Phytoseiulus mite distribution characteristic analysis method and system based on stratified sampling technology

Abstract

The invention discloses a phyoseiulus mite distribution characteristic analysis method and system based on a stratified sampling technology, and relates to the technical field of biological distribution monitoring, and the method comprises the steps: carrying out the multi-level division according to a preset region, and obtaining a plurality of region layers; building a multi-layer sensing network according to the plurality of area layers; stratified sampling is carried out on the multiple area layers according to the multi-layer sensing network, and a multi-layer monitoring result is obtained; and according to the multi-level monitoring result, carrying out phytoseiulus mite distribution characteristic analysis to obtain a phytoseiulus mite distribution characteristic report. The technical problems that in the prior art, the accuracy of phytoseiulus distribution feature monitoring is insufficient, and the phytoseiulus distribution condition cannot be comprehensively and accurately obtained are solved, and the technical effects that refined analysis of phytoseiulus distribution features is achieved, and the accuracy of phytoseiulus distribution monitoring is improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of biodistribution monitoring, and particularly to a method and system for analyzing the distribution characteristics of phytoseiid mites based on a hierarchical sampling technique. Background Art

[0002] As an important natural enemy of pests in the agricultural ecosystem, phytoseiid mites play a key role in maintaining ecological balance and the healthy growth of crops. However, there are many limitations in the current research on the distribution characteristics of phytoseiid mites. On the one hand, traditional monitoring methods mostly use simple random sampling, lacking a systematic division of different ecological regions, resulting in the data obtained being unable to accurately reflect the true distribution of phytoseiid mites in complex environments and making it difficult to comprehensively grasp the distribution differences in different regional layers. On the other hand, the existing sensor network deployments are single, unable to comprehensively monitor the living environment of phytoseiid mites from multiple dimensions such as temperature, humidity, and light at the same time, and there is a lack of effective integration between sensors, resulting in poor comprehensiveness and relevance of data collection.

[0003] The prior art has the technical problem of insufficient accuracy in monitoring the distribution characteristics of phytoseiid mites and being unable to comprehensively and accurately obtain the distribution status of phytoseiid mites. Summary of the Invention

[0004] The present application provides a method and system for analyzing the distribution characteristics of phytoseiid mites based on a hierarchical sampling technique, which are used to solve the technical problem in the prior art of insufficient accuracy in monitoring the distribution characteristics of phytoseiid mites and being unable to comprehensively and accurately obtain the distribution status of phytoseiid mites.

[0005] In view of the above problems, the present application provides a method and system for analyzing the distribution characteristics of phytoseiid mites based on a hierarchical sampling technique.

[0006] In the first aspect of the present application, a method for analyzing the distribution characteristics of phytoseiid mites based on a hierarchical sampling technique is provided. The method includes: Performing multi-level division according to a preset area to obtain multiple area layers; building a multi-level sensor network according to the multiple area layers; performing hierarchical sampling on the multiple area layers according to the multi-level sensor network to obtain multi-level monitoring results; and analyzing the distribution characteristics of phytoseiid mites according to the multi-level monitoring results to obtain a phytoseiid mite distribution characteristics report.

[0007] In the second aspect of the present application, a system for analyzing the distribution characteristics of phytoseiid mites based on a hierarchical sampling technique is provided. The system includes: The regional layer acquisition module is used to perform multi-level division according to a preset region to obtain multiple regional layers; the multi-level sensing network construction module is used to construct a multi-level sensing network according to the multiple regional layers; the multi-level monitoring result acquisition module is used to perform stratified sampling on the multiple regional layers according to the multi-level sensing network to obtain multi-level monitoring results; the phytoseiid mite distribution characteristic report acquisition module is used to analyze the phytoseiid mite distribution characteristics according to the multi-level monitoring results to obtain a phytoseiid mite distribution characteristic report.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Perform multi-level division according to a preset region to obtain multiple regional layers; construct a multi-level sensing network according to the multiple regional layers; perform stratified sampling on the multiple regional layers according to the multi-level sensing network to obtain multi-level monitoring results; analyze the phytoseiid mite distribution characteristics according to the multi-level monitoring results to obtain a phytoseiid mite distribution characteristic report. It achieves the technical effect of refined analysis of the phytoseiid mite distribution characteristics and improves the accuracy of phytoseiid mite distribution monitoring. Description of the Drawings

[0009] 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, without creative efforts, other drawings can also be obtained according to these drawings.

[0010] Figure 1 It is a schematic flowchart of the method for analyzing the distribution characteristics of phytoseiid mites based on the stratified sampling technique provided by the embodiment of the present application; Figure 2 It is a schematic structural diagram of the system for analyzing the distribution characteristics of phytoseiid mites based on the stratified sampling technique provided by the embodiment of the present application.

[0011] Description of the reference numerals: Regional layer acquisition module 10, multi-level sensing network construction module 20, multi-level monitoring result acquisition module 30, phytoseiid mite distribution characteristic report acquisition module 40. Detailed Embodiments

[0012] This application provides a method and system for analyzing the distribution characteristics of phytoseiid mites based on the stratified sampling technique, which is used to solve the technical problem that the accuracy of monitoring the distribution characteristics of phytoseiid mites in the prior art is insufficient and it is impossible to comprehensively and accurately obtain the distribution status of phytoseiid mites.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0014] Embodiment 1, as Figure 1 shown, the present application provides a method for analyzing the distribution characteristics of phytoseiid mites based on the hierarchical sampling technique, and the method includes: Step S100: Perform multi-level division according to a preset area to obtain multiple area layers.

[0015] Specifically, perform multi-level division according to a preset area to obtain multiple area layers. When performing area division, comprehensively collect the area geographical feature information and area environmental feature information of the preset area, such as topography, climate conditions, vegetation types, etc. Then, based on the area geographical feature information, initially divide the preset area to obtain the area geographical feature division result. On this basis, combined with the area environmental feature information, further subdivide the area geographical feature division result to finally generate multiple area layers. Such division can ensure that each area layer has unique and relatively consistent geographical and environmental characteristics, which is conducive to more accurately monitoring the distribution of phytoseiid mites.

[0016] Step S200: Build a multi-level sensing network according to the multiple area layers.

[0017] Specifically, build a multi-level sensing network according to multiple area layers. In order to effectively monitor each area layer, a comprehensive and accurate sensing network needs to be built. First, collect the historical phytoseiid mite distribution parameters corresponding to multiple area layers. These parameters include the distribution of phytoseiid mites in different areas and at different times, forming multiple phytoseiid mite distribution record sets. Through in-depth analysis of these record sets, understand the distribution position preferences of phytoseiid mites in different area layers. For example, it is found that phytoseiid mites tend to gather near specific vegetation in certain areas. Based on these analysis results, deploy multi-dimensional sensors within multiple area layers. Here, the multi-dimensional sensors include temperature sensors, humidity sensors, light sensors, wind speed sensors, and image sensors, etc., which can obtain the environmental information within the area layer from different dimensions. After the deployment is completed, communicate and connect the sensors within multiple area layers to ensure that the data collected by each sensor can be transmitted and summarized in a timely and accurate manner, thereby building a complete multi-level sensing network.

[0018] Step S300: Perform hierarchical sampling on the multiple area layers according to the multi-level sensing network to obtain multi-level monitoring results.

[0019] Specifically, multiple regional layers are sampled hierarchically according to the multi-level sensing network to obtain multi-level monitoring results. In order to obtain accurate and valuable data, a hierarchical sampling strategy is set based on the characteristics of multiple regional layers. This strategy takes into account factors such as the area size, importance level of different regional layers, and possible differences in the distribution of phytoseiid mites, and determines the sampling frequency, sampling locations, etc. within each regional layer. Subsequently, data is read from the multi-level sensing network according to the hierarchical sampling strategy to obtain a multi-level sensing data set. Since the data collected by the sensors contains some noise or error information, these data need to be cleaned. Through data cleaning algorithms and processes, invalid data such as outliers and duplicate values are removed, and finally accurate and reliable multi-level monitoring results are obtained, which provide a solid data foundation for subsequent analysis.

[0020] Step S400: Analyze the distribution characteristics of phytoseiid mites based on the multi-level monitoring results to obtain a report on the distribution characteristics of phytoseiid mites.

[0021] Specifically, analyze the distribution characteristics of phytoseiid mites based on the multi-level monitoring results to obtain a report on the distribution characteristics of phytoseiid mites. In this step, based on the multi-level monitoring results, identify the distribution characteristics of phytoseiid mites in multiple regional layers, so as to obtain the distribution characteristics of phytoseiid mites at each level, such as information on the density distribution and aggregation areas of phytoseiid mites in different regional layers. Then, perform trend analysis on these distribution characteristics to understand the trend of phytoseiid mite distribution over time and environmental changes, and obtain the trend analysis results of phytoseiid mite distribution. At the same time, based on the multi-level monitoring results, correlate the distribution characteristics of phytoseiid mites at each level with environmental characteristics. First, identify the environmental characteristics at each level, and then perform correlation analysis between the distribution characteristics of phytoseiid mites and these environmental characteristics to obtain the environmental correlation analysis results of phytoseiid mites at each level, in order to explore the impact of environmental factors on the distribution of phytoseiid mites. Finally, organize and summarize the distribution characteristics of phytoseiid mites at each level, the trend analysis results of phytoseiid mite distribution, and the environmental correlation analysis results of phytoseiid mites at each level, and generate a report on the distribution characteristics of phytoseiid mites according to the standard report format.

[0022] In a possible implementation manner, step S100 further includes: Step S110: Obtain the regional geographical feature information and regional environmental feature information of the preset region.

[0023] Step S120: Divide the preset region according to the regional geographical feature information to obtain a result of regional geographical feature division.

[0024] Step S130: Divide the result of regional geographical feature division according to the regional environmental feature information to generate the multiple regional layers.

[0025] Specifically, first, with the help of advanced geographic information technology, satellite remote sensing images are used to accurately obtain topographic and geomorphic data of the preset area, such as geographical feature information like the trend of mountains, the change of altitude, and the distribution range of rivers and lakes. At the same time, combined with the Global Positioning System (GPS) technology, special geographical landmark points in the area are accurately located and marked for subsequent detailed research. For the acquisition of regional environmental feature information, multiple meteorological monitoring stations are reasonably set up in the preset area to collect meteorological data such as temperature, humidity, light intensity, wind speed, and wind direction in real time. The type, pH value, nutrient content, etc. of the soil are also understood through on-site soil sampling and analysis. In addition, a comprehensive survey of the vegetation coverage in the area is carried out, recording the types, distribution ranges, and growth conditions of different vegetation. By comprehensively applying these technical means and on-site investigation methods, the regional geographical feature information and regional environmental feature information of the preset area are comprehensively and accurately obtained, providing rich and reliable data support for subsequent research work based on this information.

[0026] Using the powerful spatial analysis function of the Geographic Information System (GIS) and combining professional geographical analysis models, in-depth analysis of the regional geographical feature information is carried out. Taking the topographic and geomorphic features as an example, according to the change of altitude and the degree of terrain undulation, different topographic types such as mountains, hills, and plains in the preset area are distinguished. According to the trend of mountains and the distribution of rivers, they are divided with the mountain watershed and rivers as natural boundaries, making each divided area coherent and similar in terrain. For geographical location factors, considering the relative position relationship between the preset area and surrounding areas and the distribution of transportation hubs, the areas close to the main transportation lines or economic centers are classified into one category, and the areas far from these key nodes are classified into another category. By comprehensively considering various geographical feature information, the preset area is divided to obtain a clear and definite result of regional geographical feature division, laying a solid foundation for further subdividing the area in combination with regional environmental feature information and studying the distribution law of Phytoseiidae mites in different geographical regions.

[0027] Based on the obtained result of regional geographical feature division, it is further subdivided in combination with regional environmental feature information. For example, if there are obvious differences in vegetation types in different parts of a certain geographical division area, the areas dominated by forest vegetation, grassland vegetation, and farmland vegetation are distinguished. If there are significant differences in climate conditions in different parts of the area, such as different light durations and humidity levels, they will be divided again according to these differences. By comprehensively considering regional environmental feature information, the previous result of geographical feature division is adjusted and divided more finely, and finally multiple regional layers that consider both geographical features and environmental features are generated. These regional layers can more accurately reflect the characteristics of different parts in the preset area, providing a more reasonable regional division basis for subsequent monitoring and research on the distribution of Phytoseiidae mites.

[0028] In a possible implementation manner, step S200 further includes: Step S210: Collect the historical phytoseiid mite distribution parameters corresponding to the multiple regional layers to obtain multiple phytoseiid mite distribution record sets.

[0029] Step S220: Analyze the phytoseiid mite distribution location preferences of the multiple regional layers according to the multiple phytoseiid mite distribution record sets to obtain multiple phytoseiid mite distribution location preferences.

[0030] Step S230: Arrange multi-dimensional sensors for the multiple regional layers according to the multiple phytoseiid mite distribution location preferences, and communicatively connect the sensors arranged in the multiple regional layers to obtain the multi-level sensing network.

[0031] Specifically, in order to comprehensively understand the historical distribution of phytoseiid mites in different regional layers, past scientific research literature, agricultural production records, and relevant ecological monitoring data are consulted, and the phytoseiid mite distribution parameter information corresponding to the multiple regional layers of the preset area is screened out. These parameters include the specific distribution locations, densities, population numbers, etc. of phytoseiid mites in each regional layer at different time points. At the same time, field investigations will also be carried out, using the mark-recapture method to conduct field sampling in multiple regional layers to supplement more accurate and up-to-date phytoseiid mite distribution data. The data collected from different channels are sorted and summarized to form multiple detailed phytoseiid mite distribution record sets, which provide a rich data basis for subsequent analysis of the distribution preferences of phytoseiid mites.

[0032] Using the clustering analysis method, the distribution data in the record sets are classified according to the spatial position relationship to discover the aggregation trend of phytoseiid mites in each regional layer. For example, in the analysis, it is found that the frequency of phytoseiid mites is higher around specific vegetation communities in a certain regional layer. Then, through the association rule mining algorithm, the potential relationships between the phytoseiid mite distribution and geographical environment factors, such as altitude, soil type, light conditions, etc. are explored. For example, phytoseiid mites are more active in areas with low altitude, suitable soil humidity, and sufficient light. After multiple rounds of complex data analysis and verification, considering the influence of various factors on the phytoseiid mite distribution comprehensively, the distribution location preferences of phytoseiid mites in each regional layer are accurately determined, so as to obtain multiple phytoseiid mite distribution location preference results reflecting the distribution habits of phytoseiid mites in different regional layers, providing a key basis for more efficient monitoring of the phytoseiid mite distribution, optimizing prevention and control strategies, and protecting ecological balance in the future.

[0033] Based on the distribution position preferences of phytoseiid mites within each regional layer, determine the specific layout positions of the multi-dimensional sensors. In areas where phytoseiid mites prefer to gather, such as specific vegetation areas and environments with suitable humidity and temperature, a variety of sensors such as temperature sensors, humidity sensors, light sensors, wind speed sensors, and image sensors are densely arranged. These sensors each perform their own functions. The temperature and humidity sensors are used to monitor the changes in environmental temperature and humidity in real time. The light sensor records the light intensity and duration. The wind speed sensor captures the wind speed and direction information. The image sensor can directly obtain the activity status and quantity changes of phytoseiid mites. After carefully arranging the sensors within each regional layer, use wired network, wireless network, or hybrid network technology to communicate and connect the sensors arranged in multiple regional layers. By setting a unified communication protocol and data transmission standard, ensure that the data collected by each sensor can be accurately and quickly transmitted to the data processing center. In this way, a multi-level sensing network covering multiple regional layers and capable of real-time collecting and transmitting multi-dimensional data is built, providing strong technical support for subsequent stratified sampling and analysis of the distribution characteristics of phytoseiid mites.

[0034] In a possible implementation manner, step S230 further includes: Step S231: The multi-dimensional sensor includes a temperature sensor, a humidity sensor, a light sensor, a wind speed sensor, and an image sensor.

[0035] Specifically, when constructing a multi-level sensing network, the multi-dimensional sensors play a crucial role. They are composed of a temperature sensor, a humidity sensor, a light sensor, a wind speed sensor, and an image sensor. The temperature sensor is used to accurately measure the real-time temperature of the environment. Its data helps to understand the thermal condition of the environment where phytoseiid mites are located, because temperature changes will directly affect the metabolism, reproduction rate, and activity range of phytoseiid mites. The humidity sensor is responsible for monitoring the environmental humidity. Humidity conditions are also crucial for the survival and development of phytoseiid mites. Environments that are too dry or too wet may change the behavior patterns and distribution of phytoseiid mites. The light sensor can obtain information such as light intensity and light duration. As an important environmental factor, light will affect the phototaxis and habitat selection of phytoseiid mites. The wind speed sensor can sense the wind speed and direction in real time, which is of great significance for analyzing the way of spread and diffusion of phytoseiid mites in the air. The image sensor is more intuitive. It can take pictures of phytoseiid mites and their surrounding environment, not only directly count the number of phytoseiid mites, but also observe their behavioral characteristics, aggregation states, etc. These different types of sensors cooperate with each other, collect data from multiple dimensions, and provide a comprehensive and rich information source for in-depth study of the distribution characteristics of phytoseiid mites.

[0036] In a possible implementation manner, step S300 further includes: Step S310: Based on the multiple regional layers, set a stratified sampling strategy.

[0037] Step S320: Read data from the multi-level sensing network based on the hierarchical sampling strategy to obtain a multi-level sensing data set.

[0038] Step S330: Clean the data according to the multi-level sensing data set to obtain the multi-level monitoring results.

[0039] Specifically, a hierarchical sampling strategy is set based on multiple regional layers. Considering factors such as the area size of each regional layer, the evenness of the distribution of phytoseiid mites, geographical environment differences, and research purposes, a detailed hierarchical sampling strategy is formulated. For regional layers with a large area and obvious differences in the distribution of phytoseiid mites, the number of sampling points and the sampling frequency will be increased to ensure that the distribution characteristics of phytoseiid mites within the regional layer can be fully represented; for regional layers with a small area and relatively uniform distribution, the sampling quantity will be appropriately reduced, but samples are still ensured to cover key areas. At the same time, according to the geographical environment characteristics of different regional layers, such as the complexity of the terrain and traffic convenience, the sampling routes and positions are reasonably planned to ensure the feasibility and efficiency of the sampling work.

[0040] Read data from the multi-level sensing network based on the hierarchical sampling strategy to obtain a multi-level sensing data set. According to the pre-formulated hierarchical sampling strategy, data is read from various sensors in the multi-level sensing network. During the reading process, the time synchronization principle is strictly followed to ensure the relevance of the data collected by different sensors at the same time point. For example, within a set specific time interval, the data of temperature sensors, humidity sensors, light sensors, wind speed sensors, and image sensors are read in sequence. The data from different regional layers and different types of sensors are aggregated together to form a multi-level sensing data set containing rich information, comprehensively recording the environmental conditions and relevant information of phytoseiid mites in each regional layer at different times.

[0041] Clean the data according to the multi-level sensing data set to obtain the multi-level monitoring results. Since during the data collection process, affected by factors such as sensor failures and external interferences, there are problems such as noise data, outliers, and missing values in the multi-level sensing data set. Therefore, data cleaning algorithms are used to process the data set. By setting reasonable data thresholds, outliers beyond the normal range are identified and removed; interpolation methods and data smoothing algorithms are used to fill in the missing values; filtering algorithms are used to remove the noise data. After a series of rigorous data cleaning operations, accurate and reliable multi-level monitoring results are obtained, providing a high-quality data basis for subsequent in-depth analysis of the distribution characteristics of phytoseiid mites.

[0042] In a possible implementation manner, step S400 further includes: Step S410: Perform the recognition of the distribution characteristics of phytoseiid mites in the multiple regional layers according to the multi-level monitoring results, and obtain the distribution characteristics of phytoseiid mites at each level.

[0043] Step S420: Conduct trend analysis based on the distribution characteristics of phytoseiid mites at each level, and obtain the result of the trend analysis of the distribution of phytoseiid mites.

[0044] Step S430: Perform environmental feature correlation on the distribution characteristics of phytoseiid mites at each level according to the multi-level monitoring results, and obtain the result of the environmental correlation analysis of phytoseiid mites at each level.

[0045] Step S440: Organize the distribution characteristics of phytoseiid mites at each level, the result of the trend analysis of the distribution of phytoseiid mites, and the result of the environmental correlation analysis of phytoseiid mites at each level to generate the report on the distribution characteristics of phytoseiid mites.

[0046] Specifically, based on the multi-level monitoring results, perform the recognition of the distribution characteristics of phytoseiid mites in multiple regional layers to obtain the distribution characteristics of phytoseiid mites at each level. Use data analysis techniques to comprehensively analyze the monitoring results obtained from the multi-level sensing network. For each regional layer, first perform image recognition processing on the image data collected by the image sensor, and use image segmentation algorithms to accurately extract the individual information of phytoseiid mites from the complex background and count their numbers. At the same time, combine the data of environmental sensors such as temperature, humidity, and light to analyze the distribution differences of phytoseiid mites under different environmental conditions. Through spatial analysis methods, associate the location information of phytoseiid mites with the geographical coordinates of the regional layer, draw an accurate distribution map, and visually present the aggregation areas and dispersion degrees within the region. In addition, compare the monitoring data at different time periods to analyze the distribution change rules of phytoseiid mites in the time dimension, such as the peak activity periods in a day and the distribution differences in different seasons. Through the comprehensive processing and in-depth mining of various data, accurately identify the characteristics of phytoseiid mites at each level in terms of quantity, spatial distribution, time change, etc., laying a solid foundation for the subsequent in-depth analysis of the distribution trend and environmental correlation of phytoseiid mites.

[0047] Using time series analysis algorithms, sort out the data such as the number and distribution range of phytoseiid mites collected at different times at each level, fit a trend curve, and use this to judge the increase or decrease and periodic fluctuations in quantity. For example, it is found that the number of phytoseiid mites in certain regional layers shows seasonal fluctuations. With the help of the spatial analysis function of the Geographic Information System (GIS), perform overlay analysis on the spatial distribution data of phytoseiid mites at different times to visually present the expansion, contraction, or transfer direction of their distribution areas; through spatial autocorrelation analysis, quantify the changes in the aggregation or dispersion trends of the distribution. At the same time, combine environmental data with phytoseiid mite distribution data, use a multiple linear regression model to explore the influence degree of environmental factors such as temperature, humidity, and vegetation coverage on the distribution trend, and construct a prediction model. Through the above comprehensive analysis, fully master the distribution change rules of phytoseiid mites at different regional layers, and finally obtain accurate analysis results of the distribution trend of phytoseiid mites.

[0048] Extract the environmental characteristic data of each level from the multi-level monitoring results, including temperature, humidity, light intensity, wind speed, soil pH, etc. At the same time, sort out the distribution characteristic data of phytoseiid mites at each level, such as density, aggregation area, etc. Use the correlation analysis method to calculate the correlation coefficients between the distribution characteristic indicators of phytoseiid mites and various environmental factors, and determine which environmental factors have a significant correlation with the distribution of phytoseiid mites. For example, it is found that the correlation coefficient between the density of phytoseiid mites and humidity in a certain regional layer is relatively high, indicating that humidity has a greater impact on the distribution of phytoseiid mites in this area. Then, use regression analysis to construct a mathematical model to quantify the influence degree of environmental factors on the distribution of phytoseiid mites. For example, establish a regression equation with temperature and light intensity as independent variables and the area of the aggregation area of phytoseiid mites as the dependent variable to accurately evaluate how changes in these environmental variables cause changes in the distribution of phytoseiid mites. In addition, use the Geodetector spatial analysis tool to analyze the interaction of different environmental factors on the distribution of phytoseiid mites in space. Through these means of comprehensive analysis, clearly understand the internal relationship between the distribution characteristics and environmental characteristics of phytoseiid mites at each level, so as to obtain comprehensive and accurate analysis results of the environmental association of phytoseiid mites at each level.

[0049] Sort out the distribution characteristics of phytoseiid mites at each level, the analysis results of the distribution trend of phytoseiid mites, and the analysis results of the environmental association of phytoseiid mites at each level to generate a report on the distribution characteristics of phytoseiid mites. According to the standardized report format, systematically sort out and summarize the above analysis results. In the report, in the form of clear charts, text descriptions, etc., detail the current distribution status, change trends, and the correlation with environmental factors of phytoseiid mites in each regional layer. At the same time, combined with the research purpose and actual application requirements, put forward targeted suggestions and measures, such as early prevention and control warnings for areas where phytoseiid mites may reproduce in large numbers.

[0050] In a possible implementation manner, step S430 further includes: Step S431: Identify environmental characteristics based on the multi-level monitoring results to obtain environmental characteristics at each level.

[0051] Step S432: Conduct correlation analysis between the distribution characteristics of phytoseiid mites at each level and the environmental characteristics at each level to obtain the correlation analysis results of phytoseiid mite environment at each level.

[0052] Specifically, starting from the large amount of monitoring data collected by the multi-level sensing network, using data processing algorithms and professional analysis tools, the monitoring data of different regional layers are screened and classified. For the data collected by temperature sensors, humidity sensors, light sensors, wind speed sensors, etc., corresponding thresholds and classification criteria are set to identify basic environmental characteristics such as temperature range, humidity level, light intensity level, and wind speed in each regional layer. For soil-related data, through chemical analysis and soil classification standards, characteristics such as soil pH, nutrient content, and texture type of each layer of soil are determined. At the same time, combining geographical information data and vegetation monitoring data, topographic and geomorphic characteristics, vegetation coverage types and coverage degrees of each regional layer are identified. Through systematic analysis and collation of various types of data, environmental characteristics at each level are comprehensively and meticulously obtained, providing an accurate basis for subsequent correlation analysis.

[0053] For different regional layers, the distribution characteristic data of phytoseiid mites extracted from the monitoring data, such as quantity changes, positions and ranges of aggregation areas, etc., are integrated with the environmental characteristic data of the corresponding regional layer, such as temperature, humidity, light intensity, soil properties, and vegetation types. Then, using the correlation analysis method, the correlation coefficients between various distribution characteristics of phytoseiid mites and environmental characteristics are calculated. Based on the magnitude and sign of the correlation coefficient, the degree and direction of the association between the two are judged. For example, if it is found that the correlation coefficient between the number of phytoseiid mites and light intensity in a certain regional layer is positive and relatively high, it indicates that in this regional layer, when the light intensity increases, the number of phytoseiid mites also tends to increase. In addition to correlation analysis, multiple linear regression analysis is also used to construct a regression model with environmental characteristics as independent variables and phytoseiid mite distribution characteristics as dependent variables, so as to quantify the impact of environmental factors on the distribution of phytoseiid mites. For example, through the model, it can be calculated how much the distribution range of phytoseiid mites in this regional layer will expand when the temperature rises by one degree. In addition, with the help of the spatial analysis function of the Geographic Information System (GIS), the spatial overlap and distribution relationship between the distribution of phytoseiid mites and environmental characteristics are visually observed, further verifying and supplementing the analysis results. Through this series of systematic correlation analysis operations, the complex relationship between the distribution characteristics of phytoseiid mites and environmental characteristics at each level is comprehensively revealed, and then detailed, accurate and in-depth correlation analysis results of phytoseiid mite environment at each level are obtained, providing strong data support for in-depth understanding of the ecological habits and distribution laws of phytoseiid mites.

[0054] Example 2. Based on the same inventive concept as the method for analyzing the distribution characteristics of Phytoseiidae mites based on the hierarchical sampling technique in the foregoing embodiment, as Figure 2 shown, the present application provides a system for analyzing the distribution characteristics of Phytoseiidae mites based on the hierarchical sampling technique. The system in the embodiment of the present application and the method embodiment are based on the same inventive concept. Among them, the system includes: A regional layer acquisition module 10, configured to perform multi-level division on a preset region to obtain a plurality of regional layers.

[0055] A multi-level sensing network construction module 20, configured to construct a multi-level sensing network according to the plurality of regional layers.

[0056] A multi-level monitoring result acquisition module 30, configured to perform hierarchical sampling on the plurality of regional layers according to the multi-level sensing network to obtain multi-level monitoring results.

[0057] A Phytoseiidae mite distribution characteristic report acquisition module 40, configured to analyze the distribution characteristics of Phytoseiidae mites according to the multi-level monitoring results to obtain a Phytoseiidae mite distribution characteristic report.

[0058] Further, the system is further configured to implement the following functions: Obtain the regional geographical feature information and regional environmental feature information of the preset region; divide the preset region according to the regional geographical feature information to obtain a regional geographical feature division result; divide the regional geographical feature division result according to the regional environmental feature information to generate the plurality of regional layers.

[0059] Further, the system is further configured to implement the following functions: Collect the historical Phytoseiidae mite distribution parameters corresponding to the plurality of regional layers to obtain a plurality of Phytoseiidae mite distribution record sets; analyze the Phytoseiidae mite distribution position preferences of the plurality of regional layers according to the plurality of Phytoseiidae mite distribution record sets to obtain a plurality of Phytoseiidae mite distribution position preferences; perform multi-dimensional sensor layout on the plurality of regional layers according to the plurality of Phytoseiidae mite distribution position preferences, and communicatively connect the sensors arranged in the plurality of regional layers to obtain the multi-level sensing network.

[0060] Further, the system is further configured to implement the following functions: The multi-dimensional sensors include temperature sensors, humidity sensors, light sensors, wind speed sensors, and image sensors.

[0061] Further, the system is further configured to implement the following functions: Based on the multiple regional layers, a hierarchical sampling strategy is set; data reading is performed on the multi-level sensing network based on the hierarchical sampling strategy to obtain a multi-level sensing data set; data cleaning is performed according to the multi-level sensing data set to obtain the multi-level monitoring result.

[0062] Further, the system is also used to implement the following functions: Based on the multi-level monitoring result, the distribution characteristics of phytoseiid mites in the multiple regional layers are identified to obtain the distribution characteristics of phytoseiid mites at each level; trend analysis is performed according to the distribution characteristics of phytoseiid mites at each level to obtain the result of the distribution trend analysis of phytoseiid mites; environmental feature association is performed on the distribution characteristics of phytoseiid mites at each level according to the multi-level monitoring result to obtain the result of the environmental association analysis of phytoseiid mites at each level; the distribution characteristics of phytoseiid mites at each level, the result of the distribution trend analysis of phytoseiid mites, and the result of the environmental association analysis of phytoseiid mites at each level are sorted out to generate the report on the distribution characteristics of phytoseiid mites.

[0063] Further, the system is also used to implement the following functions: Based on the multi-level monitoring result, environmental features are identified to obtain environmental features at each level; correlation analysis is performed between the distribution characteristics of phytoseiid mites at each level and the environmental features at each level to obtain the result of the environmental association analysis of phytoseiid mites at each level.

[0064] 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 specific embodiments of the present specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] 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.

[0066] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, 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. A method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology, characterized in that: The method comprises: Perform multi-level division according to preset areas to obtain multiple area layers; Building a multi-level sensor network according to the multiple regional layers; Performing layered sampling on the multiple regional layers according to the multi-layered sensor network to obtain multi-layered monitoring results; The distribution characteristics of phytoseiid mites are analyzed based on the multi-level monitoring results to obtain a report on the distribution characteristics of phytoseiid mites.

2. The method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology according to claim 1, characterized in that: According to the preset areas, multiple levels are divided to obtain multiple regional layers, including: Obtaining regional geographic feature information and regional environmental feature information of the preset area; Divide the preset area according to the regional geographical feature information to obtain a regional geographical feature division result; The regional geographical feature division result is divided according to the regional environmental feature information to generate the multiple regional layers.

3. The method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology according to claim 1, characterized in that: According to the multiple regional layers, a multi-level sensor network is constructed, including: Collecting historical phytoseiid mite distribution parameters corresponding to the multiple regional layers to obtain multiple phytoseiid mite distribution record sets; Performing a phytoseiid mite distribution location preference analysis on the multiple regional layers according to the multiple phytoseiid mite distribution record sets to obtain multiple phytoseiid mite distribution location preferences; Multi-dimensional sensors are deployed in the multiple regional layers according to the distribution position preferences of the multiple phytoseiid mites, and the sensors deployed in the multiple regional layers are communicatively connected to obtain the multi-level sensor network.

4. The method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology according to claim 3, characterized in that: The multi-dimensional sensor includes a temperature sensor, a humidity sensor, a light sensor, a wind speed sensor and an image sensor.

5. The method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology according to claim 1, characterized in that: The plurality of regional layers are sampled in layers according to the multi-layered sensing network to obtain multi-layered monitoring results, including: Based on the multiple regional layers, setting a stratified sampling strategy; Reading data from the multi-level sensor network based on the stratified sampling strategy to obtain a multi-level sensor data set; Data cleaning is performed according to the multi-level sensor data set to obtain the multi-level monitoring result.

6. The method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology according to claim 1, characterized in that: According to the multi-level monitoring results, the distribution characteristics of phytoseiid mites are analyzed to obtain a report on the distribution characteristics of phytoseiid mites, including: According to the multi-level monitoring results, the distribution characteristics of phytoseiid mites in the multiple regional layers are identified to obtain the distribution characteristics of phytoseiid mites in each layer; Perform trend analysis based on the distribution characteristics of phytoseiid mites at each level to obtain a phytoseiid mites distribution trend analysis result; Correlating the distribution characteristics of phytoseiid mites at each level with environmental characteristics according to the multi-level monitoring results to obtain environmental correlation analysis results of phytoseiid mites at each level; The distribution characteristics of the phytoseiid mites at each level, the analysis results of the phytoseiid mites distribution trend and the analysis results of the phytoseiid mites environment at each level are sorted out to generate the phytoseiid mites distribution characteristics report.

7. The method for analyzing the distribution characteristics of phytoseiid mites based on stratified sampling technology according to claim 6, characterized in that: According to the multi-level monitoring results, the distribution characteristics of the phytoseiid mites at each level are correlated with the environmental characteristics to obtain the environmental correlation analysis results of the phytoseiid mites at each level, including: Perform environmental feature recognition according to the multi-level monitoring results to obtain environmental features at each level; Correlation analysis is performed on the distribution characteristics of the phytoseiid mites at each level and the environmental characteristics at each level to obtain correlation analysis results of the phytoseiid mites and the environment at each level.

8. A phytoseiid mite distribution characteristics analysis system based on stratified sampling technology, characterized in that: The system is used to implement the method for analyzing the distribution characteristics of phytoseiid mites based on the stratified sampling technology according to any one of claims 1 to 7, and the system comprises: A regional layer acquisition module is used to perform multi-level division according to preset regions to obtain multiple regional layers; A multi-level sensor network building module, used to build a multi-level sensor network according to the multiple regional layers; A multi-level monitoring result acquisition module, used for performing layered sampling on the multiple regional layers according to the multi-level sensor network to obtain multi-level monitoring results; The phytoseiid mite distribution characteristic report acquisition module is used to analyze the phytoseiid mite distribution characteristics according to the multi-level monitoring results to obtain the phytoseiid mite distribution characteristic report.

Images