Agricultural pest AI early warning and unmanned aerial vehicle cluster precise prevention and control system and method

Abstract

The invention discloses an agricultural pest AI early warning and unmanned aerial vehicle cluster precise prevention and control system and method, and relates to the technical field of agricultural AI early warning. Crop pictures and weather data are collected, the types, distribution conditions and diffusion conditions of pests are identified, and pest abnormal conditions and pest development directions are predicted according to the weather data in a future set time period; the method comprises the following steps: collecting flight data of an unmanned aerial vehicle in a pest development direction, predicting a pesticide spraying abnormal condition of the unmanned aerial vehicle according to weather data and the flight data, analyzing a pest control abnormal condition according to a pest abnormal condition and the pesticide spraying abnormal condition, and scheduling the number of the unmanned aerial vehicles according to a crop growth stage and the pest control abnormal condition. According to the method, pest abnormity is judged by combining pest abnormity prediction and unmanned aerial vehicle pesticide spraying abnormity in the pest development direction, so that the optimal unmanned aerial vehicle allocation number is determined by combining the crop growth stage, resource allocation optimization is facilitated, and precise prevention and control of farmland are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural AI early warning technology, in particular to an agricultural pest AI early warning and unmanned aerial vehicle cluster precision control system and method. BACKGROUND

[0002] The agricultural pest AI early warning collects multi-source data in the field through Internet of Things sensors, remote sensing technology, unmanned aerial vehicle patrol and other means, and uses artificial intelligence algorithms to analyze the data, thereby realizing the early and quantitative prediction of the occurrence period, occurrence amount, occurrence range and diffusion trend of pests. Under the unified scheduling of the task-level control system, multiple unmanned aerial vehicles work as a cooperative whole, autonomously plan paths, cooperatively work and collect data based on the spatial prescription map provided by the AI early warning system, and realize precision pesticide application in high-pest areas.

[0003] The prior art mostly analyzes the number of unmanned aerial vehicles by analyzing the farmland area, crop type, unmanned aerial vehicle spraying efficiency, etc., but lacks consideration of the spraying efficiency of unmanned aerial vehicles in the direction of pest spread. When the unmanned aerial vehicle spraying is abnormal and falls on the pest diffusion path, it will lead to the rampant spread of pests, thereby reducing the efficiency of agricultural pest control.

[0004] To solve the above problems, the present application provides an agricultural pest AI early warning and unmanned aerial vehicle cluster precision control system and method. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides an agricultural pest AI early warning and unmanned aerial vehicle cluster precision control system and method. The present application determines the abnormality of pests by combining pest abnormality prediction and abnormal unmanned aerial vehicle pesticide spraying in the direction of pest development, thereby determining the optimal number of unmanned aerial vehicles according to the growth stage of crops, which is beneficial to optimize resource allocation and realize precision control of farmland.

[0006] To achieve the above purpose, the present application provides the following technical solutions: The agricultural pest AI early warning and unmanned aerial vehicle cluster precision control method comprises the following specific steps: Collecting crop pictures and weather data continuously within a set time period, identifying the types, distribution and diffusion of pests; Predicting pest abnormality and the direction of pest development according to the weather data of a future set time period; Collecting flight data of unmanned aerial vehicles in the direction of pest development, and predicting abnormal pesticide spraying of unmanned aerial vehicles according to the weather data and flight data of a future set time period; Analyzing pest control abnormality according to pest abnormality and abnormal pesticide spraying, and scheduling the number of unmanned aerial vehicles according to the growth stage of crops and pest control abnormality.

[0007] Preferably, the continuous collection of crop pictures and weather data within a set time period, and the identification of the species, distribution, and spread of pests include the following specific steps: The continuous collection of crop pictures and weather data within a set time period, and the continuous collection of crop pictures and weather data within a set time period, and the weather data including temperature, humidity, wind direction and wind speed; Training a farmland pest identification model, inputting crop pictures, generating a pest distribution heat map, and automatically identifying the species, density, location, direction, and speed of spread of pests.

[0008] Preferably, the prediction of pest abnormal conditions and the development direction of the pest according to the weather data of the future set time period includes the following specific steps: Obtain weather data for a future set time period; Construct a pest spatio-temporal diffusion model, input the pest distribution heat map, diffusion speed at the current time, and weather data for a future set time period, and output a pest prediction distribution map for a future set time period; According to the pest prediction distribution map, extract the pest abnormal data and the development direction of the pest, and the pest abnormal data includes the number of pest abnormal regions; According to the pest abnormal region number divided by the total number of pest prediction regions, the pest abnormal value is obtained.

[0009] Preferably, the flight data of the unmanned aerial vehicle in the direction of pest development, and the prediction of the abnormal situation of pesticide spraying of the unmanned aerial vehicle according to the weather data and flight data of the future set time period includes the following specific steps: Collect flight data of the unmanned aerial vehicle in the direction of pest development, including motor load, pumping pressure, and unit time pesticide spraying amount; Obtain the standard motor load, standard pumping pressure, and standard unit time pesticide spraying amount of the unmanned aerial vehicle when it leaves the factory, calculate the motor load abnormal value by dividing the motor load by the standard motor load, calculate the pumping pressure abnormal value by dividing the pumping pressure by the standard pumping pressure, calculate the pesticide spraying amount abnormal value by dividing the unit time pesticide spraying amount by the standard unit time pesticide spraying amount, and calculate the unmanned aerial vehicle flight abnormal value by weighted sum of the motor load abnormal value, pumping pressure abnormal value and pesticide spraying amount abnormal value; Collect wind speed and maximum wind speed of the unmanned aerial vehicle for a future set time period, and calculate the wind speed abnormal value by dividing the wind speed by the maximum wind speed of the unmanned aerial vehicle; According to the product of the unmanned aerial vehicle flight abnormal value and the wind speed abnormal value, the pesticide spraying abnormal value of the unmanned aerial vehicle is obtained.

[0010] Preferably, the analysis of pest control abnormality according to the pest abnormality and pesticide spraying abnormality, and the scheduling of the number of unmanned aerial vehicles according to the growth stage of crops and the pest control abnormality includes the following specific steps: The pest control anomaly value is obtained by weighted summation of the pest anomaly value and the pesticide spraying anomaly value; The pest control anomaly threshold value is preset according to the crop growth stage; The optimal control unmanned aerial vehicle quantity is obtained according to the pest control anomaly value divided by the pest control anomaly threshold value and multiplied by the standard unmanned aerial vehicle configuration quantity.

[0011] The agricultural pest AI early warning and unmanned aerial vehicle cluster precision control system is used for realizing the agricultural pest AI early warning and unmanned aerial vehicle cluster precision control method, and comprises: The pest identification module is used for continuously collecting crop pictures and weather data in a set time period, identifying the type, distribution and diffusion of pests; The pest prediction module is used for predicting the pest anomaly situation and the development direction of pests according to the weather data of a future set time period; The pesticide spraying anomaly analysis module is used for collecting flight data of the unmanned aerial vehicle in the development direction of pests, and predicting the pesticide spraying anomaly situation of the unmanned aerial vehicle according to the weather data and the flight data of a future set time period; The control anomaly analysis module is used for analyzing the pest control anomaly situation according to the pest anomaly situation and the pesticide spraying anomaly situation; The unmanned aerial vehicle scheduling module is used for scheduling the unmanned aerial vehicle quantity according to the crop growth stage and the pest control anomaly situation.

[0012] An electronic device comprises a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the agricultural pest AI early warning and unmanned aerial vehicle cluster precision control method by calling the computer program stored in the memory.

[0013] A computer readable storage medium stores instructions, which, when executed on a computer, cause the computer to execute the agricultural pest AI early warning and unmanned aerial vehicle cluster precision control method.

[0014] Compared with the prior art, the beneficial effects of the present application are as follows: crop pictures and weather data are continuously collected in a set time period, the type, distribution and diffusion of pests are identified, the pest anomaly situation and the development direction of pests are predicted according to the weather data of a future set time period, flight data of the unmanned aerial vehicle in the development direction of pests are collected, the pesticide spraying anomaly situation of the unmanned aerial vehicle is predicted according to the weather data and the flight data of a future set time period, the pest control anomaly situation is analyzed according to the pest anomaly situation and the pesticide spraying anomaly situation, and the unmanned aerial vehicle quantity is scheduled according to the crop growth stage and the pest control anomaly situation. The present application determines the optimal unmanned aerial vehicle deployment quantity by combining pest anomaly prediction and unmanned aerial vehicle pesticide spraying anomaly in the development direction of pests, thereby optimizing resource allocation and realizing precision control of farmland. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0016] Figure 1 The present application is an agricultural pest AI early warning and unmanned aerial vehicle cluster precision control method process schematic diagram. Figure 2 The present application is an abnormal pest prediction process schematic diagram. Figure 3 The present application is an abnormal unmanned aerial vehicle pesticide spraying prediction process schematic diagram. Figure 4 The present application is an agricultural pest AI early warning and unmanned aerial vehicle cluster precision control system structure schematic diagram. Figure 5 The present application is an electronic device structure schematic diagram. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0018] Embodiment 1

[0019] As shown in the present application, an embodiment is provided: an agricultural pest AI early warning and unmanned aerial vehicle cluster precision control method, which comprises the following specific steps: Figure 1 In a set time period, crop pictures and weather data are continuously collected, and the species, distribution and spread of pests are identified. In this embodiment, in a set time period, crop pictures and weather data are continuously collected, and the species, distribution and spread of pests are identified, which comprises the following specific steps: In a set time period, crop pictures and weather data are continuously collected, and the species, distribution and spread of pests are identified. In a set time period, crop pictures and weather data are continuously collected, and the species, distribution and spread of pests are identified. In this embodiment, in the specific implementation, a high-definition camera is carried by a unmanned aerial vehicle, which flies according to a preset route, continuously shoots global and local pictures of farmland in a set time period, a meteorological data collection integrated device is deployed among the farmland, real-time collection of temperature, humidity, wind speed, wind direction, light intensity and leaf humidity and other indicators is carried out, and the picture collection and meteorological data collection time stamps are synchronized. The crop picture is input into the farmland pest identification model to generate a pest distribution heat map, and the pest species, pest density, distribution position, diffusion direction, and diffusion speed are automatically identified.

[0020] In the specific implementation of the embodiment, in order to improve the model identification accuracy, the collected pictures are subjected to batch processing such as size standardization, image enhancement, and denoising, agricultural experts are invited to use a labeling tool to label the pests in the pictures, each picture corresponds to an XML file recording the position and species of the pests, the labeled pictures are divided into a training set, a validation set, and a test set in a ratio of 8:1:1, a farmland pest identification model weight pre-trained on a large dataset is used for transfer learning, the training set is input into the farmland pest identification model for training, the farmland pest identification model learns the mapping relationship from the picture pixels to the pest species and position, the training process is monitored through the validation set to prevent overfitting, and the model performance is evaluated using the test set; The trained farmland pest identification model is deployed to a cloud server to automatically identify the pests in newly collected pictures in batches, the identification result of each picture is bound with its GPS information, GIS software is used to assign different weights to each GPS point according to the number of pests, a continuous and smooth pest distribution heat map is generated through kernel density estimation, the blue area represents low pest density, the green-yellow area represents moderate pest density, and the orange-red area represents high pest density, the pest data and the weather data are associated through the timestamp and the position information, the quantitative relationship between different weather factors and the pest occurrence degree is analyzed using a random forest, for example, according to the pest distribution heat map, the planthoppers in the northeast corner of a farmland are in high density and the pest density is significantly higher than that in other areas, combined with the fact that the area is close to a canal and the humidity is continuously higher than 85% and the temperature is stable at 25-28°C, which is the most suitable environment for planthopper reproduction; Two consecutive pest distribution heat maps are obtained, the farthest distances from the pest center points to the edges of the pest diffusion area in the two pest distribution heat maps are measured, and the diffusion speed is obtained by dividing the difference between the two farthest distances by the interval time. All new pest areas are obtained, the azimuth angles of the new pest areas relative to the original center are calculated, and an azimuth angle histogram is drawn, and the peak direction is the main diffusion direction.

[0021] The weather data of a future set time period is obtained. As shown in Figure 2 In the embodiment, predicting pest abnormal conditions and the development direction of the pests according to the weather data of a future set time period includes the following specific steps: The weather data of a future set time period is obtained. A pest spatiotemporal diffusion model is constructed, inputting a pest distribution heat map at the current time, a diffusion speed, and weather data for a future set time period, and outputting a pest prediction distribution map for the future set time period; In the specific implementation of the embodiment, the farmland is divided into a grid composed of N x N square cells in GIS, each cell represents a fixed-size real area, the input current time pest distribution heat map is superimposed on the grid, an initial pest density value M0(i, j) is assigned to each cell (i, j), the initial pest density value can take the average density of the heat map within the cell range, the weather data for the future set time period is processed into a format aligned with the grid, for planar data such as wind direction, a spatial interpolation method is used to assign data to each cell to obtain the wind direction of each cell, and the above steps convert continuous input data into a discrete format that can be processed by the model; A logistic growth model is used to simulate the reproduction of the population within the cell, which can be expressed as: wherein, M(i, j) is the pest density value of the cell (i, j), is the diffusion speed, is the maximum pest density value supported by the crop in the cell, i.e., the environmental carrying capacity, the maximum value in the stable state is recorded by monitoring the pest density in the control farmland without pesticide interference for a long time, is the interval length between the future set time period and the current time period, and the model describes the nonlinear saturation characteristics of population growth; The external migration amount is calculated to simulate the migration of pests from adjacent cells, and the external migration amount calculation formula can be expressed as: wherein, M(m, n) is the pest density value of the source cell (m, n), is a diffusion probability function, which is used to quantify the influence of wind direction and wind speed on pest migration, indicating that the diffusion probability is positively correlated with wind speed, negatively correlated with the angle between the wind direction and the direction from the source cell (m, n) to the cell (i, j), and positively correlated with the diffusion speed, reflecting that pests prefer to diffuse along the downwind direction and the faster the wind speed, the farther the diffusion, is the direction angle from the source cell (m, n) to the cell (i, j), is the wind speed direction, is the wind speed, is the wind direction empirical coefficient, to ensure downwind diffusion, is the wind speed empirical coefficient, To enhance the effect of wind speed, drone aerial photography migration trajectories were collected to record the migration probability of pests under different wind speeds and wind direction angles. Nonlinear regression or machine learning was used to fit functions. With the wind direction angle fixed, the power-law relationship between migration probability and wind speed was analyzed to estimate empirical wind speed coefficients. With the wind speed fixed, the cosine relationship between migration probability and wind direction angle was analyzed to estimate empirical wind direction coefficients. This is a diffusion kernel based on wind direction and velocity, used to describe the orientation angle of pests from source cell (m, n) to cell (i, j) as a function of distance d and distance d. The attenuation mode, The attenuation coefficient is determined by monitoring the migration trajectories of pests, statistically analyzing the percentage of migrating individuals at different distances, fitting a negative exponential function to the frequency distribution of migration distances, and then obtaining the attenuation coefficient through maximum likelihood estimation. Let be the distance between cell (i, j) and source cell (m, n). It is an exponential function with the real number e as its base; The insect population density of cell (i,j) in a future time period is the sum of internal growth and external migration, i.e. ; The processed grid data M0(i, j) is loaded into the model as the initial state. A time step is set, and the model is iterated until the predetermined prediction duration is reached. After the model finishes running, the insect population density grid for the future set time period is output. Each predicted grid is converted back to a standard spatial data format. In the GIS platform, the predicted insect population density values ​​are re-rendered as a heatmap, with the color scheme matching the input heatmap. Figure 1 This allows for the visualization of several consecutive days' forecast heatmaps, providing an intuitive view of the predicted distribution of pests, high-risk areas, and the spread paths, speed, and direction of pests.

[0022] Based on the pest prediction distribution map, abnormal pest data and the development direction of pests are extracted. The abnormal pest data includes the number of abnormal pest areas. In this embodiment, the insect population density values ​​of all grids within the insect pest prediction distribution map area are obtained, the deviation value of the insect population density value of each grid is calculated from the insect population density value of the corresponding grid in the current insect distribution heat map, and the grids that exceed the preset deviation threshold are marked as insect pest abnormal areas, and the number of insect pest abnormal areas is counted. Calculate the centroid of the current pest distribution heatmap and the predicted pest distribution map, which is the weighted average position of the insect population density of all grids. Connect the centroids of the two time points to obtain the vector that represents the direction of pest development. Divide the length of this vector by the interval between the two time points to obtain the average diffusion rate. The pest anomaly value is obtained by dividing the number of abnormal pest areas by the total number of pest prediction areas.

[0023] In this embodiment, by analyzing abnormal pest areas, the outbreak point of pests can be identified, and the area requiring emergency intervention can be quickly located.

[0024] Collect flight data of drones along the direction of pest development, and predict abnormal pesticide spraying situations of drones based on weather data and flight data for a future time period. like Figure 3 As shown, in this embodiment, collecting flight data of the drone along the direction of pest development and predicting abnormal pesticide spraying by the drone based on weather data and flight data for a future set time period includes the following specific steps: Collect flight data of the drone in the direction of pest development, including motor load, pumping pressure and spraying amount per unit time; In this embodiment, the direction of pest development represents the future spread path. If the drone's spraying happens to fall on this path, it will cause the pest to spread rampantly.

[0025] Obtain the standard motor load, standard pumping pressure, and standard spray volume per unit time of the drone at the time of manufacture. Obtain abnormal values ​​of motor load by dividing the motor load by the standard motor load, abnormal values ​​of pumping pressure by dividing the pumping pressure by the standard pumping pressure, and abnormal values ​​of spray volume by dividing the spray volume per unit time by the standard spray volume per unit time. Obtain abnormal values ​​of drone flight by weighted summation of abnormal values ​​of motor load, pumping pressure, and spray volume. In this embodiment, the motor load is obtained by reading real-time current / power data through the motor controller, reflecting the load status of the drone's power system. The pumping pressure is obtained by monitoring the pipeline pressure in real time through a pressure sensor, reflecting the stability of the drone's pesticide delivery. If the pressure fluctuation is too large, it may be due to nozzle blockage, pipeline leakage, changes in pesticide viscosity, etc. The amount of pesticide sprayed per unit time is obtained by measuring the pesticide flow rate through a flow meter, reflecting the uniformity of pesticide spraying by the drone. Abnormal spraying may be due to insufficient pressure, nozzle wear, changes in pesticide concentration, etc. Collect wind speed and the maximum wind resistance speed of the drone for a future set time period, and obtain the wind speed anomaly value by dividing the wind speed for the future set time period by the maximum wind resistance speed of the drone. The abnormal values ​​of pesticide spraying by the drone are obtained by multiplying the abnormal values ​​of drone flight and wind speed.

[0026] In practical implementation, drones often waste pesticides due to drifting, missed spraying, overspraying, and pesticide leakage. Timely warnings of problems such as motor overload and abnormal pump pressure can improve overall operational efficiency.

[0027] Analyze abnormal pest control situations based on abnormal pest and pesticide spraying situations, and schedule the number of drones according to crop growth stages and abnormal pest control situations. In the embodiment, the pest control abnormality is analyzed according to the pest abnormality and the pesticide spraying abnormality, and the number of unmanned aerial vehicles is scheduled according to the crop growth stage and the pest control abnormality, including the following specific steps: The pest control abnormality value is obtained by weighted sum of the pest abnormality value and the pesticide spraying abnormality value; The pest control abnormality threshold is preset according to the crop growth stage; In the specific implementation of the embodiment, the crop seedlings in the seedling stage are tender, the photosynthetic area is small, and a small amount of pests need to be prevented from damaging the growth point. The stems and leaves of the crop in the vegetative growth stage are vigorous, and the stress resistance is strong, and the pest density needs to be controlled to avoid nutrient competition. The crop in the reproductive growth stage is sensitive to flowers / fruits, which affects yield and quality, and needs to avoid drug damage to cause flower and fruit drop. The crop in the mature stage has strong stress resistance, and the pest needs to be controlled considering pesticide residues; The best control unmanned aerial vehicle number is obtained by dividing the pest control abnormality value by the pest control abnormality threshold and multiplying the standard unmanned aerial vehicle configuration number.

[0028] In the specific implementation of the embodiment, the standard unmanned aerial vehicle configuration number is the initial preset unmanned aerial vehicle number, and the setting method of the weight and the threshold is: collecting historical crop pictures, historical weather data and historical unmanned aerial vehicle flight data of a plurality of farmlands, inputting the above data into each step of the embodiment to obtain the pest control abnormality value and the best number of unmanned aerial vehicles, and inputting the historical actual unmanned aerial vehicle deployment number and the best number of unmanned aerial vehicles into the fitting software pre-trained to obtain the weight and the threshold value with the highest judgment accuracy. In the specific implementation of the embodiment, insufficient number of unmanned aerial vehicles will cause delay of work, miss the best opportunity, and greatly reduce the control effect, and even cause crop yield reduction. Too many unmanned aerial vehicles will cause resource idling and waste. According to the best number of unmanned aerial vehicles calculated in advance according to the control demand, the resources can be reasonably deployed to realize rapid response and precise attack.

[0029] Embodiment 2

[0030] As shown in Figure 4 The agricultural pest AI early warning and unmanned aerial vehicle cluster precise control system is realized based on the above agricultural pest AI early warning and unmanned aerial vehicle cluster precise control method, and includes: The pest identification module is used for continuously collecting crop pictures and weather data in a set time period, identifying the species, distribution and diffusion of pests; The pest prediction module is used for predicting the pest abnormality and the development direction of the pest according to the weather data of a future set time period; The pesticide spraying anomaly analysis module is used to collect flight data of drones in the direction of pest development and predict pesticide spraying anomalies of drones based on weather data and flight data for a future time period. The anomaly analysis module is used to analyze anomalies in pest control based on abnormal pest conditions and abnormal pesticide spraying conditions. The drone scheduling module is used to schedule the number of drones based on crop growth stages and abnormal pest control situations.

[0031] Example 3

[0032] like Figure 5 As shown, this embodiment provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned method for AI early warning and precise control of agricultural pests by calling the computer program stored in the memory.

[0033] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the agricultural pest AI early warning and drone swarm precision control method provided in the above-described embodiment. The electronic device may also include other components for implementing its functions. For example, it may have wired or wireless network interfaces and input / output interfaces for data input and output, which will not be elaborated upon in this embodiment.

[0034] Example 4

[0035] This embodiment proposes a computer-readable storage medium storing instructions that, when a computer program is run on a computer device, cause the computer device to execute the aforementioned method for AI-based early warning and precise control of agricultural pests by drone swarms.

[0036] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0037] It should be understood that the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0038] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product, which includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the flow or function according to the embodiments of the present application is wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD) or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0039] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the disclosed embodiments of the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0040] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of units is only one of them. Actual implementation can have another division manner. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0041] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units, and part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0042] In the description of the present specification, the description referring to the terms "one embodiment", "an example", "a specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the present application, and the illustrative description of the above terms in the present specification does not necessarily refer to the same embodiment or example, and the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0043] The preferred embodiments of the application disclosed above are only used to help explain the application, and the preferred embodiments do not describe all the details and limit the application to the specific embodiments. Obviously, many modifications and changes can be made according to the content of the present specification. The present specification selects and describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited by the claims and their entire scope and equivalents.

Claims

1. A method for AI-based early warning and precision control of agricultural pests using drone swarms, characterized in that... The specific steps include the following: The system continuously collects crop images and weather data within a set time period to identify the types, distribution, and spread of pests. Predict abnormal pest situations and the development direction of pests based on weather data for a future time period. Collect flight data of drones along the direction of pest development, and predict abnormal pesticide spraying situations of drones based on weather data and flight data for a future time period. Analyze abnormal pest control situations based on abnormal pest and pesticide spraying conditions, and schedule the number of drones according to crop growth stages and abnormal pest control conditions.

2. The method for AI-based early warning and precision control of agricultural pests using drone swarms as described in claim 1, characterized in that, The process of continuously collecting crop images and weather data within a set time period to identify the types, distribution, and spread of pests includes the following specific steps: Crop images and weather data are continuously collected within a set time period, including temperature, humidity, wind direction, and wind speed. Train a farmland pest identification model by inputting crop images, generate a pest distribution heat map, and automatically identify the pest species, population density, distribution location, diffusion direction, and diffusion speed.

3. The method for AI-based early warning and precision control of agricultural pests using drone swarms as described in claim 2, characterized in that, The method of predicting abnormal pest situations and the development direction of pests based on weather data for a future time period includes the following specific steps: Obtain weather data for a future time period; Construct a spatiotemporal diffusion model for pests, inputting the current pest distribution heatmap, diffusion rate, and weather data for a future set time period, and outputting a predicted pest distribution map for the future set time period; Based on the pest prediction distribution map, abnormal pest data and the development direction of pests are extracted. The abnormal pest data includes the number of abnormal pest areas. The pest anomaly value is obtained by dividing the number of abnormal pest areas by the total number of pest prediction areas.

4. The method for AI-based early warning and precision control of agricultural pests using drone swarms as described in claim 3, characterized in that, The process of collecting flight data of drones along the direction of pest development and predicting abnormal pesticide spraying by drones based on weather data and flight data for a future time period includes the following specific steps: Collect flight data of the drone in the direction of pest development, including motor load, pumping pressure and spraying amount per unit time; Obtain the standard motor load, standard pumping pressure, and standard spray volume per unit time of the drone at the time of manufacture. Obtain abnormal values ​​of motor load by dividing the motor load by the standard motor load, abnormal values ​​of pumping pressure by dividing the pumping pressure by the standard pumping pressure, and abnormal values ​​of spray volume by dividing the spray volume per unit time by the standard spray volume per unit time. Obtain abnormal values ​​of drone flight by weighted summation of abnormal values ​​of motor load, pumping pressure, and spray volume. Collect wind speed and the maximum wind resistance speed of the drone for a future set time period, and obtain the wind speed anomaly value by dividing the wind speed for the future set time period by the maximum wind resistance speed of the drone. The abnormal values ​​of pesticide spraying by the drone are obtained by multiplying the abnormal values ​​of drone flight and wind speed.

5. The method for AI-based early warning and precision control of agricultural pests using drone swarms as described in claim 4, characterized in that, The process of analyzing abnormal pest control situations based on abnormal pest and pesticide spraying conditions, and scheduling the number of drones according to crop growth stages and abnormal pest control conditions, includes the following specific steps: The abnormal values ​​of pest control are obtained by weighted summation of the abnormal values ​​of pests and pesticide spraying. Preset abnormal thresholds for pest control based on crop growth stages; The optimal number of pest control drones is obtained by dividing the abnormal value of pest control by the abnormal threshold of pest control and then multiplying it by the standard number of drones configured.

6. An agricultural pest AI early warning and drone swarm precision control system, used to implement the agricultural pest AI early warning and drone swarm precision control method as described in any one of claims 1-5, characterized in that, include: The pest identification module is used to continuously collect crop images and weather data within a set time period to identify the types, distribution, and spread of pests. The pest prediction module is used to predict abnormal pest situations and the development direction of pests based on weather data for a future time period. The pesticide spraying anomaly analysis module is used to collect flight data of drones in the direction of pest development and predict pesticide spraying anomalies of drones based on weather data and flight data for a future time period. The anomaly analysis module is used to analyze anomalies in pest control based on abnormal pest conditions and abnormal pesticide spraying conditions. The drone scheduling module is used to schedule the number of drones based on crop growth stages and abnormal pest control situations.

7. An electronic device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes the agricultural pest AI early warning and drone swarm precision control method according to any one of claims 1-5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: The device stores instructions that, when executed on a computer, cause the computer to perform the agricultural pest AI early warning and drone swarm precision control method as described in any one of claims 1-5.

Images