Intelligent Management Platform for Wildlife Resources Protection

Abstract

The present invention discloses an intelligent management platform for the protection of wild animal and plant resources, which relates to the field of intelligent management technology. The method includes: a global static monitoring sub-network construction module for arranging a global static monitoring sub-network based on wild plant distribution data; a historical record data acquisition module for extracting data on activity areas, migration channels and time points; a key index screening module for screening key activity areas, migration channels and migration time points; a patrol path planning module for planning a primary dynamic patrol path; and a protection area monitoring module. The present invention solves the technical problems in the prior art that the traditional wild animal and plant monitoring methods rely on fixed monitoring devices or manual patrols, with an incomplete protection scope, low monitoring efficiency and low accuracy, and achieves the technical effect of improving the comprehensiveness, accuracy and efficiency of wild animal and plant resource protection by combining static monitoring with dynamic patrol.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management, and particularly to an intelligent management platform for the protection of wild animal and plant resources. Background Art

[0002] In the field of wild animal and plant resource protection, with the continuous increase of global climate change, ecological environment damage and human activities, the habitats of wild animals and plants are facing severe challenges, and the numbers of many wild species have decreased sharply or are even on the verge of extinction. Therefore, it is particularly important to establish an efficient wild animal and plant resource protection management system for continuous and comprehensive monitoring and management.

[0003] Traditional field monitoring methods usually rely on manual inspections and fixed monitoring devices. Although these methods play a certain monitoring role to some extent, there are problems such as low inspection frequency, limited monitoring range, and untimely data analysis, and they cannot meet the real-time dynamic monitoring requirements of wild animals and plants in large-scale and complex environments. Summary of the Invention

[0004] This application provides an intelligent management platform for the protection of wild animal and plant resources, which is used to solve the technical problems in the prior art that the traditional wild animal and plant monitoring methods rely on fixed monitoring devices or manual inspections, the protection scope is not comprehensive, and the monitoring efficiency and accuracy are low.

[0005] This application provides an intelligent management platform for the protection of wild animal and plant resources. The platform includes: a global static monitoring sub-network construction module, which is used to retrieve the wild plant distribution data of the target protection area, arrange global static monitoring devices based on the wild plant distribution data, and construct a global static monitoring sub-network; a historical record data acquisition module, which is used to retrieve K wild animal types in the target protection area, retrieve the historical record data of the target protection area based on the K wild animal types, and obtain K sets of historical main activity areas, K sets of migration channels, and K sets of migration time points, where K is an integer greater than or equal to 1; a key index screening module, which is used to respectively conduct centralized screening on the K sets of historical main activity areas, K sets of migration channels, and the K sets of migration time points to determine K key activity areas, K key migration channels, and K key migration time points; a patrol path planning module, which is used to plan the patrol paths of the primary dynamic monitoring devices based on the K key activity areas, K key migration channels, and K key migration time points to determine K primary dynamic patrol paths; a protection area monitoring module, which is used to conduct protection monitoring on the target protection area based on the global static monitoring sub-network and the K primary dynamic patrol paths, and transmit the monitoring data to the intelligent management platform for processing to obtain the protection area monitoring results.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The intelligent management platform for wildlife and plant resources protection provided in this application relates to the field of intelligent management technology. By retrieving plant distribution data to deploy a static monitoring sub-network, obtaining historical activity data of K wild animals, screening key activity areas and migration channels, planning dynamic inspection paths, and combining static and dynamic monitoring for data processing, it realizes the monitoring of protected areas, solves the technical problems in the prior art that the traditional monitoring methods for wildlife and plants rely on fixed monitoring devices or manual inspections, with incomplete protection scope, low monitoring efficiency and low accuracy, and achieves the technical effect of improving the comprehensiveness, accuracy and efficiency of wildlife and plant resources protection by combining static monitoring and dynamic inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 It is a schematic structural diagram of the intelligent management platform for wildlife and plant resources protection provided in the embodiments of this application;

[0010] Figure 2 It is a schematic flowchart of determining K key activity areas, K key migration channels and K key migration time points in the intelligent management platform for wildlife and plant resources protection provided in the embodiments of this application.

[0011] Description of reference numerals: Global static monitoring sub-network construction module 11, historical record data acquisition module 12, key index screening module 13, inspection path planning module 14, protected area monitoring module 15. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] This application provides an intelligent management platform for wildlife and plant resources protection, which is used to solve the technical problems in the prior art that the traditional monitoring methods for wildlife and plants rely on fixed monitoring devices or manual inspections, with incomplete protection scope, low monitoring efficiency and low accuracy.

[0013] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to 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 of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present 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 do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, platform, product or server comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0015] Embodiment, such as Figure 1 As shown, the present application provides an intelligent management platform for the protection of wild animal and plant resources. The platform includes:

[0016] A global static monitoring sub-network construction module 11, configured to retrieve wild plant distribution data of a target protection area, and based on the wild plant distribution data, deploy global static monitoring devices to construct a global static monitoring sub-network.

[0017] Furthermore, the global static monitoring sub-network construction module 11 is further configured to perform the following steps:

[0018] P11: Extract plant height characteristics based on the wild plant distribution data to determine the wild plant height distribution characteristics; P12: Extract plant distribution density characteristics from the wild plant distribution data to obtain the wild plant density distribution characteristics; P13: Based on the wild plant height distribution characteristics and the wild plant density distribution characteristics, deploy global static monitoring devices to construct a global static monitoring sub-network.

[0019] It should be understood that the main function of the global static monitoring sub-network construction module 11 of the present application is to retrieve the wild plant distribution data of the target protection area, and based on these data, reasonably deploy global static monitoring devices, and finally construct a global static monitoring sub-network.

[0020] First, during the process of constructing the global static monitoring sub-network, the plant height is an important factor that cannot be ignored. Based on the obtained wild plant distribution data, the height characteristics of the plants are extracted. The plant height characteristics refer to the average height of different types of plants within the protected area and the range of their height variations. The plant height characteristics can be automatically extracted from the wild plant distribution data through image processing techniques and machine learning algorithms. By analyzing these height characteristics, the system can determine the coverage of plants in different areas and determine the viewing angle and coverage range when installing monitoring devices. For example, in areas with higher vegetation height, the monitoring devices need to be installed at a higher position to ensure that the entire monitoring area can be covered.

[0021] In addition to height, the distribution density of wild plants is also a key factor determining the layout density and location of monitoring devices. Spatial analysis techniques and statistical models can be used to deeply analyze the wild plant distribution data and calculate the plant density distribution characteristics in each area. The plant distribution density characteristics describe the number or coverage of plants per unit area, and these characteristics reveal the aggregation degree and spatial distribution pattern of the plant community, providing a scientific basis for optimizing the layout of monitoring devices. In high-density areas, more intensive monitoring devices may be required to ensure comprehensive coverage; while in low-density areas, the layout density can be appropriately reduced to save costs.

[0022] Finally, the global static monitoring devices are laid out by integrating the plant height distribution characteristics and the plant density distribution characteristics. Considering various factors such as terrain, climate, and lighting conditions, the optimal layout plan for monitoring devices is planned through intelligent algorithms. The selection of monitoring devices is also customized according to specific requirements, such as high-definition cameras, infrared sensors, vibration sensors, etc., to achieve all-weather and omnidirectional monitoring of the target protected area. During the layout process, the interconnection and data sharing between monitoring devices should be realized to ensure that the constructed global static monitoring sub-network can form an organic whole. Through wireless communication technology, each monitoring device can transmit monitoring data to the intelligent management platform in real time to achieve centralized processing and analysis of the data.

[0023] The historical record data acquisition module 12 is used to retrieve the K types of wild animals in the target protected area, and based on the K types of wild animals, retrieve the historical record data of the target protected area to obtain K sets of historical main activity areas, K sets of migration channels, and K sets of migration time points, where K is an integer greater than or equal to 1.

[0024] Optionally, the function of the historical record data acquisition module 12 of the present application is to retrieve historical data related to K wild animal types from the target protection area, and then conduct in-depth analysis on the activities and migration behaviors of these animals, and extract K sets of historical main activity areas, K sets of migration channels, and K sets of migration time points. Here, K represents the number of wild animal species, which is an integer greater than or equal to 1.

[0025] First, retrieve the historical record data related to K wild animal types within the target area. The wild animal types refer to different species observed in this protection area, and the activity habits, habitats, and migration behaviors of each species may vary. By selecting K representative or key species, the system can conduct more targeted monitoring and analysis of the animal activities in this area.

[0026] Next, for each wild animal type, through data analysis techniques such as big data analysis and machine learning algorithms, conduct in-depth analysis on the behavior patterns of each wild animal, and further analyze the main activity areas of each animal, including the key areas where wild animals inhabit and forage daily. By analyzing the activity data of animals over a period of time in the past, obtain K sets of historical main activity areas, so as to determine the specific locations where animals often move in the protection area.

[0027] Subsequently, for wild animals with migration habits, pay special attention to their migration routes. By tracking historical migration records, extract the set of migration channels. The migration channel refers to the path that animals move when seasons or environmental conditions change, and is usually closely related to natural terrain, food sources, and climate conditions. By analyzing these migration channels, the system can predict the possible future migration routes of animals and adjust the layout of the monitoring network according to these routes.

[0028] Finally, extract the set of migration time points for each wild animal, that is, when the animal starts to migrate and the time period during which the migration lasts. These time points are often closely related to seasonal changes, food supply, and breeding cycles. By mastering these key time points, the system can strengthen monitoring during the peak period of animal migration to ensure real-time tracking of animal behaviors.

[0029] After the analysis and processing of the above steps, integrate the sets of historical main activity areas, migration channels, and migration time points corresponding to K wild animal types, and output them to the intelligent management platform in a structured form. These results not only provide important basis for subsequent inspection path planning, protection area monitoring, etc., but also provide valuable ecological data support for scientific researchers and decision-makers.

[0030] The key index screening module 13 is used to respectively conduct centralized screening on the K historical main activity area sets, the K migration route sets, and the K migration time point sets to determine K key activity areas, K key migration routes, and K key migration time points.

[0031] Further, as Figure 2 shown, the key index screening module 13 is further used to perform the following steps:

[0032] P31: respectively conduct area intersection recognition on the K historical main activity area sets to determine K historical main activity intersection areas; P32: based on the overlapping situation of the K historical main activity area sets, perform edge transition expansion on the K historical main activity intersection areas to determine K key activity areas; P33: conduct area edge centralized screening on the K migration route sets to obtain the K key migration routes; P34: conduct time point centralized density screening on the K migration time point sets to determine the K key migration time points.

[0033] In a possible embodiment of the present application, the main function of the key index screening module 13 of the present application is to conduct centralized screening on the K historical main activity area sets, the K migration route sets, and the K migration time point sets to determine key activity areas, migration routes, and migration time points.

[0034] First, conduct area intersection recognition on the K historical main activity area sets, that is, identify the overlapping parts of multiple historical wildlife activity areas. Among them, the area intersection refers to the parts where multiple animal activity areas overlap or cross in space, and these intersection areas often represent the key areas where multiple animals frequently move. By using the area intersection recognition algorithm in spatial analysis technology, by comparing the geographical locations and boundaries of areas in different sets, find out their overlapping parts, that is, the K historical main activity intersection areas. These intersection areas may be the areas with the richest biodiversity in the ecosystem and are also the areas that should be focused on in conservation work.

[0035] Next, considering that the activity range of wild animals is not fixed and may be affected by various factors such as seasons, climate, and food supply, based on the overlapping situation of the K historical main activity area sets, perform edge transition expansion on the already identified intersection areas. Exemplarily, use the edge transition expansion technology to expand these intersection areas. This technology is based on the activity habits and ecological needs of wild animals, simulates the movement paths and range expansion trends of animals in the natural environment, so as to determine a more extensive and reasonable K key activity areas. These areas not only cover the original intersection areas but also consider the possible activity boundaries and potential habitats of wild animals.

[0036] Furthermore, the migration route is a key path that wild animals pass through during migration and is crucial for protecting the smooth passage of migratory animals. Therefore, the path optimization and edge detection algorithms in spatial analysis are used to carefully analyze each path in the set of migration routes. By identifying the edge features and width changes of the routes, migration routes with moderate width, good connectivity, and high usage rate are selected to obtain K key migration routes. These routes are the main movement paths of animals during migration and can be used as key areas for inspection and monitoring.

[0037] Finally, density screening of time points is performed on the set of K migration time points. Migration time points are key time nodes in the migration process of wild animals and are of great significance for formulating protection strategies and emergency response plans. Time series analysis and density clustering algorithms are used to process the set of migration time points. By calculating the density and frequency distribution characteristics of migration activities at each time point, K time points with the most concentrated and critical migration activities are identified. These time points will be used as time nodes that require special attention and preparation in the protection work to ensure that migratory animals can smoothly cross the protected area and reach their destinations safely.

[0038] Through the above steps, key indicators that are most instructive for the protection of wild animal and plant resources are refined from a large amount of historical data, including K key activity areas, K key migration routes, and K key migration time points. The determination of these key indicators will provide strong data support and a scientific basis for subsequent inspection path planning, protected area monitoring, and the formulation of protection strategies.

[0039] Furthermore, step P32 in the embodiment of the present application further includes:

[0040] P32-1: Identify pre-expanded areas for the K historical main activity intersection areas according to a preset transition step size to determine K pre-expanded areas; P32-2: Calculate K pre-expansion factors for the K pre-expanded areas according to the overlapping situation of the K historical main activity area sets, where the pre-expansion factor is the ratio of the area of the overlapping area in each pre-expanded area to the area of the pre-expanded area; P32-3: Perform edge transition expansion permission authentication based on the K pre-expansion factors. If the authentication passes, perform edge transition identification based on the K pre-expanded areas to determine K stage-expanded areas; P32-4: Merge the K stage-expanded areas with the K historical main activity intersection areas to obtain K stage historical main activity intersection expansion areas; P32-5: Continue edge transition expansion according to the preset transition step size and the K stage historical main activity intersection expansion areas to obtain the K key activity areas.

[0041] Specifically, to more precisely determine the K key activity areas, a more detailed edge transition expansion process is introduced. First, pre-expansion area recognition is performed on the intersection area of the K historical main activities according to a preset transition step length to determine K pre-expansion areas. The preset transition step length can be a fixed distance or ratio obtained based on ecological and ethological research for simulating the range expansion of wild animals. The transition step length refers to the area increment during expansion and is usually preset according to the natural fluctuation range of wild animal activities. Pre-expansion area recognition is performed on the intersection area of the K historical main activities according to the preset transition step length. Using the buffer analysis algorithm in spatial analysis technology, a specified step length is extended outward around the boundary of each intersection area to form K pre-expansion areas. These areas represent the potential areas where wild animals may expand their activity ranges in the future.

[0042] Next, to evaluate the rationality and importance of the pre-expansion areas, a pre-expansion factor for each pre-expansion area is calculated based on the overlap situation of the set of K historical main activity areas. The pre-expansion factor is a ratio indicating the proportion of the area of the overlapping area in the pre-expansion area to the area of the entire pre-expansion area. The higher this ratio, the higher the overlap degree of the area in the activity ranges of multiple wild animal types, and thus it is more likely to be a key area for conservation work.

[0043] After obtaining the pre-expansion factors, edge transition expansion permission certification is performed based on these factors. This certification process verifies the rationality of the expansion of each pre-expansion area to ensure that the expansion does not deviate from the actual animal activity patterns and avoid waste or damage of conservation resources caused by over-expansion. If the certification passes, edge transition recognition is performed based on the K pre-expansion areas to further determine K stage expansion areas. Using the edge detection algorithm in spatial analysis and the animal behavior model, the movement paths and range expansion trends of wild animals in the natural environment are simulated. By identifying the edge features of the pre-expansion areas and considering the migration habits and ecological needs of animals, K stage expansion areas are determined. The expansion at this stage optimizes the pre-expansion areas according to the certification results to make them more consistent with the actual animal activity ranges.

[0044] Subsequently, the K stage expansion areas are merged with the intersection area of the K historical main activities to obtain the intersection expansion areas of the K stage historical main activities. This operation aims to integrate the newly expanded areas with the original activity intersection areas to ensure that the expanded areas not only retain the core information of the historical activity areas but also cover the possible activity expansion ranges.

[0045] Finally, based on the preset transition step size and the expanded regions of the intersections of the main activities in K stages of history, continue the edge transition expansion to finally determine K key activity regions. These regions not only cover the current main activity ranges of wild animals, but also fully consider their future activity trends and expansion potentials, and will be used as the key regions for subsequent monitoring and inspection of the system. Through this progressive expansion and optimization process, the rationality of the monitoring region and the comprehensiveness of the coverage are ensured.

[0046] Furthermore, step P32-3 of the embodiment of the present application further includes:

[0047] P32-31: Determine whether the K pre-expansion factors are greater than or equal to a preset expansion factor threshold. If so, the authentication is passed; P32-32: If not, the authentication fails, and the K historical main activity intersection regions are used as the K key activity regions.

[0048] Optionally, in order to more rigorously control the rationality of the edge transition expansion, an authentication process based on the pre-expansion factor is added. The expansion operation is determined whether to continue by judging the pre-expansion factor.

[0049] First, check the calculated K pre-expansion factors one by one and compare them with the preset expansion factor threshold. The preset expansion factor threshold is a reference value set based on ecological research, animal behavior data, and the specific conditions of the protected area, and is used to evaluate whether the pre-expansion region has sufficient ecological importance and protection value. If the value of a certain pre-expansion factor is greater than or equal to this threshold, it means that the pre-expansion region occupies a relatively high overlapping ratio in the activity ranges of multiple wild animal types and has a high protection priority, so the authentication is passed. This means that the pre-expansion region may become an important region for future wild animal activities and is worthy of further edge transition expansion.

[0050] If the value of a certain pre-expansion factor is less than the preset expansion factor threshold, it means that the pre-expansion region has a relatively low overlapping ratio in the activity ranges of multiple wild animal types and may not be a key region for future wild animal activities. Therefore, the authentication fails. In this case, in order to avoid unnecessary resource waste and potential ecological damage risks, the original K historical main activity intersection regions are directly used as the K key activity regions. This not only retains the information of the current main activity regions of wild animals, but also avoids problems that may be caused by excessive expansion.

[0051] Through this extended authentication mechanism, the scientificity and rationality of each expansion are ensured, unnecessary expansion operations are avoided, and at the same time, the data of the historical activity regions can be fully utilized to define the key activity regions of wild animals.

[0052] Furthermore, step P32-3 of the embodiment of the present application further includes:

[0053] P32 - 33: Extract the edge points with the most overlapping times from the edges of the K pre - expansion regions to obtain K expansion edge starting points; P32 - 34: Use the K expansion edge starting points as the centers, and construct K iterative edge point screening regions with a preset point expansion step length as the radius, and determine the K first iterative edge points with the most overlapping times in the K iterative edge point screening regions according to the overlapping situation of the K sets of historical main activity regions; P32 - 35: Based on the K first iterative edge points, continue to iterate in the K pre - expansion regions. When the K N - th iterative edge points after iterative update coincide with the K expansion edge starting points, stop the iteration to obtain K stage expansion regions.

[0054] In a possible embodiment of the present application, in order to more accurately determine the expansion trend of the wildlife activity range, an expansion region recognition method based on edge point iteration is introduced.

[0055] First, extract the edge points with the most overlapping times from the edges of the K pre - expansion regions. These edge points are the most critical positions on the boundaries of the intersection regions of multiple historical main activity regions. Because they represent the intersection points of the activity ranges of different wildlife types and are also the starting points where the future activity range may expand. By calculating the overlapping times of each edge point (i.e., the number of historical main activity regions it is contained in), K expansion edge starting points are identified.

[0056] Next, use the K expansion edge starting points as the centers and a preset point expansion step length as the radius to construct K iterative edge point screening regions. These regions are circular or elliptical regions that expand a certain distance around the expansion edge starting points and are used to screen new edge points in the subsequent iterative process. At the same time, according to the overlapping situation of the K sets of historical main activity regions, determine the K first iterative edge points with the most overlapping times in each iterative edge point screening region. These first iterative edge points represent the new positions that may be reached along the wildlife activity trend starting from the expansion edge starting points.

[0057] Then, continue to iterate in the K pre - expansion regions based on the K first iterative edge points. Each iteration will use the current iterative edge point as the starting point to construct a new iterative edge point screening region and determine new iterative edge points. This process will be repeated continuously until the K N - th iterative edge points after iterative update coincide with the initial K expansion edge starting points. Determine the K stage expansion regions based on the final iterative edge points. These regions represent the phased expansion results that the wildlife activity range may reach in the future and will be used as the basis for further expansion or optimization, providing a reference for the finally determined key activity regions.

[0058] Furthermore, step P34 in the embodiment of the present application further includes:

[0059] P34-1: Identify the fluctuation variances of the K sets of migration time points to obtain the K migration time point fluctuation variances; P34-2: When the K migration time point fluctuation variances are greater than or equal to the preset fluctuation variance, perform data cleaning on the K sets of migration time points, and calculate the mean of the K sets of cleaned migration time points after cleaning to obtain the K key migration time points; P34-3: When the K migration time point fluctuation variances are less than the preset fluctuation variance, calculate the mean of the K sets of migration time points to obtain the K key migration time points.

[0060] It should be understood that in order to extract representative key migration time points from the K sets of migration time points, a mechanism for identifying and processing the fluctuation variances of migration time points is introduced.

[0061] First, identify the fluctuation variances of the K sets of migration time points. The fluctuation variance of migration time points is an important indicator to measure the dispersion degree of each time point in the set of migration time points. By calculating the average of the squares of the differences between each migration time point and the set average (i.e., variance), the K migration time point fluctuation variances are obtained. If the fluctuation variance is large, it means that there is a large uncertainty in the migration time points of animals in different years or conditions; if the fluctuation variance is small, it indicates that the migration time is relatively stable and the differences are small. By calculating the fluctuation variances of the K migration time points, a quantitative analysis of the volatility of these time points is carried out.

[0062] When the K migration time point fluctuation variances are greater than or equal to the preset fluctuation variance, it indicates that the dispersion degree of the migration time points is relatively high, and there may be outliers or noise data. Therefore, data cleaning is performed on the set of migration time points to remove outliers or unreasonable data points. The specific methods of data cleaning may include threshold filtering, clustering analysis, outlier detection, etc. After cleaning, calculate the mean of the remaining K sets of cleaned migration time points to obtain the K key migration time points. These key migration time points represent the central tendency of the migration activities and are important references for subsequent analysis and protection work.

[0063] If the K migration time point fluctuation variances are less than the preset fluctuation variance, it indicates that the dispersion degree of the migration time points is relatively low and the data is relatively stable. The mean can be directly calculated for the original K sets of migration time points to obtain the K key migration time points. Since the stability of the data itself is relatively high, the key migration time points can be directly obtained without data cleaning.

[0064] With the technical support of this fluctuation variance analysis and data processing, the system can flexibly respond to different fluctuations in migration time. Whether there are significant fluctuations in the migration time points, the system can extract accurate key migration time points through cleaning and mean calculation.

[0065] The inspection path planning module 14 is used to plan the inspection paths of the first-level dynamic monitoring devices based on the K key activity areas, K key migration channels, and K key migration time points, and determine K first-level dynamic inspection paths.

[0066] Furthermore, the inspection path planning module 14 is also used to perform the following steps:

[0067] P41: Construct an inspection path recognizer; P42: Use the inspection path recognizer to identify the K key activity areas, K key migration channels, and K key migration time points, and determine K first-level dynamic inspection paths.

[0068] Optionally, the main function of the inspection path planning module 14 of this application is to generate inspection paths for the first-level dynamic monitoring devices according to the K key activity areas, K key migration channels, and K key migration time points, so as to ensure that the monitoring equipment can efficiently cover the main activity and migration areas of wild animals.

[0069] Before planning the inspection path, it is first necessary to construct an inspection path recognizer. This recognizer is a comprehensive system integrating spatial analysis, time series analysis, and path optimization algorithms. It can utilize the spatial data management capabilities of the Geographic Information System (GIS), combined with time series analysis techniques, to deeply mine the spatio-temporal characteristics of wild animal activities. At the same time, by integrating path optimization algorithms (such as genetic algorithms, ant colony algorithms, etc.), it can quickly generate optimal or sub-optimal inspection paths in complex environments. Its construction is based on spatial data processing techniques, combined with the Geographic Information System (GIS) and path optimization algorithms, so as to be able to efficiently analyze the spatial distribution of different regions and plan the optimal inspection path according to the activity patterns of wild animals.

[0070] Next, the patrol path recognizer is used to recognize K key activity areas, K key migration channels, and K key migration time points. First, based on the spatial distribution of these key areas, the recognizer analyzes the geographical features of each area and the activity frequency of wild animals. For key activity areas, the recognizer focuses on identifying the core areas of these regions to ensure that the monitoring equipment can cover the main activity areas of the animals; for key migration channels, the recognizer determines the optimal patrol route based on the length, width of the channel, and the flow of animal migration to cover the migration routes of the migrating animals; for key migration time points, the patrol time arrangement is optimized based on the characteristics of the time period to ensure effective dynamic monitoring during the peak migration period.

[0071] Through the analysis of the recognizer and considering these key factors comprehensively, K first-level dynamic patrol paths are generated. Each path is optimized to maximize the coverage of the activity areas and migration paths of wild animals, while ensuring the operation efficiency of the patrol equipment and resource utilization rate. These paths will form the basis of the patrol task to ensure the effective implementation of monitoring in key times and key areas.

[0072] The protected area monitoring module 15 is used to conduct protection monitoring on the target protected area based on the global static monitoring sub-network and the K first-level dynamic patrol paths, and transmit the monitoring data to the intelligent management platform for processing to obtain the protected area monitoring results.

[0073] Specifically, the main function of the protected area monitoring module 15 of the present application is to comprehensively monitor the target protected area based on the global static monitoring sub-network and the K first-level dynamic patrol paths, and transmit the monitoring data to the intelligent management platform for processing, so as to obtain the monitoring results of the protected area.

[0074] First, the module integrates the data from the global static monitoring sub-network. The global static monitoring sub-network refers to the monitoring equipment (such as cameras, sensors, etc.) fixedly arranged in the protected area. These devices can continuously conduct real-time monitoring on the activities of wild animals and plants. Especially in areas with dense plant distribution, the static monitoring devices cover the conventional animal activity areas. Through long-term monitoring, the system can collect stable activity data in the protected area to ensure that the activity tracks of wild animals and the changes in the ecological environment can be captured.

[0075] At the same time, supplementary monitoring is carried out based on the monitoring data of the K first-level dynamic patrol paths. The first-level dynamic patrol paths are the patrol routes for dynamically monitoring the protected area by drones or other mobile monitoring devices. These paths are optimized to focus on covering the key activity areas and migration channels of wild animals and conduct efficient monitoring during key time periods. Dynamic patrol can flexibly respond to animal migration or other emergencies and supplement and optimize on the basis of static monitoring.

[0076] Next, the monitoring data obtained from the static monitoring sub-network and the dynamic patrol paths is integrated and transmitted to the intelligent management platform. The intelligent management platform is the core of the entire protected area monitoring system and is responsible for processing and analyzing the transmitted data. The platform uses technologies such as big data analysis and pattern recognition to deeply analyze the activity patterns, migration patterns of wild animals, and environmental changes, so as to generate accurate monitoring results for the protected area. The monitoring results include the distribution of wild animals and plants, changes in migration routes, dynamic changes in habitat environments, and early warnings of possible threat factors (such as illegal activities, habitat destruction, etc.). These results will help managers make quick responses and adjust the monitoring plans and protection measures according to the actual situation.

[0077] In summary, the embodiments of the present application at least have the following technical effects:

[0078] In this application, by retrieving the distribution data of wild plants in the target protected area, deploying a full-range static monitoring device, constructing a static monitoring sub-network, and at the same time retrieving the historical record data of K wild animals to obtain their activity areas, migration channels, and time point sets, and screening and determining the key activity areas, migration channels, and time points, based on this, planning dynamic patrol paths, and comprehensively monitoring the protected area in combination with the static monitoring network, transmitting the monitoring data to the intelligent management platform for processing, and generating monitoring results for the protected area.

[0079] It achieves the technical effect of improving the comprehensiveness, accuracy, and efficiency of the protection of wild animals and plant resources by combining static monitoring and dynamic patrol.

[0080] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0081] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0082] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, changes, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications 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 equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent management platform for the protection of wild animal and plant resources, characterized by: The platform includes: A global static monitoring sub-network construction module is used to retrieve the wild plant distribution data of the target protected area, deploy global static monitoring devices based on the wild plant distribution data, and construct a global static monitoring sub-network; A historical record data acquisition module is used to retrieve K types of wild animals in the target protected area, and based on the K types of wild animals, retrieve the historical record data of the target protected area to obtain K sets of historical main activity areas, K sets of migration channels and K sets of migration time points, where K is an integer greater than or equal to 1; The key indicator screening module is used to centrally screen the K historical main activity area sets, the K migration channel sets and the K migration time point sets, respectively, to determine K key activity areas, K key migration channels and K key migration time points, including: Performing area intersection identification on the K sets of historical main activity areas respectively to determine K historical main activity intersection areas; Based on the overlap of the K sets of historical main activity areas, edge transition expansion is performed on the intersection areas of the K historical main activities to determine K key activity areas; Performing regional edge concentrated screening on the K migration channel sets to obtain the K key migration channels; Performing time point concentration density screening on the K migration time point sets to determine the K key migration time points; A patrol route planning module, used to plan the patrol routes of the first-level dynamic monitoring device based on the K key activity areas, the K key migration channels and the K key migration time points, and determine K first-level dynamic patrol routes; The protection area monitoring module is used to perform protection monitoring on the target protection area based on the global static monitoring subnetwork and the K first-level dynamic inspection paths, and transmit the monitoring data to the intelligent management platform for processing to obtain the protection area monitoring results.

2. The intelligent management platform for wildlife and plant resource protection according to claim 1, characterized in that: Based on the overlap of the K historical main activity area sets, edge transition expansion is performed on the intersection area of ​​the K historical main activities to determine K key activity areas, including: Performing pre-expansion area identification on the K historical main activity intersection areas according to a preset transition step length to determine K pre-expansion areas; Calculating K pre-expansion factors of the K pre-expansion areas according to the overlap of the K historical main activity area sets, wherein the pre-expansion factor is the ratio of the area of ​​the overlapping area in each pre-expansion area to the area of ​​the previous pre-expansion area; Performing edge transition expansion license authentication based on the K pre-expansion factors, and if the authentication is passed, performing edge transition identification based on the K pre-expansion areas to determine K stage expansion areas; Merging the K stage expansion areas with the K historical main activity intersection areas to obtain the K stage historical main activity intersection expansion areas; The edge transition expansion is continued according to the preset transition step length and the intersection expansion area of ​​the K stage historical main activities to obtain the K key activity areas.

3. The intelligent management platform for wildlife resource protection according to claim 2, characterized in that: Performing edge transition expansion license authentication based on the K pre-expansion factors, and if the authentication is passed, performing edge transition identification based on the K pre-expansion areas, and determining K stage expansion areas, including: Determine whether the K pre-expansion factors are greater than or equal to a preset expansion factor threshold, if so, the authentication is passed; If not, the authentication fails, and the K historical main activity intersection areas are used as the K key activity areas.

4. The intelligent management platform for wildlife and plant resource protection according to claim 3, characterized in that: Performing edge transition expansion license authentication based on the K pre-expansion factors, and if the authentication is passed, performing edge transition identification based on the K pre-expansion areas, and determining K stage expansion areas, including: Extracting edge points with the largest number of overlaps from the edges of the K pre-expanded regions to obtain K expansion edge starting points; Constructing K iterative edge point screening areas with the K expansion edge starting points as the center and the preset point expansion step as the radius, and determining the K first iterative edge points with the largest number of overlaps in the K iterative edge point screening areas according to the overlap of the K historical main activity area sets; Iteration is continued in the K pre-expansion regions based on the K first iteration edge points, and when the iteratively updated K Nth iteration edge points coincide with the K expansion edge starting points, iteration is stopped to obtain K stage expansion regions.

5. The intelligent management platform for wildlife and plant resource protection according to claim 1, characterized in that: The K migration time point sets are screened based on the concentration density of the time points to determine the K key migration time points, including: Performing fluctuation variance identification on the K migration time point sets to obtain fluctuation variances of the K migration time points; When the fluctuation variance of the K migration time points is greater than or equal to the preset fluctuation variance, data cleaning is performed on the K migration time point sets, and mean calculation is performed on the cleaned K cleaned migration time point sets to obtain the K key migration time points; When the fluctuation variance of the K migration time points is less than the preset fluctuation variance, the mean of the K migration time point sets is calculated to obtain the K key migration time points.

6. The intelligent management platform for wildlife resource protection according to claim 1, characterized in that: Retrieve the wild plant distribution data of the target protected area, deploy global static monitoring devices based on the wild plant distribution data, and build a global static monitoring subnetwork, including: Extracting plant height characteristics based on the wild plant distribution data to determine wild plant height distribution characteristics; Extracting plant distribution density characteristics from the wild plant distribution data to obtain wild plant density distribution characteristics; Based on the wild plant height distribution characteristics and the wild plant density distribution characteristics, global static monitoring devices are deployed to construct a global static monitoring subnetwork.

7. The intelligent management platform for wildlife resource protection according to claim 1, characterized in that: include: Build an inspection path identifier; The inspection path identifier is used to identify the K key activity areas, the K key migration channels and the K key migration time points, and determine K first-level dynamic inspection paths.

Images