Method, system, device and medium for linkage inspection of tethered airship and unmanned aerial vehicle

Abstract

The application relates to the technical field of inspection, and discloses a linkage inspection method, system, equipment and medium for a tethered airship and a unmanned aerial vehicle, which comprises the following steps: receiving first attribute information for a first inspection target issued by a tethered airship; acquiring current resource information of each unmanned aerial vehicle; jointly determining a first execution cost of a candidate unmanned aerial vehicle corresponding to the first inspection target by using the first attribute information and the resource information of the candidate unmanned aerial vehicle; sending the first execution cost to the candidate unmanned aerial vehicle, so that the candidate unmanned aerial vehicle determines a task bidding gain based on the corresponding first execution cost; receiving the task bidding gains sent by each unmanned aerial vehicle, and determining a unmanned aerial vehicle corresponding to the maximum task bidding gain as a target unmanned aerial vehicle; issuing an instruction for executing a first inspection task to the target unmanned aerial vehicle, so that the target unmanned aerial vehicle collects a second inspection image for the first inspection target and sends the second inspection image to a cloud control center. By implementing the method, the inspection efficiency is ensured to be high.

Description

Technical Field

[0001] This invention relates to the field of inspection technology, specifically to a method, system, equipment, and medium for joint inspection of tethered airships and unmanned aerial vehicles. Background Technology

[0002] With the rapid development of drone technology, drones have been widely used in routine inspection tasks in airspace and water areas. However, due to the limitation of drone onboard battery capacity, drones face a bottleneck in endurance, requiring frequent returns to drone hangars for charging and battery swapping, which in turn results in a short effective operating time for drones.

[0003] However, while tethered airships can achieve uninterrupted power supply and long-term fixed-point stationing by relying on tethered composite cables, their maneuverability is insufficient, making it difficult to conduct close-range, detailed exploration.

[0004] To address the aforementioned issues, there is an urgent need for a method that can efficiently complete inspection tasks. Summary of the Invention

[0005] This invention provides a method, system, equipment, and medium for joint inspection of tethered airships and drones, in order to solve the problem of low inspection efficiency caused by relying solely on drones or tethered airships to perform inspection tasks in related technologies.

[0006] In a first aspect, the present invention provides a method for joint inspection of a tethered airship and a drone, applied in a cloud control center. The method includes: receiving first attribute information of a first inspection target from a tethered airship, wherein the first attribute information is obtained by the tethered airship through target detection based on a first inspection image it has collected; acquiring current resource information of each drone; for any candidate drone among the drones, using the first attribute information and the resource information of the candidate drone, jointly determining a first execution cost corresponding to the first inspection target for the candidate drone; sending the first execution cost to the candidate drone so that the candidate drone determines a task bidding gain based on its corresponding first execution cost; receiving the task bidding gains sent by each drone and identifying the drone with the largest task bidding gain as the target drone; issuing an instruction to the target drone to execute a first inspection task so that the target drone collects a second inspection image of the first inspection target and sends it to the cloud control center, wherein the first inspection task is used to characterize the inspection of the first inspection target.

[0007] The tethered airship and UAV linkage inspection method provided in this embodiment involves the tethered airship collecting a first inspection image of its inspection area and performing target detection on the first inspection image to obtain the first attribute information of the first inspection target. The tethered airship can then send the first attribute information of the first inspection target to the cloud control center. The cloud control center can combine the first attribute information to determine the target UAV for close-range reconnaissance of the first inspection target. The target UAV then conducts close-range reconnaissance of the first inspection target to obtain a second inspection image, which is then sent back to the cloud control center. Because the tethered airship has a long loiter time and a wide inspection coverage area, it compensates for the shortcomings of UAVs, such as limited endurance and high cost of large-scale, all-area inspections. Furthermore, the UAV is maneuverable and can approach targets at close range for detailed photography, compensating for the limitations of the tethered airship in terms of equipment carrying capacity and its inability to obtain detailed evidence at close range. The complementary advantages of both enable collaborative inspection, ensuring high overall inspection efficiency.

[0008] In one optional implementation, the first execution cost corresponding to the first inspection target for the candidate drone is jointly determined using the first attribute information and the resource information of the candidate drone. This includes: determining the normalized distance between the first inspection target and the candidate drone using the location information of the first inspection target and the location information of the candidate drone; normalizing the available power of the candidate drone using the maximum available power to obtain the normalized available power corresponding to the candidate drone, where the maximum available power is the sum of the available power of all drones; normalizing the current number of tasks of the candidate drone using the maximum number of tasks to obtain the normalized conflict coefficient corresponding to the candidate drone, where the maximum number of tasks is the maximum number of tasks that the candidate drone can execute, and the current number of tasks is the number of tasks that the drone has accepted but not yet executed; and determining the first execution cost using the fusion result of the normalized distance, normalized available power, and normalized conflict coefficient.

[0009] By normalizing the Euclidean distance between the candidate drone and the first inspection target, normalizing the available power of the candidate drone, and normalizing the total number of second inspection tasks corresponding to the candidate drone, the calculation bias corresponding to different dimensions can be eliminated. Then, by fusing the normalized distance, normalized available power, and normalized conflict coefficient, the first execution cost corresponding to the candidate drone performing the first inspection task can be evaluated more accurately.

[0010] In one optional implementation, the first execution cost of the candidate drone corresponding to the first inspection target is jointly determined by using the first attribute information and the resource information of the candidate drone. The method further includes: obtaining the waiting time of the candidate drone when performing the first inspection task; normalizing the waiting time of the candidate drone using the maximum waiting time to obtain a normalized waiting time, wherein the maximum waiting time is the maximum value of the waiting time among all drones; and determining the first execution cost by using the fusion result of normalized distance, normalized available power, normalized conflict coefficient and normalized waiting time.

[0011] By incorporating normalized waiting time into the existing normalized distance, normalized available power, and normalized conflict coefficient, the hidden costs of drone mission queuing and recharging can be taken into account, further ensuring that the determined first execution cost is more accurate and reasonable.

[0012] In one optional implementation, the process of determining the task bidding gain based on the candidate drone's corresponding first execution cost includes: using the first execution cost to determine the first total cost when the candidate drone performs the first inspection task and the second inspection task, wherein the second inspection task is an inspection task that the candidate drone has currently accepted but has not yet performed; obtaining the second total cost when the candidate drone performs the second inspection task; and using the difference between the second total cost corresponding to the candidate drone and the first total cost to determine the task bidding gain.

[0013] By calculating the first total cost of a candidate drone after it undertakes the first inspection task, and the second total cost before it undertakes the first inspection task, the task bidding gain of the candidate drone can be determined relatively quickly and efficiently.

[0014] In one optional implementation, the second inspection task corresponds to a second inspection target, and the candidate drone corresponds to a second execution cost for the second inspection target; using the first execution cost, determining the first total cost when the candidate drone performs the first inspection task and the second inspection task includes: determining the first cost using the fusion result of the first execution cost and the second execution cost; determining the penalty coefficient corresponding to the candidate drone using the total number of the first inspection task and the second inspection task; and obtaining the first total cost using the fusion result between the first cost and the penalty coefficient.

[0015] By first calculating the first execution cost when a candidate drone performs the first inspection task and the second execution cost when performing the second inspection task, the workload generated by the candidate drone when performing the first and second inspection tasks, i.e. the first cost, can be accurately assessed. Then, the first cost is corrected by a penalty coefficient. This can prevent the total number of the first and second inspection tasks corresponding to the candidate drone from exceeding its maximum executable capacity, thereby avoiding overload of the number of unexecuted tasks by a single drone.

[0016] In an optional implementation, the method further includes: if the communication quality between the cloud control center and the drone is lower than a preset threshold, then the drone closest to the inspection target is identified as the target drone.

[0017] When the communication quality between the cloud control center and the drone is lower than a preset threshold, the drone closest to the inspection target (including the first inspection target and the second inspection target) is identified as the target drone by using the nearest neighbor principle. This ensures that the target drone is dispatched in a timely manner to conduct close observation of the first inspection target. At the same time, before the communication quality between the two continues to deteriorate, the cloud control center can also receive the second inspection image transmitted back by the target drone in a timely manner, thereby determining in a timely manner whether the first inspection target has actually experienced an anomaly.

[0018] In an optional implementation, the method further includes: if any two drones have the same task bidding gain, then the target drone is determined according to a preset index, wherein the preset index is the priority of the drone or the available power of the drone.

[0019] If the target drone cannot be identified in a timely manner through the principle of maximizing task bidding gain, the target drone can be identified in a timely manner based on the drone's priority or available power. This allows the appropriate target drone to be dispatched in a timely manner to conduct close-range observation of the inspection target.

[0020] Secondly, the present invention provides a joint inspection system of a tethered airship and an unmanned aerial vehicle (UAV). The system includes: a tethered airship, used to acquire a first inspection image, perform target detection on the first inspection image to obtain a first inspection target and first attribute information of the first inspection target, and send the first attribute information to a cloud control center; a cloud control center, used to receive the first attribute information for the first inspection target, and using the first attribute information and resource information of candidate UAVs, jointly determine a first execution cost for a candidate UAV corresponding to the first inspection target, and send the first execution cost to the candidate UAV, where the candidate UAV is any one of the various UAVs; an UAV, used to receive the first execution cost issued by the cloud control center, determine the task bid gain when the UAV performs the first inspection task, and send the task bid gain to the cloud control center, where the first inspection task represents the inspection of the first inspection target; and the cloud control center is further used to identify the UAV corresponding to the largest task bid gain as the target UAV, and issue an instruction to the target UAV to perform the first inspection task, so that the target UAV acquires a second inspection image for the first inspection target and sends it to the cloud control center.

[0021] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the tethered airship and unmanned aerial vehicle linkage inspection method of the first aspect or any corresponding embodiment described above.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the tethered airship and unmanned aerial vehicle linkage inspection method of the first aspect or any corresponding embodiment described above.

[0023] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause the computer to execute the tethered airship and unmanned aerial vehicle linkage inspection method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of the present invention, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first type of joint inspection method of tethered airship and UAV according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of the joint inspection method of tethered airship and UAV according to an embodiment of the present invention; Figure 4 This is a timing diagram of a specific method for joint inspection of a tethered airship and an unmanned aerial vehicle according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a joint inspection device for a tethered airship and a drone according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0028] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] With the rapid development of drone technology, drones have been widely used in routine inspection tasks in airspace and water areas. However, due to the limitation of drone onboard battery capacity, drones face a bottleneck in endurance, requiring frequent returns to drone hangars for charging and battery swapping, which in turn results in a short effective operating time for drones.

[0030] However, while tethered airships can achieve uninterrupted power supply and long-term fixed-point stationing by relying on tethered composite cables, their maneuverability is insufficient, making it difficult to conduct close-range, detailed exploration.

[0031] To address the aforementioned issues, this application proposes a joint inspection method integrating airborne lookout, ground response, and cloud command. A tethered airship serves as a persistent aerial sensing system, while one or more distributed ground-based UAV hangars act as automatic resupply bases and forward deployment points for the UAVs. The two systems collaborate via a highly reliable communication link to achieve all-weather, fully automated, and intelligent inspection of the designated inspection area.

[0032] As an optional application scenario of this invention, such as Figure 1 As shown, the tethered airship and drone joint inspection system can include a tethered airship, a cloud control center, and drones. Specifically, there are communication connections between the tethered airship and the cloud control center, and between the cloud control center and the drones.

[0033] For example, at least one drone hangar is located at a designated location on the ground, and the corresponding drone is located inside the drone hangar; that is, one drone corresponds to one drone hangar, and the drone is used to perform inspection tasks in the designated area. In addition, the drone hangar has environmental protection capabilities such as temperature control, dustproof, and waterproof capabilities.

[0034] For example, a tethered airship takes off from the center of the area or a key location. The tethered airship integrates image acquisition equipment such as cameras or lidar, and has a built-in target detection algorithm. This algorithm performs target detection on the first inspection image of the inspection area acquired by the image acquisition equipment, obtaining the first inspection target and its corresponding first attribute information. The center of the area can be the geometric center of the area formed by the combined locations of all UAV hangars, and the key location can be a high-risk area within the inspection zone.

[0035] For example, the cloud control center can, from a global perspective, use the first inspection target issued by the tethered airship and its corresponding first attribute information to plan the target UAV that needs to be observed at close range, and issue commands to the target UAV to perform a first inspection task on the first inspection target, thereby acquiring a second inspection image of the first inspection target. After acquiring the second inspection image, the target UAV can send it to the cloud control center. The cloud control center can then perform joint analysis of the second inspection image and the first attribute information of the first inspection target to obtain the final inspection result, which can help managers determine emergency strategies.

[0036] According to an embodiment of the present invention, a method for joint inspection of tethered airships and unmanned aerial vehicles is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0037] This embodiment provides a method for joint inspection of tethered airships and drones, which can be used in a cloud control center. Figure 2 This is a flowchart of a joint inspection method for tethered airships and unmanned aerial vehicles according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Receive the first attribute information of the first inspection target sent by the tethered airship. The first attribute information is obtained by the tethered airship through target detection based on the first inspection image it has collected.

[0038] The first inspection target can be a target detected by the moored airship from the first inspection image that requires close-range inspection by the drone. As a specific example, in a power line inspection scenario, the first inspection target can be a damaged section of the line, a potential point of leaning tower, or an illegal structure under the line; in an oil and gas pipeline inspection scenario, the first inspection target can be an exposed or damaged section of the pipeline, or a third-party construction or excavation site; in a border / waterway inspection scenario, the first inspection target can be suspicious persons, illegal vessels, etc.; and in a forest inspection scenario, the first inspection target can be a forest fire site, etc.

[0039] The first attribute information of the first inspection target can be used to characterize the type of the first inspection target, the emergency level corresponding to the first inspection target, and the location information corresponding to the first inspection target.

[0040] As a specific example, as mentioned above, tethered airships are equipped with image acquisition devices such as cameras and lidar. Therefore, tethered airships can periodically acquire the first inspection image of their inspection area according to a pre-set image acquisition frequency.

[0041] Meanwhile, the tethered airship is equipped with a target detection algorithm. After acquiring the first inspection image, it can use this algorithm to detect targets within the image. If no target is detected, the tethered airship can continue to acquire the first inspection image at regular intervals. If a target is detected, its pixel coordinates in the first inspection image can be obtained first. Then, a coordinate system transformation can be performed on these pixel coordinates: first, the pixel coordinates are transformed to the coordinates of the image acquisition device, such as the camera coordinate system; then, they are transformed from the camera coordinate system to the tethered airship's coordinate system; finally, the coordinates of the tethered airship are transformed to the world coordinate system, ultimately obtaining the target's position information in the world coordinate system.

[0042] Simultaneously, based on the target detection results, the type corresponding to the first inspection target can be automatically determined, and according to the pre-set classification rules, the emergency level corresponding to the first inspection target, as shown in Table 1, can be automatically determined. Then, the tethered airship can package and send the first attribute information, including location information, type, and emergency level, to the cloud control center. Correspondingly, the cloud control center can receive the packaged first attribute information sent by the tethered airship.

[0043] Table 1

[0044] Step S202: Obtain the current resource information of each drone.

[0045] The resource information for each drone may include the location of the drone (i.e., the drone hangar), the drone's current available power, and the inspection tasks that the drone has been assigned but not yet executed.

[0046] As mentioned earlier, the cloud control center can communicate with each drone, thus obtaining the current resource information of each drone through communication and interaction.

[0047] Step S203: For any candidate drone among all drones, use the first attribute information and the resource information of the candidate drone to jointly determine the first execution cost of the candidate drone corresponding to the first inspection target.

[0048] The first execution cost corresponding to the candidate drone can be used to characterize the comprehensive cost of the candidate drone inspecting the first inspection target.

[0049] In some cases, the distance between the candidate drone and the first inspection target can be calculated first to obtain the first distance. Then, the first distance, the current available power of the candidate drone, and the number of tasks that the candidate drone has accepted but not yet executed can be weighted and fused to obtain the initial execution cost. Finally, the initial execution cost can be normalized to obtain the first execution cost that the candidate drone would need to pay if it inspects the first inspection target.

[0050] Step S204: The first execution cost is sent to the candidate drone so that the candidate drone can determine the task bidding gain based on its corresponding first execution cost.

[0051] The task bid gain here can be used to characterize the cost gain incurred by a candidate UAV if it inspects the first inspection target. Specifically, the larger the task bid gain of a candidate UAV, the more suitable it is for inspecting the first inspection target; conversely, the smaller the task bid gain, the less suitable it is for inspecting the first inspection target.

[0052] In some cases, candidate drones can first obtain the second execution cost corresponding to not inspecting the first inspection target; then, the task bidding gain can be determined by the difference between the first execution cost and the second execution cost.

[0053] Step S205: Receive the task bid gains sent by each UAV and determine the UAV with the largest task bid gain as the target UAV.

[0054] As mentioned above, the greater the task bid gain, the more suitable the UAV is for performing the first inspection task. Therefore, the UAV corresponding to the maximum task bid gain can be identified as the target UAV.

[0055] Furthermore, if there are multiple drones corresponding to the maximum task bid gain, the target drone cannot be determined based on the maximum task bid gain. In this case, the method described above can be used for multiple iterations to determine a single maximum task bid gain, thereby identifying the target drone.

[0056] Step S206: Send an instruction to the target drone to perform the first inspection task, so that the target drone can collect a second inspection image of the first inspection target and send it to the cloud control center. The first inspection task is used to represent the inspection of the first inspection target.

[0057] The first inspection task can be to assign a drone to conduct close-range on-site reconnaissance and collect real-time images of the first inspection target detected by the tethered airship.

[0058] After identifying the target drone, the cloud control center can issue a command to the target drone to execute the first inspection task. Upon receiving the command, the target drone can then execute the first inspection task. Simultaneously, when issuing the first inspection task, the cloud control center can also synchronize the type and urgency of the first inspection target to the target drone. Therefore, the target drone can comprehensively analyze the type and urgency of the first and second inspection tasks to determine the priority inspection tasks and execute each task (i.e., the first and second inspection tasks) one by one. The second inspection task can be one that the target drone had already undertaken before accepting the first inspection task.

[0059] In addition, during the initial inspection mission, the target drone, given its maneuverability, can acquire second inspection images of the target from multiple angles at close range, and then send these second inspection images to the cloud control center. Of course, in some cases, to ensure the quality of the second inspection images sent to the cloud control center, the target drone can perform image preprocessing after acquiring the second inspection images, such as increasing contrast and enhancing the outline edges of the target, before sending the preprocessed second inspection images to the cloud control center.

[0060] After receiving the second inspection image sent by the target drone, the cloud control center can perform target detection on the second inspection image to obtain the target detection result. It can then comprehensively analyze the target detection result, the type and urgency level of the first inspection target sent by the tethered airship, and generate the final target detection result.

[0061] For example, if a tethered airship detects a fire in a certain area of ​​a forest, the cloud control center can combine the second inspection image sent by the target drone to determine whether the area is actually on fire.

[0062] After completing the inspection mission, the target drone can return to its corresponding drone hangar according to the instructions of the cloud control center, and automatically complete precise landing, storage, and charging.

[0063] The tethered airship and UAV linkage inspection method provided in this embodiment involves the tethered airship collecting a first inspection image of its inspection area and performing target detection on the first inspection image to obtain the first attribute information of the first inspection target. The tethered airship can then send the first attribute information of the first inspection target to the cloud control center. The cloud control center can combine the first attribute information to determine the target UAV for close-range reconnaissance of the first inspection target. The target UAV then conducts close-range reconnaissance of the first inspection target to obtain a second inspection image, which is then sent back to the cloud control center. Because the tethered airship has a long loiter time and a wide inspection coverage area, it compensates for the shortcomings of UAVs, such as limited endurance and high cost of large-scale, all-area inspections. Furthermore, the UAV is maneuverable and can approach targets at close range for detailed photography, compensating for the limitations of the tethered airship in terms of equipment carrying capacity and its inability to obtain detailed evidence at close range. The complementary advantages of both enable collaborative inspection, ensuring high overall inspection efficiency.

[0064] This embodiment provides a method for joint inspection of tethered airships and drones, which can be used in a cloud control center. Figure 3 This is a flowchart of a joint inspection method for tethered airships and unmanned aerial vehicles according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Receive first attribute information for the first inspection target from the tethered airship. The first attribute information is obtained by the tethered airship through target detection based on the first inspection image it has collected. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0065] Step S302: Obtain the current resource information for each drone. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0066] Step S303: For any candidate drone among the drones, the first execution cost of the candidate drone corresponding to the first inspection target is jointly determined by using the first attribute information and the resource information of the candidate drone.

[0067] Specifically, step S303 includes: Step S3031: Using the location information of the first inspection target and the location information of the candidate UAV, determine the normalized distance between the first inspection target and the candidate UAV.

[0068] Here, the Euclidean distance between the first inspection target and the candidate UAV can be determined first based on their location information. Then, the maximum Euclidean distance is determined by the Euclidean distance between each drone and the first inspection target. Finally, the maximum Euclidean distance can be utilized. Euclidean distance between the first inspection target and the candidate drone After normalization, the normalized distance between the first inspection target and the candidate UAV is obtained. .

[0069] It should be understood that the location information of the drones proposed in this application refers to the location information of the drone hangar where the drones are located, that is, the location information of the drones on the ground when they are not performing a mission. Accordingly, the location information of the drones can also be understood as the location information of the drone hangars.

[0070] Step S3032: Normalize the available power of the candidate drones using the maximum available power to obtain the normalized available power of the candidate drones. The maximum available power is the sum of the available power of all drones.

[0071] This can be accessed here. The available power of the candidate drones is normalized to obtain the normalized available power of each candidate drone. Used to represent the sum of available battery power for all drones. Used to indicate the available battery power of candidate drones. Used to represent normalized available power.

[0072] Step S3033: Normalize the current number of tasks of the candidate drone using the maximum number of tasks to obtain the normalized conflict coefficient corresponding to the candidate drone. The maximum number of tasks is the maximum number of tasks that the candidate drone can execute, and the current number of tasks is the number of tasks that the drone has accepted but has not yet executed.

[0073] This can be utilized The total number of second inspection tasks corresponding to candidate drones is normalized to obtain the normalized conflict coefficient for each candidate drone. Here, k represents the total number of second inspection tasks corresponding to a candidate drone, i.e., the number of tasks that the drone had already accepted but not yet executed before undertaking the first inspection. Used to indicate the maximum number of tasks a candidate drone can undertake; Used to represent the normalized conflict coefficient corresponding to the candidate drone.

[0074] Step S3034: Determine the first execution cost by using the fusion result of normalized distance, normalized available power, and normalized conflict coefficient.

[0075] As a concrete example, the first execution cost can be expressed as: ; in, Used to represent the first execution cost Used to represent the weights corresponding to the normalized distance Used to represent the weights corresponding to the normalized available electricity. Used to represent the weights corresponding to the normalized conflict coefficients. , as well as Calibration can be performed based on simulation experiments or field tests. As a specific example, w1=0.4, w2=0.4, w3=0.2.

[0076] By normalizing the Euclidean distance between the candidate drone and the first inspection target, normalizing the available power of the candidate drone, and normalizing the total number of second inspection tasks corresponding to the candidate drone, the calculation bias corresponding to different dimensions can be eliminated. Then, by fusing the normalized distance, normalized available power, and normalized conflict coefficient, the first execution cost corresponding to the candidate drone performing the first inspection task can be evaluated more accurately.

[0077] In some optional implementations, step S303 above further includes: Step S3035: Obtain the waiting time when the candidate drone performs the first inspection task.

[0078] The waiting time may include the time it takes for the candidate drone to complete the first inspection task and the charging time for the candidate drone during the task execution.

[0079] As a specific example, the cloud control center can send the first attribute information of the first inspection target to the candidate drones, and the candidate drones can estimate the waiting time when performing the first inspection task based on the budget of the first inspection target.

[0080] Step S3036: Normalize the waiting time of candidate drones using the maximum waiting time to obtain the normalized waiting time. The maximum waiting time is the maximum value of the waiting time among all drones.

[0081] This can be accessed here. The waiting time of candidate drones is normalized to obtain the normalized waiting time, where, Used to indicate the waiting time of candidate drones, Used to indicate the maximum waiting time. Used to represent normalized wait time.

[0082] Step S3037: Determine the first execution cost by using the fusion result of normalized distance, normalized available power, normalized conflict coefficient and normalized waiting time.

[0083] As a concrete example, the first execution cost can also be expressed as: ; in, This is used to represent the weights corresponding to the normalized waiting time. Wherein, Calibration can also be performed based on simulation experiments or on-site tests.

[0084] By incorporating normalized waiting time into the existing normalized distance, normalized available power, and normalized conflict coefficient, the hidden costs of drone mission queuing and recharging can be taken into account, further ensuring that the determined first execution cost is more accurate and reasonable.

[0085] Step S304: The first execution cost is sent to the candidate drones so that the candidate drones determine their mission bidding gain based on their corresponding first execution cost. See details below. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0086] In some alternative implementations, the process of determining the mission bidding gain based on the candidate drone's corresponding first execution cost includes: Step a1: Using the first execution cost, determine the first total cost when the candidate UAV performs the first inspection task and the second inspection task. The second inspection task is the inspection task that the candidate UAV has accepted but has not yet executed.

[0087] Step a2: Obtain the second total cost when the candidate UAV performs the second inspection task.

[0088] Step a3: Determine the task bidding gain by using the difference between the second total cost and the first total cost corresponding to the candidate drone.

[0089] Candidate drones can first determine their second execution cost when performing the second inspection task, and then determine the first total cost based on the fusion result of the first and second execution costs.

[0090] As a concrete example, the task bidding gain can be expressed as: ; in, Used to represent the task bid gain, i.e., candidate drones Perform the first inspection task The corresponding task bidding gain at that time Used to represent the first total cost. Used to represent the second total cost.

[0091] By calculating the first total cost of a candidate drone after it undertakes the first inspection task, and the second total cost before it undertakes the first inspection task, the task bidding gain of the candidate drone can be determined relatively quickly and efficiently.

[0092] As mentioned above, the drone's resource information includes the second inspection tasks that the drone has accepted but not yet executed. Each second inspection task corresponds to a second inspection target and its second attribute information.

[0093] As a specific example, the second attribute information may include the location information, type, and urgency level of the second inspection target, which is the same as the specific content of the first attribute information, but is used to represent different inspection targets.

[0094] Furthermore, when a drone has a second inspection target, it can also have a second execution cost for executing that second inspection target. The calculation method for this second execution cost can refer to the calculation method for the first execution cost, and will not be repeated here. Moreover, for the drone, the corresponding second execution cost can also be sent to the drone by the cloud control center.

[0095] In some alternative implementations, step a1 above includes: Step b1: Determine the first cost by using the fusion result of the first execution cost and the second execution cost.

[0096] Step b2: Determine the penalty coefficient corresponding to the candidate drone using the total number of the first and second inspection tasks.

[0097] Step b3: Utilize the fusion result between the first cost and the penalty coefficient to obtain the first total cost.

[0098] The first total cost can be expressed as: As a concrete example, the first total cost can be expressed as: ; in, Used to represent the first total cost. Used to indicate the first cost. Used to represent the weight corresponding to the penalty coefficient. Used to represent the penalty coefficient, where This can be adjusted flexibly according to the actual situation, and this application does not impose specific limitations on it.

[0099] As a specific example, when the total number of the first and second inspection tasks corresponding to the candidate drone is less than or equal to the maximum number of tasks that the candidate drone can execute, the penalty coefficient can be 0; when the total number of the first and second inspection tasks corresponding to the candidate drone is greater than the maximum number of tasks that the candidate drone can execute, the penalty coefficient can be determined by a linear, quadratic, or exponential function, such that when the total number of the first and second inspection tasks corresponding to the candidate drone is greater than the maximum number of tasks that the candidate drone can execute, the first total execution cost increases sharply.

[0100] As a specific example, the second total cost can be expressed as: ; in, Used to represent the second total cost Used to represent the second execution cost corresponding to the candidate drone. Used to represent the weight corresponding to the penalty coefficient. Used to represent the penalty coefficient when calculating the second total cost.

[0101] By first calculating the first execution cost when a candidate drone performs the first inspection task and the second execution cost when performing the second inspection task, the workload generated by the candidate drone when performing the first and second inspection tasks, i.e. the first cost, can be accurately assessed. Then, the first cost is corrected by a penalty coefficient. This can prevent the total number of the first and second inspection tasks corresponding to the candidate drone from exceeding its maximum executable capacity, thereby avoiding overload of the number of unexecuted tasks by a single drone.

[0102] Step S305: Receive the task bid gains sent by each drone and determine the drone with the highest task bid gain as the target drone. For details, please refer to [link to details]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.

[0103] Step S306: A command to execute the first inspection task is issued to the target drone, causing the target drone to acquire a second inspection image of the first inspection target and send it to the cloud control center. The first inspection task represents the inspection of the first inspection target. For details, please refer to... Figure 2 Step S206 of the illustrated embodiment will not be described again here.

[0104] In some alternative implementations, the method further includes: Step c1: If the communication quality between the cloud control center and the drone is lower than a preset threshold, the drone closest to the inspection target will be identified as the target drone.

[0105] Communication quality can be used to characterize the reliability of the data transmission link between the cloud control center and the drone. In some cases, the packet loss rate between the cloud control center and the drone can be used to assess the communication quality; a higher packet loss rate indicates lower communication quality, while a lower packet loss rate indicates higher communication quality.

[0106] In other cases, the communication quality between the cloud control center and the drone can be assessed by measuring at least one of the following: communication latency, signal-to-noise ratio (SNR), received signal strength (RSSI), and bit error rate (BER). Generally, longer communication latency, lower SNR, weaker received signal strength, and higher BER indicate poorer communication quality.

[0107] When the communication quality between the cloud control center and the drone is lower than a preset threshold, the drone closest to the inspection target (including the first inspection target and the second inspection target) is identified as the target drone by using the nearest neighbor principle. This ensures that the target drone is dispatched in a timely manner to conduct close observation of the first inspection target. At the same time, before the communication quality between the two continues to deteriorate, the cloud control center can also receive the second inspection image transmitted back by the target drone in a timely manner, thereby determining in a timely manner whether the first inspection target has actually experienced an anomaly.

[0108] In some alternative implementations, the method further includes: Step d1: If any two drones have the same task bidding gain, then the target drone is determined according to preset indicators, which are the priority of the drone or the available power of the drone.

[0109] In some cases, multiple drones may have the same task bid gain. In such cases, it may be impossible to determine the target drone in a timely manner based on the principle of maximizing task bid gain. Therefore, in some situations, these candidate drones with the same task bid gain can continue to iterate the above-mentioned task bid gain calculation method to determine the candidate drone with the maximum task bid gain.

[0110] Of course, in some cases, to avoid the above algorithm from getting stuck in an infinite loop, and to ensure that the target drone can be identified in a timely and efficient manner, if the target drone cannot be identified in the first iteration, the drone with the highest priority level can be identified as the target drone based on the priority levels among multiple drones with the same task bidding gain, or the drone with the largest available battery power among all drones can be identified as the target drone.

[0111] If the target drone cannot be identified in a timely manner through the principle of maximizing task bidding gain, the target drone can be identified in a timely manner based on the drone's priority or available power. This allows the appropriate target drone to be dispatched in a timely manner to conduct close-range observation of the inspection target.

[0112] The tethered airship and UAV linkage inspection method provided in this embodiment determines the task bidding gain of each UAV due to undertaking the first inspection task by the difference between the second total execution cost before undertaking the first inspection task and the first total execution cost after undertaking the first inspection task. This method can accurately quantify the workload of the UAV after the addition of the inspection task and further improve the rationality of the determination of the target UAV.

[0113] As a specific application embodiment of the present invention, such as Figure 4The diagram illustrates a specific method for coordinated inspection of tethered airships and drone hangars. This method establishes communication connections between the tethered airship and the cloud control center, as well as between the cloud control center and the drone hangar. Simultaneously, network status checks are performed on the tethered airship, the cloud control center, and the drone hangar to ensure a continuous communication network connection between them.

[0114] In addition, the tethered airship can monitor inspection targets within its designated inspection area. Specifically, the image acquisition equipment on the tethered airship can capture initial inspection images, and the airship can use its built-in target detection algorithm to detect targets in these images, thereby obtaining the location information, type, and urgency level of the inspection targets. The tethered airship can then package and send the location information, type, and urgency level of the inspection targets to the cloud control center.

[0115] After receiving the location, type, and urgency information of the inspection target from the tethered airship, the cloud control center can also obtain the location information, current available power, and number of currently unexecuted inspection tasks (i.e., the number of second inspection tasks mentioned earlier) of each drone by interacting with each drone hangar. Based on the received information, the cloud control center can plan the first execution cost for each drone and distribute the first execution cost to the corresponding drone.

[0116] After receiving the first execution cost sent by the cloud control center, the drone can determine the task bid gain generated by the drone after undertaking the task of inspecting the first inspection target, and send the task bid gain to the cloud control center.

[0117] After receiving the task bid gains sent by each drone, the cloud control center can identify the drone with the largest task bid gain as the target drone and issue an inspection task to the target drone to perform a close-range inspection of the first inspection target.

[0118] After receiving the inspection command from the cloud control center, the target drone begins to perform the inspection task for the target and returns the second inspection image it has collected of the target to the cloud control center. After completing the task, the target drone returns to the drone hangar to recharge and simultaneously starts the cleaning equipment to clean the drone, in preparation for the next inspection task.

[0119] After receiving the second inspection image, the cloud control center combines the second inspection image with the location, type, and urgency information of the inspection target sent by the tethered airship to determine the final inspection result and carry out emergency handling by management personnel.

[0120] This application constructs a well-structured, complementary, and highly collaborative intelligent inspection system by deeply coupling a persistently stationary tethered airship with a cloud-based control center and automated ground-based drones. It achieves seamless integration of global perception and local precision, providing a reliable solution for large-scale infrastructure inspection, border monitoring, emergency patrols, and other fields.

[0121] This embodiment also provides a joint inspection device for tethered airships and drones, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0122] This embodiment provides a joint inspection device for tethered airships and drones, such as... Figure 5 As shown, it includes: The information receiving module 501 is used to receive the first attribute information of the first inspection target sent by the tethered airship. The first attribute information is obtained by the tethered airship through target detection based on the first inspection image it has collected.

[0123] The information acquisition module 502 is used to acquire the current resource information of each UAV.

[0124] The first determining module 503 is used to jointly determine the first execution cost of the candidate drone corresponding to the first inspection target for any candidate drone among the various drones, using the first attribute information and the resource information of the candidate drone.

[0125] The sending module 504 is used to send the first execution cost to the candidate drone so that the candidate drone can determine the task bidding gain based on its corresponding first execution cost.

[0126] The receiving module 505 is used to receive the task bid gains sent by each UAV and identify the UAV with the largest task bid gain as the target UAV.

[0127] The task issuing module 506 is used to issue instructions to the target UAV to execute the first inspection task, so that the target UAV can collect the second inspection image of the first inspection target and send it to the cloud control center. The first inspection task is used to represent the inspection of the first inspection target.

[0128] In some optional implementations, the determining module 503 is further configured to: determine the normalized distance between the first inspection target and the candidate drone using the location information of the first inspection target and the location information of the candidate drone; normalize the available power of the candidate drone using the maximum available power to obtain the normalized available power corresponding to the candidate drone, where the maximum available power is the sum of the available power of all drones; normalize the current number of tasks of the candidate drone using the maximum number of tasks to obtain the normalized conflict coefficient corresponding to the candidate drone, where the maximum number of tasks is the maximum number of tasks that the candidate drone can execute, and the current number of tasks is the number of tasks that the drone has accepted but not yet executed; and determine the first execution cost using the fusion result of the normalized distance, normalized available power, and normalized conflict coefficient.

[0129] In some optional implementations, the determining module 503 is further configured to obtain the waiting time of the candidate UAV when performing the first inspection task; normalize the waiting time of the candidate UAV using the maximum waiting time to obtain a normalized waiting time, wherein the maximum waiting time is the maximum value of the waiting time among all UAVs; and determine the first execution cost using the fusion result of normalized distance, normalized available power, normalized conflict coefficient and normalized waiting time.

[0130] In some alternative implementations, the means for determining the mission bidding gain based on the candidate drone's corresponding first execution cost includes: The second determining module is used to determine the first total cost when the candidate UAV performs the first inspection task and the second inspection task using the first execution cost. The second inspection task is the inspection task that the candidate UAV has accepted but has not yet performed.

[0131] The acquisition module is used to acquire the second total cost when the candidate UAV performs the second inspection task.

[0132] The third determination module is used to determine the mission bidding gain by using the difference between the second total cost and the first total cost corresponding to the candidate UAV.

[0133] In some optional implementations, the second inspection task corresponds to a second inspection target, and the candidate UAV corresponds to a second execution cost for the second inspection target; the second determining module is used to determine a first cost by using the fusion result of the first execution cost and the second execution cost; determine the penalty coefficient corresponding to the candidate UAV by using the total number of the first inspection task and the second inspection task; and obtain the first total cost by using the fusion result between the first cost and the penalty coefficient.

[0134] In some alternative implementations, the tethered airship and UAV joint inspection device further includes: The fourth determination module is used to determine the drone closest to the first inspection target as the target drone if the communication quality between the cloud control center and the drone is lower than a preset threshold.

[0135] In some alternative implementations, the tethered airship and UAV joint inspection device further includes: The fifth determination module is used to determine the target drone according to preset indicators if any two drones have the same task bidding gain. The preset indicators are the priority of the drone or the available power of the drone.

[0136] The tethered airship and UAV linkage inspection device provided in this embodiment of the invention can execute the tethered airship and UAV linkage inspection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0137] This embodiment provides a joint inspection system for tethered airships and drones, which includes a tethered airship, a cloud control center, and drones.

[0138] The tethered airship is used to collect the first inspection image, perform target detection on the first inspection image to obtain the first inspection target and the first attribute information of the first inspection target, and send the first attribute information to the cloud control center.

[0139] The cloud control center is used to receive the first attribute information for the first inspection target, and use the first attribute information and the resource information of the candidate drones to jointly determine the first execution cost of the candidate drones corresponding to the first inspection target, and send the first execution cost to the candidate drones, which can be any one of the drones.

[0140] The drone is used to receive the first execution cost issued by the cloud control center, determine the task bid gain when the drone performs the first inspection task, and send the task bid gain to the cloud control center. The first inspection task is used to characterize the inspection of the first inspection target.

[0141] The cloud control center is also used to identify the drone corresponding to the largest task bid gain as the target drone, and to issue an instruction to the target drone to perform the first inspection task, so that the target drone can collect a second inspection image of the first inspection target and send it to the cloud control center.

[0142] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0143] The following is a detailed reference. Figure 6This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0144] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0145] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the tethered airship and unmanned aerial vehicle linkage inspection method of the embodiments of the present invention.

[0146] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0147] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the tethered airship and UAV linkage inspection method shown in the above embodiments is implemented.

[0148] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0149] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for joint inspection of tethered airships and unmanned aerial vehicles, characterized in that, Applied to a cloud-based control center, the method includes: Receive first attribute information for the first inspection target sent by the tethered airship, wherein the first attribute information is obtained by the tethered airship based on the first inspection image it has collected; Obtain the current resource information of each drone; For any candidate drone among the drones, the first execution cost of the candidate drone corresponding to the first inspection target is jointly determined by using the first attribute information and the resource information of the candidate drone. The first execution cost is sent to the candidate drone, so that the candidate drone determines the task bidding gain based on its corresponding first execution cost; Receive the task bid gain sent by each of the drones, and determine the drone corresponding to the largest task bid gain as the target drone; An instruction is issued to the target drone to execute a first inspection task, so that the target drone can collect a second inspection image of the first inspection target and send it to the cloud control center. The first inspection task is used to characterize the inspection of the first inspection target.

2. The method according to claim 1, characterized in that, The step of jointly determining the first execution cost of the candidate drone corresponding to the first inspection target using the first attribute information and the resource information of the candidate drone includes: Using the location information of the first inspection target and the location information of the candidate UAV, the normalized distance between the first inspection target and the candidate UAV is determined; The available power of the candidate drones is normalized using the maximum available power to obtain the normalized available power of the candidate drones. The maximum available power is the sum of the available power of all the drones. Using the maximum number of tasks, the current number of tasks of the candidate drone is normalized to obtain the normalized conflict coefficient corresponding to the candidate drone. The maximum number of tasks is the maximum number of tasks that the candidate drone can execute, and the current number of tasks is the number of tasks that the drone has accepted but not yet executed. The first execution cost is determined by fusing the normalized distance, the normalized available power, and the normalized conflict coefficient.

3. The method according to claim 2, characterized in that, The step of jointly determining the first execution cost of the candidate drone corresponding to the first inspection target using the first attribute information and the resource information of the candidate drone further includes: Obtain the waiting time of the candidate drone when it performs the first inspection task; The waiting time of the candidate drones is normalized using the maximum waiting time to obtain the normalized waiting time. The maximum waiting time is the maximum value of the waiting time among all the drones. The first execution cost is determined by fusing the normalized distance, the normalized available power, the normalized conflict coefficient, and the normalized waiting time.

4. The method according to claim 1, characterized in that, The process by which the candidate drone determines the mission bidding gain based on its corresponding first execution cost includes: Using the first execution cost, a first total cost is determined when the candidate UAV performs the first inspection task and the second inspection task, wherein the second inspection task is an inspection task that the candidate UAV has currently accepted but has not yet executed; Obtain the second total cost when the candidate UAV performs the second inspection task; The task bidding gain is determined by using the difference between the second total cost and the first total cost corresponding to the candidate drone.

5. The method according to claim 4, characterized in that, The second inspection task corresponds to a second inspection target, and the candidate UAV corresponds to a second execution cost for the second inspection target; The step of determining the first total cost when the candidate UAV performs the first inspection task and the second inspection task using the first execution cost includes: The first cost is determined by fusing the first execution cost with the second execution cost; The penalty coefficient corresponding to the candidate UAV is determined by using the total number of the first inspection task and the second inspection task; The first total cost is obtained by fusing the first cost with the penalty coefficient.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: If the communication quality between the cloud control center and the drone is lower than a preset threshold, the drone closest to the inspection target will be identified as the target drone.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: If any two of the drones have the same task bid gain, the target drone is determined according to a preset indicator, which is the priority of the drone or the available power of the drone.

8. A joint inspection system for tethered airships and unmanned aerial vehicles, characterized in that, The system includes: A tethered airship is used to collect a first inspection image, perform target detection on the first inspection image to obtain a first inspection target and the first attribute information of the first inspection target, and send the first attribute information to the cloud control center. The cloud control center is used to receive first attribute information for the first inspection target, and use the first attribute information and the resource information of the candidate drones to jointly determine the first execution cost of the candidate drones corresponding to the first inspection target, and send the first execution cost to the candidate drones, wherein the candidate drones are any one of the drones. The drone is used to receive the first execution cost issued by the cloud control center, determine the task bid gain when the drone performs the first inspection task, and send the task bid gain to the cloud control center. The first inspection task is used to represent the inspection of the first inspection target. The cloud control center is also used to identify the drone corresponding to the largest task bid gain as the target drone, and to issue an instruction to the target drone to execute the first inspection task, so that the target drone can collect a second inspection image for the first inspection target and send it to the cloud control center.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the joint inspection method of tethered airship and UAV as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the tethered airship and unmanned aerial vehicle linkage inspection method according to any one of claims 1 to 7.

Images