Intelligent dispatching method, system and storage medium for plant protection drone

Abstract

The present invention relates to an intelligent scheduling method, system and storage medium for a plant protection UAV, and belongs to the technical field. The present invention obtains the historical service data information of each plant protection UAV, and predicts the fault time information of each plant protection UAV based on the historical service data information of the plant protection UAV, selects the optimal plant protection UAV based on the fault time information of each plant protection UAV, and controls the optimal plant protection UAV to perform the spraying task according to the relevant flight route. The present invention fully considers the maximum information exchange capacity information of the control base station, so as to more reasonably configure the working quantity of the plant protection UAV, so that the working data of the plant protection UAV is lower than the maximum information exchange capacity information of the control base station, thereby ensuring the control accuracy of the plant protection UAV when performing the spraying task, so that the spraying of the plant protection UAV is more reasonable.

Description

Technical Field

[0001] The present invention relates to a method for dispatching an unmanned aerial vehicle (UAV), and in particular to an intelligent dispatching method, system and storage medium for a plant protection UAV. Background Art

[0002] Agricultural modernization is the common realization of modernization of production technology, modernization of production tools, and modernization of management mode. As an emerging technology, plant protection drones have quickly emerged and have shown great application potential in modern agriculture. The use of plant protection drones has effectively solved the realistic problems of insufficient labor force in agricultural production, low production efficiency, and high risk of agricultural production activities. Whether it is to protect the health and safety of farmers, to protect the balance of the ecological environment, or to achieve good economic benefits, the advantages of plant protection drones are far beyond the reach of traditional agricultural production models. In the future, plant protection drones will play an increasingly important role in modern agriculture. However, in the existing technology, the control of drones is often achieved by controlling the information interaction between the base station and the drone to control the flight of the plant protection drone, and the control base station will also have a certain control upper limit. Once the number of connected plant protection drones increases, it will cause a delay in the transmission of information. The existing technology does not consider this type of problem, resulting in low control accuracy of the drone. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent scheduling method, system and storage medium for a plant protection UAV.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides an intelligent scheduling method for a plant protection UAV, comprising the following steps:

[0006] Obtain the pesticide application area information and pesticide application task information of the area to be applied, and determine the estimated number of pesticide application tasks performed by the plant protection drone according to the pesticide application area information and pesticide application task information of the area to be applied;

[0007] Obtain the information exchange capacity data information of the plant protection UAV within a unit time when performing the spraying task, optimize the estimated quantity information of the plant protection UAV when performing the spraying task according to the information exchange capacity data information, and obtain the actual quantity information of the plant protection UAV when performing the spraying task;

[0008] The spraying area is divided into several sub-areas, and the geographical location information of each sub-area is obtained. The relevant flight routes are formulated according to the geographical location information of each sub-area and the actual number information of the plant protection UAVs when performing the spraying task;

[0009] The historical service data information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is predicted based on the historical service data information of the plant protection UAV. The optimal plant protection UAV is selected based on the failure time information of each plant protection UAV, and the optimal plant protection UAV is controlled to perform the spraying task according to the relevant flight route.

[0010] Furthermore, in this method, the estimated quantity information of the plant protection UAV when performing the pesticide application task is determined according to the pesticide application area information of the area to be applied and the pesticide application task information, specifically including:

[0011] According to the pesticide application task information, the insect data and disease data information of the area to be applied are obtained, and based on the insect data and disease data information of the area to be applied and the application area information of the area to be applied, the pesticide application analysis is performed to obtain the estimated application amount information of the area to be applied;

[0012] The pesticide application amount information of the plant protection UAV within a unit time is obtained, and the estimated quantity information when the plant protection UAV performs the pesticide application task is calculated based on the pesticide application amount information of the plant protection UAV within a unit time and the estimated pesticide application amount information of the area to be sprayed.

[0013] Furthermore, in this method, the estimated quantity information of the plant protection UAV when performing the spraying task is optimized according to the information exchange capacity data information, and the actual quantity information of the plant protection UAV when performing the spraying task is obtained, specifically including

[0014] The total information exchange capacity data information when the plant protection UAV performs data exchange is calculated based on the information exchange capacity data information and the estimated number information when the plant protection UAV performs the spraying task;

[0015] Obtain the maximum information exchange capacity data information of the plant protection UAV control base station, and determine whether the total information exchange capacity data information when the plant protection UAV performs data exchange is greater than the maximum information exchange capacity data information of the plant protection UAV control base station;

[0016] If it is greater, the estimated number of plant protection drones performing spraying tasks is adjusted until the total information exchange capacity data information of the plant protection drone during data exchange is greater than the maximum information exchange capacity data information of the plant protection drone control base station, and the new estimated number of plant protection drones performing spraying tasks is output;

[0017] According to the estimated quantity information of the new plant protection UAV when performing the pesticide application task, the actual quantity information of the plant protection UAV when performing the pesticide application task is generated, and the actual quantity information of the plant protection UAV when performing the pesticide application task is output;

[0018] When the total information interaction capacity data information when the plant protection UAV performs data interaction is not greater than the maximum information interaction capacity data information of the plant protection UAV control base station, the estimated quantity information when the plant protection UAV performs the spraying task is output as the actual quantity information when the plant protection UAV performs the spraying task.

[0019] Furthermore, in this method, the geographical location information of each sub-area is obtained, and the relevant flight routes are formulated according to the geographical location information of each sub-area and the actual number information of the plant protection UAV when performing the spraying task, specifically including:

[0020] Obtain the geographical location information of each sub-area and the pesticide application area information of each sub-area, initialize the pesticide application end point position of each sub-area, and introduce the ant colony algorithm to obtain the pesticide application working range information of each plant protection drone;

[0021] The geographical location information of each sub-area, the pesticide application area information of each sub-area, the pesticide application end point location of each sub-area, and the pesticide application working range information of each plant protection UAV are input into the ant colony algorithm to perform pesticide application heading planning, and obtain several first flight routes;

[0022] Obtaining geographic location information of the plant protection UAV when it takes off, initializing a plurality of second flight routes according to the geographic location information of each sub-area and the geographic location information of the plant protection UAV when it takes off, and determining whether there is interference between each second flight route;

[0023] When there is interference, the second flight route is readjusted until there is no interference between the second flight routes, the second flight route is output, and a related flight route is formulated based on the first flight route and the second flight route.

[0024] Furthermore, in this method, historical service data information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is predicted based on the historical service data information of the plant protection UAV, specifically including:

[0025] Construct a timestamp, obtain the service data information of each plant protection UAV in each timestamp, and construct the historical service data information of each plant protection UAV according to the service data information of each plant protection UAV in each timestamp;

[0026] Build a UAV fault prediction model based on a deep neural network, build a feature matrix based on the historical service data of the plant protection UAV, and input the feature matrix into the UAV fault prediction model for training;

[0027] Through training, a trained UAV fault prediction model is obtained, and service data information of each plant protection UAV within a preset time is obtained, and the service data information of each plant protection UAV within the preset time is input into the trained UAV fault prediction model for prediction;

[0028] Through prediction, the failure time information of each plant protection UAV is obtained and output.

[0029] Furthermore, in this method, the optimal plant protection drone is selected based on the failure time information of each plant protection drone, specifically including:

[0030] Obtain the pesticide application task information of the area to be applied, and initialize the configuration of the plant protection UAV according to the pesticide application task information of the area to be applied, obtain the pesticide application time range information of each plant protection UAV, and determine whether the fault time information of the plant protection UAV is within the pesticide application time range information of the plant protection UAV;

[0031] When the fault time information of the plant protection drone is within the pesticide application time range information of the plant protection drone, the corresponding plant protection drone is regarded as a non-preferred plant protection drone;

[0032] When the fault time information of the plant protection drone is not within the pesticide application time range information of the plant protection drone, the corresponding plant protection drone is used as the preferred plant protection drone, and the number information of the preferred plant protection drone and the actual number information of the current plant protection drone when performing the pesticide application task are obtained;

[0033] When the preferred plant protection drone quantity information is not less than the actual quantity information of the current plant protection drone when performing the spraying task, the preferred plant protection drone with the same data as the actual quantity information of the current plant protection drone when performing the spraying task is randomly selected as the optimal plant protection drone;

[0034] When the preferred plant protection drone quantity information is less than the actual quantity information when the current plant protection drone performs the pesticide application task, the largest number of preferred plant protection drones is used as the optimal plant protection drone.

[0035] A second aspect of the present invention provides an intelligent scheduling system for a plant protection UAV. The scheduling system includes a memory and a processor. The memory includes an intelligent scheduling method program for the plant protection UAV. When the intelligent scheduling method program for the plant protection UAV is executed by the processor, the following steps are implemented:

[0036] Obtain the pesticide application area information and pesticide application task information of the area to be applied, and determine the estimated number of pesticide application tasks performed by the plant protection drone according to the pesticide application area information and pesticide application task information of the area to be applied;

[0037] Obtain the information exchange capacity data information of the plant protection UAV within a unit time when performing the spraying task, optimize the estimated quantity information of the plant protection UAV when performing the spraying task according to the information exchange capacity data information, and obtain the actual quantity information of the plant protection UAV when performing the spraying task;

[0038] The spraying area is divided into several sub-areas, and the geographical location information of each sub-area is obtained. The relevant flight routes are formulated according to the geographical location information of each sub-area and the actual number information of the plant protection UAVs when performing the spraying task;

[0039] The historical service data information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is predicted based on the historical service data information of the plant protection UAV. The optimal plant protection UAV is selected based on the failure time information of each plant protection UAV, and the optimal plant protection UAV is controlled to perform the spraying task according to the relevant flight route.

[0040] The third aspect of the present invention provides a computer-readable storage medium, which includes an intelligent scheduling method program for a plant protection drone. When the intelligent scheduling method program for a plant protection drone is executed by a processor, any step of the intelligent scheduling method for a plant protection drone is implemented.

[0041] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0042] The present invention obtains pesticide application area information and pesticide application task information of the area to be sprayed, and determines the estimated quantity information of the plant protection UAV when performing the pesticide application task according to the pesticide application area information and the pesticide application task information of the area to be sprayed, and then obtains the information interaction capacity data information of the plant protection UAV within unit time when performing the pesticide application task, optimizes the estimated quantity information of the plant protection UAV when performing the pesticide application task according to the information interaction capacity data information, obtains the actual quantity information of the plant protection UAV when performing the pesticide application task, thereby dividing the pesticide application area into several sub-areas, and obtains the geographical location information of each sub-area, formulates relevant flight routes according to the geographical location information of each sub-area and the actual quantity information of the plant protection UAV when performing the pesticide application task, finally obtains the historical service data information of each plant protection UAV, and predicts the fault time information of each plant protection UAV according to the historical service data information of the plant protection UAV, selects the optimal plant protection UAV based on the fault time information of each plant protection UAV, and controls the optimal plant protection UAV to perform the pesticide application task according to the relevant flight route. The present invention fully considers the maximum information exchange capacity information of the control base station, so as to more reasonably configure the working quantity of the plant protection UAV, so that the working data of the plant protection UAV is lower than the maximum information exchange capacity information of the control base station, thereby ensuring the control accuracy of the plant protection UAV when performing the spraying task, making the spraying of the plant protection UAV more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0044] Figure 1 The overall method flow chart of an intelligent dispatching method for plant protection UAV is shown;

[0045] Figure 2 A first method flow chart of an intelligent dispatching method for plant protection UAVs is shown;

[0046] Figure 3 A second method flow chart of an intelligent dispatching method for plant protection UAVs is shown;

[0047] Figure 4 The system block diagram of an intelligent dispatching system for plant protection UAVs is shown. DETAILED DESCRIPTION

[0048] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0050] like Figure 1 As shown, the first aspect of the present invention provides an intelligent scheduling method for a plant protection UAV, comprising the following steps:

[0051] S102: Acquire the pesticide application area information and the pesticide application task information of the area to be applied, and determine the estimated quantity information when the plant protection UAV performs the pesticide application task according to the pesticide application area information and the pesticide application task information of the area to be applied;

[0052] S104: obtaining information exchange capacity data information within a unit time when the plant protection UAV performs the pesticide application task, optimizing the estimated quantity information when the plant protection UAV performs the pesticide application task according to the information exchange capacity data information, and obtaining the actual quantity information when the plant protection UAV performs the pesticide application task;

[0053] S106: Divide the pesticide application area into several sub-areas, obtain the geographical location information of each sub-area, and formulate relevant flight routes according to the geographical location information of each sub-area and the actual number information of the plant protection UAV when performing the pesticide application task;

[0054] S108: Obtain the historical service data information of each plant protection UAV, and predict the failure time information of each plant protection UAV based on the historical service data information of the plant protection UAV, select the optimal plant protection UAV based on the failure time information of each plant protection UAV, and control the optimal plant protection UAV to perform the spraying task according to the relevant flight route.

[0055] It should be noted that the present invention fully considers the maximum information exchange capacity information of the control base station, so as to more reasonably configure the working quantity of the plant protection UAV, so that the working data of the plant protection UAV is lower than the maximum information exchange capacity information of the control base station, thereby ensuring the control accuracy of the plant protection UAV when performing the spraying task, making the spraying of the plant protection UAV more reasonable.

[0056] Furthermore, in this method, the estimated quantity information of the plant protection UAV when performing the pesticide application task is determined according to the pesticide application area information of the area to be applied and the pesticide application task information, specifically including:

[0057] According to the pesticide application task information, the insect data and disease data information of the area to be applied are obtained, and based on the insect data and disease data information of the area to be applied and the application area information of the area to be applied, the pesticide application analysis is performed to obtain the estimated application amount information of the area to be applied;

[0058] The pesticide application amount information of the plant protection UAV within a unit time is obtained, and the estimated quantity information when the plant protection UAV performs the pesticide application task is calculated based on the pesticide application amount information of the plant protection UAV within a unit time and the estimated pesticide application amount information of the area to be sprayed.

[0059] It should be noted that the pesticide application task information includes insect infestation data, disease data information, scheduled time for pesticide application, and other data in the area to be sprayed. Among them, the insect infestation data includes the type of pests, the number of pests per unit planting area, etc., and the disease data information includes the type of disease, the area where the disease occurs, etc.

[0060] Furthermore, in this method, the estimated quantity information of the plant protection UAV when performing the spraying task is optimized according to the information exchange capacity data information, and the actual quantity information of the plant protection UAV when performing the spraying task is obtained, specifically including

[0061] The total information exchange capacity data information when the plant protection UAV performs data exchange is calculated based on the information exchange capacity data information and the estimated number information when the plant protection UAV performs the spraying task;

[0062] Obtain the maximum information exchange capacity data information of the plant protection UAV control base station, and determine whether the total information exchange capacity data information when the plant protection UAV performs data exchange is greater than the maximum information exchange capacity data information of the plant protection UAV control base station;

[0063] If it is greater, the estimated number of plant protection drones performing spraying tasks is adjusted until the total information exchange capacity data information of the plant protection drone during data exchange is greater than the maximum information exchange capacity data information of the plant protection drone control base station, and the new estimated number of plant protection drones performing spraying tasks is output;

[0064] According to the estimated quantity information of the new plant protection UAV when performing the pesticide application task, the actual quantity information of the plant protection UAV when performing the pesticide application task is generated, and the actual quantity information of the plant protection UAV when performing the pesticide application task is output;

[0065] When the total information interaction capacity data information when the plant protection UAV performs data interaction is not greater than the maximum information interaction capacity data information of the plant protection UAV control base station, the estimated quantity information when the plant protection UAV performs the spraying task is output as the actual quantity information when the plant protection UAV performs the spraying task.

[0066] It should be noted that due to server limitations, there is an upper limit to the information exchange between the control base station and the plant protection drone. When the number of plant protection drones continues to increase, there may be a queue for the information exchange between the control base station and the plant protection drone, resulting in a delay in the information exchange between some plant protection drones and the control base station. This method can calculate a reasonable actual number of plant protection drones when performing spraying tasks based on the existing number of plant protection drones, thereby ensuring the timeliness of information exchange between the plant protection drones and the control base station and ensuring the control accuracy of the plant protection drones.

[0067] like Figure 2 As shown, further, in this method, the geographical location information of each sub-area is obtained, and the relevant flight route is formulated according to the geographical location information of each sub-area and the actual number information when the plant protection UAV performs the spraying task, specifically including:

[0068] S202: Obtaining geographical location information of each sub-area and pesticide application area information of each sub-area, initializing the pesticide application end point position of each sub-area, and introducing an ant colony algorithm to obtain pesticide application working range information of each plant protection drone;

[0069] S204: inputting the geographical location information of each sub-region, the pesticide application area information of each sub-region, the pesticide application end point location of each sub-region, and the pesticide application working range information of each plant protection UAV into the ant colony algorithm to perform pesticide application heading planning, and obtain a plurality of first flight routes;

[0070] S206: obtaining geographic location information of the plant protection UAV when it takes off, initializing a plurality of second flight routes according to the geographic location information of each sub-area and the geographic location information of the plant protection UAV when it takes off, and determining whether there is interference between each second flight route;

[0071] S208: When there is interference, the second flight route is readjusted until there is no interference between the second flight routes, the second flight route is output, and related flight routes are formulated based on the first flight route and the second flight route.

[0072] It should be noted that the ant colony optimization (ACO), also known as the ant algorithm, is a probabilistic algorithm used to find optimized paths in a graph. It was proposed by Marco Dorigo in his doctoral thesis in 1992, and was inspired by the behavior of ants in finding paths in the process of searching for food. The ant colony algorithm is a simulated evolutionary algorithm. Preliminary studies have shown that the algorithm has many excellent properties. The ant colony algorithm can plan the optimal navigation route for each plant protection drone in the spraying area. In actual situations, most drones take off in the same take-off area. When there is interference, the second flight route is readjusted until there is no interference between the second flight routes, and the second flight route is output to improve the rationality of flight route planning. By merging the first flight route and the second flight route, relevant flight routes are formulated.

[0073] like Figure 3 As shown, further, in this method, the historical service data information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is predicted based on the historical service data information of the plant protection UAV, specifically including:

[0074] S302: constructing a timestamp, obtaining the service data information of each plant protection drone in each timestamp, and constructing the historical service data information of each plant protection drone according to the service data information of each plant protection drone in each timestamp;

[0075] S304: constructing a UAV fault prediction model based on a deep neural network, constructing a feature matrix based on historical service data information of the plant protection UAV, and inputting the feature matrix into the UAV fault prediction model for training;

[0076] S306: obtaining a trained UAV fault prediction model through training, and obtaining service data information of each plant protection UAV within a preset time, and inputting the service data information of each plant protection UAV within the preset time into the trained UAV fault prediction model for prediction;

[0077] S308: Obtain the failure time information of each plant protection UAV through prediction, and output the failure time information of each plant protection UAV.

[0078] It should be noted that deep neural networks include long short-term memory neural networks, recursive neural networks, convolutional neural networks, etc. This method can predict the failure time information of each plant protection drone.

[0079] Furthermore, in this method, the optimal plant protection drone is selected based on the failure time information of each plant protection drone, specifically including:

[0080] Obtain the pesticide application task information of the area to be applied, and initialize the configuration of the plant protection UAV according to the pesticide application task information of the area to be applied, obtain the pesticide application time range information of each plant protection UAV, and determine whether the fault time information of the plant protection UAV is within the pesticide application time range information of the plant protection UAV;

[0081] When the fault time information of the plant protection drone is within the pesticide application time range information of the plant protection drone, the corresponding plant protection drone is regarded as a non-preferred plant protection drone;

[0082] When the fault time information of the plant protection drone is not within the pesticide application time range information of the plant protection drone, the corresponding plant protection drone is used as the preferred plant protection drone, and the number information of the preferred plant protection drone and the actual number information of the current plant protection drone when performing the pesticide application task are obtained;

[0083] When the preferred plant protection drone quantity information is not less than the actual quantity information of the current plant protection drone when performing the spraying task, the preferred plant protection drone with the same data as the actual quantity information of the current plant protection drone when performing the spraying task is randomly selected as the optimal plant protection drone;

[0084] When the preferred plant protection drone quantity information is less than the actual quantity information when the current plant protection drone performs the pesticide application task, the largest number of preferred plant protection drones is used as the optimal plant protection drone.

[0085] It should be noted that this method can further improve the rationality of the dispatching of plant protection UAVs.

[0086] In addition, the method may further comprise the following steps:

[0087] Obtain the information delay feature data of the plant protection UAV interacting with the control base station in various working environments and with different numbers of plant protection UAVs, and build an information delay feature data prediction model based on a deep neural network;

[0088] Inputting information delay characteristic data of information interaction between the plant protection UAV and the control base station in various working environments and under different numbers of plant protection UAVs into the information delay characteristic data prediction model for training, and obtaining a trained information delay characteristic data prediction model;

[0089] Acquire the working environment data of the current plant protection drone and the working number information of the plant protection drones in the current spraying area, and input the working environment data of the current plant protection drone and the working number information of the plant protection drones in the current spraying area into the trained information delay feature data prediction model for prediction;

[0090] Through prediction, the information delay characteristic data between the plant protection UAV and the control base station in the current timestamp is obtained. When the information delay characteristic data between the plant protection UAV and the control base station in the current timestamp is greater than the preset delay threshold, the working quantity of the plant protection UAV is dynamically adjusted until the information delay characteristic data between the plant protection UAV and the control base station in the current timestamp is no greater than the preset delay threshold.

[0091] It should be noted that since the interaction of information is related to the working environment and the number of plant protection UAVs working, such as temperature, humidity, haze and other data, and since electromagnetic waves are affected by such factors, the reception and transmission of information will be affected. This method can further dynamically adjust the number of plant protection UAVs working according to environmental conditions, thereby improving the rationality of plant protection UAV planning.

[0092] like Figure 4 As shown, the second aspect of the present invention provides an intelligent scheduling system 4 for a plant protection UAV, the scheduling system 4 includes a memory 41 and a processor 42, the memory 41 includes an intelligent scheduling method program for a plant protection UAV, and when the intelligent scheduling method program for a plant protection UAV is executed by the processor 42, the following steps are implemented:

[0093] Obtain the pesticide application area information and pesticide application task information of the area to be applied, and determine the estimated number of pesticide application tasks performed by the plant protection drone according to the pesticide application area information and pesticide application task information of the area to be applied;

[0094] Obtain the information exchange capacity data information of the plant protection UAV within a unit time when performing the spraying task, optimize the estimated quantity information of the plant protection UAV when performing the spraying task according to the information exchange capacity data information, and obtain the actual quantity information of the plant protection UAV when performing the spraying task;

[0095] The spraying area is divided into several sub-areas, and the geographical location information of each sub-area is obtained. The relevant flight routes are formulated according to the geographical location information of each sub-area and the actual number information of the plant protection UAVs when performing the spraying task;

[0096] The historical service data information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is predicted based on the historical service data information of the plant protection UAV. The optimal plant protection UAV is selected based on the failure time information of each plant protection UAV, and the optimal plant protection UAV is controlled to perform the spraying task according to the relevant flight route.

[0097] The third aspect of the present invention provides a computer-readable storage medium, which includes an intelligent scheduling method program for a plant protection drone. When the intelligent scheduling method program for a plant protection drone is executed by a processor, any step of the intelligent scheduling method for a plant protection drone is implemented.

[0098] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0099] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0100] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0101] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0102] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0103] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent dispatching method for plant protection drones, characterized in that: The following steps are involved: Obtaining pesticide application area information and pesticide application task information of the area to be applied, and determining the estimated quantity information when the plant protection UAV performs the pesticide application task according to the pesticide application area information and pesticide application task information of the area to be applied; Obtaining information exchange capacity data information within a unit time when the plant protection UAV performs a pesticide application task, optimizing the estimated quantity information when the plant protection UAV performs the pesticide application task according to the information exchange capacity data information, and obtaining the actual quantity information when the plant protection UAV performs the pesticide application task; The spraying area is divided into several sub-areas, and the geographical location information of each sub-area is obtained, and the relevant flight routes are formulated according to the geographical location information of each sub-area and the actual number information of the plant protection UAV when performing the spraying task; Acquire historical service data information of each plant protection UAV, and predict the failure time information of each plant protection UAV according to the historical service data information of the plant protection UAV, select the optimal plant protection UAV based on the failure time information of each plant protection UAV, and control the optimal plant protection UAV to perform the pesticide application task according to the relevant flight route; The estimated quantity information of the plant protection UAV when performing the spraying task is optimized according to the information exchange capacity data information, and the actual quantity information of the plant protection UAV when performing the spraying task is obtained, specifically including Calculate the total information interaction capacity data information when the plant protection drone performs data interaction according to the information interaction capacity data information and the estimated number information when the plant protection drone performs the pesticide application task; Acquire the maximum information exchange capacity data information of the plant protection UAV control base station, and determine whether the total information exchange capacity data information of the plant protection UAV during data exchange is greater than the maximum information exchange capacity data information of the plant protection UAV control base station; If it is greater, the estimated number information of the plant protection drone when performing the pesticide application task is adjusted until the total information exchange capacity data information of the plant protection drone when performing data exchange is greater than the maximum information exchange capacity data information of the plant protection drone control base station, and the new estimated number information of the plant protection drone when performing the pesticide application task is output; Generating actual quantity information of the plant protection drone when performing the pesticide application task according to the estimated quantity information of the new plant protection drone when performing the pesticide application task, and outputting the actual quantity information of the plant protection drone when performing the pesticide application task; When the total information exchange capacity data information when the plant protection UAV performs data exchange is not greater than the maximum information exchange capacity data information of the plant protection UAV control base station, the estimated quantity information when the plant protection UAV performs the pesticide application task is output as the actual quantity information when the plant protection UAV performs the pesticide application task; Obtain the geographical location information of each sub-area, and formulate relevant flight routes according to the geographical location information of each sub-area and the actual number information of the plant protection UAV when performing the pesticide application task, specifically including: Obtain the geographical location information of each sub-area and the pesticide application area information of each sub-area, initialize the pesticide application end point position of each sub-area, and introduce the ant colony algorithm to obtain the pesticide application working range information of each plant protection drone; Inputting the geographical location information of each sub-region, the pesticide application area information of each sub-region, the pesticide application end point position of each sub-region, and the pesticide application working range information of each plant protection UAV into the ant colony algorithm to perform pesticide application heading planning, and obtain a plurality of first flight routes; Acquire the geographic location information of the plant protection UAV when it takes off, initialize a plurality of second flight routes according to the geographic location information of each sub-area and the geographic location information of the plant protection UAV when it takes off, and determine whether there is interference between each second flight route; When there is interference, the second flight route is readjusted until there is no interference between the second flight routes, the second flight route is output, and a related flight route is formulated according to the first flight route and the second flight route; Obtaining historical service data information of each plant protection UAV, and predicting the failure time information of each plant protection UAV according to the historical service data information of the plant protection UAV, specifically including: Constructing a timestamp, obtaining the service data information of each plant protection drone in each timestamp, and constructing the historical service data information of each plant protection drone according to the service data information of each plant protection drone in each timestamp; Building a UAV fault prediction model based on a deep neural network, building a feature matrix based on historical service data information of the plant protection UAV, and inputting the feature matrix into the UAV fault prediction model for training; Through training, a trained UAV fault prediction model is obtained, and service data information of each plant protection UAV within a preset time is obtained, and the service data information of each plant protection UAV within the preset time is input into the trained UAV fault prediction model for prediction; Through prediction, the failure time information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is output.

2. The intelligent dispatching method for a plant protection UAV according to claim 1, characterized in that: According to the pesticide application area information and the pesticide application task information of the area to be applied, the estimated quantity information when the plant protection drone performs the pesticide application task is determined, specifically including: Acquire insect pest data and disease data information of the area to be sprayed according to the spraying task information, and perform spraying analysis based on the insect pest data, disease data information and spraying area information of the area to be sprayed, to obtain estimated spraying amount information of the area to be sprayed; The pesticide application amount information of the plant protection UAV within a unit time is obtained, and the estimated quantity information when the plant protection UAV performs the pesticide application task is calculated based on the pesticide application amount information of the plant protection UAV within a unit time and the estimated pesticide application amount information of the area to be sprayed.

3. The intelligent dispatching method for a plant protection UAV according to claim 1, characterized in that: Selecting the optimal plant protection drone based on the failure time information of each plant protection drone specifically includes: Acquire the pesticide application task information of the area to be applied, and initialize the configuration of the plant protection UAV according to the pesticide application task information of the area to be applied, acquire the pesticide application time range information of each plant protection UAV, and determine whether the fault time information of the plant protection UAV is within the pesticide application time range information of the plant protection UAV; When the fault time information of the plant protection drone is within the pesticide application time range information of the plant protection drone, the corresponding plant protection drone is regarded as a non-preferred plant protection drone; When the fault time information of the plant protection drone is not within the pesticide application time range information of the plant protection drone, the corresponding plant protection drone is used as the preferred plant protection drone, and the preferred plant protection drone quantity information and the actual quantity information of the current plant protection drone when performing the pesticide application task are obtained; When the preferred plant protection drone quantity information is not less than the actual quantity information of the current plant protection drone when performing the pesticide application task, a preferred plant protection drone with the same data as the actual quantity information of the current plant protection drone when performing the pesticide application task is randomly selected as the optimal plant protection drone; When the preferred plant protection drone quantity information is less than the actual quantity information of the current plant protection drone when performing the pesticide application task, the preferred plant protection drone with the largest quantity is used as the optimal plant protection drone.

4. An intelligent dispatching system for plant protection drones, characterized in that: The scheduling system includes a memory and a processor. The memory includes an intelligent scheduling method program for a plant protection UAV. When the intelligent scheduling method program for a plant protection UAV is executed by the processor, the following steps are implemented: Obtaining pesticide application area information and pesticide application task information of the area to be applied, and determining the estimated quantity information when the plant protection UAV performs the pesticide application task according to the pesticide application area information and pesticide application task information of the area to be applied; Obtaining information exchange capacity data information within a unit time when the plant protection UAV performs a pesticide application task, optimizing the estimated quantity information when the plant protection UAV performs the pesticide application task according to the information exchange capacity data information, and obtaining the actual quantity information when the plant protection UAV performs the pesticide application task; The spraying area is divided into several sub-areas, and the geographical location information of each sub-area is obtained, and the relevant flight routes are formulated according to the geographical location information of each sub-area and the actual number information of the plant protection UAV when performing the spraying task; Acquire historical service data information of each plant protection UAV, and predict the failure time information of each plant protection UAV according to the historical service data information of the plant protection UAV, select the optimal plant protection UAV based on the failure time information of each plant protection UAV, and control the optimal plant protection UAV to perform the pesticide application task according to the relevant flight route; The estimated quantity information of the plant protection UAV when performing the spraying task is optimized according to the information exchange capacity data information, and the actual quantity information of the plant protection UAV when performing the spraying task is obtained, specifically including Calculate the total information interaction capacity data information when the plant protection drone performs data interaction according to the information interaction capacity data information and the estimated number information when the plant protection drone performs the pesticide application task; Acquire the maximum information exchange capacity data information of the plant protection UAV control base station, and determine whether the total information exchange capacity data information of the plant protection UAV during data exchange is greater than the maximum information exchange capacity data information of the plant protection UAV control base station; If it is greater, the estimated number information of the plant protection drone when performing the pesticide application task is adjusted until the total information exchange capacity data information of the plant protection drone when performing data exchange is greater than the maximum information exchange capacity data information of the plant protection drone control base station, and the new estimated number information of the plant protection drone when performing the pesticide application task is output; Generating actual quantity information of the plant protection drone when performing the pesticide application task according to the estimated quantity information of the new plant protection drone when performing the pesticide application task, and outputting the actual quantity information of the plant protection drone when performing the pesticide application task; When the total information exchange capacity data information when the plant protection UAV performs data exchange is not greater than the maximum information exchange capacity data information of the plant protection UAV control base station, the estimated quantity information when the plant protection UAV performs the pesticide application task is output as the actual quantity information when the plant protection UAV performs the pesticide application task; Obtain the geographical location information of each sub-area, and formulate relevant flight routes according to the geographical location information of each sub-area and the actual number information of the plant protection UAV when performing the pesticide application task, specifically including: Obtain the geographical location information of each sub-area and the pesticide application area information of each sub-area, initialize the pesticide application end point position of each sub-area, and introduce the ant colony algorithm to obtain the pesticide application working range information of each plant protection drone; Inputting the geographical location information of each sub-region, the pesticide application area information of each sub-region, the pesticide application end point position of each sub-region, and the pesticide application working range information of each plant protection UAV into the ant colony algorithm to perform pesticide application heading planning, and obtain a plurality of first flight routes; Acquire the geographic location information of the plant protection UAV when it takes off, initialize a plurality of second flight routes according to the geographic location information of each sub-area and the geographic location information of the plant protection UAV when it takes off, and determine whether there is interference between each second flight route; When there is interference, the second flight route is readjusted until there is no interference between the second flight routes, the second flight route is output, and a related flight route is formulated according to the first flight route and the second flight route; Obtaining historical service data information of each plant protection UAV, and predicting the failure time information of each plant protection UAV according to the historical service data information of the plant protection UAV, specifically including: Constructing a timestamp, obtaining the service data information of each plant protection drone in each timestamp, and constructing the historical service data information of each plant protection drone according to the service data information of each plant protection drone in each timestamp; Building a UAV fault prediction model based on a deep neural network, building a feature matrix based on historical service data information of the plant protection UAV, and inputting the feature matrix into the UAV fault prediction model for training; Through training, a trained UAV fault prediction model is obtained, and service data information of each plant protection UAV within a preset time is obtained, and the service data information of each plant protection UAV within the preset time is input into the trained UAV fault prediction model for prediction; Through prediction, the failure time information of each plant protection UAV is obtained, and the failure time information of each plant protection UAV is output.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a program for the intelligent scheduling method of a plant protection drone. When the program for the intelligent scheduling method of a plant protection drone is executed by a processor, the steps of the intelligent scheduling method of a plant protection drone as described in any one of claims 1 to 3 are implemented.

Images