Pest population behavior dynamic monitoring method based on Internet of Things

Abstract

A pest population behavior dynamic monitoring method based on Internet of Things belongs to the technical field of Internet of Things and biological monitoring, and comprises the following steps: collecting multi-dimensional environmental physical quantities according to environmental characteristics of a monitored area by deploying a multi-physical field sensor network; the method comprises the following steps: performing spatial and hierarchical mapping on original monitoring data, and performing normalization conversion on a wind field, a temperature field and a water vapor field to obtain a preprocessing data set constructed by unified quantitative representation of different physical field data; and performing linkage integration on unified physical field data in the pre-processing data set and pest behavior data collected in the Internet of Things so as to establish a response model for performing real-time matching on pest behaviors and environmental physical conditions. And comparing a linkage monitoring result output by the response model with an actual observation result of the monitoring area, and adjusting a matching rule of the response model on pest behaviors and environmental physical conditions by utilizing environmental feedback so as to optimize the response model.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things and biological monitoring, and more specifically, relates to a method for dynamically monitoring the behavior of pest populations based on the Internet of Things. Background Art

[0002] At present, due to the deficiencies of multi-physical field linkage response, in extreme climates, special geological or complex hydrological environments, such as areas close to karst regions or along rivers and lakes, it is difficult for a single Internet of Things monitoring system to capture the non-linear response of pest behavior under the combined action of environmental multi-physical fields (such as wind fields, temperature differences, water vapor transfer, etc.). To a certain extent, this has led to difficulties in achieving high-precision monitoring of pest dynamic behavior by traditional Internet of Things systems in similar extreme or variable environments, especially in the process of physical signal transmission between different levels of ecosystems, where traditional Internet of Things systems lack a certain degree of cross-system physical quantity conversion function. Summary of the Invention

[0003] To solve the deficiencies in the prior art, the purpose of the present invention is to address the above-mentioned defects and further propose a method for dynamically monitoring the behavior of pest populations based on the Internet of Things.

[0004] The present invention adopts the following technical solutions.

[0005] The first aspect of the present invention discloses a method for dynamically monitoring the behavior of pest populations based on the Internet of Things, and the method includes: By deploying a multi-physical field sensor network, according to the environmental characteristics of the monitoring area, multi-dimensional environmental physical quantities are collected, and the multi-dimensional environmental physical quantities are the original monitoring data from different sensors; Perform spatial and hierarchical mapping on the original monitoring data, and perform normalization conversion on the wind field, temperature field, and water vapor field to obtain a preprocessing data set constructed by the unified quantization representation of different physical field data; Link and integrate the unified physical field data in the preprocessing data set with the pest behavior data collected in the Internet of Things to establish a response model for real-time matching of pest behavior and environmental physical conditions; Compare the linkage monitoring results output by the response model with the actual observation results of the monitoring area, and use environmental feedback to adjust the matching rules of the response model for pest behavior and environmental physical conditions to optimize the response model; Wherein, the multi-physical field sensor network is deployed by conducting on-site surveys and planning the layout points of the monitoring area, and the environmental characteristics include the climate characteristics, geological characteristics, and hydrological environment characteristics of the monitoring environment.

[0006] Further, the step of collecting multi-dimensional environmental physical quantities by deploying a multi-physical field sensor network according to the environmental characteristics of the monitoring area includes: Divide the monitoring area according to the climate characteristics, geological characteristics, and hydro-environmental characteristics of the monitoring area to obtain multiple sub-areas, and calculate the effective monitoring coverage area of each sub-area; Based on the effective monitoring coverage area of each sub-area, determine the sensor type, the number of sensors, and the density of the planned layout points, so as to design the installation strategy of the sensor nodes according to the density of the planned layout points and the environmental characteristics; Among them, the effective monitoring coverage area is the product of the total area of the sub-area, the terrain correction coefficient, the climate correction coefficient, and the water temperature correction coefficient; Install and deploy multiple sensors corresponding to various types according to the installation strategy, and perform on-site connectivity detection on the installed sensor nodes to determine whether the installed sensor nodes meet the preset connectivity requirements; When the installed sensor nodes meet the preset connectivity requirements, the integrated deployment of the multi-physical field sensor network is completed, and multi-dimensional environmental physical quantities are collected; when the installed sensor nodes do not meet the preset connectivity requirements, adjust the installation strategy.

[0007] Further, perform spatial and hierarchical mapping on the original monitoring data, and perform normalization conversion on the wind field, temperature field, and water vapor field to obtain a preprocessing data set constructed by the unified quantization representation of different physical field data, including: Use a linear mapping function to convert multiple groups of original monitoring data to a unified dimension, and the linear mapping function is selected based on the instrument calibration data at the monitoring site; Integrate the original monitoring data with the unified dimension of each sensor to construct a unified conversion matrix; the conversion matrix is jointly composed of the conversion coefficients of the wind field, the temperature field, and the humidity field; Add the product of the conversion matrix and the original data vector and the bias vector to be equal to the mapped unified physical field data vector; the original data vector is generated after separating and extracting different physical field data detected by the multi-physical field sensor network in real time; Perform normalization processing on the mapped unified physical field data vector to map the corresponding physical field data in the mapped unified physical field data vector to the first interval to obtain a normalized data vector; Select the normalized data vector according to the preset integration requirements to form the preprocessing data set; Among them, the mapped unified physical field data vector has the same dimension as the original data vector, and the bias vector is jointly composed of the wind field bias, the temperature field bias, and the humidity field bias.

[0008] Further, the linkage integration of the unified physical field data in the preprocessed data set with the pest behavior data collected in the Internet of Things to establish a response model for real-time matching of pest behavior and environmental physical conditions includes: Based on the preprocessed data set, determine the normalized data vectors output by each sensor node. Each sensor node has a spatial coordinate and a timestamp, and construct a spatio-temporal data matrix based on the spatial coordinates, timestamps, and the normalized data vectors output by each sensor node. Establish a pest behavior index based on each physical field data and the weight coefficient corresponding to each physical field data as a quantitative index for the response of the environmental physical field to the dynamic behavior of pests, and construct a pest behavior index model through weighted linear combination. Calculate the average pest behavior index, standard deviation, and spatial gradient in the monitoring area according to the pest behavior index of each sensor node and the spatio-temporal data matrix. The average pest behavior index, standard deviation, and spatial gradient are used to characterize the dynamic changes in pest behavior. Linkage integrate the pest behavior index model with the pest behavior data collected in the Internet of Things to establish the response model, and call the response model to generate a linkage monitoring result based on the average pest behavior index, standard deviation, and spatial gradient.

[0009] Further, comparing the linkage monitoring result output by the response model with the actual observation result of the monitoring area, and using environmental feedback to adjust the matching rule of the response model for pest behavior and environmental physical conditions to optimize the response model, includes: Obtain the actual observation result of the monitoring area from the multi-physical field sensor network, and compare the actual observation result of the monitoring area with the linkage monitoring result to calculate the error vector between the monitoring index in the current environment and the historical monitoring index in the linkage monitoring result. Calibrate and adjust the model parameters of the response model according to the error vector to determine the correction coefficients of each monitoring index. The correction coefficients include the index calibration coefficient of the average pest behavior, the standard deviation calibration coefficient, the gradient calibration coefficient, and the time series calibration coefficient, and calculate the calibration correction amount based on the correction coefficients. Apply the calibration correction amount to the linkage monitoring result to update the response model, and output by integrating the updated linkage monitoring result and the feedback interface to generate the final monitoring report and real-time feedback information of pest behavior.

[0010] The second aspect of the present invention discloses a terminal, including a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0011] The third aspect of the present invention discloses a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the steps of the method described in the first aspect.

[0012] The beneficial effects of the present invention are as follows. Compared with the prior art, the present invention has the following advantages: (1) According to the environmental characteristics of the monitoring area, the present invention conducts on-site surveys, plans the layout points, and deploys, in addition to the traditional pest behavior monitoring sensors (such as high-resolution cameras and infrared sensors), key additional wind speed and direction sensors, temperature gradient detectors, and water vapor concentration sensors for extreme climates, special geology, and complex hydrological environments (such as karst areas and areas along rivers and lakes). This can ensure coverage of each physical field, and then collect multi-dimensional environmental physical quantities, providing the original input for subsequent physical field conversion, and solving the limitation that a single Internet of Things node is difficult to comprehensively capture the response of the complex environmental physical field.

[0013] (2) The present invention performs spatial and hierarchical mapping on the original data from different sensors, normalizes and converts the wind field, temperature field, and humidity field, and realizes the unified quantitative expression of data in different physical fields. In addition, conversion rules are set according to the on-site environmental characteristics (such as the local temperature difference range, wind speed range, and water vapor concentration change) during the conversion process, and the mapping from local data to the overall physical field is completed, realizing the conversion and integration of physical signals at different levels of the ecosystem, enabling multi-physical field information in a complex environment to be uniformly applied to pest behavior monitoring, and solving the problem of insufficient linkage response of multi-physical fields in the environment.

[0014] (3) The present invention integrally links the converted unified physical field data with the pest behavior data (including images, infrared, and other behavior monitoring information) collected in the Internet of Things. A response model between pest behavior and environmental physical conditions is also established using the unified data, which can focus on the non-linear responses of pests to temperature differences, wind direction changes, and water vapor transfer under extreme environments. Through spatio-temporal mapping, the real-time matching of pest behavior and environmental changes is realized, making up for the deficiency of a single monitoring system in capturing pest behavior responses in extreme or variable environments, realizing dynamic monitoring and quantitative description, and improving the monitoring accuracy and response speed. Description of the Drawings

[0015] Figure 1 is a schematic flow chart of a method for dynamically monitoring the behavior of a pest population based on the Internet of Things provided by the present invention. Detailed Embodiments

[0016] The following further describes the present application in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and cannot be used to limit the protection scope of the present application.

[0017] As Figure 1 shown, in one embodiment, a method for dynamically monitoring the behavior of a pest population based on the Internet of Things includes the following steps: Step S110: By deploying a multi-physical field sensor network, according to the environmental characteristics of the monitoring area, collect multi-dimensional environmental physical quantities, and the multi-dimensional environmental physical quantities are the original monitoring data from different sensors.

[0018] Among them, the multi-physical field sensor network is obtained by conducting on-site surveys of the monitoring area and planning the layout of points for deployment, and includes pest behavior monitoring sensors, wind direction and wind speed sensors, temperature gradient detectors, and water vapor concentration sensors; the environmental characteristics include the climate characteristics, geological characteristics, and hydrological environment characteristics of the monitoring environment. The pest behavior monitoring sensors include high-resolution cameras and infrared sensors.

[0019] It is understandable that the environmental characteristics mentioned in the present invention, that is, the climate characteristics, geological characteristics, and hydrological environment characteristics of the monitoring environment, can be data characteristics constructed from other similar historical physical field data; in addition, the environmental characteristics are not necessarily concrete data characteristics, but can be subjective cognitive experiences formed based on human experience, etc.

[0020] In some embodiments, for a method for dynamically monitoring the behavior of a pest population based on the Internet of Things provided by the present invention, step S110 specifically includes the following steps: Step S111: According to the climate characteristics, geological characteristics, and hydrological environment characteristics of the monitoring area, divide the monitoring area to obtain multiple sub-areas, and calculate the effective monitoring coverage area of each sub-area.

[0021] Step S112: Based on the effective monitoring coverage area of each sub-area, determine the sensor type, the number of sensors, and the density of the planned layout points, so as to design the installation strategy of the sensor nodes according to the density of the planned layout points and the environmental characteristics.

[0022] Among them, the effective monitoring coverage area is the product of the total area of the sub-area, the terrain correction coefficient, the climate correction coefficient, and the water temperature correction coefficient.

[0023] In some embodiments, for a method for dynamically monitoring the behavior of a pest population based on the Internet of Things provided by the present invention, step S110 specifically further includes the following steps: Step S113: Install and deploy multiple sensors corresponding to various types according to the installation strategy, and perform on-site connectivity detection on each installed sensor node to determine whether each installed sensor node meets the preset connectivity requirements.

[0024] Step S114: When each installed sensor node meets the preset connectivity requirements, the integration deployment of the multi-physical field sensor network is completed, and multi-dimensional environmental physical quantities are collected; when each installed sensor node does not meet the preset connectivity requirements, the installation strategy is adjusted.

[0025] In a specific embodiment, a method for dynamically monitoring the behavior of pest populations based on the Internet of Things provided by the present invention includes steps 1 to 4: Step 1: Deployment of the multi-physical field sensor network.

[0026] According to the environmental characteristics of the monitoring area, conduct on-site surveys for extreme climates, special geology, and complex hydrological environments (such as karst areas, regions along rivers and lakes), plan the layout points, and deploy, in addition to traditional pest behavior monitoring sensors (such as high-resolution cameras, infrared sensors), wind speed and direction sensors, temperature gradient detectors, and water vapor concentration sensors to ensure coverage of each physical field. Step 1 is used to collect multi-dimensional environmental physical quantities, providing the original input for subsequent physical field conversion and breaking through the limitation that a single Internet of Things node cannot comprehensively capture the complex physical field response of the environment.

[0027] Specifically, it includes steps 1.1 to 1.4: Step 1.1: Region division and calculation of the effective coverage area.

[0028] Specifically, based on the environmental terrain, climate, and hydrological survey data, divide the monitoring area and calculate the effective monitoring coverage area of each sub-region. Among them, the effective monitoring coverage area = the total area of the sub-region × terrain correction coefficient × climate correction coefficient × hydrological correction coefficient. The value range of the terrain correction coefficient is 0.7 to 1.0, which is used to reflect the coverage efficiency of flat and rugged terrains; the value range of the climate correction coefficient is 0.8 to 1.0, which is determined according to climate stability (wind speed, precipitation); the value range of the hydrological correction coefficient is 0.6 to 1.0, which is used to reflect the influence of water bodies and wetland distribution.

[0029] Step 1.2: Selection of sensor types and calculation of the layout density.

[0030] Specifically, according to the environmental complexity within the sub-region, the corresponding sensor types are selected and the deployment density is determined. Among them, the number of sensors required is obtained by rounding up the ratio of the effective coverage area obtained in step 1.1 to the square of the ideal distance between sensors. The value of the ideal distance between sensors is determined according to the environmental complexity and usually ranges from 50 to 200 m. Then, a sensor type vector is constructed, which is composed of a high-resolution camera for capturing pest activity images, an infrared sensor for night monitoring and heat distribution, an anemometer and wind vane sensor for monitoring the wind field, a temperature sensor for monitoring the environmental temperature difference, and a humidity / vapor sensor for capturing water vapor transfer.

[0031] Step 1.3, Design of the physical installation scheme for sensor nodes.

[0032] Specifically, based on the deployment density and environmental characteristics, the installation scheme of sensor nodes is designed to ensure that each sensor has the best sampling position in the multi-physical field. Among them, the optimal installation height of the sensor is obtained by processing the topographic undulation index (reflecting the ground flatness), vegetation coverage rate (numerical range 0 - 1), and water body proximity factor (value range 0.5 - 1.0) through an empirical formula combined with coefficients calibrated based on field tests.

[0033] Step 1.4, Detection of physical connectivity and final integration of network nodes.

[0034] Specifically, after the physical installation of each sensor node is completed, on-site connectivity detection is carried out to ensure that all nodes can collect physical information within the expected range.

[0035] Among them, the connectivity detection expression is:

[0036] In the formula, represents the distance between any two sensor nodes, , represents the planar coordinates of node i, , represents the planar coordinates of node j. This expression is used to detect whether the preset connectivity distance requirement (such as not exceeding 150 m) is met between nodes to ensure the effective interconnection of multi-physical field information.

[0037] Step S120, Perform spatial and hierarchical mapping on the original monitoring data, and perform normalization conversion on the wind field, temperature field, and water vapor field to obtain a preprocessing dataset constructed by the unified quantization representation of data from different physical fields.

[0038] In some embodiments, a method for dynamically monitoring the behavior of pest populations based on the Internet of Things provided by the present invention, step S120 specifically includes the following steps: Step S121, using a linear mapping function to convert multiple groups of original monitoring data to a unified dimension, and the linear mapping function is selected based on the instrument calibration data at the monitoring site.

[0039] Step S122, integrating the original monitoring data with a unified dimension of each sensor to construct a unified conversion matrix, and the conversion matrix is jointly composed of the conversion coefficients of the wind field, the conversion coefficients of the temperature field, and the conversion coefficients of the humidity field.

[0040] Step S123, adding the product of the conversion matrix and the original data vector to the bias vector to be equal to the mapped unified physical field data vector, and the original data vector is generated after separating and extracting the different physical field data detected by various sensors in the multi-physical field sensor network in real time.

[0041] Step S124, performing normalization processing on the mapped unified physical field data vector to map the corresponding physical field data in the mapped unified physical field data vector to the first interval to obtain a normalized data vector.

[0042] Step S125, selecting the normalized data vector according to the preset integration requirements to form a preprocessing data set.

[0043] Among them, the mapped unified physical field data vector has the same dimension as the original data vector, and the bias vector is jointly composed of the wind field bias, the temperature field bias, and the humidity field bias.

[0044] In a specific embodiment, a method for dynamically monitoring the behavior of pest populations based on the Internet of Things provided by the present invention includes steps 1 to 4: Step 2, constructing a cross-physical field quantity conversion module.

[0045] Based on the sensor network, a physical quantity conversion module is established. This module performs spatial and hierarchical mapping on the original data from different sensors, normalizes and converts the wind field, temperature difference, and water vapor information, and realizes the unified quantitative expression of different physical field data. During the conversion process, conversion rules are set according to the characteristics of the on-site environment (such as the local temperature difference range, wind speed interval, and water vapor concentration change), and the mapping from local data to the overall physical field is completed. Step 2 is used to realize the conversion and integration of physical signals between different levels of the ecosystem, so that the multi-physical field information in a complex environment can be uniformly applied to pest behavior monitoring, and solves the problem of insufficient linkage response of the environmental multi-physical field.

[0046] Specifically, it includes steps 2.1 to 2.5: Step 2.1, accessing and extracting the original physical field data.

[0047] Specifically, various types of sensor data are accessed in real time from the constructed multi-physical field sensor network, and different physical fields (wind field, temperature field, humidity / vapor field) are separated and extracted. Among them, for each sensor node, its output data forms an original data vector, which is jointly composed of wind speed or wind direction data, temperature data, and humidity / vapor concentration data. After on-site calibration, each sensor data is passed as input.

[0048] Step 2.2, Design of multi-physical field data mapping function.

[0049] Specifically, to realize the expression of different physical field data on the same scale, a mapping function is designed to convert each original data to a unified dimension. Let the mapping function correspond to each physical quantity respectively, and the mapped data is denoted as , and in this example, a linear mapping function is adopted, and its general form is:

[0050] In the formula, is the mapped physical field, is the physical field before mapping, is the physical field conversion coefficient, is the physical field offset value.

[0051] Combined with the above formula, for the wind field: After mapping, we get , is the wind speed conversion coefficient, and the constant range can be set to 0.8 - 1.2 (determined according to the instrument calibration result), is the wind speed offset value, and the constant range is generally -0.5 - 0.5 m / s. The same applies to the temperature field and humidity / vapor field.

[0052] It should be noted that the selection of the mapping function is determined according to the on-site instrument calibration data.

[0053] Step 2.3, Construction of conversion matrix and bias correction.

[0054] Specifically, the mapping results of each sensor are integrated to construct a unified conversion matrix to ensure that the physical field data can be compared within a unified scale. The conversion model constructed based on the conversion matrix is as follows:

[0055] In the formula, is the unified physical field data vector after mapping, and its dimension is the same as that of the original data vector X, is the conversion matrix, is the bias vector, which is composed of the wind field bias, temperature field bias and humidity field bias. The conversion matrix is composed of the conversion coefficient of the wind field, the conversion coefficient of the temperature field and the conversion coefficient of the humidity field.

[0056] The above conversion model can ensure that all data have a unified dimension and standard after conversion. The conversion coefficient and bias vector can be adjusted according to the instrument calibration data, and the optimal value can be obtained by field testing.

[0057] Step 2.4, normalization and standardization preprocessing.

[0058] Specifically, in order to facilitate the direct comparison of data in different regions in a timely manner, the unified physical field data vector obtained by the conversion matrix needs to be mapped. A planning process is performed to map each physical field data to between 0 and 1.

[0059] Among them, the normalization formula is:

[0060] In the formula, is the normalized data vector, , They are respectively the maximum and minimum values of each physical field data in the historical preset data.

[0061] Step 2.5, integration testing and final output.

[0062] Specifically, the entire conversion module is integrated and tested to verify whether the normalized data Z meets the expected requirements. During the test, the output data of some sensor nodes are compared with the actual measured values on site to adjust the conversion matrix M, the bias vector B and the normalization parameters until all sensor node data are stably output, and finally the final data set is integrated and output, namely the preprocessed data set.

[0063] Step S130, linking and integrating the unified physical field data in the preprocessed data set with the pest behavior data collected in the Internet of Things to establish a response model for real-time matching of pest behavior with environmental physical conditions.

[0064] Among them, the Internet of Things is mainly used to collect pest behavior data, which often comes from on-site monitoring equipment, video sensors, RFID or other devices used to record pest movement, aggregation and activity trajectories.

[0065] In some embodiments, the present invention provides a method for dynamic monitoring of pest population behavior based on the Internet of Things, step S130 specifically includes the following steps: Step S131: Determine the normalized data vectors output by each sensor node based on the preprocessed data set. Each sensor node has spatial coordinates and timestamps, and construct a spatio-temporal data matrix based on the spatial coordinates, timestamps, and the normalized data vectors output by each sensor node.

[0066] Step S132: Establish a pest behavior index based on each physical field data and the corresponding weight coefficients of each physical field data as a quantitative index for the response of the environmental physical field to the dynamic behavior of pests, and construct a pest behavior index model through weighted linear combination.

[0067] Step S133: Calculate the average pest behavior index, standard deviation, and spatial gradient within the monitoring area according to the pest behavior index of each sensor node and the spatio-temporal data matrix. The average pest behavior index, standard deviation, and spatial gradient are used to characterize the dynamic changes in pest behavior.

[0068] Step S134: Link and integrate the pest behavior index model with the pest behavior data collected in the Internet of Things to establish a response model, and call the response model to generate linkage monitoring results based on the average pest behavior index, standard deviation, and spatial gradient.

[0069] In a specific embodiment, a method for dynamically monitoring the behavior of a pest population based on the Internet of Things provided by the present invention includes steps 1 to 4: Step 3: Linkage monitoring of pest behavior and environmental physical field.

[0070] Link and integrate the converted unified physical field data with the pest behavior data (including images, infrared, and other behavior monitoring information) collected in the Internet of Things. The monitoring system uses the unified data to establish a response model between pest behavior and environmental physical conditions, and focuses on the non-linear responses of pests to temperature differences, wind direction changes, and water vapor transfer under extreme environments. Through spatio-temporal mapping, the real-time matching of pest behavior and environmental changes is achieved, making up for the deficiencies of traditional single monitoring systems in capturing pest behavior responses in extreme or variable environments, realizing dynamic monitoring and quantitative description, and improving the monitoring accuracy and response speed.

[0071] Specifically, it includes steps 3.1 to 3.4: Step 3.1: Unified data integration and spatio-temporal mapping.

[0072] Specifically, based on the unified physical field data in the preprocessed data set after conversion and normalization, construct the data vectors output by each sensor node. The data vectors are jointly composed of the normalized wind field data, temperature field data, and humidity / water vapor field data. Then, combined with the spatial coordinates and timestamps of each sensor node, construct the corresponding spatio-temporal data matrix, which is jointly composed of each type of temperature field data and its corresponding plane coordinates and timestamps.

[0073] Step 3.2, construction of pest behavior indicator model.

[0074] Specifically, the pest behavior index is established as a quantitative index of the environmental physical field's response to the dynamic behavior of pests, and then the pest behavior index model is constructed through weighted linear combination, and its expression is:

[0075] In the formula, represents the pest behavior response index of a single sensor node, , , They are the normalized wind field data, temperature field data, and humidity / water vapor field data. , , They are the weight coefficients corresponding to wind field data, temperature field data, and humidity / water vapor field data, that is, the impact of each physical field on the activity and living environment of the well, which are obtained by field investigation and historical data correction.

[0076] Step 3.3, spatiotemporal dynamic behavior analysis and local statistical calculation.

[0077] Specifically, according to the pest behavior index B and spatiotemporal coordinates of each sensor node, local statistics and spatiotemporal dynamic analysis are performed to calculate the average pest behavior index, standard deviation and spatial gradient in the monitoring area to reflect the dynamic changes of pest behavior.

[0078] Among them, the standard deviation is used to reflect the fluctuation range of pest behavior indicators. The larger the value, the more drastic the pest behavior response changes in space or time. The spatial gradient is approximated by the two-dimensional difference method, that is, adjacent sensor nodes are selected for calculation.

[0079] Step 3.4, the linkage monitoring results and preliminary dynamic behavior analysis results are generated.

[0080] Specifically, the aforementioned statistical indicators are used to generate linkage monitoring results and preliminary dynamic behavior analysis results. The report content includes the average value, fluctuation range and time / space changes of the pest behavior indicators in the area, and then the final monitoring report is output. The final monitoring report is composed of the average pest behavior indicator, standard deviation, spatial gradient and time series analysis results. The time series analysis results are expressed as trend curve parameters of the changes in pest behavior indicators in different time periods, and its specific form can be an array of pest behavior indicators corresponding to a group of time nodes.

[0081] Step S140: Compare the linkage monitoring results output by the response model with the actual observation results of the monitoring area, and use environmental feedback to adjust the matching rules of the response model for pest behavior and environmental physical conditions to optimize the response model.

[0082] Understandably, the actual observation results can be highly integrated and summarized based on the actually observed pest behavior data. In the present invention, the pest behavior data actually integrates various data with different dimensions, such as: pest movement data, pest aggregation data, activity trajectory data, etc.; and the actual observation results integrate the pest behavior data with different dimensions into data with the same dimension as the linkage monitoring results, facilitating the classification learning of the algorithm. In some embodiments, it is possible to transform the pest behavior data into actual observation results based on means that often adopt Principal Component Analysis (PCA) and multi-modal feature fusion technology.

[0083] In some embodiments, a method for dynamically monitoring the behavior of a pest population based on the Internet of Things provided by the present invention, step S140 specifically includes the following steps: Step S141: Obtain the actual observation results of the monitoring area from the multi-physical field sensor network, and compare the actual observation results of the monitoring area with the linkage monitoring results to calculate the error vector between the monitoring indicators in the current environment and the historical monitoring indicators in the linkage monitoring results.

[0084] Step S142: Calibrate and adjust the model parameters of the response model according to the error vector to determine the correction coefficients for each monitoring indicator. The correction coefficients include the indicator calibration coefficient for the average pest behavior, the standard deviation calibration coefficient, the gradient calibration coefficient, and the time series calibration coefficient, and calculate the calibration correction amount based on the correction coefficients.

[0085] Step S143: Apply the calibration correction amount to the linkage monitoring results to update the response model, and generate the final monitoring report and real-time feedback information of pest behavior through integrating the updated linkage monitoring results and outputting through the feedback interface.

[0086] Among them, the calibration correction amount is obtained by multiplying each item of the correction coefficient by the elements in the error vector.

[0087] In a specific embodiment, a method for dynamically monitoring the behavior of a pest population based on the Internet of Things provided by the present invention includes steps 1 to 4: Step 4: Dynamic calibration and real-time feedback optimization.

[0088] Establish a dynamic calibration mechanism to compare the linkage monitoring results obtained in Step 3 with the on-site actual observation results, and use environmental feedback to adjust the mapping rules of the physical quantity conversion module. The system realizes data interaction with the agricultural prevention and control platform through a preset feedback interface, updates the monitoring model of the relationship between the on-site environment and pest behavior in real time, and displays the final results to the monitoring personnel through a visualization platform. Step 4 is used to improve the monitoring accuracy and real-time response ability in extreme or complex physical field environments, ensure that the system can automatically calibrate according to on-site environmental changes, and maintain the coherence of data transmission and monitoring results.

[0089] Specifically, it includes Steps 4.1 to 4.4: Step 4.1, Compare and verify real-time data with preliminary monitoring results.

[0090] Specifically, first, compare the new physical field data collected from the multi-physical field sensor network for on-site real-time monitoring with the previously generated linkage monitoring results to calculate the error vector between the monitoring indicators in the current environment and the indicators in the preliminary linkage monitoring results, which is composed of the differences between the corresponding data of the two.

[0091] Step 4.2, Calculate the error and adjust the calibration parameters.

[0092] Specifically, according to the error vector calculated in Step 4.1, construct a calibration parameter adjustment model to determine the correction coefficients for each monitoring indicator. Among them, the correction coefficients are jointly composed of the average pest behavior indicator calibration coefficient, the standard deviation calibration coefficient, the gradient calibration coefficient, and the time series calibration coefficient. Then, multiply each element in the correction coefficients by each element in the error vector item by item to obtain the calibration correction amount.

[0093] Step 4.3, Update the dynamic calibration model and construct the feedback interface.

[0094] Specifically, apply the calibration correction amount obtained in Step 4.2 to the preliminary linkage monitoring results to update the monitoring model (response model), and display it to the site in real time through the feedback interface. Among them, updating the monitoring model is the updated monitoring report data set, which has the same format as the preliminary linkage monitoring results and is the sum result between the preliminary monitoring report and the calibration correction amount. The feedback interface is used to transmit the updated monitoring report data set to the display terminal to achieve dynamic feedback optimization, including formatting the data into information such as charts, reports, and warning signals, and generating real-time response information according to preset rules.

[0095] Step 4.4, Generate the final monitoring report and real-time feedback information.

[0096] Specifically, by integrating the above calibration update results and the output of the feedback interface, a final monitoring report and real-time feedback information are generated, which are jointly composed of the calibrated average pest behavior indicators, standard deviation, spatial gradient, time series behavior indicators within the monitoring area, and the real-time response information generated by the feedback interface. The present invention comprehensively displays the final monitoring report and real-time feedback information, which can ensure that on-site technicians obtain complete and accurate decision-making support data.

[0097] The present disclosure may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0098] The computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punch card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed as being a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0099] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to respective computing / processing devices, or may be downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0100] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via an Internet service provider through the Internet). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0101] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer - readable program instructions.

[0102] These computer - readable program instructions can be provided to a processor of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data - processing apparatus, create a means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions comprises a manufacture, which includes instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0103] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0104] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for dynamically monitoring the behavior of pest populations based on the Internet of Things, characterized in that, The method includes: Deploying a multi-physical field sensor network to collect multi-dimensional environmental physical quantities according to the environmental characteristics of the monitoring area, where the multi-dimensional environmental physical quantities are original monitoring data from different sensors; Performing spatial and hierarchical mapping on the original monitoring data, and performing normalization conversion on the wind field, temperature field, and water vapor field to obtain a preprocessing data set constructed by the unified quantization representation of different physical field data; Linking and integrating the preprocessing data set with the pest behavior data collected in the Internet of Things to establish a response model for real-time matching of pest behavior and environmental physical conditions; Comparing the linkage monitoring results output by the response model with the actual observation results of the monitoring area, and using environmental feedback to adjust the matching rules of the response model for pest behavior and environmental physical conditions to optimize the response model; Among them, the multi-physical field sensor network is obtained by conducting on-site exploration of the monitoring area and planning the layout for deployment, and the environmental characteristics include the climate characteristics, geological characteristics, and hydrological environment characteristics of the monitoring environment.

2. The method for dynamically monitoring the behavior of a pest population based on the Internet of Things according to claim 1, wherein The deploying a multi-physical field sensor network to collect multi-dimensional environmental physical quantities according to the environmental characteristics of the monitoring area includes: Dividing the monitoring area according to the climate characteristics, geological characteristics, and hydrological environment characteristics of the monitoring area to obtain multiple sub-areas, and calculating the effective monitoring coverage area of each sub-area; Based on the effective monitoring coverage area of each sub-area, determining the sensor type, the number of sensors, and the density of the planned layout, so as to design the installation strategy of the sensor nodes according to the density of the planned layout and the environmental characteristics; where the effective monitoring coverage area is the product of the total area of the sub-area, the terrain correction coefficient, the climate correction coefficient, and the water temperature correction coefficient; Installing and deploying multiple sensors corresponding to various types according to the installation strategy, and performing on-site connectivity detection on the installed sensor nodes to determine whether the installed sensor nodes meet the preset connectivity requirements; When the installed sensor nodes meet the preset connectivity requirements, the integrated deployment of the multi-physical field sensor network is completed, and multi-dimensional environmental physical quantities are collected; when the installed sensor nodes do not meet the preset connectivity requirements, the installation strategy is adjusted.

3. The method for dynamically monitoring the behavior of a pest population based on the Internet of Things according to claim 2, wherein The performing spatial and hierarchical mapping on the original monitoring data, and performing normalization conversion on the wind field, temperature field, and water vapor field to obtain a preprocessing data set constructed by the unified quantization representation of different physical field data includes: Using a linear mapping function to convert multiple groups of original monitoring data to a unified dimension, and the linear mapping function is selected based on the instrument calibration data at the monitoring site; Integrating the original monitoring data with a unified dimension of each sensor to construct a unified conversion matrix; the conversion matrix is jointly composed of the conversion coefficient of the wind field, the conversion coefficient of the temperature field, and the conversion coefficient of the humidity field; The product of the conversion matrix and the original data vector and the bias vector are added to equal the mapped unified physical field data vector; the original data vector is generated by separating and extracting different physical field data detected by various sensors connected to the multi-physical field sensor network in real time; Normalizing the mapped unified physical field data vector to map corresponding physical field data in the mapped unified physical field data vector to a first interval to obtain a normalized data vector; Selecting normalized data vectors according to preset integration requirements to form the preprocessed data set; The mapped unified physical field data vector has the same dimension as the original data vector, and the bias vector is composed of a wind field bias, a temperature field bias, and a humidity field bias.

4. The method for dynamically monitoring the behavior of a pest population based on the Internet of Things according to claim 3, wherein The pre-processed data set is linked and integrated with the pest behavior data collected in the Internet of Things to establish a response model for real-time matching of pest behavior with environmental physical conditions, including: Determining the normalized data vector output by each sensor node based on the preprocessed data set, each sensor node having a spatial coordinate and a timestamp, and constructing a spatiotemporal data matrix based on the spatial coordinate and the timestamp in combination with the normalized data vector output by each sensor node; Based on the data of each physical field and the weight coefficient corresponding to each physical field data, a pest behavior index is established as a quantitative index of the response of the environmental physical field to the dynamic behavior of the pest, so as to construct a pest behavior index model through weighted linear combination; Calculate the average pest behavior index, standard deviation and spatial gradient in the monitoring area according to the pest behavior index of each sensor node and the spatiotemporal data matrix, wherein the average pest behavior index, standard deviation and spatial gradient are used to characterize the dynamic changes of pest behavior; The pest behavior index model is linked and integrated with the pest behavior data collected in the Internet of Things to establish the response model, and the response model is called to generate a linkage monitoring result based on the average pest behavior index, standard deviation and spatial gradient.

5. The method for dynamically monitoring the behavior of a pest population based on the Internet of Things according to claim 4, characterized in that, The step of comparing the linkage monitoring result output by the response model with the actual observation result of the monitoring area, and adjusting the matching rule of the response model between the pest behavior and the environmental physical conditions by using environmental feedback to optimize the response model, includes: Acquire actual observation results of the monitoring area from the multi-physics field sensor network, and compare the actual observation results of the monitoring area with the linkage monitoring results to calculate an error vector between the monitoring index under the current environment and the historical monitoring index in the linkage monitoring results; Calibrate and adjust the model parameters of the response model according to the error vector to determine the correction coefficients of each monitoring indicator, wherein the correction coefficients include an indicator calibration coefficient of average pest behavior, a standard deviation calibration coefficient, a gradient calibration coefficient, and a time series calibration coefficient, and calculate a calibration correction amount based on the correction coefficients; Apply the calibration correction amount to the linkage monitoring result to update the response model, and generate a final monitoring report and real-time feedback information on pest behavior by integrating the updated linkage monitoring result and output through the feedback interface; Among them, the calibration correction amount is obtained by multiplying each element in the correction coefficient and the error vector item by item.

6. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method according to any one of claims 1-5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, the steps of the method according to any one of claims 1-5 are implemented.

Images