Precise patrol scheduling method and system based on multi-source heterogeneous unmanned aerial vehicle, and medium

Abstract

The invention provides a fine patrol scheduling method and system based on a multi-source heterogeneous unmanned aerial vehicle, and a medium. The method comprises the steps of obtaining performance data of a plurality of unmanned aerial vehicles in a preset area and task priority data of a target task, performing processing through a preset unmanned aerial vehicle task allocation algorithm to obtain a plurality of corresponding allocation integrating degree coefficients, comparing the allocation integrating degree coefficients with a preset allocation integrating degree coefficient, obtaining an optimal unmanned aerial vehicle, and sending the optimal unmanned aerial vehicle to a server; obtaining task demand data of the target task, processing the task demand data through a preset partition coverage algorithm, obtaining an optimal path of the target task, obtaining a simulation task scene, carrying out simulation experiments according to the adaptive fine patrol scheduling scheme and other scheduling schemes, and recording corresponding performance index data; and performing quantitative evaluation processing according to the performance index data to obtain a corresponding scheduling effectiveness index, judging the reliability of the adaptive fine patrol scheduling scheme and taking corresponding optimization measures, thereby realizing the fine patrol scheduling technology based on the multi-source heterogeneous unmanned aerial vehicle.

Description

Technical Field

[0001] The present application relates to the field of drone scheduling technology, and more specifically, to a precision patrol scheduling method, system, and medium based on multi-source heterogeneous drones. Background Art

[0002] With the rapid development of drone technology, its application in the inspection field is becoming more and more extensive. Multi-source heterogeneous drone systems can better meet the needs of complex inspection tasks because different types of drones have different advantages, such as endurance, load capacity, flight speed, etc. However, the existing drone scheduling methods are difficult to effectively coordinate multi-source heterogeneous drones, resulting in low inspection efficiency and unreasonable task allocation.

[0003] In response to the above problems, effective technical solutions are urgently needed. Summary of the Invention

[0004] The purpose of the present application is to provide a precision patrol scheduling method, system and medium based on multi-source heterogeneous UAVs. The method can obtain the performance data of multiple UAVs in a preset area and the task priority data of the target task, and process them through a preset UAV task allocation algorithm to obtain multiple corresponding allocation fit coefficients, compare them with the preset allocation fit coefficients, and obtain the optimal UAV. The task requirement data of the target task is obtained and processed through a preset partition coverage algorithm to obtain the optimal path of the target task. Simulation experiments are carried out according to the adapted precision patrol scheduling scheme and other scheduling schemes respectively, and quantitative evaluation processing is carried out according to the performance indicator data to obtain the corresponding scheduling effectiveness index. The reliability of the adapted precision patrol scheduling scheme is judged and corresponding optimization measures are taken to realize the technology of precision patrol scheduling based on multi-source heterogeneous UAVs.

[0005] This application also provides a precision patrol scheduling method based on multi-source heterogeneous UAVs, including the following steps: Acquire the performance data of multiple drones in a preset area, and simultaneously obtain the task priority data of the target task, and process them through a preset drone task allocation algorithm to obtain multiple corresponding allocation fit coefficients; Comparing the allocation fit coefficient with a preset allocation fit coefficient, and obtaining the optimal drone; Obtaining the task requirement data of the target task and processing it through a preset partition covering algorithm to obtain the optimal path of the target task; The optimal UAV executes the target task according to the optimal path, thereby realizing an adaptive precise patrol scheduling scheme for UAVs in the preset area; Obtain a simulated task scenario, conduct simulation experiments based on the adapted precise patrol scheduling solution and other scheduling solutions, and record corresponding performance indicator data; Perform quantitative evaluation processing based on the performance index data to obtain the corresponding scheduling effectiveness index, and judge the reliability of the adapted refined patrol scheduling scheme and take corresponding optimization measures.

[0006] Optionally, in the refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles (UAVs) of the present application, obtaining the performance data of multiple UAVs within a preset area, simultaneously obtaining the task priority data of the target task, and processing through a preset UAV task allocation algorithm to obtain corresponding multiple allocation fitness coefficients, including: Obtain the performance data of multiple UAVs within a preset area, including flight speed data, endurance time data, payload capacity data, and sensor accuracy data; Obtain the task priority data of the target task, including task importance data, task urgency data, and task timeliness data; According to the flight speed data, endurance time data, payload capacity data, and sensor accuracy data, and combining the task importance data, task urgency data, and task timeliness data, process through a preset UAV task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each UAV.

[0007] Optionally, in the refined patrol scheduling method based on multi-source heterogeneous UAVs of the present application, comparing the allocation fitness coefficient with a preset allocation fitness coefficient and obtaining the optimal UAV, including: Compare the allocation fitness coefficient with a preset allocation fitness coefficient to obtain a corresponding set of allocation fitness coefficient deviation rates; Perform comparison and screening processing according to the set of allocation fitness coefficient deviation rates to obtain the minimum value data in the set of allocation fitness coefficient deviation rates; Mark the UAV corresponding to the minimum value data as the optimal UAV.

[0008] Optionally, in the refined patrol scheduling method based on multi-source heterogeneous UAVs of the present application, obtaining the task requirement data and environmental condition data of the target task, and processing through a preset partition coverage algorithm to obtain the optimal path of the target task, including: Obtain the task requirement data of the target task, including coverage range data of the inspection area, detection point distribution data, inspection accuracy requirement data, and inspection time requirement data; Obtain the environmental condition data of the inspection area, including meteorological condition data, geographical environment data, and electromagnetic environment data; According to the task requirement data and the environmental condition data, and combining the performance data of the optimal UAV, process through a preset partition coverage algorithm to obtain the optimal path of the target task.

[0009] Optionally, in the fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles (UAVs) described in this application, obtaining a simulated mission scenario, and respectively conducting simulation experiments according to the adapted fine patrol scheduling scheme and other scheduling schemes, and recording corresponding performance index data, including: Obtaining a simulated mission scenario of the inspection area, and respectively conducting experiments on simulating the execution of the target mission according to the adapted fine patrol scheduling scheme and other scheduling schemes; The other scheduling schemes include a random scheduling scheme and a fixed order scheduling scheme; Recording corresponding performance index data according to the experiments, including inspection coverage rate data, target detection accuracy rate data, and energy consumption rate data.

[0010] Optionally, in the fine patrol scheduling method based on multi-source heterogeneous UAVs described in this application, performing a quantitative evaluation process according to the performance index data, obtaining a corresponding scheduling effectiveness index, and judging the reliability of the adapted fine patrol scheduling scheme and taking corresponding optimization measures, including: Processing the inspection coverage rate data, target detection accuracy rate data, and energy consumption rate data through a preset quantitative evaluation model to obtain a corresponding scheduling effectiveness index; Comparing the scheduling effectiveness index corresponding to the adapted fine patrol scheduling scheme with the scheduling effectiveness indexes corresponding to the other scheduling schemes respectively to obtain corresponding comparison results; Judging the reliability of the adapted fine patrol scheduling scheme according to the comparison results; If the scheduling effectiveness index corresponding to the adapted fine patrol scheduling scheme is greater than the scheduling effectiveness indexes corresponding to all the other scheduling schemes, the reliability of the adapted fine patrol scheduling scheme meets the requirements; Otherwise, the reliability of the adapted fine patrol scheduling scheme does not meet the requirements, and corresponding optimization measures need to be taken.

[0011] In a second aspect, this application provides a fine patrol scheduling system based on multi-source heterogeneous UAVs. The system includes: a memory and a processor. The memory includes a program of the fine patrol scheduling method based on multi-source heterogeneous UAVs. When the program of the fine patrol scheduling method based on multi-source heterogeneous UAVs is executed by the processor, the following steps are implemented: Obtaining performance data of multiple UAVs within a preset area, and at the same time obtaining task priority data of a target mission, and processing through a preset UAV task allocation algorithm to obtain corresponding multiple allocation fitness coefficients; Comparing the allocation fitness coefficients with a preset allocation fitness coefficient to obtain an optimal UAV; Obtain the task requirement data of the target task, and process it through a preset partition coverage algorithm to obtain the optimal path of the target task; The optimal unmanned aerial vehicle executes the target task according to the optimal path, realizing the adaptive precise patrol scheduling scheme of the unmanned aerial vehicles within the preset area; Obtain a simulated task scenario, and conduct simulation experiments respectively according to the adaptive precise patrol scheduling scheme and other scheduling schemes, and record the corresponding performance index data; Conduct quantitative evaluation processing according to the performance index data, obtain the corresponding scheduling effectiveness index, and judge the reliability of the adaptive precise patrol scheduling scheme and take corresponding optimization measures.

[0012] Optionally, in the precise patrol scheduling system based on multi-source heterogeneous unmanned aerial vehicles of the present application, obtaining the performance data of multiple unmanned aerial vehicles within a preset area, simultaneously obtaining the task priority data of the target task, and processing through a preset unmanned aerial vehicle task allocation algorithm to obtain corresponding multiple allocation fitness coefficients, including: Obtain the performance data of multiple unmanned aerial vehicles within a preset area, including flight speed data, endurance time data, payload capacity data, and sensor accuracy data; Obtain the task priority data of the target task, including task importance data, task urgency data, and task timeliness data; According to the flight speed data, endurance time data, payload capacity data, and sensor accuracy data, and combining the task importance data, task urgency data, and task timeliness data, process through a preset unmanned aerial vehicle task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each unmanned aerial vehicle.

[0013] Optionally, in the precise patrol scheduling system based on multi-source heterogeneous unmanned aerial vehicles of the present application, comparing the allocation fitness coefficient with a preset allocation fitness coefficient and obtaining the optimal unmanned aerial vehicle, including: Compare the allocation fitness coefficient with a preset allocation fitness coefficient to obtain a corresponding set of allocation fitness coefficient deviation rates; Conduct comparison and screening processing according to the set of allocation fitness coefficient deviation rates to obtain the minimum value data in the set of allocation fitness coefficient deviation rates; Mark the unmanned aerial vehicle corresponding to the minimum value data as the optimal unmanned aerial vehicle.

[0014] In a third aspect, the present application also provides a computer-readable storage medium, in which a program for the precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles is stored. When the program for the precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles is executed by a processor, the steps of the precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles as described in any one of the above are realized.

[0015] As can be seen from the above, the refined patrol scheduling method, system, and medium based on multi-source heterogeneous unmanned aerial vehicles provided by this application obtain the performance data of multiple unmanned aerial vehicles within a preset area, and at the same time obtain the task priority data of the target task, and process it through a preset unmanned aerial vehicle task allocation algorithm to obtain corresponding multiple allocation fitness coefficients. Compare the allocation fitness coefficients with the preset allocation fitness coefficients, and obtain the optimal unmanned aerial vehicle. Obtain the task requirement data of the target task, and process it through a preset partition coverage algorithm to obtain the optimal path of the target task. The optimal unmanned aerial vehicle executes the target task according to the optimal path, realizes the adaptive refined patrol scheduling scheme of the unmanned aerial vehicles within the preset area, obtains the simulated task scenario, and conducts simulation experiments according to the adaptive refined patrol scheduling scheme and other scheduling schemes respectively, and records the corresponding performance index data. Perform quantitative evaluation processing on the performance index data to obtain the corresponding scheduling effectiveness index, and judge the reliability of the adaptive refined patrol scheduling scheme and take corresponding optimization measures, so as to realize the technology of refined patrol scheduling based on multi-source heterogeneous unmanned aerial vehicles.

[0016] Other features and advantages of this application will be described in the subsequent specification, and, in part, will become obvious from the specification, or can be understood by implementing the embodiments of this application. The objectives and other advantages of this application can be realized and obtained through the structures specifically pointed out in the written specification and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required to be used in the embodiments of this application. It should be understood that the following drawings only show some embodiments of this application, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles provided by the embodiments of this application; Figure 2 It is a flowchart of obtaining corresponding multiple allocation fitness coefficients of the refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles provided by the embodiments of this application; Figure 3 It is a flowchart of obtaining the optimal unmanned aerial vehicle of the refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles provided by the embodiments of this application; Figure 4 It is a flowchart of obtaining the optimal path of the target task of the refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles provided by the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1 which is a flowchart of a precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles in some embodiments of the present application. The precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles is used in terminal devices, such as computers, mobile phone terminals, etc. The precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles includes the following steps: S11. Obtain the performance data of multiple unmanned aerial vehicles within a preset area, and at the same time obtain the task priority data of the target task, and process them through a preset unmanned aerial vehicle task allocation algorithm to obtain corresponding multiple allocation fitness coefficients; S12. Compare the allocation fitness coefficients with the preset allocation fitness coefficients, and obtain the optimal unmanned aerial vehicle; S13. Obtain the task requirement data of the target task, and process it through a preset partition coverage algorithm to obtain the optimal path of the target task; S14. The optimal unmanned aerial vehicle executes the target task according to the optimal path to implement the adaptive precise patrol scheduling scheme of the unmanned aerial vehicles within the preset area; S15. Obtain a simulated task scenario, and conduct simulation experiments according to the adaptive precise patrol scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data; S16. Perform quantitative evaluation processing according to the performance index data to obtain the corresponding scheduling effectiveness index, and judge the reliability of the adaptive precise patrol scheduling scheme and take corresponding optimization measures.

[0022] It should be noted that with the rapid development of UAV technology, its application in the inspection field is becoming more and more extensive. Multi-source heterogeneous UAV systems can better meet the needs of complex inspection tasks because different types of UAVs have different advantages, such as endurance, payload capacity, flight speed, etc. However, existing UAV scheduling methods are difficult to effectively coordinate multi-source heterogeneous UAVs, resulting in problems such as low inspection efficiency and unreasonable task allocation. In addition, multi-source heterogeneous UAVs face many challenges in inspection tasks in complex environments, such as changes in task requirements caused by environmental changes and UAV malfunctions. Traditional scheduling methods lack the ability to adaptively adjust to these dynamic factors and cannot ensure the efficient and stable execution of inspection tasks. Therefore, a reliable and efficient precise inspection scheduling method for UAVs is needed. In this embodiment, first, the performance data of multiple UAVs in a preset area is obtained, and at the same time, the task priority data of the target task is obtained, and through a preset UAV task allocation algorithm for processing, a corresponding plurality of allocation fitness coefficients are obtained. The allocation fitness coefficients are compared with the preset allocation fitness coefficients, and the optimal UAV is obtained. The task requirement data of the target task is obtained, and through a preset partition coverage algorithm for processing, the optimal path of the target task is obtained. The optimal UAV executes the target task according to the optimal path, realizing the adaptive precise inspection scheduling scheme of UAVs in the preset area. A simulated task scenario is obtained, and simulation experiments are respectively carried out according to the adaptive precise inspection scheduling scheme and other scheduling schemes, and the corresponding performance index data is recorded. Quantitative evaluation processing is carried out according to the performance index data, the corresponding scheduling effectiveness index is obtained, and the reliability of the adaptive precise inspection scheduling scheme is judged and corresponding optimization measures are taken, so as to realize the technology of precise inspection scheduling based on multi-source heterogeneous UAVs.

[0023] Please refer to Figure 2 , Figure 2 FIG. is a flowchart of obtaining a corresponding plurality of allocation fitness coefficients of the precise inspection scheduling method based on multi-source heterogeneous UAVs in some embodiments of the present application. According to an embodiment of the present invention, the obtaining the performance data of multiple UAVs in a preset area, and at the same time obtaining the task priority data of the target task, and processing through a preset UAV task allocation algorithm to obtain a corresponding plurality of allocation fitness coefficients includes: S21. Obtain the performance data of multiple UAVs in a preset area, including flight speed data, endurance time data, payload capacity data, and sensor accuracy data; S22. Obtain the task priority data of the target task, including task importance data, task urgency data, and task timeliness data; S23. Process the flight speed data, endurance data, payload capacity data, and sensor accuracy data, and combine them with the task importance data, task urgency data, and task timeliness data through a preset UAV task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each UAV.

[0024] It should be noted that before receiving each target task and allocating the task, it is necessary to obtain the UAV most suitable for the target task through the UAV task allocation algorithm. For this purpose, it is necessary to first obtain the performance data of all UAVs in the area, including flight speed, endurance, payload capacity, and sensor accuracy data. Then, combine the above performance data of each UAV with the task priority data of the target task, including task importance, task urgency, and task timeliness data, and process them through a preset UAV task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each UAV. Among them, the preset UAV task allocation algorithm includes: performing data preprocessing on the UAV performance data and task priority data; for the target task, clarifying the UAV performance indicators that match it; selecting a suitable task allocation algorithm according to different scenarios; and calculating the allocation fitness coefficients for each UAV to execute the target task based on the matching degree indicators between the task and the UAV and combining the task priority data.

[0025] Please refer to Figure 3 , Figure 3 is the flowchart for obtaining the optimal UAV in the fine patrol scheduling method based on multi-source heterogeneous UAVs in some embodiments of the present application. According to the embodiments of the present invention, the comparison of the allocation fitness coefficients with the preset allocation fitness coefficients and obtaining the optimal UAV includes: S31. Compare the allocation fitness coefficients with the preset allocation fitness coefficients to obtain a corresponding set of allocation fitness coefficient deviation rates; S32. Perform comparison and screening processing on the set of allocation fitness coefficient deviation rates to obtain the minimum value data in the set of allocation fitness coefficient deviation rates; S33. Mark the UAV corresponding to the minimum value data as the optimal UAV.

[0026] It should be noted that in order to find the optimal UAV most suitable for executing the target task, it is necessary to process the obtained multiple allocation fitness coefficients. First, determine the ideal preset allocation fitness coefficient, and then compare and process each allocation fitness coefficient with it to obtain a set of allocation fitness coefficient deviation rates. Then, perform screening to find the one closest to the ideal preset allocation fitness coefficient. Then, the UAV corresponding to this allocation fitness coefficient is the optimal UAV most suitable for executing the target task.

[0027] Please refer toFigure 4 , Figure 4 is a flowchart for obtaining the optimal path of the target task in the fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles in some embodiments of the present application. According to the embodiments of the present invention, obtaining the task requirement data and environmental condition data of the target task, and processing them through a preset partition coverage algorithm to obtain the optimal path of the target task includes: S41. Obtain the task requirement data of the target task, including the coverage range data of the inspection area, the detection point distribution data, the inspection accuracy requirement data, and the inspection time requirement data; S42. Obtain the environmental condition data of the inspection area, including meteorological condition data, geographical environment data, and electromagnetic environment data; S43. According to the task requirement data and the environmental condition data, combined with the performance data of the optimal unmanned aerial vehicle, process them through a preset partition coverage algorithm to obtain the optimal path of the target task.

[0028] It should be noted that for the adapted fine patrol scheduling scheme, in addition to screening the unmanned aerial vehicle most suitable for the target task, it is also necessary to obtain the optimal path for executing the target task. For this, it is necessary to obtain the task requirement data of the target task, including the coverage range of the inspection area, the detection point distribution, the inspection accuracy requirement, and the inspection time requirement data, and then combined with the environmental conditions of the unmanned aerial vehicle inspection area, including meteorological conditions, geographical environment, and electromagnetic environment data, process them through a preset partition coverage algorithm to obtain the optimal path of the target task. The preset partition coverage algorithm refers to dividing the entire target area into several smaller sub-areas based on the environmental map and task requirements, and then finding the appropriate path for each sub-area according to the adapted improved algorithm, and then adding partition information so that the unmanned aerial vehicle can traverse each sub-area in a certain order. Then, some optimization methods, such as smoothing the path curve, are used to optimize the initially planned path. Finally, the appropriate paths of each sub-area are integrated into a global path planning scheme to obtain the optimal path.

[0029] According to the embodiments of the present invention, obtaining the simulated task scenario, and respectively conducting simulation experiments according to the adapted fine patrol scheduling scheme and other scheduling schemes, and recording the corresponding performance index data, including: Obtain the simulated task scenario of the inspection area, and respectively conduct experiments on simulating the execution of the target task according to the adapted fine patrol scheduling scheme and other scheduling schemes; The other scheduling schemes include a random scheduling scheme and a fixed order scheduling scheme; Record the corresponding performance index data according to the experiment, including the inspection coverage rate data, the target detection accuracy rate data, and the energy consumption rate data.

[0030] It should be noted that in order to verify the effectiveness of the previously obtained adapted precise patrol scheduling scheme, it can be verified through simulation experiments. First, a simulated task scenario of the patrol area is built using drone simulation software. Then, under this simulated task scenario, different scheduling schemes are respectively run, including the adapted precise patrol scheduling scheme, the random scheduling scheme, and the fixed-order scheduling scheme, and the corresponding performance index data of the experiments for the target tasks executed by these schemes are recorded, including the patrol coverage rate, the target detection accuracy rate, and the energy consumption rate data.

[0031] According to an embodiment of the present invention, the performance index data is subjected to a quantitative evaluation process to obtain a corresponding scheduling effectiveness index, and the reliability of the adapted precise patrol scheduling scheme is judged and corresponding optimization measures are taken, including: The corresponding scheduling effectiveness index is obtained by processing the patrol coverage rate data, the target detection accuracy rate data, and the energy consumption rate data through a preset quantitative evaluation model; The corresponding scheduling effectiveness index of the adapted precise patrol scheduling scheme is compared with the corresponding scheduling effectiveness indices of the other scheduling schemes respectively to obtain a corresponding comparison result; The reliability of the adapted precise patrol scheduling scheme is judged according to the comparison result; If the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme is greater than the scheduling effectiveness indices corresponding to all the other scheduling schemes, then the reliability of the adapted precise patrol scheduling scheme meets the requirements; Otherwise, the reliability of the adapted precise patrol scheduling scheme does not meet the requirements, and corresponding optimization measures need to be taken.

[0032] It should be noted that by comparing with the effectiveness of other scheduling schemes, the reliability of the adapted precise patrol scheduling scheme can be quantitatively evaluated. First, the corresponding scheduling effectiveness indices of each scheduling scheme are obtained by processing the patrol coverage rate data, the target detection accuracy rate data, and the energy consumption rate data through a preset quantitative evaluation model. Among them, the quantitative evaluation model belongs to a neural network model, which is trained by a large amount of historical patrol coverage rate data, target detection accuracy rate data, and energy consumption rate data to obtain a trained quantitative evaluation model. Then, the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme is compared with the corresponding scheduling effectiveness indices of the other scheduling schemes respectively. If the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme is greater than the scheduling effectiveness indices corresponding to all the other scheduling schemes, it indicates that the reliability of the adapted precise patrol scheduling scheme meets the requirements; otherwise, it does not meet the requirements and corresponding optimization measures need to be taken.

[0033] According to an embodiment of the present invention, it further includes: Obtain multiple scheduling effectiveness indices corresponding to historical inspection tasks based on the adapted refined patrol scheduling scheme within the preset area, and process them to obtain the average scheduling effectiveness index; Perform a correction process on the scheduling effectiveness index according to the average scheduling effectiveness index through a preset scheduling effectiveness correction model to obtain a scheduling effectiveness correction index; Compare the scheduling effectiveness correction index with the scheduling effectiveness indices corresponding to other scheduling schemes respectively to obtain corresponding second comparison results; Further judge the reliability of the adapted refined patrol scheduling scheme according to the second comparison result and take corresponding optimization measures.

[0034] It should be noted that, in order to more accurately judge the reliability of the adapted refined patrol scheduling scheme, the scheduling effectiveness index can be corrected according to historical index data to make the index more reliable. First, perform an averaging process on multiple scheduling effectiveness indices corresponding to the historical inspection tasks of the adapted refined patrol scheduling scheme to obtain the average scheduling effectiveness index, and then perform a correction process on the scheduling effectiveness index through a preset scheduling effectiveness correction model to obtain the scheduling effectiveness correction index. Among them, the scheduling effectiveness correction model belongs to a neural network model, which is trained on a large amount of historical scheduling effectiveness index data and average scheduling effectiveness index data to initialize the scheduling effectiveness correction model to obtain a trained scheduling effectiveness correction model, and then compare and process the scheduling effectiveness correction index with the scheduling effectiveness indices corresponding to other scheduling schemes respectively, and judge the reliability of the adapted refined patrol scheduling scheme according to the comparison result and take corresponding optimization measures.

[0035] In a second aspect, the present invention also discloses a refined patrol scheduling system based on multi-source heterogeneous unmanned aerial vehicles, including a memory and a processor. The memory includes a refined patrol scheduling method program based on multi-source heterogeneous unmanned aerial vehicles. When the refined patrol scheduling method program based on multi-source heterogeneous unmanned aerial vehicles is executed by the processor, the following steps are implemented: Obtain the performance data of multiple unmanned aerial vehicles within a preset area, and at the same time obtain the task priority data of the target task, and process them through a preset unmanned aerial vehicle task allocation algorithm to obtain corresponding multiple allocation fitness coefficients; Compare the allocation fitness coefficients with the preset allocation fitness coefficients and obtain the optimal unmanned aerial vehicle; Obtain the task requirement data of the target task, and process it through a preset partition coverage algorithm to obtain the optimal path of the target task; The optimal unmanned aerial vehicle executes the target task according to the optimal path to implement the adapted refined patrol scheduling scheme of the unmanned aerial vehicles within the preset area; Obtain a simulated task scenario, and conduct simulation experiments according to the adapted precise patrol scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data; Perform quantitative evaluation processing according to the performance index data, obtain the corresponding scheduling effectiveness index, and judge the reliability of the adapted precise patrol scheduling scheme and take corresponding optimization measures.

[0036] It should be noted that with the rapid development of UAV technology, its application in the inspection field is becoming more and more extensive. Multi-source heterogeneous UAV systems can better meet the needs of complex inspection tasks because different types of UAVs have different advantages, such as endurance, payload capacity, flight speed, etc. However, existing UAV scheduling methods are difficult to effectively coordinate multi-source heterogeneous UAVs, resulting in problems such as low inspection efficiency and unreasonable task allocation. In addition, multi-source heterogeneous UAVs face many challenges in inspection tasks in complex environments, such as changes in task requirements caused by environmental changes and UAV malfunctions. Traditional scheduling methods lack the ability to adaptively adjust to these dynamic factors and cannot ensure the efficient and stable execution of inspection tasks. Therefore, a reliable and efficient precise patrol scheduling method for UAVs is needed. In this embodiment, first, obtain the performance data of multiple UAVs in a preset area, and at the same time obtain the task priority data of the target task, and process them through a preset UAV task allocation algorithm to obtain corresponding multiple allocation fitness coefficients. Compare the allocation fitness coefficients with the preset allocation fitness coefficients to obtain the optimal UAV. Obtain the task requirement data of the target task and process it through a preset partition coverage algorithm to obtain the optimal path of the target task. The optimal UAV executes the target task according to the optimal path to implement the adapted precise patrol scheduling scheme of the UAVs in the preset area. Obtain a simulated task scenario, and conduct simulation experiments according to the adapted precise patrol scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data. Perform quantitative evaluation processing according to the performance index data to obtain the corresponding scheduling effectiveness index, and judge the reliability of the adapted precise patrol scheduling scheme and take corresponding optimization measures, so as to realize the technology of precise patrol scheduling based on multi-source heterogeneous UAVs.

[0037] According to an embodiment of the present invention, the obtaining the performance data of multiple UAVs in a preset area, and at the same time obtaining the task priority data of the target task, and processing them through a preset UAV task allocation algorithm to obtain corresponding multiple allocation fitness coefficients includes: Obtain the performance data of multiple UAVs in a preset area, including flight speed data, endurance time data, payload capacity data, and sensor accuracy data; Obtain the task priority data of the target task, including task importance data, task urgency data, and task timeliness data; Based on the flight speed data, endurance time data, payload capacity data, and sensor accuracy data, combined with the task importance data, task urgency data, and task timeliness data, it is processed through a preset UAV task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each UAV.

[0038] It should be noted that before receiving each target task and allocating the task, it is necessary to obtain the UAV most suitable for the target task through the UAV task allocation algorithm. For this, it is necessary to first obtain the performance data of all UAVs in the area, including flight speed, endurance time, payload capacity, and sensor accuracy data, and then combine the above performance data of each UAV with the task priority data of the target task, including task importance, task urgency, and task timeliness data, and process it through a preset UAV task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each UAV. Among them, the preset UAV task allocation algorithm includes: performing data preprocessing on the UAV performance data and task priority data; for the target task, clarifying the UAV performance indicators matching it; selecting a suitable task allocation algorithm according to different scenarios; and calculating the allocation fitness coefficient of each UAV for executing the target task based on the matching degree index between the task and the UAV and combining the task priority data.

[0039] According to an embodiment of the present invention, the comparing the allocation fitness coefficient with a preset allocation fitness coefficient and obtaining the optimal UAV includes: Comparing the allocation fitness coefficient with the preset allocation fitness coefficient to obtain a corresponding set of allocation fitness coefficient deviation rates; Performing comparison and screening processing on the set of allocation fitness coefficient deviation rates to obtain the minimum value data in the set of allocation fitness coefficient deviation rates; Marking the UAV corresponding to the minimum value data as the optimal UAV.

[0040] It should be noted that to find the optimal UAV most suitable for executing the target task, it is necessary to process the obtained multiple allocation fitness coefficients. First, determine the ideal preset allocation fitness coefficient, then compare and process each allocation fitness coefficient with it to obtain a set of allocation fitness coefficient deviation rates, and then perform screening to find the one closest to the ideal preset allocation fitness coefficient. Then, the UAV corresponding to this allocation fitness coefficient is the optimal UAV most suitable for executing the target task.

[0041] According to an embodiment of the present invention, the obtaining the task requirement data and environmental condition data of the target task and processing it through a preset partition coverage algorithm to obtain the optimal path of the target task includes: Obtain the task requirement data of the target task, including the coverage range data of the inspection area, the detection point distribution data, the inspection accuracy requirement data, and the inspection time requirement data; Obtain the environmental condition data of the inspection area, including meteorological condition data, geographical environment data, and electromagnetic environment data; According to the task requirement data and the environmental condition data, combined with the performance data of the optimal UAV, process through a preset partition coverage algorithm to obtain the optimal path of the target task.

[0042] It should be noted that for the adapted precise inspection scheduling scheme, in addition to screening the UAV most suitable for the target task, it is also necessary to obtain the optimal path for executing the target task. For this, it is necessary to obtain the task requirement data of the target task, including the coverage range of the inspection area, the detection point distribution, the inspection accuracy requirement, and the inspection time requirement data, and then combine the environmental conditions of the UAV inspection area, including meteorological conditions, geographical environment, and electromagnetic environment data, and process through a preset partition coverage algorithm to obtain the optimal path of the target task. The preset partition coverage algorithm refers to dividing the entire target area into several smaller sub-areas based on the environmental map and task requirements, and then finding the appropriate path for each sub-area according to the adapted improved algorithm, and then adding partition information so that the UAV can traverse each sub-area in a certain order. Then, use some optimization methods, such as smoothing the path curve, to optimize the initially planned path. Finally, integrate the appropriate paths of each sub-area into a global path planning scheme to obtain the optimal path.

[0043] According to the embodiments of the present invention, obtain the simulated task scenario, and conduct simulation experiments according to the adapted precise inspection scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data, including: Obtain the simulated task scenario of the inspection area, and conduct experiments on simulating the execution of the target task according to the adapted precise inspection scheduling scheme and other scheduling schemes respectively; The other scheduling schemes include a random scheduling scheme and a fixed order scheduling scheme; Record the corresponding performance index data according to the experiment, including inspection coverage rate data, target detection accuracy rate data, and energy consumption rate data.

[0044] It should be noted that in order to verify the effectiveness of the previously obtained adapted precise patrol scheduling scheme, it can be verified through simulation experiments. First, a simulated task scenario of the patrol area is built using drone simulation software. Then, under this simulated task scenario, different scheduling schemes are respectively run, including the adapted precise patrol scheduling scheme, the random scheduling scheme, and the fixed-order scheduling scheme, and the corresponding performance index data of the experiments of the target tasks executed by these schemes are recorded, including the patrol coverage rate, the target detection accuracy rate, and the energy consumption rate data.

[0045] According to an embodiment of the present invention, performing a quantitative evaluation process based on the performance index data to obtain a corresponding scheduling effectiveness index, and judging the reliability of the adapted precise patrol scheduling scheme and taking corresponding optimization measures, including: Processing the patrol coverage rate data, the target detection accuracy rate data, and the energy consumption rate data through a preset quantitative evaluation model to obtain a corresponding scheduling effectiveness index; Comparing the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme with the scheduling effectiveness indices corresponding to the other scheduling schemes respectively to obtain corresponding comparison results; Judging the reliability of the adapted precise patrol scheduling scheme according to the comparison results; If the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme is greater than the scheduling effectiveness indices corresponding to all the other scheduling schemes, then the reliability of the adapted precise patrol scheduling scheme meets the requirements; Otherwise, the reliability of the adapted precise patrol scheduling scheme does not meet the requirements, and corresponding optimization measures need to be taken.

[0046] It should be noted that by comparing with the effectiveness of other scheduling schemes, the reliability of the adapted precise patrol scheduling scheme can be quantitatively evaluated. First, the patrol coverage rate data, the target detection accuracy rate data, and the energy consumption rate data are processed through a preset quantitative evaluation model to obtain the scheduling effectiveness indices corresponding to each scheduling scheme. Among them, the quantitative evaluation model belongs to a neural network model, which is trained based on a large amount of historical patrol coverage rate data, target detection accuracy rate data, and energy consumption rate data to obtain a trained quantitative evaluation model. Then, the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme is compared with the scheduling effectiveness indices corresponding to the other scheduling schemes respectively. If the scheduling effectiveness index corresponding to the adapted precise patrol scheduling scheme is greater than the scheduling effectiveness indices corresponding to all the other scheduling schemes, it indicates that the reliability of the adapted precise patrol scheduling scheme meets the requirements; otherwise, it does not meet the requirements and corresponding optimization measures need to be taken.

[0047] According to an embodiment of the present invention, it further includes: Obtain multiple scheduling effectiveness indices corresponding to the historical inspection tasks based on the adapted precise patrol scheduling scheme within the preset area, and process them to obtain the average scheduling effectiveness index; Perform correction processing on the scheduling effectiveness index through a preset scheduling effectiveness correction model according to the average scheduling effectiveness index to obtain a scheduling effectiveness correction index; Compare the scheduling effectiveness correction index with the scheduling effectiveness indices corresponding to other scheduling schemes respectively to obtain corresponding second comparison results; Further judge the reliability of the adapted precise patrol scheduling scheme according to the second comparison result and take corresponding optimization measures.

[0048] It should be noted that in order to more accurately judge the reliability of the adapted precise patrol scheduling scheme, the scheduling effectiveness index can be corrected according to historical index data to make the index more reliable. First, perform an averaging process on multiple scheduling effectiveness indices corresponding to the historical inspection tasks of the adapted precise patrol scheduling scheme to obtain the average scheduling effectiveness index, and then perform correction processing on the scheduling effectiveness index through a preset scheduling effectiveness correction model to obtain a scheduling effectiveness correction index. Among them, the scheduling effectiveness correction model belongs to a neural network model, which is trained on a large amount of historical scheduling effectiveness index data and average scheduling effectiveness index data to obtain a trained scheduling effectiveness correction model, and then compare and process the scheduling effectiveness correction index with the scheduling effectiveness indices corresponding to other scheduling schemes respectively. Judge the reliability of the adapted precise patrol scheduling scheme according to the comparison result and take corresponding optimization measures.

[0049] The third aspect of the present invention provides a readable storage medium, in which a program for the precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles is stored. When the program for the precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles is executed by a processor, the steps of the precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles as described in any one of the above are implemented.

[0050] The fine patrol scheduling method, system and medium based on multi-source heterogeneous unmanned aerial vehicles (UAVs) disclosed in the present invention obtain the performance data of multiple UAVs within a preset area, and at the same time obtain the task priority data of the target task, and process them through a preset UAV task allocation algorithm to obtain corresponding multiple allocation fitness coefficients. By comparing the allocation fitness coefficients with the preset allocation fitness coefficients, the optimal UAV is obtained. The task requirement data of the target task is obtained and processed through a preset partition coverage algorithm to obtain the optimal path of the target task. The optimal UAV executes the target task according to the optimal path, realizing the adaptive fine patrol scheduling scheme of the UAVs within the preset area. A simulated task scenario is obtained, and simulation experiments are respectively carried out according to the adaptive fine patrol scheduling scheme and other scheduling schemes, and the corresponding performance index data is recorded. Quantitative evaluation processing is carried out according to the performance index data to obtain the corresponding scheduling effectiveness index, and the reliability of the adaptive fine patrol scheduling scheme is judged and corresponding optimization measures are taken, so as to realize the technology of fine patrol scheduling based on multi-source heterogeneous UAVs.

[0051] In 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 illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, 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. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0052] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0053] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit; the above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0054] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0055] Alternatively, if the above integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

Claims

1. A precise patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles, characterized in that, It includes the following steps: Obtain the performance data of multiple drones within a preset area, and at the same time obtain the task priority data of the target task, and process them through a preset drone task allocation algorithm to obtain corresponding multiple allocation fitness coefficients; Compare the allocation fitness coefficients with the preset allocation fitness coefficients, and obtain the optimal drone; Obtain the task requirement data of the target task, and process it through a preset partition coverage algorithm to obtain the optimal path of the target task; The optimal drone executes the target task according to the optimal path, realizing the adaptive fine patrol scheduling scheme of the drones within the preset area; Obtain a simulated task scenario, and conduct simulation experiments according to the adaptive fine patrol scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data; Conduct quantitative evaluation processing according to the performance index data, obtain the corresponding scheduling effectiveness index, and judge the reliability of the adaptive fine patrol scheduling scheme and take corresponding optimization measures.

2. The refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles according to claim 1, wherein, The obtaining of the performance data of multiple drones within a preset area, and at the same time obtaining the task priority data of the target task, and processing them through a preset drone task allocation algorithm to obtain corresponding multiple allocation fitness coefficients includes: Obtain the performance data of multiple drones within a preset area, including flight speed data, endurance time data, payload capacity data, and sensor accuracy data; Obtain the task priority data of the target task, including task importance data, task urgency data, and task timeliness data; According to the flight speed data, endurance time data, payload capacity data, and sensor accuracy data, and combining the task importance data, task urgency data, and task timeliness data, process them through a preset drone task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each drone.

3. The refined patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles according to claim 2, wherein The comparing the allocation fitness coefficients with the preset allocation fitness coefficients, and obtaining the optimal drone includes: Compare the allocation fitness coefficients with the preset allocation fitness coefficients to obtain a corresponding set of allocation fitness coefficient deviation rates; Conduct comparison and screening processing according to the set of allocation fitness coefficient deviation rates to obtain the minimum value data in the set of allocation fitness coefficient deviation rates; Mark the drone corresponding to the minimum value data as the optimal drone.

4. The fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles according to claim 3, wherein The obtaining of the task requirement data and environmental condition data of the target task, and processing them through a preset partition coverage algorithm to obtain the optimal path of the target task includes: Obtain the task requirement data of the target task, including the coverage range data of the inspection area, the distribution data of detection points, the inspection accuracy requirement data, and the inspection time requirement data; Obtain the environmental condition data of the inspection area, including meteorological condition data, geographical environment data, and electromagnetic environment data; According to the task requirement data and the environmental condition data, and combining the performance data of the optimal drone, process them through a preset partition coverage algorithm to obtain the optimal path of the target task.

5. The fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles according to claim 4, wherein, Obtain the simulated task scenario, and conduct simulation experiments according to the adapted fine patrol scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data, including: Obtain the simulated task scenario of the inspection area, and conduct experiments on simulating the execution of the target task according to the adapted fine patrol scheduling scheme and other scheduling schemes respectively; The other scheduling schemes include a random scheduling scheme and a fixed order scheduling scheme; Record the corresponding performance index data according to the experiments, including inspection coverage rate data, target detection accuracy data, and energy consumption rate data.

6. The fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles according to claim 5, wherein Perform a quantitative evaluation process according to the performance index data, obtain the corresponding scheduling effectiveness index, and judge the reliability of the adapted fine patrol scheduling scheme and take corresponding optimization measures, including: Process the inspection coverage rate data, target detection accuracy data, and energy consumption rate data through a preset quantitative evaluation model to obtain the corresponding scheduling effectiveness index; Compare the scheduling effectiveness index corresponding to the adapted fine patrol scheduling scheme with the scheduling effectiveness index corresponding to the other scheduling schemes respectively to obtain the corresponding comparison result; Judge the reliability of the adapted fine patrol scheduling scheme according to the comparison result; If the scheduling effectiveness index corresponding to the adapted fine patrol scheduling scheme is greater than the scheduling effectiveness indices corresponding to all the other scheduling schemes, the reliability of the adapted fine patrol scheduling scheme meets the requirements; Otherwise, the reliability of the adapted fine patrol scheduling scheme does not meet the requirements, and corresponding optimization measures need to be taken.

7. Precision patrol scheduling system based on multi-source heterogeneous unmanned aerial vehicles, characterized in that, The system includes: a memory and a processor. The memory includes a program of the fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles. When the program of the fine patrol scheduling method based on multi-source heterogeneous unmanned aerial vehicles is executed by the processor, the following steps are implemented: Obtain the performance data of multiple unmanned aerial vehicles in a preset area, and at the same time obtain the task priority data of the target task, and process them through a preset unmanned aerial vehicle task allocation algorithm to obtain corresponding multiple allocation fitness coefficients; Compare the allocation fitness coefficients with the preset allocation fitness coefficients to obtain the optimal unmanned aerial vehicle; Obtain the task requirement data of the target task, and process it through a preset partition coverage algorithm to obtain the optimal path of the target task; The optimal unmanned aerial vehicle executes the target task according to the optimal path to implement the adapted fine patrol scheduling scheme of the unmanned aerial vehicles in the preset area; Obtain the simulated task scenario, and conduct simulation experiments according to the adapted fine patrol scheduling scheme and other scheduling schemes respectively, and record the corresponding performance index data; Perform a quantitative evaluation process according to the performance index data, obtain the corresponding scheduling effectiveness index, and judge the reliability of the adapted fine patrol scheduling scheme and take corresponding optimization measures.

8. The refined patrol scheduling system based on multi-source heterogeneous unmanned aerial vehicles according to claim 7, characterized in that The obtaining of the performance data of multiple unmanned aerial vehicles in a preset area, and at the same time obtaining the task priority data of the target task, and processing them through a preset unmanned aerial vehicle task allocation algorithm to obtain corresponding multiple allocation fitness coefficients, includes: Obtain the performance data of multiple drones within a preset area, including flight speed data, endurance time data, payload capacity data, and sensor accuracy data; Obtain the task priority data of the target task, including task importance data, task urgency data, and task timeliness data; According to the flight speed data, endurance time data, payload capacity data, and sensor accuracy data, and in combination with the task importance data, task urgency data, and task timeliness data, process through a preset drone task allocation algorithm to obtain multiple allocation fitness coefficients corresponding to each drone.

9. The refined patrol scheduling system based on multi-source heterogeneous unmanned aerial vehicles according to claim 8, wherein The comparison of the allocation fitness coefficient with the preset allocation fitness coefficient and obtaining the optimal drone includes: Compare the allocation fitness coefficient with the preset allocation fitness coefficient to obtain a corresponding set of allocation fitness coefficient deviation rates; Perform comparison and screening processing according to the set of allocation fitness coefficient deviation rates to obtain the minimum value data in the set of allocation fitness coefficient deviation rates; Mark the drone corresponding to the minimum value data as the optimal drone.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a fine patrol scheduling method program for multi-source heterogeneous drones. When the fine patrol scheduling method program for multi-source heterogeneous drones is executed by a processor, the steps of the fine patrol scheduling method for multi-source heterogeneous drones as described in any one of claims 1 to 6 are implemented.

Images