A method and system for managing trusted association between a drone and a pilot at two locations

Abstract

This application relates to the field of unmanned aerial vehicle (UAV) management technology, and in particular to a method and system for reliable association management of UAV and pilot positions. The method includes: acquiring a set of farmland information for UAV operations; based on this set, analyzing the spatial compatibility between the pilot's position and the farmland from a spatial perspective, while simultaneously verifying the compliance of the matching between pesticide type and field crops, to obtain a compliant association information set; acquiring a dynamic environmental information set; based on this set and combined with the compliant association information set, predicting and analyzing the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effects of wind field, field heat convection, and multi-rotor downwash airflow in the farmland, to obtain a spraying prediction information set; and generating and outputting a collaborative management strategy for pilot-UAV-pesticide based on the spraying prediction information set. This achieves a dynamic and reliable association between the pilot, UAV, and pesticides, improves the accuracy of spraying predictions, compensates for lag, and thus enhances the precision of plant protection operations.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) management technology, and in particular to a method and system for managing the trusted association between the dual positions of a UAV and its pilot. Background Technology

[0002] With the acceleration of agricultural modernization, drone-based plant protection operations have been widely used in agricultural production due to their high efficiency and precision. Current drone-based plant protection management typically relies on positioning systems to obtain the real-time coordinates of the pilot and drone, confirming the compliance of the work area by determining whether the coordinates are within the pre-defined boundaries of the work plot. Simultaneously, it checks the matching relationship between the selected pesticide type and the target crop species based on a pre-set task list. Regarding environmental factors, existing technologies mostly use wind speed and direction data provided by weather stations, combined with simple physical models to estimate the drift distance of pesticide droplets, using this as a reference for adjusting flight paths or spraying parameters. Management strategies are primarily generated based on real-time data feedback collected by sensors, with the pilot making manual decisions or executing pre-set automated commands based on information displayed at the ground station to complete the spraying task.

[0003] However, existing technologies lack a comprehensive analysis of the dynamic spatial relationship between the pilot's position, the drone's status, and the farmland boundary. Furthermore, the failure to thoroughly verify the precise adaptation of pesticide properties to crop canopy structure creates blind spots in the multi-dimensional compliance verification of the human-machine-pesticide system. In addition, current predictions often neglect the coupling effect of field heat convection and rotor downwash airflow, and fail to consider the time lag characteristics of the entire system chain. This makes the generated management strategies ill-suited to complex and changing operating environments, easily leading to uneven spraying or pesticide damage in non-target areas. Summary of the Invention

[0004] This application provides a method and system for managing the trusted association between the locations of a drone and its pilot, in order to solve the above-mentioned problems.

[0005] Firstly, this application provides a method for reliable association management of dual locations of drones and drone pilots. The method includes: acquiring a set of information on farmland where the drone is operating; based on the set of information on farmland where the drone is operating, analyzing the spatial compatibility between the drone pilot's location and the operating farmland from a spatial dimension, while verifying the compliance of the matching between the pesticide type and the field crops, to obtain a compliant association information set; acquiring a set of dynamic environmental information; based on the dynamic environmental information set and combined with the compliant association information set, predicting and analyzing the spatiotemporal diffusion interference characteristics of the sprayed pesticide caused by the coupling effect of wind field, field heat convection, and multi-rotor downwash airflow in the operating farmland, to obtain a spraying prediction information set; and generating and outputting a collaborative management strategy for drone pilot-drone-pesticide based on the spraying prediction information set.

[0006] Through the above technical solutions, a closed-loop reliable management system was constructed. First, the constructed compliance-related information set sets strict spatial and chemical safety boundaries for the entire operation process, ensuring the compliance of the basic human-machine-pesticide relationship and providing accurate initial constraints for subsequent environmental predictions. On this basis, the introduced dynamic environmental information set fully utilizes the drug parameters and crop structure data in the compliance-related information set to accurately simulate the spatiotemporal diffusion interference characteristics under the interaction of three key factors: natural wind field, field thermal convection, and multi-rotor downwash airflow. This solves the technical problem that existing single-factor models cannot accurately predict droplet trajectories under complex flow fields. The generated spraying prediction information set not only reveals potential drift risks but also provides high-precision data support for the formulation of control strategies. Furthermore, based on the spraying prediction information set, an innovative full-link time lag compensation mechanism was introduced, transforming the predicted future spatiotemporal deviations into specific pilot command lead, drone speed adjustment levels, and dynamic adjustment strategies for drug flow, achieving the foresight and adaptability of the management strategy. These three steps are interconnected. Spatial and drug compliance verification ensures the bottom-line safety of the operation, three-dimensional coupled diffusion prediction improves the process accuracy of the operation, and the collaborative management strategy based on time delay compensation ensures the real-time effectiveness of the execution. The three work together to reduce the risk of pesticide damage in non-target areas and avoid missed spraying or over-spraying due to delays, thus realizing the high efficiency, precision and intelligence of drone plant protection operations.

[0007] Optionally, based on the drone operation farmland information set, the spatial adaptation relationship between the drone operator's location and the farmland is analyzed from a spatial dimension, while verifying the compliance of the matching between the pesticide type and the crop in the field, to obtain a compliance-related information set. This includes: the drone operation farmland information set includes plant protection operation information, drone operator information, and drone information; based on the drone operator information, the drone information, and the plant protection operation information, the relative distance between the current location of the drone operator and the drone and the farmland operation boundary is analyzed to obtain spatial compliance information; based on the plant protection operation information, the adaptation information between the pesticide droplet size and the crop canopy structure is analyzed, and the compatibility information between the pesticide type and crop resistance is verified to obtain pesticide compliance information; the spatial compliance information and the pesticide compliance information are integrated to construct the compliance-related information set.

[0008] Through the above technical solutions, a deep, multi-dimensional linkage analysis was conducted on the pilot's position, drone position, farmland boundary geometry, and the physical characteristics of pesticide droplets and crop biological characteristics. By collaboratively constructing spatial compliance information and pesticide compliance information, not only was the problem of isolated spatial verification and pesticide verification in existing methods solved, but a complete human-machine-pesticide-field credible correlation evaluation system was also formed. This system can identify and intercept potential spatial violation risks and pesticide damage risks in the early stages of operation, providing high-quality input data for subsequent spraying prediction based on complex environmental coupling, thereby improving the overall safety and scientific nature of plant protection operations.

[0009] Optionally, the process of constructing the drug compliance information includes: based on the plant protection operation information, analyzing the penetration path and attachment position of drug droplets of different sizes inside the canopy to obtain droplet-canopy compatibility information; based on the droplet-canopy compatibility information, verifying the compatibility information between drug type and crop resistance for different deposition areas to obtain the drug compliance information.

[0010] The above technical solution achieves a significant leap from macroscopic drug matching to microscopic canopy internal deposition compatibility. First, by utilizing droplet dynamics models to analyze the penetration paths and attachment locations of droplets of different sizes within the complex canopy structure, precise droplet-canopy compatibility information is obtained. Based on this, the granularity of drug compliance verification is refined to specific deposition areas within the canopy. This location-first, verification-later processing mechanism allows for the keen detection of localized phytotoxic risks overlooked by traditional overall verification methods. This solves the technical challenge of damage to sensitive areas even when the drug is generally applicable, due to uneven droplet distribution. Through this hierarchical compatibility verification, the final generated drug compliance information not only includes the legality of the drug type but also incorporates a safety assessment based on the actual deposition distribution. This provides a data foundation for the subsequent generation of spraying prediction information sets, effectively ensuring the ecological safety and application effectiveness of plant protection operations.

[0011] Optionally, based on the dynamic environmental information set and combined with the compliance-related information set, the method for predicting and analyzing the spatiotemporal diffusion interference characteristics of the sprayed pesticide caused by the coupling effects of the farmland wind field, field thermal convection, and multi-rotor downwash airflow is used to obtain a spraying prediction information set. This includes: the dynamic environmental information set includes field surface temperature, farmland wind field information, and rotor airflow information; based on the farmland wind field information, the influence of the farmland wind field on the horizontal transport direction and velocity of pesticide droplets is analyzed to obtain wind field airflow disturbance information; based on the rotor airflow information, By combining the wind field airflow disturbance information, the influence of the multi-rotor downwash airflow on the forced settling velocity and lateral diffusion range of drug droplets is analyzed to obtain downwash airflow disturbance information. Based on the field surface temperature and the downwash airflow disturbance information, the influence of thermal convection on the lifting intensity and height distribution of near-surface vertical airflow is analyzed to obtain diffusion characteristic information. Based on the diffusion characteristic information and the compliance association information set, the landing position and coverage range of drug droplets at different heights and different horizontal distances are predicted to obtain the spraying prediction information set.

[0012] Through the above technical solution, a multi-layered disturbance transmission chain was constructed from the outside to the inside and from horizontal to vertical. First, the horizontal drift benchmark was established using farmland wind field information. Then, rotor airflow information was introduced and coupled with the wind field to correct vertical settling and lateral diffusion. Finally, the thermal convection effect caused by the surface temperature in the field was superimposed. This realistically reproduced the three-dimensional complex flow field environment in which three major factors coexist: wind field, mechanical downwash airflow, and surface thermal convection. This progressive analysis mechanism not only overcomes the limitations of existing single wind field prediction models, but also effectively captures key phenomena such as drift caused by thermal lifting. This allows the obtained spraying prediction information set to accurately reflect the spatiotemporal diffusion behavior of pesticide droplets in actual operations, thus providing a reliable data foundation for avoiding pesticide damage accidents in adjacent sensitive crop areas and improving the uniformity of pesticide application.

[0013] Optionally, the process of constructing the downwash airflow disturbance information includes: based on the rotor airflow information and combined with the wind field airflow disturbance information, analyzing the influence of farmland wind field on the flight attitude and rotor speed of the multi-rotor UAV to obtain the rotor initial disturbance information; based on the rotor initial disturbance information, analyzing the airflow deflection and diffusion characteristics caused by the farmland wind field directly acting on the downwash airflow to obtain the downwash airflow disturbance information.

[0014] Through the above technical solution, high-precision downwash airflow disturbance information was constructed. By combining rotor airflow information with wind field airflow disturbance information, the microscopic influence of farmland wind field on UAV flight attitude and rotor speed was first captured, forming initial rotor disturbance information. Then, based on this initial disturbance, the macroscopic airflow deflection and diffusion characteristics caused by the direct action of farmland wind field on downwash airflow were analyzed in depth. In this process, the initial rotor disturbance information serves as a bridge connecting the external environmental wind field and the internal downwash airflow variation, enabling the model to not only consider the direct blowing of wind on droplets, but also incorporate the second-order coupling effect of wind-induced attitude change → rotor response adjustment → downwash airflow distortion. This progressive analysis mechanism effectively solves the problem of downwash airflow prediction distortion caused by the neglect of the UAV's own state being modulated by the wind field in existing models. It ensures that the generated downwash airflow disturbance information can accurately reflect the shift of the airflow center and asymmetric diffusion phenomenon under crosswind conditions, thus laying a solid physical foundation for subsequent prediction of the spatiotemporal distribution of drug droplets.

[0015] Optionally, the process of constructing the diffusion characteristic information includes: analyzing the non-uniform characteristics of the upward velocity of hot air convection and the intensity of turbulence in different temperature regions based on the field surface temperature to obtain thermal lift information; and analyzing the vertical lifting or suppression effect of the downwash airflow coupled with the downwash airflow and hot air convection on drug droplets based on the thermal lift information and the downwash airflow disturbance information to obtain the diffusion characteristic information.

[0016] The above technical solution achieves a leap from single environmental factor analysis to multi-physics field coupling analysis. By transforming the spatial non-uniformity of field surface temperature into specific thermal uplift information and dynamically coupling it with the downwash airflow disturbance information of the UAV itself, it can not only identify vertical abnormal airflow that cannot be captured by conventional wind field models, but also quantitatively assess the net effect after the game of downpressure and uplift. This synergistic effect enables accurate prediction of the residence time and vertical migration path of drug droplets in specific areas such as high-temperature bare land, effectively revealing the potential risk mechanism of thermal uplift-drift.

[0017] Optionally, the step of predicting the landing location and coverage area of ​​pesticide droplets at different heights and horizontal distances based on the diffusion characteristic information and the compliance association information set to obtain the spraying prediction information set includes: analyzing the differentiated effects of wind field, multi-rotor downwash airflow, and hot air convection coupling on pesticide droplets at different height layers based on the diffusion characteristic information to obtain stratified airflow action information; analyzing the settling time and retention tendency of pesticide droplets after being affected by airflow at each height layer based on the stratified airflow action information and the compliance association information set to obtain stratified settling information; and analyzing the migration path of pesticide droplets from the application height through each height layer to the crop canopy and ground based on the stratified settling information to obtain the spraying prediction information set.

[0018] The above technical solution discretizes the continuous and complex atmospheric space into functional layers with different airflow characteristics, realizing cross-scale mapping from the macroscopic environmental field to the microscopic droplet trajectory. By analyzing the differentiated coupling effects of wind field, multi-rotor downwash, and thermal convection at different altitude layers, a refined layered airflow interaction information is constructed, overcoming the shortcomings of existing models that treat the environment as a homogeneous medium. Furthermore, by combining the physical properties of the drug itself, the settling time and retention tendency of droplets at each level are quantified, forming layered settling information. This effectively identifies the turbulent hindrance effect in key areas such as the top of the canopy and reveals the aggregation, rebound, or drift of droplets in specific altitude ranges (such as the area of ​​conflict between thermal convection and downwash). This provides a solid theoretical basis and data support for optimizing the application altitude, adjusting the droplet size distribution, and formulating targeted flight control strategies, thereby improving the safety of plant protection operations.

[0019] Optionally, generating and outputting a collaborative management strategy for pilot-drone-drug based on the spraying prediction information set includes: analyzing the time lag characteristics between drug droplet spraying deviation and drone sensor prediction, pilot operation, and drug feedback based on the spraying prediction information set to obtain reliable lag correlation information; and generating and outputting a dynamic adjustment strategy for pilot control command timing advance information, drone flight speed adjustment level, and drug spraying flow rate based on the reliable lag correlation information, as the collaborative management strategy for pilot-drone-drug-drug.

[0020] Through the above technical solutions, a leap from passive response to proactive prediction and compensation has been achieved. By quantifying the time lag characteristics of the entire chain and mapping them to spatial deviation, the future spraying status can be known in advance. On this basis, the generated advance timing information directly compensates for the pilot's physiological reaction delay. The flight speed adjustment actively counteracts drift caused by environmental interference using aerodynamic principles, while the dynamic adjustment strategy of pesticide spraying flow fills the prediction deposition gap. These three are not isolated but coupled: the reduction of flight speed not only reduces horizontal displacement but also enhances the downwash airflow, thereby changing the required flow compensation coefficient. The pilot's advance operation provides a valuable time window for the physical response of the drone and the actuator. This multi-dimensional collaborative management strategy enables the drone operation system to maintain a high degree of consistency between human, machine, and pesticide in complex coupled flow field environments, effectively eliminating control inaccuracies caused by time lag and improving the accuracy and safety of agricultural plant protection operations.

[0021] Optionally, the process of constructing the lag-related reliable information includes: based on the spraying prediction information set, analyzing the entire link time interval of UAV sensor data acquisition and transmission, pilot reliable association decision and command execution, and drug spraying feedback to obtain lag information for each link; and establishing a corresponding correlation between time lag and spraying deviation based on the lag information for each link to obtain the lag-related reliable information.

[0022] Secondly, this application provides a reliable dual-location association management system for drones and pilots. The system includes: a compliance association module, used to acquire a set of information on farmland where the drone is operating; based on the information set, it analyzes the spatial compatibility between the pilot's location and the farmland from a spatial perspective, and verifies the compliance of the matching between the pesticide type and the field crops to obtain a compliance association information set; a spraying prediction module, used to acquire a set of dynamic environmental information; based on the dynamic environmental information set and combined with the compliance association information set, it predicts and analyzes the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effect of wind field, field heat convection, and multi-rotor downwash airflow in the farmland to obtain a spraying prediction information set; and a collaborative management module, used to generate and output a collaborative management strategy for pilot-drone-pesticide based on the spraying prediction information set.

[0023] The above technical solution achieves transparent modeling and quantitative analysis of inherent delays. By decomposing and summing the time intervals of the three independent links—drone sensor data acquisition and transmission, pilot's reliable association decision-making and command execution, and drug spraying feedback—not only is the delay contribution of each subsystem clarified, but a quantitative correlation between time lag and spraying deviation is also established. This time lag-spatial deviation correlation model enables the prediction of actual spraying position deviations caused by delays at specific future time points, thereby transforming the management strategy from traditional post-event correction to pre-event prediction and compensation. With the help of this reliable information on lag correlation, subsequent collaborative management strategies can calculate the time when pilot commands need to be issued in advance, the level of drone speed adjustment, and the value of drug flow rate pre-compensation, effectively offsetting the risk of overshoot or missed spraying caused by end-to-end lag, and improving the accuracy and reliability of collaborative operations among pilots, drones, and drugs. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1This is a schematic diagram of an application scenario provided in an embodiment of this application.

[0026] Figure 2 A flowchart illustrating a trusted association management method for dual positions of a drone and its pilot, provided as an embodiment of this application.

[0027] Figure 3 This is a schematic diagram of a trusted dual-position association management system for drones and pilots provided in an embodiment of this application. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0029] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0030] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0031] In the field of agricultural plant protection drone operations, existing management methods typically rely solely on GPS coordinates to determine whether the pilot's position is within the plot boundary. This lacks spatial dimension analysis that links the pilot's position, the drone's real-time attitude, and the farmland operation boundary, easily leading to misjudgments of the human-machine spatial relationship. Furthermore, the matching and verification of pesticide types and crop varieties often lags behind the operation process or relies on manual offline verification, lacking a real-time dynamic compliance verification mechanism, which easily triggers pesticide damage risks. In addition, existing technologies, when predicting spraying effects, often consider the impact of natural wind speed on droplet drift in isolation, ignoring the convection of hot air generated by the heated field surface and the complex coupling effect of the downwash airflow of the multi-rotor drone with the natural wind field. This results in a single and inaccurate prediction model for the spatiotemporal diffusion characteristics of pesticides. Moreover, the inherent time lag in the system from sensor data acquisition and transmission to pilot decision-making and execution mechanism response makes it difficult for existing management strategies to provide proactive compensation, often resulting in uneven spraying, missed spraying, or over-spraying, failing to achieve efficient collaboration and reliable management among the pilot, drone, and pesticides.

[0032] Based on this, this application provides a reliable association management method and system for dual positions of drones and pilots, and establishes a closed-loop reliable management method. First, it defines the compliance and safety boundaries of human, machine and pesticide, and then relies on a three-dimensional coupling model to simulate droplet diffusion and predict drift risk. It introduces a time delay compensation mechanism to dynamically adjust the operation parameters, realize intelligent plant protection operation, and reduce pesticide damage and missed or repeated spraying problems.

[0033] Figure 1 This application provides an illustration of an application scenario. In the operation of agricultural plant protection drones, the method provided in this application is used to deduce the spatiotemporal diffusion law of droplets by combining a compliant information set with a three-dimensional coupled airflow model. The flight and application parameters are dynamically optimized by full-link time delay compensation, which effectively suppresses pesticide damage, eliminates missed spraying and re-spraying, and empowers intelligent and efficient plant protection operations by drones.

[0034] Specifically, the method provided in this application can be applied to any server. The server interacts with the UAV flight control and detection platform and the micro meteorological sensor to obtain the UAV operation farmland information set provided by the UAV flight control and detection platform and the dynamic environmental information set provided by the micro meteorological sensor. It constructs a reliable closed-loop management and control system for the entire process, delineates the safety operation boundary of humans, machines and pesticides based on compliance information, analyzes the droplet diffusion characteristics under multi-factor coupling through a three-dimensional coupled airflow model, generates and outputs a collaborative management strategy to the UAV and the pilot's position perception management platform, effectively reduces non-target pesticide damage, eliminates the drawbacks of missed spraying and re-spraying, and achieves intelligent and efficient UAV plant protection operations.

[0035] The specific implementation method can be referred to in the following embodiments, wherein the data mentioned in the embodiments are only for reference and examples, so that relevant personnel can better understand them.

[0036] Figure 2 This is a flowchart illustrating a trusted association management method for dual locations of a drone and its pilot, provided as an embodiment of this application. The method of this embodiment can be applied to servers in the above-described scenarios. Figure 2 As shown, the method includes: Example 1: S201. Obtain the information set of farmland where the drone is operating. Based on the information set of farmland where the drone is operating, analyze the spatial compatibility between the drone operator's location and the farmland from a spatial perspective. At the same time, verify the compliance of the matching between the pesticide type and the crops in the field to obtain a compliance association information set.

[0037] The drone-based farmland information set refers to a collection of static basic data describing the current plant protection operation scenario, with the drone flight control and detection platform serving as the data source. This information set specifically includes plant protection operation information, pilot information, and drone information. Plant protection operation information covers the geographic boundary coordinates of the operation plot, the type of crop planted, the types of pests and diseases targeted for control, a list of recommended pesticides, and standard application dosages. Pilot information includes the pilot's real-time geographic location coordinates, operational qualification certification level, and historical operational reputation score. Drone information includes parameters such as drone model, maximum payload capacity, current three-dimensional spatial coordinates, flight attitude angle, and remaining battery power. The spatial adaptation relationship between the pilot's position and the operation plot refers to determining whether the pilot is within a preset safe operating area (e.g., the distance from the plot boundary is greater than a safe threshold and the line of sight is unobstructed) and whether the drone is strictly restricted to operating over the target plot by calculating the geometric distance and azimuth angle between the pilot's current position coordinates and the polygonal boundary of the farmland operation, thereby generating spatial compliance information characterizing the legality of the pilot-plot-drone triangular spatial relationship. The compliance verification process for matching pesticide types with field crops begins with an adaptation analysis based on crop canopy structure parameters (such as leaf inclination angle, density, and plant height) from plant protection operation information, comparing them with pesticide droplet size distribution to obtain the expected penetration path and attachment location of droplets within the canopy. Subsequently, for different expected deposition areas, the chemical composition of the pesticide is further compared with the resistance database of the current crop variety to confirm the existence of phytotoxicity risks, thereby generating pesticide compliance information. Spatial compliance information and pesticide compliance information work together to construct a compliance-related information set. This set serves as the basic constraint for generating subsequent environmental prediction and management strategies, ensuring that the initial state of both the operator and the target crop meets safety and regulatory requirements. For example, if the drone operator's coordinates are detected to be only 2 meters from the cornfield boundary (less than the set 5-meter safety threshold), or if the pesticide to be sprayed is detected to pose a known high sensitivity risk to the current soybean variety, the compliance-related information set will mark the corresponding violation, blocking the subsequent automated operation process. Through this multi-dimensional static information fusion and dual verification mechanism, safety accidents and legal disputes caused by improper personnel positioning or incorrect pesticide selection can be prevented at the source.

[0038] S202. Obtain a dynamic environmental information set. Based on the dynamic environmental information set and the compliance-related information set, predict and analyze the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effect of the wind field of the operating farmland, the field heat convection and the downwash airflow of the multi-rotor, and obtain a spraying prediction information set.

[0039] The dynamic environmental information set refers to a collection of dynamic data reflecting real-time meteorological conditions at the operational site and the flight status of the UAV, with miniature meteorological sensors on the UAV serving as the data source. This information set specifically includes field surface temperature, farmland wind field information, and rotor airflow information. Field surface temperature reflects the differences in thermal radiation between different plots (such as bare land and vegetated areas) and is a key heat source driving hot air convection; farmland wind field information includes near-surface wind speed vectors, wind direction angles, and turbulence intensity, determining the basic background field for the horizontal transport of droplets; rotor airflow information records the rotational speed, blade tilt angle, and theoretical downwash velocity distribution of the multi-rotor UAV. Spatiotemporal diffusion interference characteristics refer to the complex three-dimensional flow field characteristics formed after the drug droplets leave the nozzle and are simultaneously subjected to the superposition and interference of three airflow sources—the natural wind field in the horizontal direction, the hot air convection generated by the surface temperature difference in the vertical direction, and the forced downwash airflow generated by the rotor rotation. The predictive analysis process first calculates the horizontal drift velocity and directional offset of the droplets based on farmland wind field information. Then, combining rotor airflow information, it analyzes how crosswinds alter the central axis and diffusion range of the downwash airflow, forming downwash airflow disturbance information. Next, based on the spatial distribution of field surface temperature, it analyzes the non-uniform characteristics of the upward velocity and turbulence intensity of hot air convection, and simulates the vertical lift or suppression effect produced after coupling with the downwash airflow, obtaining diffusion characteristic information. Finally, based on this diffusion characteristic information, and combined with the drug physicochemical parameters (such as droplet size, density, and volatility) provided in the compliance-related information set, a simplified fluid dynamics model is used to simulate the complete migration trajectory of the droplets from the application height through different atmospheric layers until landing. This calculates the probabilistic landing point and coverage range of the drug droplets at different altitude layers and horizontal distances, thus obtaining the spraying prediction information set. For example, during operations at midday on a hot, sunny day, areas with surface temperatures reaching 45°C will generate strong updrafts. If a drone is flying at 6 m / s and encounters a 3 m / s crosswind, the prediction model will calculate that the downwash is offset by thermal uplift, causing fine droplets to remain above the canopy for an extended period and drift laterally and rearward. The spray prediction information set will clearly indicate the risk area where the actual deposition center may deviate from the predetermined flight path by 2-3 meters. This step, by constructing a three-dimensional coupled model of wind field, thermal convection, and downwash, overcomes the limitations of existing single-factor predictions and improves the prediction accuracy of spray landing points in complex environments.

[0040] S203. Based on the spraying prediction information set, generate and output a collaborative management strategy for the pilot, drone, and pesticide.

[0041] The collaborative management strategy of drone pilot, drone, and pesticide can refer to a set of instructions that includes time lead compensation, dynamic adjustment of flight parameters, and adaptive control of pesticide application rate. Its generation logic is based on the droplet distribution deviation revealed by the spray prediction information set at future moments, and the optimal control solution is derived in reverse. The generation process of this strategy first analyzes the correspondence between the expected deposition deviation shown in the spray prediction information set and the system's end-to-end time lag characteristics. The end-to-end time lag characteristics encompass the drone's sensor data acquisition and transmission delays, the pilot's reaction delay in receiving information, making cognitive decisions, and issuing commands, and the physical response delays of pesticide spraying actuators (such as solenoid valves and metering pumps). By establishing a mapping model between time lag and spatial spray deviation, the deviation distance of the actual landing point from the target area at a specific future time point (e.g., 0.6 seconds later) without intervention is quantified.

[0042] Based on these quantitative results, the collaborative management strategy specifically includes: advance information on the timing of pilot control commands, i.e., prompting pilots to issue turning or start / stop commands several milliseconds before reaching the target work point to compensate for human reaction lag; adjustment of drone flight speed, i.e., automatically suggesting or executing operations to reduce / increase flight speed based on the predicted wind field and thermal convection coupling strength, using speed changes to alter the coupling state between the downwash airflow and the relative wind field, optimizing droplet penetration or suppressing drift; and a dynamic adjustment strategy for drug spraying flow rate, i.e., increasing the spraying flow rate per unit time in advance when it is predicted that insufficient deposition may occur in a certain area due to airflow interference, or reducing the spraying flow rate in advance when the risk of overlapping spraying is predicted. For example, when the prediction model shows that the droplet deposition density 10 meters ahead will be lower than 70% of the target value due to the coupling of strong crosswinds and thermal lift, the strategy will generate a command requiring the pilot to prepare to adjust the heading 0.5 seconds in advance, while automatically reducing the drone flight speed from 8 m / s to 6 m / s to enhance the downwash suppression effect, and instantly increasing the spraying flow rate to 1.25 times the standard value. The strategy's output shifts from post-event correction to pre-event prediction and compensation, effectively eliminating control errors caused by system lag and ensuring a high degree of synchronization and matching between pilot operation, drone flight status, and drug spraying effect in time and space.

[0043] Example 2: In some embodiments, based on the information set of farmland operated by drones, the spatial adaptation relationship between the drone operator's location and the farmland is analyzed from a spatial dimension, while the compliance of the matching between pesticide type and field crops is verified to obtain a compliance association information set. The method includes the following steps: Step 1: The information set for drone operations in farmland includes plant protection operation information, pilot information, and drone information.

[0044] The plant protection operation information refers to the basic data set describing the current farmland operation task, specifically including crop type, plot boundary coordinate sequence, types of pests and diseases to be controlled, recommended pesticide names, and standard application dosages. Pilot information comes from the ground control terminal or the positioning device worn by the pilot, including the pilot's real-time geographical coordinates, operational qualification certification level, and identity identifier. UAV information comes from the airborne flight control system and telemetry link, including the UAV model, maximum payload capacity, current three-dimensional spatial coordinates, flight attitude angle, and battery status. Plant protection operation information serves as the basic constraint condition, defining the physical boundaries and agronomic requirements of the operation; pilot and UAV information serve as dynamic input variables, reflecting the real-time status of the personnel and the machine. By acquiring these three types of information, a data foundation is constructed for subsequent spatial and pesticide compliance verification, ensuring the comprehensiveness of the analysis dimensions. For example, the plant protection operation information might include information such as a plot planted with corn, plot boundaries enclosed by a set of latitude and longitude coordinates, pilot information showing a southeast direction, and UAV information showing a payload of 20 liters and a current altitude of 3 meters. By fusing these multi-dimensional data, we can accurately pinpoint the specific parameters of the current work scenario, providing data support for subsequent analysis.

[0045] Step 2: Based on the pilot information, drone information, and plant protection operation information, analyze the relative distance between the current location of the pilot and drone and the boundary of the farmland operation to obtain spatial compliance information.

[0046] Spatial compliance information refers to quantitative indicators characterizing the safety of the drone operator's position and the legality of the drone's operating area. The generation process is as follows: First, extract the plot boundary coordinates from the plant protection operation information to construct a geometric model of the farmland operation area; then, calculate the Euclidean distance between the coordinates in the drone's information and the boundary of this geometric model, and the horizontal projection distance between the coordinates in the drone's information and the boundary. If the drone's distance is less than a preset safety threshold (e.g., 5 meters), the drone is determined to be in a danger zone; if the drone's coordinates do not fall within the plot boundary or exceed the allowed operating buffer zone, the drone is determined to have crossed the boundary. The drone's positional constraints and the drone's area constraints work together to form a dual safety defense line in the spatial dimension. Specifically, the system can set the drone to be located outside the plot boundary and at a distance greater than 5 meters, while the drone must be strictly within the plot boundary. For example, when the calculated distance between the drone and the plot boundary is only 2 meters, the space is deemed non-compliant, posing a risk of accidental injury from the drone; or when the drone drifts to 3 meters outside the plot boundary due to strong winds, its operating area is deemed to be in violation of regulations. By calculating the relative distance in real time, it is possible to effectively prevent pilots from entering the core operation area or drones from flying out of the designated operation area, thus ensuring the safety of the operation from a spatial perspective.

[0047] Step 3: Based on the plant protection operation information, analyze the compatibility information between the pesticide droplet size and the crop canopy structure, and verify the compatibility information between the pesticide type and crop resistance to obtain pesticide compliance information.

[0048] Among these, drug compliance information refers to a comprehensive conclusion assessing whether the application plan is scientifically sound and safe from an agronomical perspective. The analysis logic for compatibility information is as follows: obtain the recommended median volume diameter (VMD) of drug droplets from plant protection operation information, match it with crop canopy structure parameters (such as leaf inclination angle, leaf area index, canopy height, and leaf density) to determine whether the droplets can effectively penetrate the upper canopy and deposit on the target site (such as the underside of leaves or stems). The verification logic for compatibility information is as follows: compare the drug type (chemical composition) with the crop variety's resistance database to confirm whether the crop faces any risk of phytotoxicity from the drug. The physical penetration ability of droplet size and the biocompatibility of drug chemical properties complement each other; the former ensures accurate application, while the latter ensures minimal damage. For example, in a high-density corn canopy with a leaf area index of 4, if the recommended pesticide droplet size is too large (e.g., greater than 300 micrometers), it is prone to bounce and runoff at the top of the canopy, failing to reach the middle and lower pest habitats, resulting in poor compatibility. Similarly, if a crop variety is sensitive to a certain herbicide, but the task list incorrectly includes that herbicide, the compatibility check will fail. These two layers of checks ensure that the selected pesticide effectively covers the target without damaging the crop itself.

[0049] Step 4: Integrate space compliance information and drug compliance information to build a compliance-related information set.

[0050] The compliance-related information set serves as the final decision-making basis, formed by logically combining the safety status of the spatial dimension with the scientific status of the drug dimension. The construction process encapsulates the generated spatial compliance Boolean values ​​(or scores) and drug compliance Boolean values ​​(or scores) into a unified data structure. Only when both spatial and drug compliance information indicate safety and compatibility is the compliance-related information set marked as passed, allowing subsequent spraying prediction and management strategy generation. If either dimension is non-compliant, the set is marked as blocked, triggering an alarm. This synergistic integration of spatial and drug compliance information achieves a leap from single-factor verification to multi-dimensional coordinated control, avoiding the one-sidedness of focusing solely on location while neglecting drug safety or solely on drug use while ignoring operational risks. For example, even if both the pilot's and drone's locations are fully compliant, if drug incompatibility with the crop is detected, the constructed compliance-related information set will still be judged as overall non-compliant, thus preventing the issuance of erroneous spraying instructions. This integrated information set provides a reliable prerequisite for subsequent spatiotemporal diffusion prediction, ensuring the entire management process begins from a safe and scientific baseline state.

[0051] Example 3: In some embodiments, the process of constructing drug compliance information includes the following steps: Step 1: Based on plant protection operation information, analyze the penetration path and attachment position of drug droplets of different sizes inside the canopy to obtain droplet-canopy compatibility information.

[0052] Droplet-canopy adaptation information is obtained by coupling the aerodynamic characteristics of pesticide droplets with the geometry of the crop canopy. Its purpose is to quantitatively assess whether droplets of a specific size can effectively penetrate the upper canopy barrier and reach the target deposition area. Specifically, based on the Lagrange particle tracking principle, the trajectory of droplets of different sizes as they traverse the canopy is simulated. For example, when plant protection information indicates that the crop is high-density corn and the canopy leaf area index is greater than 4, if the pesticide droplet size is too small (e.g., less than 100 micrometers), the simulation results show that most droplets will be intercepted by the upper canopy leaves and will have difficulty penetrating to the middle and lower parts of the canopy; conversely, if the droplet size is too large (e.g., greater than 400 micrometers), rebound and loss are likely to occur. Through this dynamic analysis of penetration path and attachment location, droplet-canopy adaptation information describing the expected deposition ratio of droplets in the upper, middle, and lower layers of the canopy can be generated, providing a data foundation for subsequent refined verification.

[0053] Step 2: Based on the droplet-canopy adaptation information, verify the compatibility information between drug type and crop resistance for different deposition areas to obtain drug compliance information.

[0054] Different deposition zones can refer to spatial units with different physiological characteristics, such as the upper canopy young leaf zone, the middle functional leaf zone, and the lower stem zone, as determined by the aforementioned penetration path analysis. The compatibility information between drug type and crop resistance is obtained by mapping the concentration distribution of the proposed drug's chemical components to these different deposition zones and comparing it with the tolerance thresholds of crop tissues in each zone. Its function is to identify local phytotoxicity risks and ensure that the drug concentration at a specific deposition location does not exceed the tolerance limit of the corresponding part of the crop. Specifically, instead of making a single phytotoxicity judgment on the entire crop, a stratified verification logic is executed. For example, for a certain herbicide, although it is safe for mature functional leaves (middle zone), if the droplet-canopy compatibility information shows that 20% of the herbicide will be deposited in the extremely sensitive apical meristem (upper zone), and this concentration exceeds the tolerance threshold of the apical meristem, then it is determined to be incompatible. Based on this, only when the drug concentration in all key deposition zones is lower than the resistance threshold of the corresponding part is the final drug compliance information generated. This improves the safety of drug use and avoids crop burn or growth inhibition caused by excessive local deposition.

[0055] Example 4: In some embodiments, based on a dynamic environmental information set and a compliance-related information set, the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effects of wind field, field thermal convection, and multi-rotor downwash airflow in the operating farmland are predicted and analyzed to obtain a spraying prediction information set. This method includes the following steps: Step 1: The dynamic environmental information set includes field surface temperature, farmland wind field information, and rotor airflow information.

[0056] Among these, field surface temperature is obtained by scanning the surface of the work area using an infrared thermal imaging sensor to obtain a temperature distribution matrix, which is used to quantify the thermal differences caused by uneven surface heating; farmland wind field information includes wind speed vector, wind direction angle, and turbulence intensity, usually measured by an ultrasonic anemometer or airborne pitot tube, used to describe the horizontal transport capacity of natural airflow for droplets; rotor airflow information includes the rotational speed, blade tilt angle, and initial downwash velocity field of the multi-rotor UAV, derived from the state telemetry data of the flight control system. These three types of information together constitute the basic input variables for predicting the spatiotemporal diffusion of pesticides. For example, when the UAV is operating at noon, the infrared sensor measures the surface temperature of the bare area to be 45°C, while the temperature in the crop canopy-covered area is 32°C, while the anemometer records a crosswind speed of 3 m / s, and the flight control system reports a rotor speed of 6000 rpm. These discrete data are immediately integrated into the current dynamic environmental information set. By constructing this multi-dimensional environmental information set, we can comprehensively capture key external disturbance sources that affect the trajectory of drug droplets, providing data support for subsequent accurate simulation of complex coupled flow fields.

[0057] Step 2: Based on farmland wind field information, analyze the influence of farmland wind field on the horizontal transport direction and velocity of drug droplets to obtain wind field airflow disturbance information.

[0058] The wind field airflow disturbance information refers to the characteristic parameters that cause horizontal displacement and velocity changes in drug droplets after they leave the nozzle due to the action of natural wind. This information is calculated using fluid dynamics equations based on wind speed and direction data from farmland wind field information, combined with the aerodynamic characteristics of the droplets (such as particle size and density). Specifically, the wind field airflow disturbance information describes the drift velocity vector of the droplets in the horizontal plane and the diffusion trend caused by wind shear. For example, if the farmland wind field information indicates that the wind direction is at a 45-degree angle to the UAV's flight direction and the wind speed is 3 m / s, analysis shows that a 200 μm diameter droplet will generate a lateral drift velocity component of approximately 2 m / s, and wind field airflow disturbance information including drift direction and correction coefficients is generated accordingly. This step aims to quantify the primary interference factor of natural environmental wind on the drug spraying trajectory and establish the basic boundary conditions for the horizontal movement of droplets.

[0059] Step 3: Based on the rotor airflow information and combined with the wind field airflow disturbance information, analyze the influence of the multi-rotor downwash airflow on the forced settling velocity and lateral diffusion range of drug droplets, and obtain the downwash airflow disturbance information.

[0060] The downwash airflow disturbance information refers to the comprehensive characterization of the vertical forced settling force and lateral diffusion effect exerted on drug droplets by the downward airflow generated by the rotation of a multi-rotor UAV after interacting with the natural wind field. The generation process first determines the initial velocity field and rotational momentum of the downwash airflow based on the rotor airflow information. Then, the wind field airflow disturbance information obtained above is introduced to analyze the disturbance of the UAV's fuselage attitude by the lateral natural wind and the resulting rotor airflow deflection. This coupling effect causes the downwash airflow center to shift and changes its outward diffusion range. For example, when the UAV is affected by a 3 m / s crosswind, the fuselage may tilt by 3 degrees, causing the originally vertically downward downwash airflow center to shift 1 meter to the leeward side, and the diffusion radius of the downwash airflow in the crosswind direction to increase by 15%. Based on this, the corrected forced settling velocity distribution and lateral diffusion range are calculated, forming the downwash airflow disturbance information. By integrating the dual effects of the wind field and rotor airflow, this step can more realistically reflect the actual effect of the UAV's own dynamic field in complex wind environments.

[0061] Step 4: Based on the field surface temperature and the downwash airflow disturbance information, analyze the influence of hot air convection on the lifting intensity and height distribution of near-surface vertical airflow to obtain diffusion characteristic information.

[0062] The diffusion characteristics information refers to the final diffusion behavior of drug droplets in three-dimensional space, formed by integrating three mechanisms: horizontal disturbance of the natural wind field, vertical suppression of the rotor downwash, and vertical lifting of surface hot air convection. This information is obtained by analyzing the non-uniformity of the upward velocity and turbulence intensity of hot air convection in different temperature regions based on the spatial distribution differences of surface temperature in the field, and then performing vector superposition analysis with the downwash disturbance information obtained above. Specifically, the strong hot air convection generated in high-temperature regions will create an upward lifting force, which interacts with the downward downwash, thus determining the final vertical movement trend of the droplets near the ground (whether they are suppressed and settled or lifted and drifted) and their distribution pattern at different altitude layers. For example, in bare land areas where the surface temperature is as high as 45°C, the upward airflow generated by thermal convection can reach a speed of 1.5 m / s. When coupled with the downwash airflow with a speed of about 6 m / s, a turbulent transition zone of sinking and rising will be formed at the top of the crop canopy. This will cause the residence time of the droplets in this area to be prolonged and the vertical distribution range to be expanded. This complex vertical velocity profile and turbulence intensity distribution are recorded as diffusion characteristic information.

[0063] Step 5: Based on the diffusion characteristic information and the compliance-related information set, predict the landing location and coverage of drug droplets at different heights and horizontal distances to obtain the spraying prediction information set.

[0064] The spraying prediction information set refers to a dataset of predicted results that simulates the complete migration path of pesticide droplets from the application height, traversing different atmospheric layers until reaching the crop canopy or ground, based on the aforementioned diffusion characteristic information. This dataset includes the final landing point coordinates and deposition coverage. The generation of this information set is based on the differences in the coupling strength of wind fields, downwash airflow, and thermal convection at each altitude layer in the diffusion characteristic information. Combined with pesticide droplet size, density, and crop canopy structure parameters provided in the compliance-related information set, the settling time and retention tendency of droplets at each altitude layer are calculated, thus inferring their stratified settling trajectory. For example, based on the diffusion characteristic information, it is determined that there is a strong coupling effect of crosswinds and thermal uplift at the 2-4 meter altitude layer. Combining this with the parameter of a 2-meter corn canopy height in the compliance-related information set, the lateral offset and vertical suspension that droplets will experience when traversing this layer are predicted. Finally, it is calculated that in the area 10 meters in front and 3 meters to the side of the flight direction, the droplet deposition density will be less than 70% of the target value, and this area with insufficient landing point deviation and coverage is marked in the spraying prediction information set. This step, as the final output of the predictive analysis, transforms the complex flow field coupling effect into intuitive data predicting the drug application effect, providing a direct basis for decision-making in the subsequent generation of collaborative management strategies.

[0065] Example 5: In some embodiments, the process of constructing downwash airflow disturbance information includes the following steps: Step 1: Based on the rotor airflow information and combined with the wind field airflow disturbance information, analyze the influence of farmland wind field on the flight attitude and rotor speed of multi-rotor UAV, and obtain the initial rotor disturbance information.

[0066] The rotor airflow information refers to a set of data characterizing the rotor operation state of a multi-rotor UAV in an ideal windless environment. Specifically, it includes rotor speed, blade tilt angle, and the initial velocity distribution of the downwash airflow. This information comes from real-time telemetry data from the UAV's flight control system. The wind field airflow disturbance information consists of horizontal airflow disturbance parameters obtained from the analysis of natural wind fields in farmland. In this step, analyzing the impact of farmland wind fields on flight attitude and rotor speed can refer to establishing a mapping relationship between external wind loads and the UAV's aerodynamic response. Specifically, when farmland wind fields act on the UAV fuselage, they generate lateral and pitch moments, causing the UAV to tilt (e.g., roll or pitch angle changes) to maintain hovering or its flight path. Simultaneously, the flight control system automatically adjusts the output power of each motor to counteract the wind disturbance, resulting in dynamic fluctuations in rotor speed. These changes in the UAV's own state induced by external wind fields (attitude angle deviation and speed adjustment) constitute the initial rotor disturbance information. For example, when a crosswind speed of 4 m / s is detected, the drone's fuselage may experience a 3-degree roll tilt, and the rotor speed on the windward side needs to increase by 200 rpm to maintain balance. These specific attitude angle values ​​and speed differences together constitute the initial rotor disturbance information. By acquiring this initial rotor disturbance information, the modulation effect of the external environment on the drone itself as an airflow source can be quantified, providing accurate initial boundary conditions for subsequent precise calculations of downwash airflow changes.

[0067] Step 2: Based on the initial disturbance information of the rotor, analyze the airflow deflection and diffusion characteristics caused by the direct action of the farmland wind field on the downwash airflow to obtain the downwash airflow disturbance information.

[0068] The downwash airflow disturbance information refers to the characteristic data of trajectory deviation and coverage changes caused by the altered downwash airflow after the drug droplets leave the rotor. This step further derives the macroscopic motion pattern of the airflow based on the aforementioned initial rotor disturbance information. Specifically, due to the tilt of the UAV's flight attitude, the originally vertically downward axis of the downwash airflow will undergo spatial deflection, no longer perpendicular to the ground, but generating a horizontal velocity component along the tilt direction of the fuselage; at the same time, the non-uniform adjustment of the rotor speed will change the velocity field distribution of the downwash airflow, causing the airflow diffusion range to increase or decrease in a specific direction. In addition, the farmland wind field will directly shear the downwash airflow column, exacerbating its lateral diffusion. The analysis process involves substituting the initial rotor disturbance information (attitude angle, speed difference) into the aerodynamic model to calculate the offset distance of the downwash airflow center, the deflection angle, and the deformation coefficient of the effective coverage area. For example, if the initial rotor disturbance information shows that the fuselage is tilted 5 degrees to the left, the calculated downwash airflow disturbance information will include characteristic parameters such as the airflow center shifting 1.2 meters to the left and the diffusion radius on the left being 15% larger than that on the right. The resulting downwash airflow disturbance information accurately reflects the actual transport field of drug carriers under complex wind conditions, thus improving the accuracy of subsequent droplet landing point prediction.

[0069] Example 6: In some embodiments, the process of constructing diffusion feature information includes the following steps: Step 1: Based on the field surface temperature, analyze the non-uniform characteristics of the upward velocity of hot air convection and the intensity of turbulence in different temperature regions to obtain information on thermal uplift.

[0070] Field surface temperature refers to the spatial distribution data of farmland surface temperature collected in real time by infrared thermal imaging sensors or distributed temperature sensors. This step aims to quantify the specific impact of surface temperature differences on near-surface aerodynamics. Specifically, the work area is first divided into several grid cells, and the surface temperature value of each cell is read. Due to uneven surface heating (e.g., temperature differences between bare soil and crop canopy, irrigated areas and dry areas), the convection of hot air generated in different temperature zones exhibits non-uniform characteristics. High-temperature areas heat the air above them, causing a decrease in air density and generating buoyancy, forming rising air currents; low-temperature areas are relatively calm or generate sinking air currents. By analyzing the temperature gradient, the upward velocity of hot air convection and the accompanying turbulence intensity in each area are calculated. For example, when the surface temperature of a bare land area is detected to be 45℃, while the temperature of the adjacent corn canopy area is 32℃, it is determined that there is a strong thermal uplift effect in the bare land area. The vertical updraft velocity in this area is calculated to reach 1.5 m / s, and the turbulence intensity coefficient is higher than that of the surrounding area. This generates thermal uplift information including spatial location, updraft velocity vector, and turbulence intensity distribution. Through this refined analysis, local anomalous airflow caused by hotspots can be accurately captured, providing key vertical interference parameters for subsequent coupled analysis.

[0071] Step 2: Based on the thermal lift information and the downwash airflow disturbance information, analyze the vertical lifting or suppression effect of the downwash airflow and hot gas convection coupling on the drug droplets to obtain diffusion characteristic information.

[0072] The downwash airflow disturbance information is the state data described by the downward jet airflow from the multi-rotor UAV and its deflection by the wind field, obtained from the above-mentioned analysis of farmland wind field and rotor airflow. The core of this step lies in analyzing the interaction mechanism of two airflows in opposite directions (downward downwash airflow and upward thermal convection) in vertical space. Specifically, the upward velocity vector in the thermal lift information is superimposed with the settling velocity vector in the downwash airflow disturbance information. In most areas, the strong downwash airflow generated by the UAV rotor (e.g., with a velocity of 6 m / s) dominates, exerting a vertical suppression effect on the pesticide droplets and accelerating their settling into the crop canopy; however, in specific areas with extremely high surface temperatures, the strong thermal convection uplift force may partially offset or even locally reverse the suppressive effect of the downwash airflow. For example, in the aforementioned 45°C bare ground region, if the vertical component of the downwash airflow, after attenuation, is 2 m / s, while the upward velocity of the hot air convection is 1.5 m / s, the net vertical velocity is only 0.5 m / s. This results in a prolonged residence time of droplets at this altitude, and may even lead to the formation of localized suspension-lifting turbulence zones. Through this coupled analysis, the risk of unexpected droplet lifting or drift due to thermal factors can be predicted, solving the problem of vertical prediction bias caused by existing models neglecting surface temperature heterogeneity.

[0073] Example 7: In some embodiments, based on diffusion characteristic information and in conjunction with a compliance-related information set, the landing locations and coverage areas of drug droplets at different heights and horizontal distances are predicted to obtain the spraying prediction information set. The method includes the following steps: Step 1: Based on diffusion characteristic information, analyze the differential effects of wind field at different altitude layers, multi-rotor downwash airflow and hot gas convection coupling on drug droplets, and obtain information on stratified airflow effects.

[0074] Here, different altitude layers refer to dividing the vertical space between the UAV spraying point and the ground into several discrete functional zones based on differences in airflow dominance mechanisms. Examples include the initial spraying layer, intermediate transition layer, top canopy turbulence layer, and inner canopy infiltration layer. Layered airflow information refers to the net vector field characteristics describing the coupling of natural wind, rotor downwash, and field thermal convection within each specific altitude layer. This includes the magnitude of the resultant velocity, directional deflection angle, and turbulence intensity coefficient within that layer. This information is calculated by mapping the diffusion characteristic information (i.e., the three-dimensional airflow distribution data of the entire field) obtained in the above embodiments onto a preset altitude layering model. Its function is to quantify the specific interference of each airflow environment on droplet motion, providing boundary conditions for subsequent layered trajectory calculation. For example, in the turbulent layer at the top of the canopy, 2 to 3 meters above the ground, the upward velocity of hot air convection generated by the high surface temperature clashes violently with the powerful downwash from the UAV. The stratified airflow information in this layer will show extremely high vertical turbulence intensity and unstable horizontal wind speed components. In the intermediate transition layer above 5 meters above the ground, the downwash weakens significantly, and the stratified airflow information mainly reflects the horizontal transport characteristics of the natural wind field. This stratified analysis method can capture localized abrupt airflow changes that cannot be identified by existing single models, especially the suspension-rebound effect zone at the top of the canopy.

[0075] Step 2: Based on the information on the effects of stratified airflow and combined with the compliance-related information set, analyze the settling time and retention tendency of drug droplets after being affected by airflow at each height layer to obtain stratified settling information.

[0076] The stratified sedimentation information refers to a set of data characterizing the residence time required for drug droplets to traverse each specific height layer and the probability of abnormal residence or aggregation within that layer. This information is derived from the aforementioned stratified airflow information, combined with drug physical parameters (such as droplet size, density, and evaporation rate) recorded in the compliance-related information set, through kinetic calculations. Using a modified Stokes' law formula, the airflow vector of each layer is used as the external force input to calculate the net sedimentation velocity of the droplets in the vertical direction of that layer, thereby deriving the sedimentation time. Simultaneously, based on the ratio of the turbulence intensity to the droplet inertial force at that layer, the tendency of droplets to be trapped by vortices is assessed. For example, for droplets with a diameter of 150 micrometers, if the updraft component detected in the turbulent layer at the top of the canopy is close to its gravitational sedimentation velocity, the calculated sedimentation time will be prolonged, and the retention tendency will be marked as high, meaning that the droplets are very likely to form aerosol clouds in this height range and have difficulty penetrating to the lower part of the crop; conversely, if the downwash airflow dominates the layer, the sedimentation time will be shortened, and the retention tendency will be marked as low. This step combines the macroscopic airflow environment with the microscopic characteristics of fog droplets, enabling a refined quantification of the movement state of fog droplets in different atmospheric levels.

[0077] Step 3: Based on the stratified sedimentation information, analyze the migration path of the pesticide droplets as they gradually pass through each height layer from the application height to the crop canopy and the ground, and obtain the spraying prediction information set.

[0078] The migration path refers to the complete three-dimensional spatial trajectory coordinate sequence of drug droplets after being sprayed from the nozzle, sequentially traversing the aforementioned height layers, and finally reaching the crop canopy surface or ground. This path is generated by temporally stitching and spatially integrating the sedimentation time and retention tendency data of each layer obtained above. In practice, starting from the application point, the exit position and velocity vector of the droplets when leaving the first layer are calculated based on the stratified sedimentation information of the first layer, and this is used as the initial entry condition for the next layer, recursively applying this method layer by layer until the droplets touch the ground or adhere to the crop leaves. The spray prediction information set is the collection of all simulated droplet migration paths, which includes the distribution map of the final landing point of the droplets at different heights and horizontal distances, as well as the coverage area heat map. For example, if the simulation shows that a large number of droplets have a high retention tendency in the turbulent layer at the top of the canopy, the generated spray prediction information set will indicate that the drug deposition density in this area is abnormally high, while the coverage area in the lower part of the canopy will be lower than the expected threshold, thus intuitively reflecting the problem of insufficient penetration caused by airflow coupling. The resulting spraying prediction information set not only provides the final landing point prediction, but also reveals the dynamic process mechanism that leads to the result, providing a high-confidence spatiotemporal data foundation for the subsequent generation of collaborative management strategies.

[0079] Example 8: In some embodiments, a collaborative management strategy for drone pilot-drone-pesticide is generated and output based on a spraying prediction information set. The method further includes the following steps: Step 1: Based on the spraying prediction information set, analyze the spraying deviation of drug droplets and the time lag characteristics between UAV sensor prediction, pilot operation and drug feedback to obtain reliable information on lag correlation.

[0080] The spraying prediction information set is based on the predicted data obtained from the preceding steps, which includes the landing positions and coverage areas of drug droplets at different heights and horizontal distances. Analyzing drug droplet spraying deviation refers to comparing the difference between the ideal droplet deposition distribution and the predicted distribution after environmental disturbances. Time lag characteristics refer to the total time delay generated throughout the entire chain from sensing environmental changes to finally executing the spraying action. Specifically, this includes the physical delay of UAV sensor data acquisition and transmission, the pilot's reaction delay in making reliable correlation decisions and issuing control commands after receiving information, and the physical action delay of the drug spraying actuators (such as flow pumps and solenoid valves) in responding to commands. Lag-related reliable information is a data set establishing the correspondence between time lag and spraying deviation, used to quantify the spatial offset of the actual landing point relative to the predicted landing point at a specific lag time. For example, if the system detects a sensor transmission delay of 0.1 seconds, an average pilot reaction delay of 0.3 seconds, and a flow pump response delay of 0.2 seconds, then the total lag time is 0.6 seconds. Based on the condition that the concentrated wind speed of the spray prediction information is 3 m / s, it is calculated that after 0.6 seconds, the actual deposition center of the droplets will have a longitudinal drift deviation of approximately 1.8 meters relative to the predicted center corresponding to the current command. This deviation value constitutes the core content of the lag correlation reliability information. By constructing this time-space mapping relationship, the abstract system delay can be transformed into specific spatial correction parameters, providing a precise basis for subsequent compensation control.

[0081] Step 2: Based on the reliable information of the lag association, generate and output the timing advance information for the pilot's control commands, the adjustment level of the drone's flight speed, and the dynamic adjustment strategy of the drug spraying flow rate, as a collaborative management strategy for the pilot-drone-drug.

[0082] Specifically, the advance timing information for pilot control commands can refer to the system calculating the ideal time when the pilot should issue commands based on the total lag time, and then visually or audibly prompting the pilot to perform the operation at a certain point in time before the current moment to compensate for human reaction delays. Adjusting the drone's flight speed can refer to the drone flight control system automatically selecting a preset speed level (such as switching from high speed to low speed) based on predicted drift trends. By changing the flight speed, it adjusts the coupling state between the downwash airflow and the droplets, thereby suppressing lateral drift or enhancing penetration. The dynamic adjustment strategy for drug spraying flow rate can refer to the control unit increasing or decreasing the amount of drug sprayed per unit time in advance based on the predicted future landing point deviation area to compensate for insufficient or excessive local deposition caused by drift. For example, when reliable information based on lag indicates a risk of droplet lift and loss due to thermal convection 10 meters ahead, the generated strategy is as follows: prompt the pilot to execute a turning command 0.6 seconds in advance; simultaneously, automatically adjust the drone's flight speed from 8 m / s to 6 m / s to enhance the downwash's suppression of droplets; and instruct the spraying system to dynamically increase the flow rate from 2 L / min to 2.5 L / min before reaching the area. This proactive compensation mechanism effectively solves the overspraying or underspraying problems caused by system inertia in existing perception-response models, improving the uniformity and controllability of plant protection operations.

[0083] Example 9: In some embodiments, the process of constructing delayed associated trusted information includes the following steps: Step 1: Based on the spraying prediction information set, analyze the time interval of the entire link of UAV sensor data acquisition and transmission, pilot reliable association decision-making and command execution, and drug spraying feedback to obtain the lag information of each link.

[0084] Among them, the full-link time interval can refer to the complete time series experienced from when the environmental state is sensed to when the drug actually acts on the target area. Specifically, in this process, the quantization of the UAV sensor data acquisition and transmission link is carried out first. After the sensors (such as wind speed meters, GPS modules, inertial measurement units) collect the dynamic data in the field, they need to go through analog-to-digital conversion, protocol encapsulation and wireless link transmission to the ground station or flight control center. The time delay generated in this process is recorded as the first lag component. Secondly, the reliable association decision-making and instruction execution link of the pilot is analyzed. After the pilot receives the system warning or suggestion, the time required for visual perception, brain judgment and hand operation of the remote control to issue instructions is recorded as the second lag component. Finally, the drug spraying feedback link is analyzed. When the adjustment instruction is sent to the UAV, the physical response time required for the actuator such as the flow control pump and solenoid valve to move from receiving the signal to the mechanical components and stably output a new flow rate is recorded as the third lag component. For example, in a plant protection operation scenario in a corn field, the sensor data upload delay is about 0.1 seconds, the average decision-making reaction time of the pilot is 0.3 seconds, and the mechanical response delay of the liquid medicine flow pump is about 0.2 seconds. By adding up the above three components, the total full-link time interval is 0.6 seconds, that is, the lag information of each link is formed. Through this decomposition and quantization method, the originally vague system delay can be made transparent, providing basic data support for the subsequent establishment of an accurate compensation model.

[0085] Step 2: According to the lag information of each link, establish the corresponding association relationship between the time lag and the spraying deviation, and obtain the reliable lag association information.

[0086] Among them, the corresponding association relationship is a mathematical mapping model that describes the spatial displacement of the actual landing point of the drug droplets relative to the theoretical predicted landing point caused by the total system delay time. Specifically, based on the full-link time interval obtained in the previous step, combined with the current flight speed vector of the UAV and the above-obtained spraying prediction information set (including the droplet movement trajectory under the coupling of the wind field, downwash airflow and thermal convection), calculate the change in the position of the UAV during the lag period and the additional drift amount of the droplets affected by the coupled airflow. For example, if the UAV is flying at a speed of 8 m / s and the full-link lag time is 0.6 seconds, then at the moment when the pilot makes a reaction, the UAV has flown forward 4.8 meters. At the same time, considering the influence of the side wind and thermal convection, the actual deposition center of the droplets may deviate further from the preset target area by 2 to 3 meters; bind these time values with the calculated spatial deviation values (such as a lag of 0.6 seconds corresponding to a forward deviation of 4.8 meters and a lateral deviation of 2.5 meters) to construct a time-space deviation lookup table or function curve, so as to obtain the reliable lag association information.

[0087] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0088] Figure 3 This application provides a schematic diagram of the structure of a trusted dual-location association management system for drones and pilots, as shown in one embodiment. Figure 3 As shown, the UAV and pilot dual-location trusted association management system 300 of this embodiment includes: a compliance association module 301, a spraying prediction module 302, and a collaborative management module 303.

[0089] The compliance association module 301 is used to acquire a set of information about farmland where the drone is operating. Based on this set, it analyzes the spatial compatibility between the drone operator's location and the farmland, and verifies the compliance of the matching between the pesticide type and the crops in the field, thus obtaining a compliance association information set. The spraying prediction module 302 is used to acquire a set of dynamic environmental information. Based on this set and the compliance association information set, it predicts and analyzes the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effect of wind field, field heat convection, and multi-rotor downwash airflow in the farmland, thus obtaining a spraying prediction information set. The collaborative management module 303 is used to generate and output a collaborative management strategy for the drone operator, drone, and pesticides based on the spraying prediction information set.

[0090] Optionally, when the compliance association module 301 analyzes the spatial compatibility between the drone operator's location and the farmland based on the drone operation farmland information set, and verifies the compliance of the matching between the pesticide type and the field crops to obtain the compliance association information set, it is specifically used for: the drone operation farmland information set including plant protection operation information, drone operator information, and drone information; based on the drone operator information, the drone information, and the plant protection operation information, analyzing the relative distance between the current location of the drone operator and the drone and the farmland operation boundary to obtain spatial compliance information; based on the plant protection operation information, analyzing the compatibility information between the pesticide droplet size and the crop canopy structure, and verifying the compatibility information between the pesticide type and crop resistance to obtain pesticide compliance information; and integrating the spatial compliance information and the pesticide compliance information to construct the compliance association information set.

[0091] Optionally, the compliance association module 301, during the construction process of the drug compliance information, is specifically used to: analyze the penetration path and attachment position of drug droplets of different sizes inside the canopy based on the plant protection operation information to obtain droplet-canopy adaptation information; and, based on the droplet-canopy adaptation information, verify the compatibility information between drug type and crop resistance for different deposition areas to obtain the drug compliance information.

[0092] Optionally, when the spraying prediction module 302 predicts and analyzes the spatiotemporal diffusion interference characteristics of the sprayed pesticide caused by the coupling effect of farmland wind field, field thermal convection, and multi-rotor downwash airflow based on the dynamic environmental information set and the compliance association information set, and obtains the spraying prediction information set, it is specifically used for: the dynamic environmental information set including field surface temperature, farmland wind field information, and rotor airflow information; based on the farmland wind field information, analyzing the influence of the farmland wind field on the horizontal transport direction and velocity of pesticide droplets to obtain wind field airflow disturbance information; based on the dynamic environmental information set and the compliance association information set, analyzing the spatiotemporal diffusion interference characteristics of the sprayed pesticide caused by the coupling effect of farmland wind field, field thermal convection, and multi-rotor downwash airflow, and obtaining the ... and obtaining the spatiotemporal diffusion interference information of farmland wind field, and obtaining the spatiotemporal diffusion interference information of farmland wind field, and obtaining the spatiotemporal diffusion interference characteristics of the sprayed pesticide caused by the coupling effect of farmland wind field, and obtaining the spatiotemporal diffusion interference information of farmland wind field, and obtaining the spatiotempor The rotor airflow information, combined with the wind field airflow disturbance information, is used to analyze the influence of the multi-rotor downwash airflow on the forced settling velocity and lateral diffusion range of drug droplets, thus obtaining downwash airflow disturbance information. Based on the field surface temperature and the downwash airflow disturbance information, the influence of thermal convection on the lifting intensity and height distribution of near-surface vertical airflow is analyzed, thus obtaining diffusion characteristic information. Based on the diffusion characteristic information and the compliance association information set, the landing position and coverage range of drug droplets at different heights and different horizontal distances are predicted, thus obtaining the spraying prediction information set.

[0093] Optionally, the spraying prediction module 302, during the construction of the downwash airflow disturbance information, is specifically used to: analyze the influence of farmland wind field on the flight attitude and rotor speed of the multi-rotor UAV based on the rotor airflow information and the wind field airflow disturbance information, and obtain the rotor initial disturbance information; based on the rotor initial disturbance information, analyze the airflow deflection and diffusion characteristics caused by the farmland wind field directly acting on the downwash airflow, and obtain the downwash airflow disturbance information.

[0094] Optionally, the spraying prediction module 302, during the construction of the diffusion characteristic information, is specifically used to: analyze the non-uniform characteristics of the upward velocity of hot air convection and the intensity of turbulence in different temperature regions based on the field surface temperature, to obtain thermal lift information; and, based on the thermal lift information and combined with the downwash airflow disturbance information, analyze the vertical lifting or suppression effect of the downwash airflow and hot air convection on the drug droplets, to obtain the diffusion characteristic information.

[0095] Optionally, when the spray prediction module 302 predicts the landing position and coverage of pesticide droplets at different heights and horizontal distances based on the diffusion characteristic information and the compliance association information set to obtain the spray prediction information set, it is specifically used to: analyze the differential effects of wind field, multi-rotor downwash airflow, and hot air convection coupling on pesticide droplets at different height layers based on the diffusion characteristic information to obtain stratified airflow action information; analyze the settling time and retention tendency of pesticide droplets after being affected by airflow at each height layer based on the stratified airflow action information and the compliance association information set to obtain stratified settling information; and analyze the migration path of pesticide droplets from the application height through each height layer to the crop canopy and the ground based on the stratified settling information to obtain the spray prediction information set.

[0096] Optionally, when the collaborative management module 303 generates and outputs the collaborative management strategy of pilot-drone-drug based on the spraying prediction information set, it is specifically used to: analyze the time lag characteristics between drug droplet spraying deviation and drone sensor prediction, pilot operation, and drug feedback based on the spraying prediction information set to obtain lag correlation reliability information; and generate and output the timing advance information for pilot control commands, the adjustment level of drone flight speed, and the dynamic adjustment strategy of drug spraying flow rate based on the lag correlation reliability information, as the collaborative management strategy of pilot-drone-drug-drug.

[0097] Optionally, the collaborative management module 303, during the construction process of the delayed correlation credible information, is specifically used to: analyze the entire link time interval of UAV sensor data acquisition and transmission, pilot credible correlation decision and command execution, and drug spraying feedback based on the spraying prediction information set, to obtain the delay information of each link; and establish the corresponding correlation between time delay and spraying deviation according to the delay information of each link, to obtain the delayed correlation credible information.

[0098] The system in this embodiment can be used to execute the methods of any of the above embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

Claims

1. A method for managing the trusted association between the locations of a drone and its pilot, characterized in that, include: Obtain a set of information on farmland where drones are operating. Based on this set of information, analyze the spatial compatibility between the drone operator's location and the farmland in terms of spatial dimensions. At the same time, verify the compliance of the matching between pesticide type and field crops to obtain a set of compliant association information. A dynamic environmental information set is obtained. Based on the dynamic environmental information set and the compliance association information set, the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effect of the wind field of the operating farmland, the field heat convection and the downwash airflow of the multi-rotor are predicted and analyzed to obtain a spraying prediction information set. Based on the spraying prediction information set, a collaborative management strategy for pilot-drone-drug is generated and output.

2. The method according to claim 1, characterized in that, Based on the information set of farmland operations using drones, the spatial adaptation relationship between the drone operator's location and the farmland is analyzed from a spatial perspective. Simultaneously, the compliance of the matching between pesticide types and field crops is verified to obtain a compliance-related information set, including: The drone operation farmland information set includes plant protection operation information, drone operator information, and drone information; Based on the pilot information, the drone information, and the plant protection operation information, the relative distance between the current location of the pilot and the drone and the boundary of the farmland operation is analyzed to obtain spatial compliance information. Based on the plant protection operation information, the compatibility information between drug droplet size and crop canopy structure is analyzed, and the compatibility information between drug type and crop resistance is verified to obtain drug compliance information; Integrate the spatial compliance information and the drug compliance information to construct the compliance-related information set.

3. The method according to claim 2, characterized in that, The process of constructing the drug compliance information includes: Based on the plant protection operation information, the penetration path and attachment position of drug droplets of different sizes inside the canopy are analyzed to obtain droplet-canopy adaptation information; Based on the droplet-canopy adaptation information, the compatibility information between drug type and crop resistance is verified for different deposition areas to obtain the drug compliance information.

4. The method according to claim 1, characterized in that, Based on the dynamic environmental information set and the compliance-related information set, the system predicts and analyzes the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effects of wind field, field heat convection, and multi-rotor downwash airflow in the operating farmland, thus obtaining a spraying prediction information set, including: The dynamic environmental information set includes field surface temperature, farmland wind field information, and rotor airflow information; Based on the farmland wind field information, the influence of the farmland wind field on the horizontal transport direction and velocity of drug droplets is analyzed to obtain wind field airflow disturbance information. Based on the rotor airflow information and the wind field airflow disturbance information, the influence of the multi-rotor downwash airflow on the forced settling velocity and lateral diffusion range of drug droplets is analyzed to obtain downwash airflow disturbance information; Based on the field surface temperature and the downwash airflow disturbance information, the influence of hot air convection on the lifting intensity and height distribution of near-surface vertical airflow is analyzed to obtain diffusion characteristic information. Based on the diffusion characteristic information and the compliance association information set, the landing position and coverage of drug droplets at different heights and different horizontal distances are predicted to obtain the spraying prediction information set.

5. The method according to claim 4, characterized in that, The process of constructing the downwash airflow disturbance information includes: Based on the rotor airflow information and the wind field airflow disturbance information, the influence of farmland wind field on the flight attitude and rotor speed of multi-rotor UAV is analyzed to obtain the initial rotor disturbance information. Based on the initial rotor disturbance information, the airflow deflection and diffusion characteristics caused by the direct action of the farmland wind field on the downwash airflow are analyzed to obtain the downwash airflow disturbance information.

6. The method according to claim 4, characterized in that, The process of constructing the diffusion feature information includes: Based on the field surface temperature, the non-uniform characteristics of the upward velocity of hot air convection and the intensity of turbulence in different temperature regions are analyzed to obtain information on thermal uplift. Based on the thermal lift information and the downwash airflow disturbance information, the vertical lifting or suppression effect on drug droplets after the downwash airflow and hot air convection coupling is analyzed to obtain the diffusion characteristic information.

7. The method according to claim 4, characterized in that, Based on the diffusion characteristic information and combined with the compliance association information set, the landing point and coverage area of ​​drug droplets at different heights and horizontal distances are predicted to obtain the spraying prediction information set, which includes: Based on the diffusion characteristic information, the differential effects of wind field, multi-rotor downwash airflow and hot gas convection coupling on drug droplets at different altitude layers are analyzed to obtain stratified airflow effect information; Based on the stratified airflow information and the compliance-related information set, the settling time and retention tendency of drug droplets after being affected by airflow in each height layer are analyzed to obtain stratified settling information. Based on the stratified sedimentation information, the migration path of the pesticide droplets from the application height through each height layer to the crop canopy and the ground is analyzed to obtain the spraying prediction information set.

8. The method according to claim 7, characterized in that, The step of generating and outputting a collaborative management strategy for drone pilots, drones, and pesticides based on the spraying prediction information set includes: Based on the spraying prediction information set, analyze the time lag characteristics between drug droplet spraying deviation and UAV sensor prediction, pilot operation and drug feedback to obtain reliable information on lag correlation. Based on the aforementioned hysteresis-related reliable information, a dynamic adjustment strategy is generated and output for the timing advance information of the pilot's control commands, the adjustment level of the drone's flight speed, and the dynamic adjustment strategy of the drug spraying flow rate, as the collaborative management strategy of pilot-drone-drug.

9. The method according to claim 8, characterized in that, The process of constructing the delayed associated reliable information includes: Based on the spraying prediction information set, the time interval of the entire link of UAV sensor data acquisition and transmission, pilot reliable association decision and command execution, and drug spraying feedback is analyzed to obtain the lag information of each link; Based on the lag information of each stage, a corresponding correlation between time lag and spraying deviation is established to obtain the reliable information of the lag correlation.

10. A reliable system for the dual-location association of unmanned aerial vehicles (UAVs) and pilots, characterized in that, The method applied to any one of claims 1-9 includes: The compliance association module is used to acquire a set of information on farmland where drones are operating. Based on this set of information, the module analyzes the spatial compatibility between the drone operator's location and the farmland, and verifies the compliance of the matching between pesticide type and field crops to obtain a set of compliance association information. The spraying prediction module is used to acquire a dynamic environmental information set. Based on the dynamic environmental information set and the compliance association information set, it predicts and analyzes the spatiotemporal diffusion interference characteristics of the sprayed pesticides caused by the coupling effect of the wind field of the working farmland, the field heat convection and the downwash airflow of the multi-rotor, and obtains the spraying prediction information set. The collaborative management module is used to generate and output a collaborative management strategy for the pilot, drone, and pesticide based on the spraying prediction information set.

Images