Bird disease analysis management and control method and device in combination with ecological environment data

Abstract

The invention discloses a bird disease analysis and control method and device in combination with ecological environment data, and relates to the technical field of bird disease governance, and the method comprises the steps: collecting bird activity rules and historical ecological environment data, building an environment behavior correlation model, and carrying out the dynamic analysis and risk prediction in combination with multi-source ecological and bird data collected in real time, and generating a prediction risk space-time distribution diagram, adjusting a risk grading standard by adopting a dynamic self-adaptive mechanism based on the prediction risk space-time distribution diagram, implementing distributed precise management and control on different risk areas, and performing closed-loop management optimization according to feedback data. The technical problems of poor risk prediction real-time performance and low resource allocation efficiency caused by insufficient dynamic association analysis of bird activities and the ecological environment in an existing bird disease management and control method are solved, and the effects of accurately predicting bird activity risks and improving the risk prediction efficiency by fusing and analyzing the ecological environment and bird activity data are achieved. And the real-time performance of bird disease control and the resource utilization efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bird infestation control, and in particular to a method and device for analyzing and controlling bird infestations in combination with ecological environment data. Background Art

[0002] With the continuous improvement of ecological protection awareness and the intensification of human activities, the relationship between birds and human production and life is becoming increasingly close. In some areas, bird activities may have adverse effects on agricultural production, power facilities, airport operations, etc., and even cause serious economic losses and safety hazards.

[0003] Traditional bird control methods mainly rely on artificial or fixed equipment to drive birds away, and lack the ability to scientifically analyze the patterns of bird activity and dynamically predict risks. Such methods not only waste resources, but may also lead to poor governance effects due to the lag or singleness of response measures. At the same time, bird activities are affected by multiple factors of the ecological environment (such as meteorological conditions and geographical features), and their activity patterns are dynamic in time and space. In the absence of effective analysis and comprehensive management of these complex factors, existing methods are difficult to achieve accurate prediction and dynamic control of bird activities. Summary of the invention

[0004] The present application provides a method and device for analyzing and controlling bird infestations in combination with ecological and environmental data, which is used to solve the technical problems that existing bird infestation control methods are insufficient in analyzing the dynamic correlation between bird activities and the ecological environment, resulting in poor real-time risk prediction and inefficient resource allocation.

[0005] The first aspect of the present application provides a method for analyzing and controlling bird infestations in combination with ecological and environmental data, the method comprising: collecting information on the activity patterns of common birds in the target prevention and control area, conducting environmental behavior correlation analysis in combination with historical ecological and environmental data of the target prevention and control area, and establishing an environmental behavior correlation model; collecting ecological and environmental data and bird activity data in real time, conducting multi-dimensional data fusion analysis, and obtaining multi-source fusion data; using the multi-source fusion data as basic data, inputting the environmental behavior correlation model, conducting dynamic analysis and risk prediction of bird activities, and generating a predicted risk spatiotemporal distribution map; performing regional risk classification according to the predicted risk spatiotemporal distribution map, adjusting the classification standards through a dynamic adaptive mechanism, and performing distributed bird infestation control according to the divided regional risk levels; real-time monitoring of bird infestation control effects and ecological and environmental changes, collecting real-time feedback data, and performing closed-loop optimization of the environmental behavior correlation model and distributed control strategy.

[0006] According to a second aspect of the present application, a bird infestation analysis and control device combined with ecological and environmental data is provided, the device comprising: an environmental behavior association analysis module, the environmental behavior association analysis module is used to collect activity pattern information of common birds in a target prevention and control area, and conduct environmental behavior association analysis in combination with historical ecological and environmental data of the target prevention and control area to establish an environmental behavior association model; a multi-dimensional data fusion analysis module, the multi-dimensional data fusion analysis module is used to collect ecological and environmental data and bird activity data in real time, conduct multi-dimensional data fusion analysis, and obtain multi-source fusion data; an activity risk prediction module, the activity risk prediction module is used to use the multi-source fusion data as basic data, input the environmental behavior association model, conduct dynamic analysis and risk prediction of bird activities, and generate a predicted risk spatiotemporal distribution map; a distributed bird infestation control module, the distributed bird infestation control module is used to perform regional risk classification according to the predicted risk spatiotemporal distribution map, adjust the classification standard through a dynamic adaptive mechanism, and perform distributed bird infestation control according to the divided regional risk level; a closed-loop optimization module, the closed-loop optimization module is used to monitor the bird infestation control effect and ecological and environmental changes in real time, collect real-time feedback data, and perform closed-loop optimization on the environmental behavior association model and the distributed control strategy.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The bird hazard analysis and control method and device combined with ecological environment data provided in the present application relate to the technical field of bird hazard control. By combining the bird activity patterns with ecological environment data, an environmental behavior correlation model is established, multi-source data is collected in real time for dynamic analysis and risk prediction, and a risk spatiotemporal distribution map is generated. By dynamically and adaptively adjusting the classification standards, precise control is implemented for different risk areas, and the control effect and environmental changes are monitored in real time. Feedback optimization models and strategies are collected to build a closed-loop control system. The technical problems that the existing bird hazard control methods are insufficient in dynamic correlation analysis between bird activities and the ecological environment, resulting in poor real-time risk prediction and inefficient resource allocation, are solved. The technical effect of accurately predicting bird activity risks and improving the real-time and resource utilization efficiency of bird hazard control is achieved by integrating and analyzing the ecological environment and bird activity data. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a method for analyzing and controlling bird infestations in combination with ecological environmental data provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the structure of a bird infestation analysis and control device combined with ecological environment data provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: environmental behavior correlation analysis module 11, multi-dimensional data fusion analysis module 12, activity risk prediction module 13, distributed bird control module 14, closed-loop optimization module 15. DETAILED DESCRIPTION

[0012] The present application provides a method and device for analyzing and controlling bird infestations in combination with ecological and environmental data, which is used to solve the technical problems that existing bird infestation control methods are insufficient in analyzing the dynamic correlation between bird activities and the ecological environment, resulting in poor real-time risk prediction and inefficient resource allocation.

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, 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 "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0015] Embodiment 1, as Figure 1 As shown, the present application provides a bird infestation analysis and control method combined with ecological environment data, the method comprising: P10: Collect information on the activity patterns of common birds in the target prevention and control areas, conduct environmental behavior correlation analysis based on historical ecological and environmental data of the target prevention and control areas, and establish an environmental behavior correlation model.

[0016] Furthermore, step P10 of the embodiment of the present application further includes: P11: Based on bird control records, collect information on the activity patterns of common birds in the target prevention and control area, and obtain historical ecological and environmental data of the target prevention and control area; P12: Standardize the activity pattern information and historical ecological and environmental data, and perform environmental behavior correlation analysis through feature screening to extract significant environmental influencing factors of bird activities and establish environment-behavior correlation; P13: Based on the environment-behavior correlation, establish an environmental behavior correlation model.

[0017] It should be understood that by collecting and analyzing information on bird activity patterns and related ecological and environmental data in the target prevention and control areas, a scientific environmental behavior correlation model can be established to provide support for subsequent bird activity predictions and risk management.

[0018] First, based on historical bird control records, comprehensive information on the activity patterns of common birds in the target prevention and control area is collected, including but not limited to activity frequency, population size, migration time, foraging habits, and habitat distribution. This information can reflect the dependence and behavioral characteristics of birds on the ecological environment. At the same time, key data items are extracted from the historical ecological and environmental data of the target area, such as meteorological conditions (temperature, humidity, wind speed, rainfall), geographical characteristics (vegetation coverage, water distribution, terrain characteristics), and human interference information (such as noise levels and human activity frequency). By combining information on bird activity patterns and ecological and environmental data, sufficient basic data can be provided for subsequent correlation analysis.

[0019] It is worth noting that the integrity and timeliness of data are the basis for model construction, so a combination of high-precision sensing equipment (such as radar, cameras, acoustic sensors) and historical records can be used to ensure data coverage and reliability. At the same time, based on geographic information system (GIS) technology, the collected ecological and environmental data can be spatially located and analyzed.

[0020] The collected data usually come from various sources and have different dimensions. For example, the frequency of bird activities is usually count data, while ecological and environmental data may include continuous and categorical data. Therefore, it is necessary to standardize the activity pattern information and historical ecological and environmental data to eliminate dimensional differences and ensure that the data are comparable within the same scale. Then, the feature screening method is used to perform environmental behavior association analysis on the standardized data to extract environmental factors that significantly affect bird activities. The screening process can be achieved through statistical correlation analysis or machine learning methods (such as random forest feature importance analysis). For example, analyze the impact of wind speed, vegetation coverage and noise level on bird migration behavior and extract significant factors from them.

[0021] Finally, based on the extracted significant environmental influencing factors, the environment-behavior association is constructed. The environment-behavior association refers to the process of quantitatively associating the activity patterns of birds with the ecological and environmental variables on which they depend, such as using variables such as wind speed and temperature to predict the activity frequency of birds.

[0022] On this basis, an environmental behavior association model is constructed.

[0023] Furthermore, to construct an environmental behavior association model, step P13 of the embodiment of the present application further includes: P13-1: Based on the environment-behavior association, the bird activity pattern information and historical ecological environment data are converted into multivariate feature indicators, wherein the multivariate feature indicators include benefit-based indicators and cost-based indicators; P13-2: Based on the multivariate feature indicators, a decision matrix framework is generated, and the decision matrix framework is initialized for weight allocation; P13-3: The optimal solution and the worst solution are defined, and the distance calculation rules are designed to construct the environment-behavior association model.

[0024] Optionally, the specific process of establishing the environmental behavior association model may be, first, according to the environment-behavior association, the bird activity law information and historical ecological environment data are converted into multivariate characteristic indicators. Among them, the multivariate characteristic indicators refer to the classification of the original data into benefit indicators and cost indicators according to their effects on bird activities. The benefit indicators refer to environmental factors that have a positive attraction to bird activities, such as vegetation coverage, water area, etc. The higher the value of the benefit indicator, the greater the attraction to birds. The cost indicator refers to an environmental factor that has a negative inhibitory effect on bird activities, such as noise intensity, frequency of human activities, etc. The higher the value of the cost indicator, the stronger the inhibitory effect on birds. The classification of benefit and cost indicators can effectively distinguish the positive and negative effects of different environmental factors on bird activities.

[0025] Furthermore, based on the extracted multivariate characteristic indicators, a decision matrix framework is constructed to form a comprehensive data structure that describes bird activities and environmental conditions in multiple dimensions. Each column of the decision matrix framework represents a characteristic indicator (such as temperature, humidity, wind speed, etc.), and each behavior records a set of specific environmental conditions and the corresponding relationship between bird activities.

[0026] For example, the multivariate characteristic indicators are constructed into a matrix form according to time or space samples to generate a decision matrix framework: ; where m represents the number of samples and n represents the number of features. represents the j-th eigenvalue of the i-th sample.

[0027] In order to ensure that the influence weights of different characteristic indicators in the model are reasonable, the decision matrix framework is initialized with weight allocation, and each characteristic indicator is assigned an initial weight. The setting of weights reflects the relative size of the influence of each indicator on bird activities. For example, suitable temperature may have a more important impact on bird activities than wind speed. Exemplarily, the weights can be calculated based on the information entropy of the indicators to automatically reflect the distribution differences of the indicators. The decision matrix framework converts multidimensional data into a unified analysis structure, which is convenient for subsequent calculations and model optimization, and the weight allocation determines the contribution of the features to the results. Its dynamic adjustment capability enhances the adaptability of the model.

[0028] Furthermore, based on the decision matrix framework, the optimal solution and the worst solution of the target behavior are defined, and calculation rules are designed to quantify the correlation of each sample. The optimal solution refers to the ideal state under the conditions where all benefit indicators are maximized and cost indicators are minimized, which is used as a positive reference in the analysis. For example, environmental conditions with moderate temperature, suitable humidity and minimum noise interference can be regarded as the optimal solution. The worst solution represents an extremely unfavorable state under the conditions where all benefit indicators are minimized and cost indicators are maximized, which is used as a negative reference in the analysis. The distance calculation rule refers to evaluating the risk correlation of each sample in the multidimensional feature space by calculating the relative distance of the sample data to the optimal solution and the worst solution.

[0029] In summary, the construction of the environmental behavior association model was completed through the scientific transformation of multivariate characteristic indicators, the structured generation of the decision matrix framework, and the quantitative design of the distance between the optimal solution and the worst solution. This model can effectively support the dynamic analysis of bird activity patterns and provide a reliable theoretical basis and technical support for subsequent risk prediction and control.

[0030] P20: Collect ecological environment data and bird activity data in real time, conduct multi-dimensional data fusion analysis, and obtain multi-source fusion data.

[0031] Furthermore, step P20 of the embodiment of the present application further includes: P21: Based on a preset collection cycle, collect ecological environment data and bird activity data of the target area in real time; P22: After aligning the ecological environment data and bird activity data in time and space, perform multi-dimensional feature clustering to generate the multi-source fusion data.

[0032] Specifically, in order to achieve accurate monitoring and dynamic analysis of the ecological environment and bird activities in the target area, multi-source fusion data is generated through real-time data collection and multi-dimensional data fusion, providing high-quality basic data support for subsequent analysis and prediction.

[0033] First, based on the preset collection cycle, the ecological environment data and bird activity data of the target area are collected in real time to ensure the dynamic update and integrity of the data. The preset collection cycle refers to the data collection time interval set according to the actual application requirements, such as once every hour or every day, to ensure that the collection frequency meets the analysis requirements and optimizes resource utilization. Based on the preset collection cycle, with the help of meteorological stations and drone remote sensing technology, the environmental variables of the target area are collected, including meteorological data (such as temperature, humidity, wind speed, precipitation) and geographic information (such as vegetation coverage, water body distribution), and the ecological environment data is generated. Through video monitoring, radar detection or sensor networks, the activity trajectory, species distribution and behavioral characteristics of birds are obtained to generate bird activity data.

[0034] Furthermore, the collected ecological environment data and bird activity data are aligned in time and space. First, different data sources are synchronized on the same time axis, such as unifying the temperature, humidity and bird activity information collected by different devices to the same time node to ensure the timeliness and consistency of the analysis. Then, based on geographic information, the collected data is unified into the same spatial range or grid area. For example, GPS positioning is used to accurately locate the data to a specific location within the prevention and control area, which is convenient for regional analysis.

[0035] After completing the time and space alignment, the ecological environment data and bird activity data are subjected to feature extraction and cluster analysis. Clustering algorithms (such as K-means and DBSCAN) are used to identify the potential associations between ecological environment factors (such as temperature and wind speed) and bird activity patterns based on the similarity and regularity of the data, and the data are grouped to generate multi-source fusion data. The structured output of multi-source fusion data contains association information of different feature dimensions, such as the correspondence between the environmental conditions of a certain area in a specific time period and the frequency of bird activities. The multi-source fusion data can comprehensively reflect the ecological environment characteristics and bird activity patterns of the target area, laying a solid data foundation for dynamic analysis, risk prediction and bird control.

[0036] P30: Taking the multi-source fusion data as basic data, input the environmental behavior association model to conduct dynamic analysis and risk prediction of bird activities, and generate a predicted risk spatiotemporal distribution map.

[0037] Furthermore, step P30 of the embodiment of the present application further includes: P31: Input the multi-source fusion data into the environmental behavior association model, perform decision matrix framework assignment and feature index weight optimization, and generate a target decision matrix; P32: Based on the target decision matrix, calculate the risk correlation to obtain the sample risk correlation; P33: Based on the sample risk correlation, combined with the sample time dimension information and the sample space dimension information, identify the risk area and generate a predicted risk spatiotemporal distribution map.

[0038] It should be understood that by inputting multi-source fusion data into the environmental behavior association model, dynamically analyzing bird activities, and generating predicted risk spatiotemporal distribution maps through risk prediction, a scientific basis is provided for precise bird control.

[0039] First, the multi-source fusion data is input into the environmental behavior association model, and the decision matrix framework is assigned and the characteristic index weight is optimized to generate the target decision matrix. Among them, the decision matrix assignment refers to filling the corresponding characteristic index in the decision matrix framework according to the characteristic values ​​in the multi-source fusion data. For example, data such as temperature and humidity in the ecological environment, as well as the frequency and distribution of bird activities, are assigned to the corresponding positions of the matrix to form a multi-dimensional data representation. The characteristic index weight optimization refers to dynamically adjusting the weight of different characteristic indicators according to the degree of influence on bird activities. For example, the weight of key indicators (such as the impact of temperature on bird migration) is increased through optimization algorithms (such as entropy weight method or genetic algorithm), and the influence of secondary indicators is weakened, thereby improving the scientificity and accuracy of the matrix.

[0040] Furthermore, based on the target decision matrix, the sample risk correlation is calculated to quantify the risk impact of different samples on bird activities. The sample risk correlation refers to the quantitative relationship between different samples (time points or spatial areas) and risk states. The calculation process can be to first define the optimal solution (ideal conditions) and the worst solution (extremely unfavorable conditions), and use this as a reference standard for analysis, calculate the relative distance from the sample data to the optimal solution and the worst solution, for example, through the Euclidean distance formula, obtain the risk deviation degree of each sample, that is, the relative distance, and calculate the comprehensive risk correlation of the sample based on these relative distances to form a sample risk correlation set.

[0041] Furthermore, based on the sample risk correlation, combined with the time and space information of the sample, risk area identification is performed, and the sample risk correlation is mapped to a specific time point and spatial area to identify high-risk, medium-risk and low-risk areas. For example, a clustering algorithm is used to divide adjacent high-risk areas into risk hotspots to form a clear division of risk areas. Then, the changing trends of different risk areas are marked in the time dimension, and a regional distribution map is drawn in the spatial dimension. The spatiotemporal distribution map intuitively reflects the dynamic risk situation of bird activities and can provide an important basis for the formulation of prevention and control strategies.

[0042] Furthermore, step P32 of the embodiment of the present application also includes: P32-1: Based on the target decision matrix, calculate the optimal solution and the worst solution; P32-2: Extract sample data according to the target decision matrix, and calculate the sample relative distance of each sample data to the optimal solution and the worst solution; P32-3: Based on the sample relative distance, calculate the sample risk correlation and generate a sample risk correlation set.

[0043] Wherein, based on the target decision matrix, the optimal solution and the worst solution are calculated, including: , ; in, is the optimal solution, is the worst solution, is a profit indicator. is a cost-based indicator. Represents the jth environmental factor value of the i-th time or regional sample.

[0044] Optionally, based on the target decision matrix, define and calculate the optimal solution and the worst solution to construct a benchmark reference for risk association. The optimal solution consists of the maximum value of all benefit indicators and the minimum value of cost indicators, representing the environmental conditions under ideal conditions, and the formula is as follows: , the worst solution is composed of the minimum value of all benefit indicators and the maximum value of cost indicators, indicating the environmental conditions under extremely unfavorable conditions. The formula is as follows: ;in, is a collection of profit indicators. is a collection of cost-type indicators, It represents the jth environmental factor value of the i-th time or regional sample. In addition, the maximum and minimum values ​​of the indicator can be directly extracted from the decision matrix, and the data can be scanned and screened using statistical methods to ensure the accuracy of the calculation.

[0045] Furthermore, the sample data in the target decision matrix is ​​extracted, and the relative distance of each sample to the optimal solution and the worst solution is calculated using the Euclidean distance formula: ; ;in, and Respectively represent the distance from sample i to the optimal solution and the worst solution, is the weight of the jth indicator. Through distance calculation, the deviation degree of the sample in the multidimensional feature space can be quantified, further revealing the risk status of the sample.

[0046] Calculate the sample risk association based on the relative distance of the samples: ;in, is the sample risk correlation of sample i, which is between 0 and 1. The closer the value is to 1, the higher the risk of the sample; the closer the value is to 0, the lower the risk of the sample. The risk correlation results of all samples are stored as a set , which will serve as the basis for subsequent risk area identification.

[0047] P40: Carry out regional risk classification based on the predicted risk spatiotemporal distribution map, adjust the classification standards through a dynamic adaptive mechanism, and conduct distributed bird control according to the classified regional risk levels.

[0048] In a possible embodiment of the present application, the target area is graded for risk by analyzing the predicted risk spatiotemporal distribution map, and the grading standards are adjusted in real time in combination with a dynamic adaptive mechanism, thereby achieving scientific and efficient distributed bird control.

[0049] For example, first, based on the predicted risk spatiotemporal distribution map, the target area is classified according to the risk level, and high-risk, medium-risk and low-risk areas are identified. The initial classification standard can be set by historical data and risk correlation statistical results, such as dividing the risk threshold: high risk (risk correlation >0.7), medium risk (0.3≤ ≤0.7), low risk ( <0.3). At the same time, according to the spatiotemporal characteristics of the risk distribution map, continuously distributed high-risk points are divided into concentrated areas to form identifiable risk hotspots. For example, in some bird migration concentration areas, multiple adjacent high-risk samples may appear, which need to be merged into an overall area.

[0050] Furthermore, considering the dynamic characteristics of ecological environment and bird activities, a dynamic adaptive mechanism is used to optimize the risk classification standards in real time. By analyzing the real-time monitoring data, the risk classification threshold is dynamically adjusted according to the current environmental conditions (such as weather changes and seasonal influences). For example, during the migration season, the high risk threshold can be lowered (such as adjusted to >0.6), improving the sensitivity of risk identification. The adaptive mechanism can be rule-driven or model-driven based on machine learning. Rule-driven adjusts the classification standards based on preset conditions, while machine learning models can predict the best classification strategy based on historical trends, such as using Bayesian optimization algorithms or reinforcement learning methods to improve the accuracy and timeliness of classification.

[0051] Furthermore, according to the risk level of the divided regions, differentiated distributed bird control strategies are implemented to optimize resource allocation and improve control efficiency. For example, key intervention measures are taken for high-risk areas, such as deploying ultrasonic repellent devices, using drones for active dispersal, or reducing attractiveness through environmental adjustments (such as vegetation pruning). For the control of medium-risk areas, routine monitoring and early warning measures are implemented, such as installing video surveillance systems or acoustic detection equipment, closely observing the trend of risk changes, and reserving rapid response measures. For the control of low-risk areas, basic monitoring is mainly used to reduce resource investment, while tracking and recording environmental changes so as to intervene quickly when risks escalate. Distributed control relies on an efficient resource scheduling system, such as the intelligent networking and collaborative control of various monitoring and intervention equipment through the Internet of Things technology, thereby maximizing resource utilization.

[0052] P50: Monitor the bird control effect and ecological environment changes in real time, collect real-time feedback data, and perform closed-loop optimization of the environmental behavior association model and distributed control strategy.

[0053] Specifically, by real-time monitoring of bird control effects and ecological environment changes, building a closed-loop feedback mechanism, and continuously optimizing environmental behavior correlation models and distributed control strategies, we can achieve continuous improvement and efficient operation of bird control.

[0054] Real-time monitoring is the basis of closed-loop optimization. Through an efficient data collection system, the bird control effect and the ecological environment changes in the target area are dynamically monitored, including the actual effect of monitoring control measures in high-risk areas, such as recording changes in bird activity frequency through video monitoring, and evaluating whether the intervention effect of repelling measures (such as ultrasonic bird repellent equipment or drone dispersal) has achieved the expected goal. Collect real-time ecological and environmental data in the target area (such as temperature, humidity, wind speed, vegetation cover changes, etc.) to analyze whether there are significant changes in environmental conditions, which may directly affect the activity patterns of birds and risk distribution.

[0055] During the monitoring process, bird activity data, the effects of control measures, and ecological environment change data are collected to form real-time feedback data. Based on the real-time feedback data, the environmental behavior association model is continuously optimized to enhance the model's adaptability and predictive ability to dynamic changes. Exemplarily, the weights of significant environmental factors are updated according to environmental changes and control effects. For example, the impact of humidity on bird activity becomes stronger over a period of time, and the distribution ratio of feature weights in the model needs to be adjusted. Use the newly collected feedback data to retrain the environmental behavior association model to improve the model's prediction accuracy and robustness.

[0056] At the same time, the distributed control strategy is dynamically optimized based on the latest predicted risk distribution and control effects. For example, when the risk level of a high-risk area is reduced to medium risk, resource allocation can be adjusted to reduce the intervention in that area, while transferring resources to other high-risk areas. The closed-loop optimization mechanism is used to achieve continuous evolution of models and strategies, improving the accuracy and efficiency of bird control.

[0057] In summary, the embodiments of the present application have at least the following technical effects: This application combines the activity patterns of birds with ecological and environmental data to establish an environmental behavior correlation model, collects multi-source data in real time for dynamic analysis and risk prediction, generates a risk spatiotemporal distribution map, and dynamically and adaptively adjusts the classification standards to implement precise control of different risk areas. It also monitors the control effects and environmental changes in real time, collects feedback to optimize models and strategies, builds a closed-loop governance system, and improves the accuracy and efficiency of bird control.

[0058] The technical effect of integrating and analyzing ecological environment and bird activity data to accurately predict bird activity risks and improve the real-time nature and resource utilization efficiency of bird control has been achieved.

[0059] Embodiment 2, based on the same inventive concept as the bird disaster analysis and control method combined with ecological environment data in the above embodiment, Figure 2 As shown, the present application provides a bird infestation analysis and control device combined with ecological environment data, and the device and method embodiments in the present application embodiment are based on the same inventive concept. Among them, the device includes: The environmental behavior association analysis module 11 is used to collect the activity pattern information of common birds in the target prevention and control area, conduct environmental behavior association analysis based on the historical ecological environment data of the target prevention and control area, and establish an environmental behavior association model.

[0060] The multi-dimensional data fusion analysis module 12 is used to collect ecological environment data and bird activity data in real time, perform multi-dimensional data fusion analysis, and obtain multi-source fusion data.

[0061] The activity risk prediction module 13 is used to use the multi-source fusion data as basic data, input the environmental behavior association model, perform dynamic analysis and risk prediction of bird activities, and generate a predicted risk spatiotemporal distribution map.

[0062] The distributed bird infestation control module 14 is used to perform regional risk classification according to the predicted risk spatiotemporal distribution map, adjust the classification standard through a dynamic adaptive mechanism, and perform distributed bird infestation control according to the divided regional risk levels.

[0063] The closed-loop optimization module 15 is used to monitor the bird control effect and ecological environment changes in real time, collect real-time feedback data, and perform closed-loop optimization on the environmental behavior association model and distributed control strategy.

[0064] Furthermore, the environment behavior association analysis module 11 is also used to perform the following steps: Based on bird control records, collect information on the activity patterns of common birds in the target prevention and control area, and obtain historical ecological and environmental data of the target prevention and control area; perform data standardization on the activity pattern information and historical ecological and environmental data, and perform environmental behavior correlation analysis through feature screening to extract significant environmental influencing factors of bird activities and establish environment-behavior correlation; based on the environment-behavior correlation, establish an environmental behavior correlation model.

[0065] Furthermore, the environment behavior association analysis module 11 is also used to perform the following steps: Based on the environment-behavior association, the bird activity pattern information and historical ecological environment data are converted into multivariate feature indicators, wherein the multivariate feature indicators include benefit-type indicators and cost-type indicators; based on the multivariate feature indicators, a decision matrix framework is generated, and the decision matrix framework is initialized with weight allocation; the optimal solution and the worst solution are defined, and the distance calculation rules are designed to construct the environment-behavior association model.

[0066] Furthermore, the multi-dimensional data fusion analysis module 12 is also used to perform the following steps: Based on a preset collection cycle, the ecological environment data and bird activity data of the target area are collected in real time; after the ecological environment data and bird activity data are aligned in time and space, multi-dimensional feature clustering is performed to generate the multi-source fusion data.

[0067] Furthermore, the activity risk prediction module 13 is also used to perform the following steps: The multi-source fusion data is input into the environmental behavior association model, and the decision matrix framework is assigned and the characteristic index weights are optimized to generate a target decision matrix; based on the target decision matrix, the risk correlation degree is calculated to obtain the sample risk correlation degree; based on the sample risk correlation degree, combined with the sample time dimension information and the sample space dimension information, the risk area is identified to generate a predicted risk spatiotemporal distribution map.

[0068] Furthermore, the activity risk prediction module 13 is also used to perform the following steps: Based on the target decision matrix, the optimal solution and the worst solution are calculated; sample data are extracted according to the target decision matrix, and the sample relative distance from each sample data to the optimal solution and the worst solution is calculated; based on the sample relative distance, the sample risk correlation is calculated to generate a sample risk correlation set.

[0069] Furthermore, the activity risk prediction module 13 is also used to perform the following steps: , ;in, is the optimal solution, is the worst solution, is a profit indicator. is a cost-based indicator. Represents the jth environmental factor value of the i-th time or regional sample.

[0070] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0072] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A bird-infestation analysis and control method combined with ecological environment data, characterized in that: The method comprises: Collect information on the activity patterns of common birds in the target control area, conduct environmental behavior correlation analysis based on historical ecological environment data in the target control area, and establish an environmental behavior correlation model; Collect ecological environment data and bird activity data in real time, conduct multi-dimensional data fusion analysis, and obtain multi-source fusion data; Taking the multi-source fusion data as basic data, inputting the environmental behavior association model, performing dynamic analysis and risk prediction of bird activities, and generating a predicted risk spatiotemporal distribution map; Performing regional risk classification according to the predicted risk spatiotemporal distribution map, adjusting classification standards through a dynamic adaptive mechanism, and performing distributed bird infestation control according to the classified regional risk levels; Monitor the bird control effect and ecological environment changes in real time, collect real-time feedback data, and perform closed-loop optimization of the environmental behavior association model and distributed control strategy.

2. The bird infestation analysis and control method combined with ecological environment data as claimed in claim 1, characterized in that: Collect the activity patterns of common birds in the target control area, conduct environmental behavior correlation analysis based on the historical ecological environment data of the target control area, and establish an environmental behavior correlation model, including: Based on bird control records, collect information on the activity patterns of common birds in the target control area, and obtain historical ecological environment data in the target control area; The activity pattern information and historical ecological environment data are processed in a standardized manner, and environmental-behavior correlation analysis is performed through feature screening to extract significant environmental influencing factors of bird activities and establish environment-behavior correlation; Based on the environment-behavior association, an environment-behavior association model is established.

3. The bird infestation analysis and control method combined with ecological environment data as claimed in claim 2, characterized in that: Based on the environment-behavior association, an environment-behavior association model is established, including: Based on the environment-behavior association, the bird activity law information and historical ecological environment data are converted into multivariate characteristic indicators, wherein the multivariate characteristic indicators include benefit-type indicators and cost-type indicators; Based on the multivariate characteristic index, a decision matrix framework is generated, and initialization weight allocation is performed on the decision matrix framework; The optimal solution and the worst solution are defined, and the distance calculation rules are designed to construct the environmental behavior association model.

4. The bird infestation analysis and control method combined with ecological environment data as claimed in claim 1, characterized in that: Collect ecological environment data and bird activity data in real time, conduct multi-dimensional data fusion analysis, and obtain multi-source fusion data, including: Based on the preset collection cycle, collect ecological environment data and bird activity data of the target area in real time; After the ecological environment data and the bird activity data are aligned in time and space, multi-dimensional feature clustering is performed to generate the multi-source fusion data.

5. The bird infestation analysis and control method combined with ecological environment data as claimed in claim 3, characterized in that: Taking the multi-source fusion data as basic data, the environmental behavior association model is input to perform dynamic analysis and risk prediction of bird activities, and generate a predicted risk spatiotemporal distribution map, including: Input the multi-source fusion data into the environmental behavior association model, perform decision matrix framework assignment and feature index weight optimization, and generate a target decision matrix; Based on the target decision matrix, risk correlation is calculated to obtain sample risk correlation; According to the sample risk correlation, combined with the sample time dimension information and the sample space dimension information, risk area identification is performed to generate a predicted risk spatiotemporal distribution map.

6. The bird infestation analysis and control method combined with ecological environment data as claimed in claim 5, characterized in that: Based on the target decision matrix, the risk correlation degree is calculated to obtain the sample risk correlation degree, including: Based on the target decision matrix, calculate and obtain the optimal solution and the worst solution; Extracting sample data according to the target decision matrix, and calculating the sample relative distances of each sample data to the optimal solution and the worst solution; According to the sample relative distance, the sample risk association degree is calculated to generate a sample risk association degree set.

7. The bird infestation analysis and control method combined with ecological environment data as claimed in claim 6, characterized in that: Based on the target decision matrix, the optimal solution and the worst solution are calculated, including: ， ； in, is the optimal solution, is the worst solution, is a profit indicator. is a cost-based indicator. Represents the jth environmental factor value of the i-th time or regional sample.

8. A bird-infestation analysis and control device combined with ecological environment data, characterized in that: The device comprises: An environmental behavior association analysis module, which is used to collect information on the activity patterns of common birds in the target prevention and control area, conduct environmental behavior association analysis based on historical ecological environment data in the target prevention and control area, and establish an environmental behavior association model; A multi-dimensional data fusion analysis module, which is used to collect ecological environment data and bird activity data in real time, perform multi-dimensional data fusion analysis, and obtain multi-source fusion data; An activity risk prediction module, wherein the activity risk prediction module is used to use the multi-source fusion data as basic data, input the environmental behavior association model, perform dynamic analysis and risk prediction of bird activities, and generate a predicted risk spatiotemporal distribution map; A distributed bird infestation control module, which is used to perform regional risk classification according to the predicted risk spatiotemporal distribution map, adjust the classification standard through a dynamic adaptive mechanism, and perform distributed bird infestation control according to the divided regional risk levels; A closed-loop optimization module is used to monitor the bird control effect and ecological environment changes in real time, collect real-time feedback data, and perform closed-loop optimization on the environmental behavior association model and distributed control strategy.

Images