] In the infectious disease prevention and control system, the monitoring and early warning of infectious diseases is in a core position, and the prediction of the epidemic trend of infectious diseases is the key in this core work. Infectious disease transmission is sporadic, with fast virus variation, rapid transmission and strong infectivity. Once a case appears, the place becomes a potential risk point immediately, and the frequent flow of the crowd further expands the risk range, resulting in a sharp increase in the number of risk points. However, the current infectious disease prediction method is mostly driven by traditional data, lacking the guidance of prior knowledge of the spatio-temporal distribution characteristics of the case monitoring data within the region, and it is difficult to provide high-precision spatio-temporal prediction information required for precise prevention and control of infectious diseases in each region. SUMMARY

[0003] Embodiments of the present application provide a data-knowledge driven fine-scale infectious disease prediction model training and infectious disease prediction method, device, medium and program, which can improve the spatio-temporal prediction accuracy of the infectious disease risk area.

[0004] According to an aspect of the present application, a data-knowledge driven fine-scale infectious disease prediction model training method is provided, comprising:

[0005] acquiring case monitoring data of a target infectious disease in a target infectious disease associated region;

[0006] determining the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region;

[0007] training a target infectious disease prediction model according to the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region;

[0008] The target infectious disease prediction model is used to predict the target infectious disease in a to-be-predicted region according to the case monitoring data of the target infectious disease in the to-be-predicted region.

[0009] According to another aspect of the present application, an infectious disease prediction method is provided, comprising:

[0010] acquiring case monitoring data of a target infectious disease in a to-be-predicted region;

[0011] inputting case monitoring data of the target infectious disease in the to-be-predicted region into a target infectious disease prediction model, and predicting the target infectious disease in the to-be-predicted region by using the target infectious disease prediction model.

[0012] The target infectious disease prediction model is obtained by using the data-knowledge driven fine-scale infectious disease prediction model training method in any of the embodiments of the present application.

[0013] According to another aspect of the present application, there is provided a data-knowledge driven fine-scale infectious disease prediction model training device, comprising:

[0014] a first case monitoring data acquisition module configured to acquire case monitoring data of a target infectious disease in a target infectious disease associated region;

[0015] a time-space distribution feature determination module configured to determine a time-space distribution feature of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region;

[0016] a target infectious disease prediction model training module configured to train a target infectious disease prediction model according to the time-space distribution feature of the target infectious disease in the target infectious disease associated region;

[0017] The target infectious disease prediction model is configured to predict the target infectious disease in a to-be-predicted region according to case monitoring data of the target infectious disease in the to-be-predicted region.

[0018] According to another aspect of the present application, there is provided an infectious disease prediction device, comprising:

[0019] a second case monitoring data acquisition module configured to acquire case monitoring data of a target infectious disease in a to-be-predicted region;

[0020] a target infectious disease prediction module configured to input the case monitoring data of the target infectious disease in the to-be-predicted region into a target infectious disease prediction model, and predict the target infectious disease in the to-be-predicted region by using the target infectious disease prediction model;

[0021] The target infectious disease prediction model is obtained by using the data-knowledge driven fine-scale infectious disease prediction model training method in any of the embodiments of the present application.

[0022] According to another aspect of the present application, there is provided an electronic device, comprising:

[0023] at least one processor; and

[0024] a memory in communication connection with the at least one processor; wherein,

[0025] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method according to any one of the embodiments of the present application.

[0026] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method according to any one of the embodiments of the present application when executed by the processor.

[0027] According to another aspect of the present application, a computer program product is also provided, which comprises a computer program for implementing the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method according to any one of the embodiments of the present application when executed by a processor.

[0028] The embodiments of the present application obtain case monitoring data of a target infectious disease in a target infectious disease associated region, and determine time-space distribution characteristics of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region. After the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region are determined, a target infectious disease prediction model is trained according to the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region. After the target infectious disease prediction model is trained, case monitoring data of the target infectious disease in a region to be predicted is obtained, and the case monitoring data of the target infectious disease in the region to be predicted is input into the target infectious disease prediction model to predict the target infectious disease in the region to be predicted by using the target infectious disease prediction model. The above-mentioned solution solves the problem that the prior knowledge of the time-space distribution characteristics of the case monitoring data in the region itself is lacked in the existing infectious disease prediction method, and can improve the time-space prediction accuracy of the infectious disease risk region.

[0029] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0031] Figure 1 is a flow chart of a data-knowledge driven fine-scale infectious disease prediction model training method provided by an embodiment of the present application;

[0032] Figure 2 is a flow chart of a data-knowledge driven fine-scale infectious disease prediction model training method provided by an embodiment of the present application;

[0033] Figure 3 is a flow chart of an infectious disease prediction method provided by an embodiment of the present application;

[0034] Figure 4 is a dengue fever prediction risk map provided by an embodiment of the present application;

[0035] Figure 5 is a schematic diagram of a data-knowledge driven fine-scale infectious disease prediction model training device provided by an embodiment of the present application;

[0036] Figure 6 is a schematic diagram of an infectious disease prediction device provided by an embodiment of the present application;

[0037] Figure 7 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the personnel in the art better understand the present application scheme, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should belong to the scope of protection of the present application.

[0039] It should be noted that the terms "first", "second", "target" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0040] Embodiment one

[0041] Figure 1 FIG. 1 is a flowchart of a data-knowledge driven fine-scale infectious disease prediction model training method according to an embodiment of the present application. The embodiment can be applied to training an infectious disease prediction model according to the time and space distribution characteristics of the infectious disease. The method can be executed by an infectious disease prediction model training device, which can be implemented by software and / or hardware and can be integrated in an electronic device, which can be a terminal device or a server device, as long as it can execute the infectious disease prediction model training method. The specific type of the electronic device is not limited in the present application. Correspondingly, as shown in FIG. 2, the method includes the following operations: Figure 1

[0042] S110, obtaining case monitoring data of a target infectious disease in a target infectious disease associated region.

[0043] The target infectious disease can be an infectious disease to be predicted in a risk region. For example, the target infectious disease can include, but is not limited to, dengue fever, chikungunya fever, and Oropouche fever, and the specific type of the target infectious disease is not limited in the present application. The target infectious disease associated region can be a region closely related to the spread, monitoring, and prevention and control of the target infectious disease. The case monitoring data of the target infectious disease in the target infectious disease associated region can be case information related to the target infectious disease collected in the target infectious disease associated region by various monitoring means.

[0044] In the embodiment of the present application, the infectious disease to be predicted in the risk region can be taken as the target infectious disease. Further, the target infectious disease associated region can be determined according to the type of the target infectious disease. After determining the target infectious disease associated region, the case information related to the target infectious disease in the target infectious disease associated region can be collected as the case monitoring data of the target infectious disease in the target infectious disease associated region. It should be noted that the case monitoring data can include the case monitoring data of the target infectious disease in the target infectious disease associated region and the case monitoring data of the target infectious disease input from an external region to the target infectious disease associated region.

[0045] It can be understood that the case monitoring data in a certain period of time can be selected as the case monitoring data of the target infectious disease in the target infectious disease associated region, for example, the case monitoring data of the target infectious disease in each target infectious disease associated region from 2006 to 2018 can be selected. In a specific example, assuming that the target infectious disease is dengue fever, some regions prone to dengue fever can be taken as the target infectious disease associated region.

[0046] ​S120, determine a time-space distribution feature of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region.

[0047] The time-space distribution feature can be a time-space distribution feature of the target infectious disease in the target infectious disease associated region.

[0048] Correspondingly, after obtaining the case monitoring data of the target infectious disease in the target infectious disease associated region, the case monitoring data of the target infectious disease in the target infectious disease associated region can be deeply analyzed, so that the time-space distribution feature of the target infectious disease in the target infectious disease associated region can be determined.

[0049] S130, train a target infectious disease prediction model according to the time-space distribution feature of the target infectious disease in the target infectious disease associated region; wherein the target infectious disease prediction model is used to predict the target infectious disease in a to-be-predicted region according to case monitoring data of the target infectious disease in the to-be-predicted region.

[0050] The target infectious disease prediction model can be a model used to predict the target infectious disease. The to-be-predicted region can be a region to be predicted for the target infectious disease. The case monitoring data of the target infectious disease in the to-be-predicted region can be case information related to the target infectious disease collected in the to-be-predicted region by various monitoring means.

[0051] Correspondingly, after determining the time-space distribution feature of the target infectious disease in the target infectious disease associated region, the target infectious disease prediction model can be trained using the time-space distribution feature of the target infectious disease in the target infectious disease associated region, so that the target infectious disease prediction model can predict the target infectious disease in the to-be-predicted region according to the case monitoring data of the target infectious disease in the to-be-predicted region.

[0052] In summary, the infectious disease prediction model training provided by the embodiment of the present application trains the target infectious disease prediction model through the time-space distribution feature of the target infectious disease in the target infectious disease associated region. This training method can enable the target infectious disease prediction model to deeply learn and master the key information of the target infectious disease, such as the propagation rule, the diffusion rhythm, and the spatial distribution pattern in a specific region, so as to significantly enhance the time-space prediction ability of the target infectious disease prediction model for the target infectious disease, and further improve the time-space prediction accuracy of the infectious disease risk region.

[0053] The embodiment of the present application obtains case monitoring data of a target infectious disease in a target infectious disease associated region, and determines time-space distribution characteristics of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region. After the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region are determined, a target infectious disease prediction model is trained according to the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region. The target infectious disease prediction model is used to predict the target infectious disease in a to-be-predicted region according to case monitoring data of the target infectious disease in the to-be-predicted region. The above scheme solves the problem that the prior knowledge of the time-space distribution characteristics of the case monitoring data in the region itself is not guided in the existing infectious disease prediction method, and can improve the time-space prediction accuracy of the infectious disease risk region.

[0054] Embodiment two

[0055] Figure 2 is a flowchart of a data-knowledge driven fine-scale infectious disease prediction model training method provided by the second embodiment of the present application. The present embodiment is based on the above-mentioned embodiment and is specific. In the present embodiment, a specific optional implementation manner of training a target infectious disease prediction model according to time-space distribution characteristics of a target infectious disease in a target infectious disease associated region is given. Correspondingly, as shown in Figure 2 the method of the present embodiment can include:

[0056] S210, obtaining case monitoring data of a target infectious disease in a target infectious disease associated region.

[0057] S220, determining time-space distribution characteristics of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region.

[0058] In an optional embodiment of the present application, the determination of the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region can include: statistical analysis of the case monitoring data of the target infectious disease in the target infectious disease associated region to determine the time variation characteristics of the target infectious disease in the target infectious disease associated region; and spatial aggregation analysis of the case monitoring data of the target infectious disease in the target infectious disease associated region to determine the spatial distribution characteristics of the target infectious disease in the target infectious disease associated region.

[0059] The time variation characteristic of the target infectious disease in the target infectious disease associated region can be the epidemic trend, seasonal variation, periodic variation, and other time-related dynamic characteristics of the target infectious disease in different time scales in the target infectious disease associated region. The spatial aggregation analysis can be a statistical method for studying the aggregation degree of the case monitoring data of the target infectious disease in the target infectious disease associated region. The spatial distribution characteristic of the target infectious disease in the target infectious disease associated region can be the distribution pattern and rule of the target infectious disease in geographical space in the target infectious disease associated region.

[0060] In the embodiment of the present application, when determining the time-space distribution characteristic of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region, first, the case monitoring data of the target infectious disease in the target infectious disease associated region can be statistically analyzed to determine the time variation characteristic of the target infectious disease in the target infectious disease associated region. In a specific example, the case monitoring data of the target infectious disease in the target infectious disease associated region during the study period can be summarized and analyzed using a statistical chart. It is found through analyzing the case monitoring data of the target infectious disease in the target infectious disease associated region that the target infectious disease period occurs mostly in summer and autumn, rarely in spring and winter, and presents a characteristic of increasing first and then subsiding.

[0061] At the same time, the spatial aggregation of the case monitoring data of the target infectious disease in the target infectious disease associated region can be analyzed by means of an analysis tool. Specifically, the spatial distribution characteristic of the target infectious disease in the target infectious disease associated region can be determined by analyzing the global Moran index, local Moran index, and significance relationship of the case monitoring data of the target infectious disease in the target infectious disease associated region. In a specific example, if the significance P is less than 0.05, it indicates that the cases of the target infectious disease in the target infectious disease associated region are non-uniformly distributed in space, having obvious spatial aggregation distribution characteristic and rule.

[0062] S230, determining the transmission risk level of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region.

[0063] The transmission risk level of the target infectious disease in the target infectious disease associated region can be a quantitative classification of the transmission risk of the target infectious disease in the target infectious disease associated region.

[0064] Specifically, after obtaining the case monitoring data of the target infectious disease in the target infectious disease associated region, the case monitoring data of the target infectious disease in the target infectious disease associated region can be analyzed to determine the transmission risk level of the target infectious disease in the target infectious disease associated region.

[0065] In an optional embodiment of the present application, the determination of the risk level of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region can comprise: determining the risk level of the target infectious disease in the target infectious disease associated region according to a preset target infectious disease case threshold and the case monitoring data of the target infectious disease in the target infectious disease associated region.

[0066] The preset target infectious disease case threshold can be a threshold of the number of preset target infectious disease cases.

[0067] In the embodiments of the present application, when determining the risk level of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region, a threshold of the number of target infectious disease cases can be preset first. Further, the preset target infectious disease case threshold and the case monitoring data of the target infectious disease in the target infectious disease associated region can be compared, so as to determine the risk level of the target infectious disease in the target infectious disease associated region.

[0068] In a specific example, the risk level of the target infectious disease in the target infectious disease associated region with more than 3 target infectious disease cases can be marked as high risk, and the risk level of the target infectious disease in the target infectious disease associated region with no more than 3 target infectious disease cases can be marked as low risk.

[0069] S240, acquiring a target transmission risk variable of the target infectious disease in the target infectious disease associated region.

[0070] The target transmission risk variable can be a variable affecting the transmission of the target infectious disease in the target infectious disease associated region.

[0071] Specifically, to achieve accurate prediction of the target infectious disease in the to-be-predicted region, the target transmission risk variable of the target infectious disease in the target infectious disease associated region can be further acquired, and the above variable can be used as a key input feature for training and parameter optimization of the target infectious disease prediction model, so as to improve the prediction performance and generalization ability of the target infectious disease prediction model.

[0072] In an optional embodiment of the present application, the obtaining of the target transmission risk variable of the target infectious disease in the target infectious disease related region can include: obtaining initial infectious disease transmission risk variables; calculating significance values and correlation coefficients between each of the initial infectious disease transmission risk variables; in a case where it is determined that the significance values between the target reference infectious disease transmission risk variables are less than a preset significance threshold value, and it is determined that the correlation coefficients between the target reference infectious disease transmission risk variables are less than or equal to a preset correlation threshold value, the target reference infectious disease transmission risk variables are taken as the target transmission risk variable of the target infectious disease; wherein the target reference infectious disease transmission risk variables include two of the initial infectious disease transmission risk variables.

[0073] The initial infectious disease transmission risk variable can be all variables related to the transmission of the target infectious disease. The significance value can be used to determine whether the relationship between two initial infectious disease transmission risk variables is unlikely to be accidentally produced by random factors. The correlation coefficient can be used to quantify the direction and strength of the linear relationship between two initial infectious disease transmission risk variables. The preset significance threshold value can be a preset threshold value of the significance value. The preset correlation threshold value can be a preset threshold value of the correlation coefficient. The target reference infectious disease transmission risk variable can be a combination of two initial infectious disease transmission risk variables.

[0074] In the embodiments of the present application, when obtaining the target transmission risk variable of the target infectious disease in the target infectious disease related region, the initial infectious disease transmission risk variables in the target infectious disease related region can be obtained first. Further, the significance values and correlation coefficients between each of the initial infectious disease transmission risk variables can be calculated. If the significance values between two initial infectious disease transmission risk variables are less than a preset significance threshold value, and the correlation coefficients between the two initial infectious disease transmission risk variables are less than or equal to a preset correlation threshold value, that is, the two initial infectious disease transmission risk variables are significantly correlated and the correlation is not large, the two initial infectious disease transmission risk variables can be taken as the target transmission risk variable.

[0075] It can be understood that if the correlation between two initial infectious disease transmission risk variables is high, it can lead to a multicollinearity problem of the target infectious disease prediction model, affecting the accuracy of the prediction result, and therefore, the initial infectious disease transmission risk variables with small correlation can be selected as the target transmission risk variable.

[0076] In a specific example, the Pearson correlation coefficient between each two initial infectious disease transmission risk variables can be calculated as a reference index for measuring the correlation between the two initial infectious disease transmission risk variables. If the correlation coefficient is greater than 0.7, it is considered that there is serious collinearity between the two initial infectious disease transmission risk variables, otherwise there is no obvious collinearity. At this time, if the correlation between the two initial infectious disease transmission risk variables is not significant, there will be no obvious collinearity problem when predicting the risk area level of the target infectious disease.

[0077] In the prediction scenario of dengue fever, the environmental variables of the initial infectious disease transmission risk variables can be natural and socio-economic factors closely related to the growth, development, reproduction and case transmission of dengue fever vectors, which can include but are not limited to temperature, rainfall, population density, vegetation index, etc. The above initial infectious disease transmission risk variables can to some extent accelerate the transmission rate of dengue fever among the population by affecting the density of vectors, for example, temperature can affect the growth and development speed of larvae to affect the transmission rate of dengue fever; rainfall can affect the density of vectors by providing a suitable aquatic environment for the survival of larvae, creating a good environment for the transmission of dengue fever. Therefore, temperature and rainfall can be used as influencing variables affecting the density of larvae. In addition, dengue fever, which mainly follows the mode of mosquito-human-mosquito, is also affected by factors such as population density and vegetation, for example, parks with high vegetation coverage can provide suitable habitats for dengue fever vectors, accelerating the prevalence of dengue fever, and conversely, bare land and other environments have lower dengue fever prevalence; dense population distribution can affect the prevalence of local dengue fever by providing sufficient food for the development of dengue fever vectors and reducing the probability of mosquito bites. It should be noted that the above is only an example of the initial infectious disease transmission risk variables of dengue fever, and the specific types of the initial infectious disease transmission risk variables of dengue fever are not limited.

[0078] It should be noted that the transmission of dengue fever is not only related to the attribute data of the initial infectious disease transmission risk variables of the current month, but also closely related to the attribute data of the initial infectious disease transmission risk variables in the lag period. Therefore, the target transmission risk variables of the target infectious disease can be selected based on the following three principles: (1) there is no obvious collinearity between the two initial infectious disease transmission risk variables; (2) there is a significant correlation between the lag period variables and local dengue fever; (3) the two initial infectious disease transmission risk variables satisfy the correlation and significance relationship at the same time, and the two initial infectious disease transmission risk variables with strong significant correlation are preferred. In a specific example, the case monitoring data of dengue fever lagged by 1 month, the average temperature lagged by 2 months, the cumulative precipitation lagged by 3 months, the normalized vegetation index data mean of the current month, and the population density can be selected as the target transmission risk variables of the dengue fever prediction model.

[0079] S250, training a target infectious disease prediction model according to the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region, the attribute data of the target transmission risk variable of the target infectious disease, and the transmission risk level of the target infectious disease.

[0080] The attribute data of the target transmission risk variable of the target infectious disease can be a numerical value of the target transmission risk variable of the target infectious disease.

[0081] Correspondingly, after obtaining the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region, the attribute data of the target transmission risk variable of the target infectious disease, and the transmission risk level of the target infectious disease, the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region, the attribute data of the target transmission risk variable of the target infectious disease, and the transmission risk level of the target infectious disease can be used as inputs of the target infectious disease prediction model for training the target infectious disease prediction model.

[0082] In an optional embodiment of the present application, the training of the target infectious disease prediction model according to the time-space distribution characteristics of the target infectious disease in the target infectious disease associated region, the attribute data of the target transmission risk variable of the target infectious disease, and the transmission risk level of the target infectious disease can include: converting the spatial distribution characteristics of the target infectious disease in the target infectious disease associated region into spatial distribution explicit characteristics of the target infectious disease by using a target clustering algorithm; and using the time variation characteristics of the target infectious disease in the target infectious disease associated region, the transmission risk level of the target infectious disease, the spatial distribution explicit characteristics of the target infectious disease, and the attribute data of the target transmission risk variable of the target infectious disease as training sample data to train the target prediction model.

[0083] The target clustering algorithm can be a clustering algorithm for converting the spatial distribution characteristics of the target infectious disease in the target infectious disease associated region into the spatial distribution explicit characteristics of the target infectious disease, and can include but not limited to K-nearest neighbor algorithm. The spatial distribution explicit characteristics of the target infectious disease can be the spatial distribution characteristics of the target infectious disease represented by indicators or languages that can be directly quantified and visualized. The training sample data can be sample data used for training the target infectious disease prediction model.

[0084] In the embodiment of the present application, when the target infectious disease prediction model is trained according to the time and space distribution characteristics of the target infectious disease in the target infectious disease associated region, the attribute data of the target transmission risk variable of the target infectious disease, and the transmission risk level of the target infectious disease, first, the target clustering algorithm can be used to convert the spatial distribution characteristics of the target infectious disease in the target infectious disease associated region into the spatial distribution explicit characteristics of the target infectious disease, as the prior knowledge for constructing the target infectious disease prediction model. Further, the time variation characteristics of the target infectious disease in the target infectious disease associated region, the transmission risk level of the target infectious disease, the spatial distribution explicit characteristics of the target infectious disease, and the attribute data of the target transmission risk variable of the target infectious disease can be used as training sample data to train the target infectious disease prediction model, so as to predict the transmission risk level of the target infectious disease in the to-be-predicted region by using the trained target infectious disease prediction model.

[0085] In a specific example, the attribute data of the target transmission risk variable, the time variation characteristics, the spatial distribution explicit characteristics of the target infectious disease in region A, and the transmission risk level of the target infectious disease in region A can be used as first training sample data; the attribute data of the target transmission risk variable, the time variation characteristics, the spatial distribution explicit characteristics of the target infectious disease in region B, and the transmission risk level of the target infectious disease in region B can be used as second training sample data; the attribute data of the target transmission risk variable, the time variation characteristics, the spatial distribution explicit characteristics of the target infectious disease in region C, and the transmission risk level of the target infectious disease in region C can be used as third training sample data to train the random forest model, so as to predict the target infectious disease in the to-be-predicted region according to the case monitoring data of the target infectious disease in the to-be-predicted region by using the random forest model.

[0086] In an optional embodiment of the present application, after the target infectious disease prediction model is trained according to the time and space distribution characteristics of the target infectious disease in the target infectious disease associated region, the parameters of the target clustering algorithm are further optimized according to the accuracy evaluation index of the target infectious disease prediction model; and the parameters of the target infectious disease prediction model are optimized by cross-validation.

[0087] The accuracy evaluation index of the target infectious disease prediction model can be a quantitative index for measuring the accuracy of the target infectious disease prediction model. The parameters of the target clustering algorithm can be key input quantities or hyperparameters in the target clustering algorithm that affect the clustering results. The cross-validation method can be a method of verifying the performance of the target infectious disease prediction model by repeatedly dividing the data and training the target infectious disease prediction model. The parameters of the target infectious disease prediction model can be hyperparameters in the target infectious disease prediction model that affect the prediction accuracy.

[0088] In an optional embodiment of the present application, after training the target infectious disease prediction model according to the temporal and spatial distribution characteristics of the target infectious disease in the target infectious disease associated region, the parameters of the target clustering algorithm can be optimized according to the accuracy evaluation index of the target infectious disease prediction model, and the parameters of the target infectious disease prediction model can be optimized through cross-validation.

[0089] In a specific example, assuming that the target clustering algorithm is the K-nearest neighbor algorithm, the target infectious disease prediction model can be trained using prior knowledge on different K-nearest neighbor units, and the comprehensive performance difference of the target infectious disease prediction model on ROC-AUC (Receiver Operating Characteristic-Area Under the Curve, Receiver Operating Characteristic-Area Under the Curve) and PR-AUC (Precision-Recall-Area Under the Curve, Precision-Recall-Area Under the Curve) indicators can be compared to determine the optimal K-nearest neighbor unit value in the K-nearest neighbor algorithm.

[0090] Assuming that the target infectious disease prediction model is a random forest model, the original data set can be randomly divided into training and test sets through cross-validation, and the model is established on the training set to predict the remaining data for optimization of the mtry (number of feature samples when a single decision tree is split) parameter in the random forest model. In addition, by repeatedly comparing the performance curves of the target infectious disease prediction model with different ntree (total number of decision trees in the random forest) parameters, the optimal parameter combination of the model can be selected to establish the target infectious disease prediction model. For example, assuming that the data of the dengue fever epidemic period from 2006 to 2014 is selected as the training set, and the data of the dengue fever epidemic period from 2015 to 2018 is selected as the test set, when the model parameters mtry = 5 and ntree = 250, the performance of the target infectious disease prediction model is relatively stable, and the experimental parameters are selected as the final modeling parameters.

[0091] The embodiment of the present application obtains case monitoring data of a target infectious disease in a target infectious disease associated region, and determines the time and space distribution characteristics of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region. After determining the time and space distribution characteristics of the target infectious disease in the target infectious disease associated region, the propagation risk level of the target infectious disease in the target infectious disease associated region is determined according to the case monitoring data of the target infectious disease in the target infectious disease associated region, and the target propagation risk variable of the target infectious disease in the target infectious disease associated region is obtained, so as to train the target infectious disease prediction model according to the time and space distribution characteristics of the target infectious disease in the target infectious disease associated region, the attribute data of the target propagation risk variable of the target infectious disease, and the propagation risk level of the target infectious disease. The above scheme solves the problem that the prior knowledge of the time and space distribution characteristics of the case monitoring data in the region is not guided in the existing infectious disease prediction method, and can improve the time and space prediction accuracy of the infectious disease risk region.

[0092] Embodiment three

[0093] Figure 3 is a flowchart of an infectious disease prediction method provided by the third embodiment of the present application. The present embodiment can be applied to the case of predicting an infectious disease risk by using a data-knowledge driven fine-scale infectious disease prediction model. The method can be executed by an infectious disease prediction device, which can be realized by software and / or hardware, and can generally be integrated in an electronic device. The electronic device can be a terminal device or a server device, as long as it can execute the infectious disease prediction method. The specific type of the electronic device is not limited in the present application. Correspondingly, as shown in Figure 3 the method includes the following operations:

[0094] S310, obtaining case monitoring data of a target infectious disease in a to-be-predicted region.

[0095] The to-be-predicted region can be a region to be predicted for a target infectious disease.

[0096] In the embodiment of the present application, when the target infectious disease prediction model is used to predict the target infectious disease in the to-be-predicted region, the case monitoring data of the target infectious disease in the to-be-predicted region can be obtained as the input data of the target infectious disease prediction model.

[0097] S320, inputting the case monitoring data of the target infectious disease in the to-be-predicted region into the target infectious disease prediction model, and predicting the target infectious disease in the to-be-predicted region by using the target infectious disease prediction model.

[0098] Correspondingly, after obtaining the case monitoring data of the target infectious disease in the to-be-predicted region, the case monitoring data of the target infectious disease in the to-be-predicted region can be input into the target infectious disease prediction model, and the target infectious disease in the to-be-predicted region can be predicted by using the target infectious disease prediction model.

[0099] Optionally, after predicting the target infectious disease in the to-be-predicted region by using the target infectious disease prediction model, the probability prediction result can be converted into a risk level of the target infectious disease in the to-be-predicted region by using a 10th percentile conversion method, and a prediction risk map of the target infectious disease in the to-be-predicted region can be drawn according to the risk level.

[0100] Figure 4 is a dengue fever prediction risk map provided by an embodiment of the present application. As shown in Figure 4 In one specific example, 28 high-risk areas are accurately predicted by using the target infectious disease prediction model provided in the present application, and the overall recall rate of the target infectious disease prediction model is about 78%.

[0101] The embodiment of the present application obtains the case monitoring data of the target infectious disease in the to-be-predicted region, and inputs the case monitoring data of the target infectious disease in the to-be-predicted region into the target infectious disease prediction model, so as to predict the target infectious disease in the to-be-predicted region by using the target infectious disease prediction model. The above scheme solves the problem that the prior knowledge of the spatial and temporal distribution characteristics of the internal case monitoring data of the region is lacking in the existing infectious disease prediction method, and can improve the spatial and temporal prediction accuracy of the infectious disease risk region.

[0102] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information (such as case monitoring data of the target infectious disease) and other processing comply with relevant laws and regulations and do not violate public order and good customs.

[0103] It should be noted that the related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, analyzed data, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data comply with relevant laws, regulations and standards in the relevant region.

[0104] It should be noted that any arrangement and combination of technical features among the above embodiments also belong to the protection scope of the present application.

[0105] Embodiment Four

[0106] Figure 5 is a schematic diagram of a data-knowledge-driven fine-scale infectious disease prediction model training device provided by an embodiment of the present application, as shown in Figure 5As shown, the device comprises: a first case monitoring data acquisition module 410, a time-space distribution feature determination module 420, and a target infectious disease prediction model training module 430, wherein:

[0107] The first case monitoring data acquisition module 410 is configured to acquire case monitoring data of a target infectious disease in a target infectious disease associated region.

[0108] The time-space distribution feature determination module 420 is configured to determine a time-space distribution feature of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region.

[0109] The target infectious disease prediction model training module 430 is configured to train a target infectious disease prediction model according to the time-space distribution feature of the target infectious disease in the target infectious disease associated region.

[0110] The target infectious disease prediction model is configured to predict the target infectious disease in a to-be-predicted region according to case monitoring data of the target infectious disease in the to-be-predicted region.

[0111] The embodiment of the present application acquires case monitoring data of a target infectious disease in a target infectious disease associated region, and determines a time-space distribution feature of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region. After determining the time-space distribution feature of the target infectious disease in the target infectious disease associated region, a target infectious disease prediction model is trained according to the time-space distribution feature of the target infectious disease in the target infectious disease associated region. The target infectious disease prediction model is configured to predict the target infectious disease in a to-be-predicted region according to case monitoring data of the target infectious disease in the to-be-predicted region. The above-mentioned scheme solves the problem that the prior knowledge of the time-space distribution feature of the case monitoring data in the region is lacking in the existing infectious disease prediction method, and can improve the time-space prediction accuracy of the infectious disease risk region.

[0112] Optionally, the device can further comprise a data acquisition module configured to: determine a transmission risk level of the target infectious disease in the target infectious disease associated region according to the case monitoring data of the target infectious disease in the target infectious disease associated region; and acquire a target transmission risk variable of the target infectious disease in the target infectious disease associated region.

[0113] Optionally, the target infectious disease prediction model training module 430 is specifically configured to train the target infectious disease prediction model according to the time-space distribution feature of the target infectious disease in the target infectious disease associated region, attribute data of the target transmission risk variable of the target infectious disease, and the transmission risk level of the target infectious disease.

[0114] Optionally, the data acquisition module is specifically configured to: acquire initial infectious disease transmission risk variables; calculate significance values and correlation coefficients between the initial infectious disease transmission risk variables; in a case where it is determined that the significance values between the target reference infectious disease transmission risk variables are less than a preset significance threshold, and it is determined that the correlation coefficients between the target reference infectious disease transmission risk variables are less than or equal to a preset correlation threshold, the target reference infectious disease transmission risk variables are taken as the target transmission risk variables of the target infectious disease; and the target reference infectious disease transmission risk variables include two initial infectious disease transmission risk variables.

[0115] Optionally, the time-space distribution feature determination module 420 is specifically configured to: statistically analyze the case monitoring data of the target infectious disease in the target infectious disease associated region to determine the time variation feature of the target infectious disease in the target infectious disease associated region; and perform spatial aggregation analysis on the case monitoring data of the target infectious disease in the target infectious disease associated region to determine the spatial distribution feature of the target infectious disease in the target infectious disease associated region.

[0116] Optionally, the data acquisition module is further configured to: determine the risk level of the target infectious disease in the target infectious disease associated region according to a preset target infectious disease case threshold and the case monitoring data of the target infectious disease in the target infectious disease associated region.

[0117] Optionally, the target infectious disease prediction model training module 430 is further configured to: convert the spatial distribution feature of the target infectious disease in the target infectious disease associated region into a spatial distribution explicit feature of the target infectious disease by using a target clustering algorithm; and take the time variation feature of the target infectious disease in the target infectious disease associated region, the transmission risk level of the target infectious disease, the spatial distribution explicit feature of the target infectious disease, and attribute data of the target transmission risk variables of the target infectious disease as training sample data to train the target prediction model.

[0118] Optionally, the above device can further include a parameter optimization module configured to: optimize parameters of the target clustering algorithm according to an accuracy evaluation index of the target infectious disease prediction model; and optimize parameters of the target infectious disease prediction model in a cross-validation manner.

[0119] The above data-knowledge driven fine-scale infectious disease prediction model training device can execute the data-knowledge driven fine-scale infectious disease prediction model training method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of executing the method. Technical details not described in detail in the present embodiment can be referred to the data-knowledge driven fine-scale infectious disease prediction model training method provided by any embodiment of the present application.

[0120] Since the data-knowledge driven fine-scale infectious disease prediction model training device described above is a device that can perform the data-knowledge driven fine-scale infectious disease prediction model training method in the embodiments of the present application, based on the data-knowledge driven fine-scale infectious disease prediction model training method described in the embodiments of the present application, those skilled in the art can understand the specific implementation of the data-knowledge driven fine-scale infectious disease prediction model training device of the present embodiment and its various forms, so the data-knowledge driven fine-scale infectious disease prediction model training device how to implement the data-knowledge driven fine-scale infectious disease prediction model training method in the embodiments of the present application will not be introduced in detail. As long as the device used to implement the data-knowledge driven fine-scale infectious disease prediction model training method in the embodiments of the present application is implemented by those skilled in the art, it belongs to the scope of the present application.

[0121] Embodiment five

[0122] Figure 6 is a schematic diagram of an infectious disease prediction device provided by the fifth embodiment of the present application, as shown in Figure 6 The device comprises a second case monitoring data acquisition module 510 and a target infectious disease prediction module 520, wherein:

[0123] The second case monitoring data acquisition module 510 is configured to acquire case monitoring data of a target infectious disease in a to-be-predicted area.

[0124] The target infectious disease prediction module 520 is configured to input the case monitoring data of the target infectious disease in the to-be-predicted area into a target infectious disease prediction model, and use the target infectious disease prediction model to predict the target infectious disease in the to-be-predicted area.

[0125] The target infectious disease prediction model is obtained by the infectious disease prediction model training method of any embodiment of the present application.

[0126] The embodiments of the present application acquire the case monitoring data of the target infectious disease in the to-be-predicted area, and input the case monitoring data of the target infectious disease in the to-be-predicted area into a target infectious disease prediction model, so as to use the target infectious disease prediction model to predict the target infectious disease in the to-be-predicted area. The above-mentioned scheme solves the problem of lack of prior knowledge guidance of the spatial and temporal distribution characteristics of the internal case monitoring data of the region in the existing infectious disease prediction method, and can improve the spatial and temporal prediction accuracy of the infectious disease risk area.

[0127] The infectious disease prediction device can perform the infectious disease prediction method provided by any embodiment of the present application, has the function modules and beneficial effects corresponding to the execution method. The technical details not described in detail in the present embodiment can refer to the infectious disease prediction method provided by any embodiment of the present application.

[0128] Since the infectious disease prediction device described above is a device that can perform the infectious disease prediction method in the embodiments of the present application, based on the infectious disease prediction method described in the embodiments of the present application, those skilled in the art can understand the specific implementation of the infectious disease prediction device of the present embodiment and its various forms, so the infectious disease prediction device how to implement the infectious disease prediction method in the embodiments of the present application will not be described in detail here. As long as the device used to implement the infectious disease prediction method in the embodiments of the present application is implemented by those skilled in the art, it belongs to the scope of protection of the present application.

[0129] Embodiment six

[0130] Figure 7 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0131] As shown in Figure 7 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is in communication with the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0132] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0133] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method.

[0134] In some embodiments, the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the data-knowledge driven fine-scale infectious disease prediction model training method or the infectious disease prediction method by any other appropriate means, such as by means of firmware.

[0135] Optionally, the data-knowledge driven fine-scale infectious disease prediction model training method can comprise: obtaining case monitoring data of a target infectious disease within a target infectious disease associated region; determining a time-space distribution feature of the target infectious disease within the target infectious disease associated region according to the case monitoring data of the target infectious disease within the target infectious disease associated region; training a target infectious disease prediction model according to the time-space distribution feature of the target infectious disease within the target infectious disease associated region; wherein the target infectious disease prediction model is used to predict the target infectious disease within a to-be-predicted region according to case monitoring data of the target infectious disease within the to-be-predicted region.

[0136] Optionally, the infectious disease prediction method can comprise: acquiring case monitoring data of a target infectious disease in a region to be predicted; inputting the case monitoring data of the target infectious disease in the region to be predicted into a target infectious disease prediction model, and predicting the target infectious disease in the region to be predicted by using the target infectious disease prediction model; wherein the target infectious disease prediction model is obtained by the infectious disease prediction model training method of any one of the embodiments of the present application.

[0137] Various embodiments of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0138] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flow diagrams and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as part of a standalone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0139] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, 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.

[0140] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device 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 electronic device. Other kinds of devices can be used to provide for interaction with a user as well; 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.

[0141] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, 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 communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0142] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0143] It should be understood that the steps shown above in various forms of flow can be reordered, added, or deleted. For example, the steps described 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 of the present disclosure can be achieved, which are not limited herein.

[0144] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A data-knowledge-driven method for training a fine-scale infectious disease prediction model, characterized in that, include: Obtain case surveillance data for the target infectious disease within the associated region; The temporal and spatial distribution characteristics of the target infectious disease within the associated region are determined based on case surveillance data of the target infectious disease within the associated region. A target infectious disease prediction model is trained based on the temporal and spatial distribution characteristics of the target infectious disease within the associated region. The target infectious disease prediction model is used to predict the target infectious disease in the area to be predicted based on case surveillance data of the target infectious disease in the area to be predicted.

2. The method according to claim 1, characterized in that, The method further includes: The transmission risk level of the target infectious disease within the associated area is determined based on case surveillance data of the target infectious disease within the associated area. Obtain the target transmission risk variables of the target infectious disease within the region associated with the target infectious disease; The step of training a target infectious disease prediction model based on the spatiotemporal distribution characteristics of the target infectious disease within the associated region includes: A target infectious disease prediction model is trained based on the temporal and spatial distribution characteristics of the target infectious disease within the associated region, the attribute data of the target infectious disease's transmission risk variables, and the transmission risk level of the target infectious disease.

3. The method according to claim 2, characterized in that, The acquisition of the target transmission risk variables of the target infectious disease within the associated region includes: Obtain initial infectious disease transmission risk variables; Calculate the significance values ​​and correlation coefficients among the initial infectious disease transmission risk variables; If the significance value between the target reference infectious disease transmission risk variables is less than a preset significance threshold, and the correlation coefficient between the target reference infectious disease transmission risk variables is less than or equal to a preset correlation threshold, the target reference infectious disease transmission risk variables shall be used as the target transmission risk variables of the target infectious disease; wherein, the target reference infectious disease transmission risk variables include two initial infectious disease transmission risk variables.

4. The method according to claim 2, characterized in that, The step of determining the temporal and spatial distribution characteristics of the target infectious disease within the target infectious disease-associated area based on case surveillance data of the target infectious disease within the target infectious disease-associated area includes: Statistical analysis is performed on the case surveillance data of the target infectious disease within the area associated with the target infectious disease to determine the temporal variation characteristics of the target infectious disease within the area associated with the target infectious disease; Spatial clustering analysis is performed on the case surveillance data of the target infectious disease within the associated region to determine the spatial distribution characteristics of the target infectious disease within the associated region. The step of determining the transmission risk level of the target infectious disease within the associated area based on case surveillance data of the target infectious disease within the associated area includes: The risk level of the target infectious disease in the associated region is determined based on a preset target infectious disease case threshold and case surveillance data of the target infectious disease in the associated region.

5. The method according to claim 4, characterized in that, The step of training a target infectious disease prediction model based on the spatiotemporal distribution characteristics of the target infectious disease within the associated region, the attribute data of the target infectious disease's transmission risk variables, and the transmission risk level of the target infectious disease includes: The spatial distribution characteristics of the target infectious disease within the associated region are converted into the explicit spatial distribution characteristics of the target infectious disease using a target clustering algorithm. The target infectious disease prediction model is trained using the temporal variation characteristics of the target infectious disease within the associated region, the transmission risk level of the target infectious disease, the spatial distribution dominance characteristics of the target infectious disease, and the attribute data of the target transmission risk variable of the target infectious disease as training sample data.

6. The method according to claim 5, characterized in that, After training the target infectious disease prediction model based on the spatiotemporal distribution characteristics of the target infectious disease within the target infectious disease association region, the method further includes: Optimize the parameters of the target clustering algorithm based on the accuracy evaluation index of the target infectious disease prediction model; The parameters of the target infectious disease prediction model are optimized using cross-validation.

7. A method for predicting infectious diseases, characterized in that, include: Obtain case surveillance data of the target infectious disease within the area to be predicted; The case surveillance data of the target infectious disease in the area to be predicted is input into the target infectious disease prediction model, and the target infectious disease prediction model is used to predict the target infectious disease in the area to be predicted. The target infectious disease prediction model is obtained by the data-knowledge driven fine-scale infectious disease prediction model training method described in any one of claims 1-6.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor, such that the at least one processor is able to execute the data-knowledge-driven fine-scale infectious disease prediction model training method according to any one of claims 1-6 or the infectious disease prediction method according to claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the data-knowledge-driven fine-scale infectious disease prediction model training method of any one of claims 1-6 or the infectious disease prediction method of claim 7.

10. A computer program product comprising a computer program / instructions, wherein, When the computer program / instruction is executed by the processor, it implements the data-knowledge-driven fine-scale infectious disease prediction model training method of any one of claims 1-6 or the infectious disease prediction method of claim 7.

Images