Method and device for sampling and monitoring spatial and temporal distribution characteristics of avian influenza

Abstract

The invention discloses an avian influenza space-time distribution characteristic sampling monitoring method and device, and relates to the field of avian influenza data processing, and the method comprises the steps: obtaining multi-source data of a research region; the multi-source data comprises an avian influenza outbreak data set, a land utilization data set, a vegetation index data set, a climate change data set, a population density data set and a topographic data set; performing time sequence analysis on the outbreak starting time according to months by using the avian influenza outbreak data set, counting the outbreak frequency per month, and determining the avian influenza outbreak time characteristics of the research area; performing avian influenza outbreak risk hot spot area and key factor identification according to the multi-source data by using a maximum entropy model to obtain avian influenza outbreak space distribution characteristics of the research area; the bird flu outbreak time characteristic and the bird flu outbreak space distribution characteristic form a bird flu space-time distribution characteristic, and the bird flu outbreak time characteristic and the bird flu outbreak space distribution characteristic aim at overcoming the defects in the existing monitoring technology and providing scientific basis and technical support for bird flu prevention and control.

Description

Technical Field

[0001] This application relates to the field of avian influenza data processing, and particularly to a sampling and monitoring method and device for spatio-temporal distribution characteristics of avian influenza based on a stratified sampling method. Background Art

[0002] Avian Influenza (AI) is a highly contagious animal disease caused by the Influenza A virus, posing a serious threat to the poultry farming industry and public health security. In recent years, with the intensification of global climate change, poultry trade, and migratory bird migration activities, the spread of avian influenza virus has shown significant spatio-temporal heterogeneity, and its outbreak frequency and impact range have been continuously expanding. Therefore, developing an efficient and accurate sampling and monitoring scheme for spatio-temporal distribution characteristics of avian influenza is of great significance for epidemic early warning, transmission risk assessment, and optimal allocation of prevention and control resources.

[0003] Currently, avian influenza monitoring mainly relies on random sampling or fixed monitoring point sampling methods, combined with laboratory detection techniques (such as RT-PCR, serological detection) for virus identification. However, the existing methods have limitations such as insufficient spatio-temporal coverage, limited data integration ability, and lagging response speed. Traditional sampling methods are mostly based on administrative divisions or fixed monitoring points, and do not fully consider the spatio-temporal dynamic characteristics of avian influenza transmission (such as seasonal outbreaks, migratory bird migration routes), resulting in missed detections in high-risk areas or waste of resources in low-risk areas; at the same time, monitoring data are scattered in different departments (such as agriculture, forestry, meteorology), lacking a unified spatial integration and analysis platform, making it difficult to comprehensively depict the spatio-temporal patterns of virus transmission; in addition, existing monitoring schemes mostly rely on manual experience to formulate, lacking the ability of dynamic adjustment, and are difficult to meet the needs of rapid epidemic evolution.

[0004] To address the above challenges, in recent years, scholars at home and abroad have carried out a large number of studies in the field of avian influenza monitoring, mainly focusing on spatial stratified sampling techniques, spatio-temporal data analysis models, and intelligent monitoring techniques. Spatial stratified sampling techniques divide sampling levels through Geographic Information System (GIS) combined with environmental factors (such as land use type, poultry breeding density) to improve sample representativeness. For example, the spatial stratified method based on kernel density analysis has been used to identify high-risk areas of avian influenza; spatio-temporal data analysis models use tools such as Kriging interpolation and Bayesian networks to integrate historical epidemic data and environmental variables to predict the virus diffusion trend. For example, some studies have constructed a risk map of avian influenza transmission by combining meteorological data and migratory bird migration routes; intelligent monitoring techniques introduce machine learning algorithms (such as random forest, support vector machine) to optimize the sampling strategy and use real-time data streams to achieve dynamic early warning. For example, epidemic prediction models based on deep learning have been piloted in some countries and regions.

[0005] Despite certain progress in related technologies, there are still technical gaps such as the lack of dynamic stratification strategies, insufficient multi-source data fusion, lack of spatio-temporal consistency, and insufficient real-time response capabilities. Summary of the Invention

[0006] The purpose of this application is to provide a method and device for sampling and monitoring the spatio-temporal distribution characteristics of avian influenza, aiming to make up for the deficiencies in existing monitoring technologies and provide scientific basis and technical support for avian influenza prevention and control.

[0007] To achieve the above purpose, this application provides the following solutions:

[0008] In the first aspect, this application provides a method for sampling and monitoring the spatio-temporal distribution characteristics of avian influenza, including:

[0009] Obtain multi-source data of the research area; the multi-source data includes an avian influenza outbreak dataset, a land use dataset, a vegetation index dataset, a climate change dataset, a population density dataset, and a terrain dataset;

[0010] Using the avian influenza outbreak dataset, perform a time series analysis on the start time of the outbreak by month, count the outbreak frequency per month, and determine the avian influenza outbreak time characteristics of the research area;

[0011] Using the maximum entropy model, identify the avian influenza outbreak risk hotspots and key factors based on the multi-source data to obtain the avian influenza outbreak spatial distribution characteristics of the research area; the avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics constitute the avian influenza spatio-temporal distribution characteristics.

[0012] Optionally, the method for sampling and monitoring the spatio-temporal distribution characteristics of avian influenza further includes:

[0013] Using a geographic information system, perform a spatial overlay analysis on the avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics of the research area to generate a comprehensive risk probability map;

[0014] Determine the high-priority level area, the medium-priority level area, and the low-priority level area according to the comprehensive risk probability map;

[0015] According to the historical avian influenza outbreak data, compare the virus detection frequencies in the high-priority level area, the medium-priority level area, and the low-priority level area to obtain a comparison result.

[0016] Optionally, obtaining the multi-source data of the research area specifically includes:

[0017] Obtain the original data; the original data includes the spatio-temporal geographic information data of multiple regions;

[0018] Perform spatial cropping on the original data to obtain the response data of the research area;

[0019] Divide the avian influenza outbreak dataset in the response data of the research area to obtain wild animal avian influenza outbreak data and poultry avian influenza outbreak data;

[0020] Resample the response data of the research area to the same spatial resolution to obtain resampled data;

[0021] Convert the format of the resampled data to obtain multi-source data of the research area.

[0022] Optionally, use the maximum entropy model to identify avian influenza outbreak risk hotspots and key factors based on the multi-source data, and obtain the spatial distribution characteristics of avian influenza outbreaks in the research area, specifically including:

[0023] Use the avian influenza outbreak dataset as the dependent variable, and input the land use dataset, vegetation index dataset, climate change dataset, population density dataset, and terrain dataset as independent variables into the maximum entropy model;

[0024] Select the quadratic Quadratic feature type, and obtain the model prediction result through the maximum entropy principle. The model prediction result is the spatial distribution characteristics of avian influenza outbreaks in the research area.

[0025] Optionally, the spatial distribution characteristics of avian influenza outbreaks include a risk probability map, contribution rates of influencing factors, and response curves; among them, the risk probability map is used to generate a spatial probability distribution map of avian influenza outbreaks in the research area; the contribution rates of influencing factors are used to calculate the contribution rates of each variable to the model prediction result and identify key influencing factors; the response curves are used to show the relationship between key influencing factors and the probability of avian influenza outbreaks.

[0026] Optionally, the avian influenza outbreak dataset includes avian influenza name, start time, end time, longitude, latitude, and animal category.

[0027] In a second aspect, the present application provides an avian influenza spatio-temporal distribution characteristic sampling and monitoring device, including:

[0028] A multi-source data acquisition module for acquiring multi-source data of the research area; the multi-source data includes an avian influenza outbreak dataset, a land use dataset, a vegetation index dataset, a climate change dataset, a population density dataset, and a terrain dataset;

[0029] An outbreak time characteristic determination module for using the avian influenza outbreak dataset to perform time series analysis on the outbreak start time by month, counting the outbreak frequency per month, and determining the avian influenza outbreak time characteristics of the research area;

[0030] A spatial distribution feature determination module, which is used to utilize the maximum entropy model to identify the hot spots and key factors of avian influenza outbreak risk based on the multi-source data, so as to obtain the spatial distribution characteristics of avian influenza outbreak in the research area; the avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics constitute the avian influenza spatio-temporal distribution characteristics.

[0031] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the above-mentioned avian influenza spatio-temporal distribution feature sampling and monitoring method.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-mentioned avian influenza spatio-temporal distribution feature sampling and monitoring method.

[0033] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above-mentioned avian influenza spatio-temporal distribution feature sampling and monitoring method.

[0034] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0035] The present application provides an avian influenza spatio-temporal distribution feature sampling and monitoring method and device, which integrates multi-source data (including avian influenza outbreak datasets, land use datasets, vegetation index datasets, climate change datasets, population density datasets, and terrain datasets), and based on the maximum entropy model, identifies the hot spots and key influencing factors of avian influenza outbreak risk, and conducts multi-faceted coupling analysis from both time and space dimensions, so as to formulate an avian influenza spatio-temporal distribution feature sampling and monitoring scheme based on the stratified sampling method, and solves the problems of lack of dynamic stratification strategy, insufficient multi-source data fusion, lack of spatio-temporal consistency, and insufficient real-time response ability in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0037] Figure 1 It is an application environment diagram of an avian influenza spatio-temporal distribution feature sampling and monitoring method in an embodiment of the present application.

[0038] Figure 2 It is a flowchart of an avian influenza spatio-temporal distribution feature sampling and monitoring method provided by an embodiment of the present application.

[0039] Figure 3 Schematic diagram of the comparison results of the detection rates of different sampling priority ranges provided by an embodiment of the present application.

[0040] Figure 4 Schematic diagram of the functional modules of a sampling and monitoring device for the spatio-temporal distribution characteristics of avian influenza provided by an embodiment of the present application.

[0041] Figure 5 Schematic diagram of the structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0042] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0043] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific implementation manners.

[0044] The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed on the cloud or other servers. The terminal 102 can send multi-source data to be processed to the server 104. After receiving the multi-source data to be processed, the server 104 uses the avian influenza outbreak dataset to perform a time series analysis on the outbreak start time by month, counts the outbreak frequency per month, determines the avian influenza outbreak time characteristics in the research area, and uses the Maximum Entropy Model (MaxEnt) to identify the avian influenza outbreak risk hotspots and key factors based on the multi-source data, obtaining the avian influenza outbreak spatial distribution characteristics in the research area. The avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics constitute the avian influenza spatio-temporal distribution characteristics. The server 104 can feedback the obtained avian influenza spatio-temporal distribution characteristics to the terminal 102. In addition, in some embodiments, the avian influenza spatio-temporal distribution characteristics sampling and monitoring method can also be implemented separately by the server 104 or the terminal 102. For example, the terminal 102 can directly perform avian influenza spatio-temporal distribution characteristics sampling and monitoring on the video to be processed, or the server 104 can obtain the video to be processed from the data storage system and perform avian influenza spatio-temporal distribution characteristics sampling and monitoring on the video to be processed.

[0045] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0046] In an exemplary embodiment, as Figure 2 shown, a method for sampling and monitoring avian influenza spatio-temporal distribution characteristics is provided. This method is executed by a computer device, and specifically can be executed separately by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server 104 in as an example for illustration, it includes the following steps 201 to step 203. Among them:

[0047] Step 201, obtain multi-source data of the research area; the multi-source data includes an avian influenza outbreak dataset, a land use dataset, a vegetation index dataset, a climate change dataset, a population density dataset, and a terrain dataset.

[0048] Step 202: Using the avian influenza outbreak dataset, conduct a time series analysis of the outbreak start time by month, count the outbreak frequency each month, and determine the avian influenza outbreak time characteristics in the study area.

[0049] Step 203: Using the maximum entropy model, identify the avian influenza outbreak risk hotspots and key factors based on the multi-source data to obtain the avian influenza outbreak spatial distribution characteristics in the study area; the avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics constitute the avian influenza spatio-temporal distribution characteristics.

[0050] Implementing the above Steps 201 to 203 integrates multi-source data, identifies the key influencing factors and influencing rules of avian influenza outbreaks, thereby obtaining a comprehensive risk probability map (outbreak risk map). Identifying the avian influenza outbreak risk hotspots and key influencing factors based on the maximum entropy model, and conducting a multi-faceted coupling analysis from two dimensions of time and space, thus formulating a sampling monitoring scheme for avian influenza spatio-temporal distribution characteristics based on the stratified sampling method, which solves the problems of the lack of dynamic stratification strategy, insufficient multi-source data fusion, lack of spatio-temporal consistency, and insufficient real-time response ability in the related technologies.

[0051] In another exemplary embodiment of the present application, the above Step 201 may include the following Steps 301 to 305.

[0052] Step 301: Obtain the original data; the original data includes the spatio-temporal data of geographical information in multiple regions.

[0053] First, this embodiment integrates the spatio-temporal data source of geographical information (the spatio-temporal data source of geographical information is the original data), including the avian influenza outbreak dataset, land use dataset, vegetation index dataset, climate change dataset, population density dataset, and terrain dataset, laying a data foundation for data fusion and constructing a monitoring sampling scheme adapted to the spatio-temporal distribution characteristics of avian influenza pathogens.

[0054] Among them, the avian influenza outbreak dataset is sourced from the World Animal Health Information System; the land use dataset is sourced from the 100-meter resolution global land use dataset CGLS-LC100 provided by the Copernicus Global Land Service, with a total of 23 land use classifications; the vegetation index dataset is derived from the Normalized Difference Vegetation Index dataset GIMMS NDVI 3gv1, with a spatial resolution of 0.0833 degrees; the climate change dataset includes a rainfall dataset and a temperature dataset. The rainfall dataset is sourced from the global climate dataset of WorldClim, with a time resolution of 1 month and a spatial resolution of 2.5 minutes (about 21 km 2) The temperature dataset is sourced from the global climate dataset of WorldClim and POLES-data. WorldClim provides monthly maximum temperature and monthly minimum temperature, while POLES-data provides monthly average surface temperature. The population density dataset is sourced from the landscan-global global population distribution dataset developed by the laboratory, with a time resolution of 1 kilometer. The terrain dataset is sourced from the DEM dataset of ETOPO2022, with a resolution of 15 arcseconds.

[0055] Step 302: Perform spatial cropping on the original data to obtain the response data of the study area.

[0056] Step 303: Divide the avian influenza outbreak dataset in the response data of the study area to obtain wild animal avian influenza outbreak data and domestic animal avian influenza outbreak data.

[0057] Step 304: Resample the response data of the study area to the same spatial resolution to obtain resampled data.

[0058] Step 305: Perform format conversion on the resampled data to obtain the multi-source data of the study area.

[0059] The above steps 302 - 305 are the preprocessing process of multi-source data. The preprocessing of the fused multi-source data includes: (1) Select China and the United States as the study area, and perform spatial cropping on the obtained multi-source data to obtain the response data of the study area. (2) Classify the avian influenza outbreak data into two categories: wild animals and domestic animals, and divide the avian influenza outbreak dataset into wild animal avian influenza outbreak data and domestic animal avian influenza outbreak data. (3) Resample all predictor variable data and response variable data to the same spatial resolution. Predictor variable data refers to avian influenza outbreak data, and response variable data refers to land use data, vegetation index data, climate change data, population density data, and terrain data. (4) Perform format conversion to unify the data into the GeoTIFF format.

[0060] The avian influenza outbreak dataset includes information such as avian influenza name, start time, end time, longitude, latitude, and animal category. The construction of the sampling scheme based on time characteristics includes: performing time series analysis on the outbreak start time by month using the avian influenza outbreak dataset, and counting the outbreak frequency each month to clarify the time characteristics of avian influenza outbreaks.

[0061] In another exemplary embodiment of the present application, step 203 specifically includes: taking the avian influenza outbreak dataset as the dependent variable, and inputting the land use dataset, vegetation index dataset, climate change dataset, population density dataset, and terrain dataset as independent variables into the maximum entropy model; selecting the Quadratic feature type, and obtaining the model prediction result through the principle of maximum entropy. The model prediction result is the spatial distribution characteristics of avian influenza outbreaks in the study area.

[0062] In the construction of an avian influenza sampling scheme based on spatial characteristics, the maximum entropy model (MaxEnt model) is used to accurately identify the hotspots of avian influenza outbreak risks and the key influencing factors. The construction process of the maximum entropy model includes the following four steps.

[0063] (1) Model input: Take the avian influenza outbreak dataset as the dependent variable, and input the land use dataset, vegetation index dataset, climate change dataset, population density dataset, and terrain dataset as independent variables into the maximum entropy model. Remove highly correlated influencing factors through correlation analysis (Pearson correlation coefficient) to avoid overfitting of the model. The influencing factors refer to data such as land use data, vegetation index data, climate change data, population density data, and terrain data that are used as independent variables. Among them, the correlation analysis is realized by calculating the Pearson correlation coefficient. Sort all influencing factors according to the calculated Pearson correlation coefficient, and remove the highly correlated influencing factors, that is, remove the influencing factors ranked in the top K (K>0) according to the Pearson correlation coefficient.

[0064] (2) Parameter setting: First, select the Quadratic feature type to capture the complex relationship between the influencing factors and avian influenza outbreaks; then, determine the optimal regularization parameter (RegularizationMultiplier) through cross-validation to balance the model complexity and fitting degree and avoid overfitting or underfitting problems; finally, set the number of background points (about 10,000 times the number of positive samples) to ensure that the model can fully reflect the background conditions of the study area.

[0065] (3) Model operation: The model calculates the probability distribution of avian influenza outbreaks under given conditions through the principle of maximum entropy. The given conditions refer to data such as land use data, vegetation index data, climate change data, population density data, and terrain data that are used as independent variables.

[0066] (4) Model Output: The model output (model prediction results) includes a risk probability map, contribution rates of influencing factors, and response curves. The risk probability map is used to generate a spatial probability distribution map of avian influenza outbreaks within the study area (with probability values ranging from 0 to 1). The contribution rates of influencing factors are used to calculate the contribution rates of each variable to the model prediction results and identify key driving factors. The response curves show the relationship between key influencing factors and the probability of avian influenza outbreaks, thus comprehensively analyzing the spatial distribution characteristics and driving mechanisms of avian influenza outbreaks.

[0067] Then, the spatial distribution characteristics of avian influenza outbreaks include a risk probability map, contribution rates of influencing factors, and response curves. Among them, the risk probability map is used to generate a spatial probability distribution map of avian influenza outbreaks within the study area; the contribution rates of influencing factors are used to calculate the contribution rates of each variable to the model prediction results and identify key influencing factors; the response curves are used to show the relationship between key influencing factors and the probability of avian influenza outbreaks.

[0068] In another exemplary embodiment of the present application, after obtaining the time characteristics and spatial distribution characteristics of avian influenza outbreaks, it further includes: using a geographic information system to perform a spatial overlay analysis on the time characteristics and spatial distribution characteristics of avian influenza outbreaks in the study area to generate a comprehensive risk probability map; determining high-priority level areas, medium-priority level areas, and low-priority level areas according to the comprehensive risk probability map; and comparing the virus detection frequencies of the high-priority level areas, medium-priority level areas, and low-priority level areas based on historical avian influenza outbreak data to obtain a comparison result.

[0069] Perform a spatial overlay analysis using a geographic information system (GIS) to generate a comprehensive risk probability map and identify high-priority level areas, medium-priority level areas, and low-priority level areas. Then, based on historical avian influenza outbreak data, compare the virus detection frequencies of the high-priority level areas with the medium-priority level areas and the low-priority level areas to verify the effectiveness and scientificity of the sampling scheme through frequency comparison.

[0070] Through in-depth mining of historical avian influenza outbreak data by time series analysis, it is found that winter (usually from November to February of the following year) is a high-frequency period for avian influenza outbreaks, and the outbreak frequency is significantly higher than that in other seasons.

[0071] Through model simulation, in this embodiment, an outbreak risk map of avian influenza in animals was obtained, and the main outbreak hotspots were identified. The results showed that the outbreak risks were concentrated in the west coast and the central and eastern regions of the United States, from Europe to northern Central Asia, and from central and eastern China to the far east. The high risks in these regions are closely related to human activities and environmental changes. For example, agriculture and aquaculture are very developed on the west coast of the United States. Abundant water sources and suitable climates make this area a breeding ground for avian influenza viruses. In the area from Europe to northern Central Asia, the current situation of variable climate and frequent human activities, combined with large-scale farming production, also makes this area a region with frequent avian influenza outbreaks. In particular, the change in temperature directly affects the survival and transmission of avian influenza viruses, which largely explains its widespread outbreak in this region. In the area from central and eastern China to the far east, the wide distribution of wetlands and paddy fields provides sufficient habitats for water birds and also promotes the transmission of viruses between wild birds and poultry.

[0072] In addition, this embodiment analyzed the key influencing factors of avian influenza outbreaks. The results showed that for wild birds (Wild), the order of the contribution rates of the influencing factors was the annual minimum temperature (var7) > the annual average temperature (var4) > land use (var1) > the growing season rainfall (var9) > the annual maximum temperature (var5) > the annual rainfall (var8) > the population density (var2) > the annual maximum NDVI (var6) > elevation (var3); for domestic poultry (Domestic), the order of the contribution rates of the influencing factors was the annual minimum temperature (var7) > the annual average temperature (var4) > land use (var1) > the annual maximum temperature (var5) > the annual rainfall (var8) > the population density (var2) > the growing season rainfall (var9) > the annual maximum NDVI (var6) > elevation (var3); for all animals (Total), the order of the contribution rates of the influencing factors was the annual minimum temperature (var7) > the annual average temperature (var4) > land use (var1) > the annual maximum temperature (var5) > the annual rainfall (var8) > the growing season rainfall (var9) > the population density (var2) > the annual maximum NDVI (var6) > elevation (var3). In summary, temperature and land use are two key influencing factors for avian influenza outbreaks. The temperature factor affects the survival ability and environmental suitability of the virus. Under different temperature conditions, the pathogenicity and transmission ability of avian influenza viruses will change significantly. High-temperature and rainy climate conditions are usually closely related to the high risks of avian influenza outbreaks, and these conditions create a favorable environment for the survival and transmission of the virus. Changes in land use directly affect the habitats of animals. In particular, habitat fragmentation caused by human activities increases the contact opportunities between wild animals and domestic poultry, thus increasing the possibility of avian influenza outbreaks. This impact is more obvious in areas with intensive agricultural production.

[0073] Based on the overlay analysis of high-outbreak-risk areas of key influencing factors, a distribution map of the sampling priority levels of avian influenza positive cases was obtained, including high-priority areas, medium-priority areas, and low-priority areas. The incidence risks of avian influenza positive cases in the high-priority, medium-priority, and low-priority levels decrease in turn. The distribution results of the sampling priority levels of avian influenza positive cases in wild birds are as follows: the high-priority area accounts for 95%, the medium-priority area accounts for 4.7%, and the low-priority area accounts for 0.3%; the distribution results of the sampling priority levels of avian influenza positive cases in poultry are as follows: the high-priority area accounts for 66%, the medium-priority area accounts for 32%, and the low-priority area accounts for 2%; the distribution map results of the sampling priority levels of all animal avian influenza positive cases are as follows: the high-priority area accounts for 77%, the medium-priority area accounts for 21%, and the low-priority area accounts for 2%. In this embodiment, the avian influenza data of animals causing diseases from 2014 to 2019 was selected as the basic data set, and the number of disease samples in different sampling priority level areas was compared. The comparison results of the detection rates in different sampling priority ranges are as Figure 3 shown. The results show that the total number of samples and the number of samples per unit area of avian influenza positive cases in the high-priority area are significantly higher than those in the other two levels, which verifies the scientific nature of the sampling method. In the high-priority area, the transmission of avian influenza virus is more active and the risk of avian influenza outbreak is higher. Therefore, in the process of epidemic prevention and control, it is particularly important to conduct key monitoring on high-risk areas in winter.

[0074] This application also provides an application scenario, which applies the above-mentioned sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza. Specifically: The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza provided in this embodiment can be applied in the avian influenza prevention and control scenario. The avian influenza prevention and control scenario includes a content production link, a content processing link, and a content distribution link; multi-source data enters the content processing link from the content production link, obtains the corresponding spatio-temporal distribution characteristics of avian influenza, and enters the downstream content distribution link. The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza provided in this embodiment belongs to the content processing link. Specifically, in the process of the content processing link for multi-source data, an avian influenza outbreak data set can be used to conduct a time series analysis of the outbreak start time by month, count the outbreak frequency per month, determine the avian influenza outbreak time characteristics of the research area, and use the maximum entropy model to identify the avian influenza outbreak risk hotspots and key factors based on the multi-source data, so as to obtain the avian influenza outbreak spatial distribution characteristics of the research area. The avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics constitute the spatio-temporal distribution characteristics of avian influenza.

[0075] Based on the same inventive concept, an embodiment of the present application further provides an avian influenza spatio-temporal distribution feature sampling and monitoring device for implementing the avian influenza spatio-temporal distribution feature sampling and monitoring method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the avian influenza spatio-temporal distribution feature sampling and monitoring device provided below can refer to the limitations on the avian influenza spatio-temporal distribution feature sampling and monitoring method in the above text, and will not be repeated here.

[0076] In an exemplary embodiment, as Figure 4 shown, an avian influenza spatio-temporal distribution feature sampling and monitoring device is provided, which includes the following modules:

[0077] A multi-source data acquisition module T1, configured to acquire multi-source data of the research area; the multi-source data includes an avian influenza outbreak dataset, a land use dataset, a vegetation index dataset, a climate change dataset, a population density dataset, and a terrain dataset;

[0078] An outbreak time feature determination module T2, configured to perform time series analysis on the outbreak start time by month using the avian influenza outbreak dataset, count the outbreak frequency per month, and determine the avian influenza outbreak time feature of the research area;

[0079] A spatial distribution feature determination module T3, configured to use the maximum entropy model to identify the avian influenza outbreak risk hotspots and key factors based on the multi-source data, and obtain the avian influenza outbreak spatial distribution feature of the research area; the avian influenza outbreak time feature and the avian influenza outbreak spatial distribution feature constitute the avian influenza spatio-temporal distribution feature.

[0080] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store avian influenza spatio-temporal distribution processing data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements an avian influenza spatio-temporal distribution feature sampling and monitoring method.

[0081] Those skilled in the art can understand that Figure 5 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0082] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0083] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0084] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0085] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0086] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0087] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0088] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0089] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza, characterized in that, The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza includes: Obtaining multi-source data of the research area; the multi-source data includes an avian influenza outbreak dataset, a land use dataset, a vegetation index dataset, a climate change dataset, a population density dataset, and a terrain dataset; Using the avian influenza outbreak dataset, performing a time series analysis on the start time of the outbreak by month, counting the outbreak frequency per month, and determining the avian influenza outbreak time characteristics of the research area; Using the maximum entropy model, identifying the avian influenza outbreak risk hotspots and key factors based on the multi-source data to obtain the avian influenza outbreak spatial distribution characteristics of the research area; the avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics constitute the avian influenza spatio-temporal distribution characteristics.

2. The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza according to claim 1, wherein The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza further includes: Using a geographic information system to perform a spatial overlay analysis on the avian influenza outbreak time characteristics and the avian influenza outbreak spatial distribution characteristics of the research area to generate a comprehensive risk probability map; Determining a high-priority area, a medium-priority area, and a low-priority area based on the comprehensive risk probability map; Comparing the virus detection frequencies of the high-priority area, the medium-priority area, and the low-priority area according to the historical avian influenza outbreak data to obtain a comparison result.

3. The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza according to claim 1, wherein Obtaining the multi-source data of the research area, specifically including: Obtaining original data; the original data includes the spatio-temporal geographic information data of multiple regions; Performing spatial clipping on the original data to obtain the response data of the research area; Dividing the avian influenza outbreak dataset in the response data of the research area to obtain wild animal avian influenza outbreak data and poultry avian influenza outbreak data; Resampling the response data of the research area to the same spatial resolution to obtain resampled data; Converting the format of the resampled data to obtain the multi-source data of the research area.

4. The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza according to claim 1, wherein, Using the maximum entropy model, identifying the avian influenza outbreak risk hotspots and key factors based on the multi-source data to obtain the avian influenza outbreak spatial distribution characteristics of the research area, specifically including: Taking the avian influenza outbreak dataset as the dependent variable and inputting the land use dataset, the vegetation index dataset, the climate change dataset, the population density dataset, and the terrain dataset as independent variables into the maximum entropy model; Selecting the quadratic Quadratic feature type and obtaining the model prediction result through the maximum entropy principle, and the model prediction result is the avian influenza outbreak spatial distribution characteristics of the research area.

5. The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza according to claim 4, wherein The avian influenza outbreak spatial distribution characteristics include a risk probability map, an influence factor contribution rate, and a response curve; among them, the risk probability map is used to generate the spatial probability distribution map of avian influenza outbreaks within the research area; The influence factor contribution rate is used to calculate the contribution rate of each variable to the model prediction result and identify the key influencing factors; The response curve is used to show the relationship between the key influencing factors and the avian influenza outbreak probability.

6. The sampling and monitoring method for the spatio-temporal distribution characteristics of avian influenza according to claim 1, wherein The avian influenza outbreak dataset includes the avian influenza name, start time, end time, longitude, latitude, and animal category.

7. An avian influenza spatio-temporal distribution characteristic sampling and monitoring device, characterized in that, The sampling and monitoring device for the spatio-temporal distribution characteristics of avian influenza includes: A multi-source data acquisition module for acquiring multi-source data of a research area; the multi-source data includes an avian influenza outbreak dataset, a land use dataset, a vegetation index dataset, a climate change dataset, a population density dataset, and a terrain dataset; An outbreak time feature determination module for performing time series analysis on the outbreak start time by month using the avian influenza outbreak dataset, counting the outbreak frequency per month, and determining the avian influenza outbreak time feature of the research area; A spatial distribution feature determination module for identifying the avian influenza outbreak risk hotspots and key factors based on the multi-source data using the maximum entropy model to obtain the avian influenza outbreak spatial distribution feature of the research area; the avian influenza outbreak time feature and the avian influenza outbreak spatial distribution feature constitute the avian influenza spatio-temporal distribution feature.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the avian influenza spatio-temporal distribution feature sampling and monitoring method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the avian influenza spatio-temporal distribution feature sampling and monitoring method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the avian influenza spatio-temporal distribution feature sampling and monitoring method according to any one of claims 1-6.

Images