An Unmanned Aerial Vehicle Inspection Method and System Based on an Unmanned Aerial Vehicle Nest

Abstract

An embodiment of this specification provides a method and system for unmanned aerial vehicle (UAV) inspection based on a UAV nest. The method includes: A method for UAV inspection based on a UAV nest, the method including: obtaining at least one planned inspection path of at least one inspection UAV in the current area, and based on the at least one planned inspection path, determining a corresponding first nest and planned charging data for each of the at least one inspection UAVs; taking one of the at least one inspection UAVs in the current area as the current inspection UAV, and obtaining the corresponding first nest of the planned inspection path of the current inspection UAV and the duration of the first nest; determining a corresponding modified time interval based on the current inspection UAV; and in response to the duration of the first nest of the current inspection UAV exceeding the modified time interval, actively adjusting the first nest of the current inspection UAV.

Description

Technical Field

[0001] This specification relates to the field of patrol inspections, and particularly to a drone patrol inspection method and system based on a drone nest. Background Art

[0002] In the prior art, drone technology has been widely used in patrol inspection, surveillance, and reconnaissance tasks due to its high efficiency, flexibility, and cost-effectiveness. However, in existing drone patrol inspection systems, the limited endurance of patrol drones restricts their ability to perform tasks for a long time. The traditional charger nest layout and management methods fail to effectively solve the balance problem between charging requirements and task execution, resulting in problems such as low patrol inspection efficiency and insufficient charging management in drone patrol inspection systems. Especially in complex environments, more intelligent and adaptive solutions are needed to optimize task execution efficiency and energy utilization rate.

[0003] Therefore, it is desired to provide a drone patrol inspection method and system based on a drone nest. By dynamically adjusting the selection of drone nests, on the one hand, overuse of a single nest can be reduced, thereby extending its service life and reducing maintenance requirements. On the other hand, the waiting time for drone charging can be reduced, significantly improving the efficiency and stability of the drone patrol inspection system. Summary of the Invention

[0004] A drone patrol inspection method and system based on a drone nest provided in this specification can, by dynamically adjusting the paths and nest selections of drones, on the one hand, reduce overuse of a single nest, thereby extending its service life and reducing maintenance requirements. On the other hand, the waiting time for drone charging can be reduced, significantly improving the efficiency and stability of the drone patrol inspection system.

[0005] One embodiment of this specification provides a drone patrol inspection method based on a drone nest. The method includes: obtaining at least one planned patrol path of at least one patrol drone in a current area, and based on the at least one planned patrol path, determining a corresponding first nest and planned charging data for each of the at least one patrol drones; taking one of the at least one patrol drones in the current area as the current patrol drone, and obtaining the first nest corresponding to the planned patrol path of the current patrol drone and the duration of the first nest; determining a corresponding modification time interval based on the current patrol drone; and actively adjusting the first nest of the current patrol drone in response to the duration of the first nest of the current patrol drone exceeding the modification time interval.

[0006] One embodiment of this specification provides a drone inspection system based on a drone nest. The system includes: a first acquisition module, configured to acquire at least one planned inspection path of at least one inspection drone within a current area, and based on the at least one planned inspection path, determine a corresponding first nest and planned charging data for each of the at least one inspection drones; a second acquisition module, configured to use one of the at least one inspection drones within the current area as the current inspection drone, and acquire the corresponding first nest of the planned inspection path of the current inspection drone and the duration of the first nest; a time interval determination module, configured to determine a corresponding modified time interval based on the current inspection drone; and a modification time module, configured to actively adjust the first nest of the current inspection drone in response to the duration of the first nest of the current inspection drone exceeding the modified time interval.

[0007] One embodiment of this specification provides a drone inspection device based on a drone nest. The device includes a processor and a memory; the memory is configured to store instructions, and when the instructions are executed by the processor, the device is caused to implement the drone inspection method based on a drone nest as described in any one of the above.

[0008] One embodiment of this specification provides a computer-readable storage medium, characterized in that the storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer runs the drone inspection method based on a drone nest as described in any one of the above. Description of the Drawings

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0010] Figure 1 is a schematic diagram of an application scenario of a drone inspection system based on a drone nest shown according to some embodiments of this specification;

[0011] Figure 2 is a schematic diagram of modules of a drone inspection system based on a drone nest shown according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flowchart of a drone inspection method based on a drone nest shown according to some embodiments of this specification. Detailed Embodiments

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structures or operations.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0015] As shown in this specification and the claims, unless the context clearly indicates an exceptional situation, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the operations before or after do not necessarily need to be executed precisely in sequence. On the contrary, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0017] Figure 1 is a schematic diagram of the application scenario of the unmanned aerial vehicle (UAV) inspection system based on a UAV nest as shown in some embodiments of this specification. As Figure 1 shown, the scenario 100 involved in the UAV inspection system based on a UAV nest may include a processor 110, an inspection UAV 120, a storage device 130, a network 140, a user terminal 150, and a charging nest 160.

[0018] In some embodiments, the processor 110 can be used to process information and / or data related to the scenario 100. For example, the processor 110 can obtain a network map based on the data. In some embodiments, the processor 110 can be local or remote. For example, the processor 110 can access the information and / or data stored in the storage device 130 and the user terminal 150 via the network 140. Another example is that the processor 110 can be directly connected to the storage device 130 and the user terminal 150 to access the stored information and / or data.

[0019] The inspection UAV 120 may refer to a UAV used for inspection within the current area. There may be at least one inspection UAV 120. The number of inspection UAVs 120 may be multiple. The number of charging hangars 160 may be at least one, which may be distributed within the current area and used to charge the inspection UAV 120.

[0020] The storage device 130 may be used to store data and / or instructions related to UAV inspection based on the UAV hangar. In some embodiments, the storage device 130 may store data obtained / retrieved from the user terminal 150. In some embodiments, the storage device 130 may store data and / or instructions for the processor 110 to execute or use to complete the exemplary methods described in this application. In some embodiments, the storage device 130 may be implemented on a cloud platform.

[0021] In some embodiments, the storage device 130 may be connected to the network 140 to communicate with one or more components of the scenario 100 (e.g., the processor 110, the inspection UAV 120, the user terminal 150, the charging hangar 160). One or more components of the scenario 100 may access the data or instructions stored in the storage device 130 via the network 140. In some embodiments, the storage device 130 may be directly connected to or communicate with one or more components of the scenario 100 (e.g., the processor 110, the inspection UAV 120, the user terminal 150). In some embodiments, the storage device 130 may be a part of the processor 110. In some embodiments, the storage device 130 may be a separate memory. The storage device 140 may store historical data. The storage device 140 may also store machine learning models, preset correspondence relationships, etc.

[0022] The network 140 may facilitate the exchange of information and / or data. In some embodiments, one or more components of the scenario 100 (e.g., the processor 110, the inspection UAV 120, the user terminal 150) may send information and / or data to other components of the scenario 100 via the network 140.

[0023] The user terminal 150 may be a device used by the user and connected to the inspection UAV 120 to view the working status of the inspection UAV 120.

[0024] Figure 2 is a schematic diagram of the modules of a UAV inspection system based on a UAV hangar shown in some embodiments of this specification. As Figure 2 shown, the UAV inspection system 200 based on a UAV hangar may include a first acquisition module 210, a second acquisition module 220, a time interval determination module 230, and a modification time module 240.

[0025] The first acquisition module 210 is configured to acquire at least one planned inspection path of at least one inspection UAV in the current area, and based on the at least one planned inspection path, determine the corresponding first hangar and planned charging data for each of the at least one inspection UAVs.

[0026] The second acquisition module 220 is configured to use one of the at least one inspection UAVs in the current area as the current inspection UAV, and acquire the corresponding first hangar of the planned inspection path of the current inspection UAV and the duration of the first hangar.

[0027] The time interval determination module 230 is configured to determine the corresponding modified time interval based on the current inspection UAV. In some embodiments, the time interval determination module is configured to determine the modified time interval, and further includes: a relationship preset module, configured to determine the difference-interval relationship between the difference between the preset planned waiting time and the waiting time threshold and the modified time interval based on historical data; a current difference determination module, configured to determine the current difference between the planned waiting time and the waiting time threshold of the current inspection UAV; and a current interval determination module, configured to determine the modified time interval corresponding to the current inspection UAV based on the current difference through the difference-interval relationship.

[0028] In some embodiments, the current difference determination module is configured to determine the planned waiting time, and further includes: a deviation degree determination module, configured to acquire the deviation degree of the planned waiting sequence, where the deviation degree of the planned waiting sequence includes the deviation degree of the planned charging data of the waiting UAVs, and the planned waiting sequence includes the waiting UAV numbers waiting for charging and the corresponding planned charging data; an adjusted charging module, configured to re-determine the adjusted charging data of the waiting UAVs in the planned waiting sequence based on the deviation degree; and an adjusted time module, configured to determine the adjusted waiting time based on the adjusted charging data and determine the adjusted modified time interval based on the adjusted waiting time.

[0029] In some embodiments, the deviation determination module is used to determine the deviation of the planned waiting sequence, including: a first historical data determination module, which is used to obtain at least one first historical charging data of each waiting drone at a historical first time for each waiting drone. Each first historical charging data includes the historical start charging time corresponding to the historical charging and the historical planned charging duration. Each set of first historical charging data corresponds to a corresponding first historical inspection path; a second historical data determination module, which is used to compare the similarity between the first historical inspection path of the waiting drone and the inspection path that has been completed this time, and determine the second historical charging data from the first historical charging data; a third historical data determination module, which is used to determine a set of second historical charging data and historical planned charging data corresponding to each historical first time; a drone feature determination module, which is used to determine the charging feature of each waiting drone based on the difference between a set of second historical charging data and historical planned charging data corresponding to each historical first time; a charging deviation module, which is used to obtain the feature data of the first nest and the charging features of at least one waiting drone, and determine the deviation of the planned charging data of the waiting drone in the first nest at the first time through a machine learning model.

[0030] The modification time module 240 is used to actively adjust the first nest of the current inspection drone in response to the duration of the first nest of the current inspection drone exceeding the modification time interval.

[0031] It should be understood that the above modules are only simple examples of the relevant modules mainly involved in this specification, and do not represent the display of all relevant contents of this application. There are still some modules and units not shown in this module diagram, and they will not be exemplified one by one here. And the above modules and units do not exist completely independently, and there may still be cross-involvements.

[0032] Figure 3 is an exemplary flowchart of an unmanned aerial vehicle (UAV) inspection method based on a UAV nest shown in some embodiments of this specification. Process 300 can be executed by a processor. As Figure 3 shown, process 300 may include the following steps:

[0033] Step 310, obtain at least one planned inspection path of at least one inspection UAV in the current area, and based on the at least one planned inspection path, determine the corresponding first nest and planned charging data of each of the at least one inspection UAVs.

[0034] For each of at least one inspection drone, each planned inspection path corresponds to a set of first hangars and planned charging data. The planned charging data of each inspection drone may include the planned start charging time and the planned charging duration. The first hangar of each inspection drone may refer to the charging hangar corresponding to the first planned inspection path. The planned charging duration can at least ensure that the battery level of the inspection drone after charging is the same as the charge level before the start of the planned inspection path. The planned start charging time may be the time after the inspection drone completes the planned inspection path, or the time when the current charging drone in the first hangar finishes charging. For example, when there is an inspection drone A charging in the first hangar A, and at this time the inspection drone B completes the current planned inspection path, then the planned start charging time of the inspection drone B is the time when the inspection drone A finishes charging.

[0035] The current area can be determined by preset area division. For example, according to administrative area division. The current area includes at least one point of interest. The processor can obtain all the points of interest in the current area from the database or real-time data sources. Each point of interest includes point-of-interest attributes, which may include the importance, usage, geographical location, etc. of the point-of-interest facilities. The processor can determine the points of interest with relatively high matching degrees based on the point-of-interest attributes of all the points of interest in the current area and the inspection purpose.

[0036] There are at least one inspection drone in the current area for inspecting the current area to achieve the inspection purpose. In some embodiments, the inspection drones in the current area can be numbered for easy later identification and determination of commands. In some embodiments, the planned inspection paths can be preset by the system. In some embodiments, at least one planned point of interest in the current area is obtained according to the matching degree between the point-of-interest attributes and the inspection purpose of each inspection drone, and based on at least one planned point of interest, the planned inspection paths corresponding to the inspection drones at future time points are determined. The planned inspection paths of all the inspection drones in this area can at least cover the current area to achieve the inspection purpose. In some embodiments, the planned inspection path of each inspection drone can be a historical inspection path. The historical inspection purpose with relatively high similarity can be determined semantically according to the planned inspection purpose at the future time point, and the historical inspection path of the historical drone corresponding to the historical inspection purpose is used as the planned inspection path at the future time point.

[0037] In some embodiments, the inspection paths of some drones may have intersections. For example, the inspection paths of drones A and B can both include point of interest 1.

[0038] In some embodiments, for each inspection drone, the planned inspection path may include the planned points of interest passed during the inspection and the corresponding access times, and the planned inspection path may be a sequence sorted by the access times for the planned points of interest.

[0039] Each inspection drone can correspond to at least one planned inspection path including different starting time points. This is because the battery capacity of each inspection drone is limited, and at least one planned inspection path needs to be determined according to the battery capacity. In the previous planned inspection path, it must reach the first hangar for charging before starting the next planned inspection path.

[0040] Step 320: Select one of the at least one inspection drones in the current area as the current inspection drone, and obtain the first hangar corresponding to the planned inspection path of the current inspection drone and the duration of the first hangar.

[0041] The first hangar can be a charging hangar whose distance from the last planned interest point in the planned inspection path is less than the distance threshold.

[0042] The duration of the first hangar can refer to the duration of the first hangar as the charging hangar after the current inspection drone completes the planned inspection path, which can be determined by the system. Specifically, when the planned inspection path remains unchanged, whenever the current inspection drone executes the planned inspection path, the duration of the first hangar can refer to the duration of the first hangar as the charging hangar. For example, starting from October 1, 2022, inspection drone A executes planned inspection path 1. Among them, the first hangar A serves as the charging hangar after inspection drone A completes planned inspection path 1 starting from October 1, 2022, until October 4, 2022, with a duration of 4 days.

[0043] Step 330: Determine the corresponding modification time interval based on the current inspection drone.

[0044] When the selection of each first hangar completely depends on the last planned interest point included in the planned inspection path, it may lead to an increase in the consistency of the selection of the first hangars of at least one inspection drone calculated by the processor because the positions of the planned interest points finally passed by the planned inspection paths corresponding to multiple inspection drones are similar or the same. For example, inspection drones A, B, and C all complete the planned inspection path around the first time, and the positions of the last planned interest points of inspection drones A, B, and C are all similar. Then, the first hangars corresponding to drones A, B, and C are very likely to be the same charging hangar. When the planned inspection path remains unchanged, the inspection drones that complete the planned inspection path later need to wait for charging. Therefore, when the waiting time for charging at the first time is getting longer and longer, the charging hangar needs to be adjusted.

[0045] The modified time interval can refer to actively adjusting the time interval of the current inspection UAV charging hangar, that is, the time interval between the start time and the end time when the first hangar serves as the charging hangar. For example, starting from January 1, 2024, charging hangar 1 is used as the first hangar for inspection UAV A, and on February 1, 2024, charging hangar 2 is used as the second hangar for inspection UAV A, then the modified time interval is 1 month.

[0046] In some embodiments, based on the first hangar of the current inspection UAV, the planned waiting time at the first time is obtained, and the modified time interval is determined based on the planned waiting time and the waiting time threshold. The first time can refer to the time corresponding to when the current UAV completes the current planned inspection path. The planned waiting time can refer to the waiting time for the current inspection UAV to enter the first hangar for charging after completing the current inspection task, that is, the difference between the first time and the planned start charging time.

[0047] The greater the difference between the planned waiting time and the waiting time threshold, the higher the urgency to modify the first hangar of the current UAV. As the first hangar serves as the charging hangar and the waiting time for charging is longer, it will affect the work arrangement of the current inspection UAV, so it is necessary to modify the first hangar of the current inspection UAV as soon as possible, that is, the modified time interval is smaller.

[0048] In some embodiments, the steps for determining the modified time interval may include: determining the difference-interval relationship between the difference between the preset planned waiting time and the waiting time threshold and the modified time interval based on historical data; determining the current difference between the planned waiting time and the waiting time threshold of the current inspection UAV; and determining the modified time interval corresponding to the current inspection UAV based on the current difference through the preset difference-interval relationship.

[0049] When the number of UAVs far exceeds the number of the first hangars or the inspection tasks are relatively heavy, at the first time, there may be at least one inspection UAV waiting for charging in the first hangar.

[0050] The planned waiting time can be determined based on the planned waiting sequence of the first hangar at the first time. The planned waiting sequence may include the waiting UAV numbers waiting for charging and the corresponding planned charging data. The planned charging data can refer to the planned start charging time and the planned charging duration.

[0051] In some embodiments, the planned waiting time of the current inspection UAV can be determined based on the planned start charging time and the planned charging duration of other waiting UAVs ahead of the current inspection UAV in the planned waiting sequence at the first time. For example, the first time when the current inspection UAV completes the current inspection task is 10:00. At 10:00, there are waiting UAVs A, B, and C ahead of the current inspection UAV in the planned waiting sequence, and the corresponding planned charging durations are all 20 minutes. And waiting UAV A starts charging at the first time. If the planned start charging times of waiting UAVs B and C are the charging end times of the previous inspection UAV, then the planned waiting time of the current UAV is 20 minutes + 20 minutes + 20 minutes = 1 hour. The planned charging duration of each inspection UAV is determined by the most recently completed planned inspection path. For example, the planned charging duration can refer to the duration required for the inspection UAV to restore its power to the power level at the start of the planned inspection path.

[0052] The waiting time threshold can refer to the shortest time that the current inspection UAV can wait for charging. The waiting time threshold can be set manually. For example, the waiting time threshold can be the time that can be waited based on the remaining power of the current inspection UAV after completing the current inspection task.

[0053] Due to possible faults of the inspection UAV or the nest or other reasons, the planned start charging times and the planned charging durations of multiple waiting UAVs waiting for charging in the planned waiting sequence may deviate, thereby affecting the accuracy of the planned waiting time of the current inspection UAV. The planned waiting time includes an adjusted waiting time. The adjusted waiting time is the adjusted planned waiting time. In some embodiments, it is necessary to obtain the deviation degree of the planned waiting sequence, re-determine the adjusted charging data of the waiting UAVs in the planned waiting sequence based on the deviation degree, determine the adjusted waiting time based on the adjusted charging data, and determine the adjusted modified time interval based on the adjusted waiting time. The deviation degree of the planned waiting sequence can include the deviation degree of the planned charging data of the waiting UAVs. In some embodiments, determine the adjusted difference between the adjusted waiting time of the current inspection UAV and the waiting time threshold; re-determine the adjusted modified time interval of the current inspection UAV based on the difference-interval relationship through the adjusted difference.

[0054] In some embodiments, determining the deviation degree of the planned charging data of the waiting UAVs at the first time in the first nest may include:

[0055] Step S1, for each waiting UAV, obtain at least one set of first historical charging data of the waiting UAV at the historical first time. Each set of first historical charging data includes the historical start charging time corresponding to the historical charging and the historical planned charging duration. Each set of first historical charging data corresponds to a recently completed first historical inspection path.

[0056] For example, the first time is 8:00 in the morning on May 10, 2022, the historical first time is 8:00 in the morning for each day before May 10, 2022, the first historical charging data is the historical charging data at 8:00 for each day before May 10, 2022, and the first historical inspection path is the most recently completed historical inspection path before 8:00 for each day before May 10, 2022.

[0057] Step S2: Compare the similarity between the first historical inspection path of the waiting drone and the inspection path completed this time, and determine the second historical charging data from the first historical charging data.

[0058] Determine the planned charging duration according to the historical inspection path corresponding to each historical charging data. For example, in the first historical inspection path, there is the first historical path 1 (passing through points of interest A and B), and the second historical path 2 (passing through points of interest A and D). The inspection path completed by the current waiting drone in the planned waiting sequence is passing through points of interest A and B. Then the second historical charging data only includes the historical charging data corresponding to the path passing through points of interest A and B in the inspection path historically completed by the current waiting drone. The first historical inspection path with a similarity higher than the path similarity threshold can be used as the second historical inspection path, and the historical charging data corresponding to the second historical inspection path can be used as the second historical charging data.

[0059] Step S3: Determine a set of second historical charging data and historical planned charging data corresponding to each historical first time.

[0060] The historical charging data can refer to the historical actual charging data corresponding to the historical first time. The historical charging data can be obtained based on historical data. The historical planned charging data can be determined based on the historical inspection path. For example, the historical planned charging data can be determined according to the historical power consumption of the historical inspection path.

[0061] Step S4: Determine the charging characteristics of each waiting drone based on the difference between a set of second historical charging data and historical planned charging data corresponding to each historical first time.

[0062] Since the planned charging data is determined according to the planned inspection path, but due to the characteristics of the inspection drone itself, for example, long usage time and many charging times, there may be a difference between the actual charging data and the planned charging data. Based on the difference between multiple sets of second historical charging data and historical planned charging data, the charging characteristics suitable for each waiting drone can be determined. The charging characteristics of each waiting drone can be the average value of the differences between multiple sets of second historical charging data and historical planned charging data.

[0063] Step S5: Obtain the feature data of the first drone hangar and the charging characteristics of at least one waiting drone, and determine the deviation degree of the planned charging data of the waiting drones at the first time in the first drone hangar through a machine learning model.

[0064] Since the authenticity of the planned charging data of the waiting drones is directly related to the decision-making of the current drone charging hangar, by increasing the authenticity of the planned charging data of the drones in the planned waiting sequence, the accuracy of the decision-making can be effectively improved, and excessive changes to the current charging hangar of the inspection drones can be prevented.

[0065] In some embodiments, the adjusted planned charging data can be determined based on the deviation degree of the planned charging data of the waiting drones in the first drone hangar and the planned charging data of the waiting drones at the first time (for example, determination methods such as multiplication, correspondence, etc.), and the planned waiting time of the current inspection drones can be re-determined.

[0066] The feature data of the first drone hangar may include the busyness degree of the first drone hangar.

[0067] The busyness degree may refer to the current busyness level of the first drone hangar, and the busyness degree can be represented by a number. The higher the number, the higher the busyness degree of the first drone hangar. The busyness degree can be determined based on the total usage duration, usage frequency, and maintenance rate of the first drone hangar within a preset time period. The higher the total usage duration, usage frequency, and maintenance rate, the higher the busyness degree of the first drone hangar.

[0068] In some embodiments, the busyness degree score of the first drone hangar can be determined based on the total usage duration, usage frequency, and maintenance rate of the current first drone hangar through a preset relationship. The higher the total usage duration, usage frequency, and maintenance rate, the higher the corresponding busyness degree score.

[0069] In actual situations, since the higher the busyness degree score of the drone hangar, the more frequently the drone hangar is used and the greater the wear and tear. To mitigate this, which not only affects the efficiency of the drones but also increases the maintenance cost, the system needs to effectively allocate the drones to different hangars to ensure the load balance of each hangar.

[0070] Step 340: In response to the duration of the first drone hangar of the current inspection drone exceeding the modification time interval, actively adjust the first drone hangar of the current inspection drone.

[0071] In some embodiments, actively adjust the first drone hangar of the current inspection drone to the second drone hangar.

[0072] In some embodiments, based on the remaining power of the current unmanned aerial vehicle (UAV) at a first time, a travelable distance is determined, at least one preset charging hangar within the travelable distance from the last point of interest when the planned inspection path of the current inspection UAV is completed is determined, and the preset charging hangar with the lowest busyness is determined as the second hangar.

[0073] Through some embodiments of this specification, by monitoring and dynamically adjusting the path and hangar selection of the UAV, overuse of a single hangar can be reduced, thereby extending its service life and reducing maintenance requirements.

[0074] Since the planned charging hangar of the UAV changes through dynamic calculation based on the planned path, after some time periods, after dynamically adjusting the charging hangar, there may be more and more inspection UAVs using the second hangar as the charging hangar. Through some embodiments of this specification, the charging hangar can be continuously dynamically adjusted to prevent excessive waiting charging time and excessive utilization rate of a certain UAV hangar, and to achieve the ability of highly automated and intelligent management of the inspection UAV system.

[0075] It should be noted that the beneficial effects that may be produced by different embodiments are different. In different embodiments, the beneficial effects that may be produced can be any one or several combinations of the above, or any other beneficial effects that may be obtained.

[0076] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0077] Meanwhile, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0078] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical and alphabetical characters, or the use of other names described in this specification are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments have been discussed through various examples in the above disclosure, it should be understood that such details are only for illustrative purposes. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0079] Similarly, it should be noted that, in order to simplify the presentation of the disclosure in this specification and thus help the understanding of one or more embodiments, in the foregoing description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0080] In some embodiments, numbers are used to describe components and attribute quantities. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximate" or "substantially" in some examples. Unless otherwise stated, "about", "approximate" or "substantially" indicate that the stated number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and these approximate values can change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, the setting of such numerical values is as precise as possible within the feasible range.

[0081] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification as references. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and except for the documents that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0082] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A drone inspection method based on a drone nest, characterized in that: The method comprises: Obtain at least one planned inspection path of at least one inspection drone in the current area, and determine a first machine nest and planned charging data corresponding to each of the at least one inspection drone based on the at least one planned inspection path; Taking one of the at least one inspection drone in the current area as the current inspection drone, obtaining the first machine nest corresponding to the planned inspection path of the current inspection drone and the duration of the first machine nest, when the planned inspection path does not change, whenever the current inspection drone executes the planned inspection path, the duration of the first machine nest refers to the duration of the first machine nest as a charging machine nest; Determine the corresponding modification time interval based on the current inspection drone, where the modification time interval refers to actively adjusting the time interval of the current inspection drone charging nest, that is, the time interval between the start time and the end time of the first nest as the charging nest; In response to the duration of the first machine nest of the current inspection drone exceeding the modification time interval, actively adjusting the first machine nest of the current inspection drone; The step of determining the modification time interval comprises: Determine the difference-interval relationship between the preset planned waiting time and the waiting time threshold and the modified time interval based on historical data, wherein the waiting time threshold refers to the shortest time that the current inspection drone waits for charging; Determine the current difference between the planned waiting time and the waiting time threshold of the current inspection drone; Determine the modification time interval corresponding to the current inspection drone based on the current difference through the difference-interval relationship; The planned waiting time includes an adjusted waiting time, and the determination method thereof includes: Obtaining a deviation degree of a planned waiting sequence, wherein the deviation degree of the planned waiting sequence includes a deviation degree of planned charging data of the waiting drone, wherein the planned waiting sequence includes a number of the waiting drone waiting to be charged and corresponding planned charging data; re-determining the adjusted charging data of the waiting drone in the planned waiting sequence based on the deviation; determining an adjusted waiting time based on the adjusted charging data, and determining an adjusted modified time interval based on the adjusted waiting time; Among them, determining the deviation degree of the planned waiting sequence includes: For each of the waiting drones, obtaining at least one first historical charging data of the waiting drone at a first historical time, each of the first historical charging data includes a historical charging start time and a historical planned charging duration corresponding to the historical charging, each group of the first historical charging data corresponds to a corresponding first historical inspection path, and the first time refers to the time corresponding to when the current drone completes the current planned inspection path; Comparing the similarity between the first historical inspection path of the waiting drone and the inspection path that has been completed this time, and determining the second historical charging data from the first historical charging data; Determine a set of second historical charging data and historical planned charging data corresponding to each of the historical first times; determining a charging characteristic of each waiting drone based on a difference between a set of second historical charging data corresponding to each of the historical first times and the historical planned charging data; Acquire characteristic data of the first machine nest and charging characteristics of at least one waiting drone, and determine the deviation of the planned charging data of the waiting drone in the first machine nest at the first time through a machine learning model. The characteristic data of the first machine nest includes the busyness of the first machine nest. Based on the total usage time, usage frequency and maintenance rate of the first machine nest, determine the busyness score of the first machine nest through a preset relationship.

2. A drone inspection system based on a drone nest, characterized in that: The system comprises: A first acquisition module, used to acquire at least one planned inspection path of at least one inspection drone in the current area, and determine a first machine nest and planned charging data corresponding to each of the at least one inspection drone based on the at least one planned inspection path; A second acquisition module is used to use one of the at least one inspection drones in the current area as the current inspection drone, and obtain the first machine nest corresponding to the planned inspection path of the current inspection drone and the duration of the first machine nest. When the planned inspection path does not change, whenever the current inspection drone executes the planned inspection path, the duration of the first machine nest refers to the duration of the first machine nest as a charging machine nest; A time interval determination module is used to determine a corresponding modification time interval based on the current inspection drone, where the modification time interval refers to actively adjusting the time interval of the current inspection drone charging nest, that is, the time interval between the start time and the end time of the first nest as the charging nest; A modification time module, configured to actively adjust the first nest of the current inspection drone in response to the duration of the first nest of the current inspection drone exceeding the modification time interval; The time interval determination module is used to determine the modification time interval, further comprising: Determine the difference-interval relationship between the preset planned waiting time and the waiting time threshold and the modified time interval based on historical data, wherein the waiting time threshold refers to the shortest time that the current inspection drone waits for charging; Determine the current difference between the planned waiting time and the waiting time threshold of the current inspection drone; Determine the modification time interval corresponding to the current inspection drone based on the current difference through the difference-interval relationship; The current difference determination module is used to determine the planned waiting time, further comprising: A deviation degree determination module is used to obtain the deviation degree of the planned waiting sequence, wherein the deviation degree of the planned waiting sequence includes the deviation degree of the planned charging data of the waiting drone, and the planned waiting sequence includes the number of the waiting drone waiting to be charged and the corresponding planned charging data; An adjusting charging module, used for re-determining the adjusted charging data of the waiting drone in the planned waiting sequence based on the deviation degree; An adjustment time module, configured to determine an adjustment waiting time based on the adjustment charging data, and determine an adjusted modification time interval based on the adjustment waiting time; The deviation degree determination module is used to determine the deviation degree of the planned waiting sequence, including: A first historical data determination module is used to obtain, for each of the waiting drones, at least one first historical charging data of the waiting drone at a first historical time, each of the first historical charging data includes a historical charging start time and a historical planned charging duration corresponding to the historical charging, each group of the first historical charging data corresponds to a corresponding first historical inspection path, and the first time refers to the time corresponding to when the current drone completes the current planned inspection path; A second historical data determination module, used to compare the similarity between the first historical inspection path of the waiting drone and the inspection path that has been completed this time, and determine the second historical charging data from the first historical charging data; A third historical data determination module is used to determine a set of second historical charging data and historical planned charging data corresponding to each of the historical first time; a drone characteristic determination module, configured to determine a charging characteristic of each waiting drone based on a difference between a set of second historical charging data corresponding to each of the historical first times and the historical planned charging data; A charging deviation module is used to obtain characteristic data of a first machine nest and charging characteristics of at least one waiting drone, and determine the deviation of the planned charging data of the waiting drone in the first machine nest at a first time through a machine learning model. The characteristic data of the first machine nest includes the busyness of the first machine nest. The busyness score of the first machine nest is determined based on a preset relationship based on the total usage time, usage frequency and maintenance rate of the first machine nest.

3. A drone inspection device, comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements the drone inspection method as described in claim 1.

4. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the drone inspection method as described in claim 1.

Images