Unmanned aerial vehicle management and control system, method, device, related equipment, storage medium and computer program product

Abstract

The application discloses an unmanned aerial vehicle management and control system, method, device, related equipment, storage medium and computer program product. The method comprises the following steps: an unmanned aerial vehicle AI self-management center receives one or more to-be-executed businesses issued by a cloud platform; based on the one or more to-be-executed businesses, a target to-be-executed business suitable for a target unmanned aerial vehicle is matched; the target unmanned aerial vehicle represents an unmanned aerial vehicle in a state of empty load among the one or more unmanned aerial vehicles, and the target to-be-executed business meets the demand of the target unmanned aerial vehicle for mixed business guarantee; and optimization of communication resource configuration is performed based on the target to-be-executed business, so that the communication target of the target to-be-executed business is realized.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a drone management system, method, apparatus, related equipment, storage medium and computer program product. Background Technology

[0002] With the development of the Internet of Things (IoT), drones (also known as unmanned aerial vehicles, UAVs) are taking on increasingly more roles and responsibilities, playing a vital role in various fields. Therefore, to manage and optimize these operations more efficiently, drone systems must be able to flexibly respond to various complex communication environments and business needs. Utilizing artificial intelligence (AI) technology for intelligent support of drone operations is particularly important.

[0003] However, in drone service support solutions for related technologies, the design of drone communication and flight control systems is typically tailored to a single business need, such as food delivery, logistics transportation, or medical supply delivery. It is evident that while this drone service support solution can meet the needs of specific scenarios, it lacks flexibility and scalability, easily leading to wasted airspace resources and low operational efficiency. Furthermore, the scope of application of this drone service support solution is narrow, unable to cope with more complex mixed business needs, resulting in low service support capabilities. Summary of the Invention

[0004] To address the technical problems existing in related technologies, embodiments of this application provide an unmanned aerial vehicle (UAV) management system, method, apparatus, related equipment, storage medium, and computer program product.

[0005] To achieve the above objectives, the technical solution of this application embodiment is implemented as follows:

[0006] In a first aspect, embodiments of this application provide a drone management system, the system comprising: a cloud platform and a drone AI self-management center, the drone AI self-management center being equipped on one or more drones, and the drone AI self-management center including a service matching module and a communication resource configuration module; wherein;

[0007] The service matching module is used to receive one or more services to be executed from the cloud platform, and match a suitable target service to be executed for the target drone based on the one or more services to be executed; the target drone represents the drone in the one or more drones that is in an empty state, and the target service to be executed meets the requirements of the target drone for mixed service protection;

[0008] The communication resource configuration module is used to optimize the communication resource configuration based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

[0009] Secondly, embodiments of this application provide a drone management method applied to a drone AI self-management center, wherein the drone AI self-management center is equipped on one or more drones, and the method includes:

[0010] Receive one or more pending business requests from the cloud platform;

[0011] Based on the one or more pending services, a suitable target pending service is matched for the target drone; the target drone represents the drone in the one or more drones that is in an idle state, and the target pending service meets the requirements of the target drone for hybrid service assurance;

[0012] Optimize the configuration of communication resources based on the target service to be executed, so as to achieve the communication objective of the target service to be executed.

[0013] Thirdly, this application also provides another method for controlling unmanned aerial vehicles (UAVs) applied to a cloud platform, the method comprising:

[0014] One or more pending tasks are issued to the UAV AI self-management center, so that the UAV AI self-management center can match a target pending task suitable for the target UAV based on the one or more pending tasks; and optimize the configuration of communication resources based on the target pending task to achieve the communication goal of the target pending task.

[0015] The drone AI self-management center is equipped on one or more drones, the target drone represents the drone in an empty state among the one or more drones, and the target service to be executed meets the needs of the target drone for hybrid service assurance.

[0016] Fourthly, embodiments of this application provide a drone management device applied to a drone AI self-management center, wherein the drone AI self-management center is equipped on one or more drones, and the device includes:

[0017] The first receiving unit is used to receive one or more pending business operations issued by the cloud platform;

[0018] The matching unit is used to match a target service to be executed that is suitable for the target drone based on the one or more services to be executed; the target drone represents the drone in the one or more drones that is in an idle state, and the target service to be executed meets the requirements of the target drone for hybrid service assurance;

[0019] The optimization unit is used to optimize the configuration of communication resources based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

[0020] Fifthly, this application also provides another drone control device applied to a cloud platform, the device comprising:

[0021] The first sending unit is configured to send one or more pending services to the UAV AI self-management center, so that the UAV AI self-management center can match a target pending service suitable for the target UAV based on the one or more pending services; and optimize the communication resource configuration based on the target pending service to achieve the communication target of the target pending service.

[0022] The drone AI self-management center is equipped on one or more drones, the target drone represents the drone in an empty state among the one or more drones, and the target service to be executed meets the needs of the target drone for hybrid service assurance.

[0023] Sixthly, embodiments of this application provide a drone AI self-management center, including: a first processor and a first memory for storing computer programs capable of running on the first processor;

[0024] Wherein, when the first processor is used to run the computer program, it executes the steps of the drone control method on the drone AI self-management center side as described in the embodiments of this application.

[0025] In a seventh aspect, embodiments of this application provide a cloud platform, including: a second processor and a second memory for storing computer programs capable of running on the second processor;

[0026] Wherein, when the second processor is used to run the computer program, it executes the steps of the cloud platform-side drone management method described in the embodiments of this application.

[0027] Eighthly, this application embodiment also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the drone AI self-management center-side drone control method described in this application embodiment, or implements the steps of the cloud platform-side drone control method described in this application embodiment.

[0028] Ninthly, embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the drone AI self-management center-side drone control method described in embodiments of this application, or implements the steps of the cloud platform-side drone control method described in embodiments of this application.

[0029] The UAV management system, method, apparatus, related equipment, storage medium, and computer program products provided in this application embodiment include a UAV AI self-management center that receives one or more pending services from a cloud platform; the UAV AI self-management center is equipped on one or more UAVs; based on the one or more pending services, a suitable target pending service is matched for the target UAV; the target UAV represents a UAV in an empty state among the one or more UAVs, and the target pending service meets the target UAV's requirements for mixed service support; communication resource configuration is optimized based on the target pending service to achieve the communication goal of the target pending service. By adopting the solution of this application embodiment, through the UAV AI self-management center equipped on the UAV, diverse services issued by the cloud platform are intelligently matched with suitable target pending services for the target UAV, and communication resource configuration is optimized based on the target pending service to achieve the communication goal of the target pending service. This not only improves the utilization efficiency of airspace resources and increases operational efficiency, but also meets the intelligent and flexible adaptive adjustment requirements when facing diverse services, i.e., it can cope with more complex mixed service requirements and improve service support capabilities. Attached Figure Description

[0030] Figure 1 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 1 ;

[0031] Figure 2 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 2 ;

[0032] Figure 3 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 3 ;

[0033] Figure 4 This is a schematic diagram of the composition structure of the unmanned aerial vehicle (UAV) control system according to an embodiment of this application;

[0034] Figure 5 A schematic diagram of the architecture of an intelligent drone management and control system for hybrid service assurance, as shown in an embodiment of this application.

[0035] Figure 6 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 4 ;

[0036] Figure 7 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 5 ;

[0037] Figure 8This is a schematic diagram of the composition and structure of the unmanned aerial vehicle (UAV) control device according to an embodiment of this application. Figure 1 ;

[0038] Figure 9 This is a schematic diagram of the composition and structure of the unmanned aerial vehicle (UAV) control device according to an embodiment of this application. Figure 2 ;

[0039] Figure 10 This is a schematic diagram of the hardware composition structure of the drone AI self-management center according to an embodiment of this application;

[0040] Figure 11 This is a schematic diagram of the hardware structure of the cloud platform according to an embodiment of this application. Detailed Implementation

[0041] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0043] With the development of the Internet of Things (IoT), drones are taking on more and more roles and businesses, playing an important role in various fields. From agricultural monitoring and environmental monitoring to food delivery, logistics transportation, emergency rescue, and security, the application scope of drones is expanding daily. Furthermore, the services offered by drones are becoming increasingly diverse, with different services, such as low-latency services and high-bandwidth services, having different requirements for communication services, as shown in Table 1 below.

[0044]

[0045]

[0046] Table 1

[0047] Therefore, in order to manage and optimize these operations more efficiently, drone systems are required to be able to flexibly respond to various complex communication environments and business needs. It is particularly important to use AI technology for intelligent support of drone operations.

[0048] In related technologies, the means of ensuring unmanned aerial vehicle (UAV) operations include:

[0049] 1. Dedicated hardware configuration: Design the drone's hardware system for specific business needs, such as increasing payload capacity, endurance, and flight speed to meet specific business requirements.

[0050] 2. Software algorithm optimization: Improve the efficiency and safety of UAVs by improving flight control and path planning algorithms.

[0051] 3. Network communication support: Provide customized communication services for specific businesses to ensure the stability and reliability of data transmission.

[0052] 4. Ground station monitoring system: Establish a dedicated ground control center to monitor the status of the UAV in real time and remotely control it as needed.

[0053] In drone service support solutions for related technologies, the design of drone communication and flight control systems is usually tailored to a single business need, such as food delivery, express delivery, or medical supply delivery.

[0054] However, this drone service support solution has the following drawbacks:

[0055] 1. Waste of resources and low operational efficiency: While existing methods can meet the needs of specific scenarios, they lack flexibility and scalability. For example, during delivery, drones carry goods on their outbound journey but often return empty, which not only wastes airspace resources but also increases energy consumption and reduces operational efficiency.

[0056] 2. Narrow applicability and low operational support capability: Due to the lack of a flexible resource scheduling mechanism, these drones often cannot respond quickly and adjust their operations when unexpected situations or urgent needs arise. Therefore, although the related technologies ensure the completion of operations under single business needs, there is a waste of resources, and they cannot cope with more complex mixed business needs.

[0057] Based on this, this application proposes a drone management method. In various embodiments of this application, by equipping the drone with a drone AI self-management center, the diverse services issued by the cloud platform are intelligently matched with target services to be executed by the target drone, and the communication resource configuration is optimized based on the target services to be executed, so as to achieve the communication goals of the target services to be executed. In this way, not only can the utilization efficiency of airspace resources be improved and the operational efficiency be increased, but also the intelligent and flexible adaptive adjustment needs in the face of diverse services can be met, that is, it can cope with more complex mixed service needs and improve service assurance capabilities.

[0058] This application provides a method for controlling unmanned aerial vehicles (UAVs). This method is applied to a UAV AI self-management center, which is equipped on one or more UAVs. Figure 1 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 1 ;like Figure 1 As shown, the method includes:

[0059] Step 101: Receive one or more pending business requests from the cloud platform.

[0060] In this embodiment, the cloud platform can be a centralized management platform on the cloud side, which can be deployed on a service provider (SP). Here, the centralized management platform includes a service delivery module, a drone management module, and a visualization module. The service delivery module is responsible for delivering various services (i.e., one or more of the aforementioned services to be executed) to the airborne drone (i.e., the target drone). The drone management module is responsible for determining the target drone's services to be executed (i.e., the target services to be executed) based on the matching score and matching results, as well as the drone's take-off and landing control, etc. The visualization module is used to manage and record information such as the flight trajectories, completed services, and services in progress of multiple drones.

[0061] Here, the drone AI self-management center that executes the drone management method of this application embodiment is equipped on one or more drones. It can be understood that the drone management method of this application embodiment is aimed at multiple drones equipped with drone AI self-management centers. That is, in the face of diverse business needs under low-altitude networks, a drone AI self-management center with inherent capabilities is designed to realize differentiated configuration based on business and intelligently manage the communication and flight strategies of drones.

[0062] It should be noted that the communication strategy of intelligent control drones can be understood as intelligently adjusting the signal transmission power, bandwidth and other communication parameters between the drone and the 5G (5th Generation Mobile Communication Technology) base station (i.e., the next generation node base (gNB)); the flight strategy of intelligent control drones can be understood as intelligently adjusting the drone's direction, angle, speed and other flight parameters.

[0063] Step 102: Based on the one or more pending services, match the target pending services suitable for the target drone.

[0064] In this embodiment of the application, the target drone refers to a drone that is in an unloaded state among the one or more drones, and may also be referred to as an unloaded drone.

[0065] In this embodiment, the target service to be executed meets the requirements of the target drone for hybrid service assurance. That is to say, the drone management method in this embodiment is no longer only for a single service requirement, but for more complex hybrid service assurance requirements, such as two or more of the following: food delivery, logistics transmission, environmental monitoring, medical supply delivery, urban security, geographic surveying and mapping, and virtual reality (VR) live streaming. Generally speaking, different business application scenarios of drones have different communication requirements such as low latency and high bandwidth, and different flight requirements such as speed, stability, trajectory periodic circling, and intelligent trajectory planning.

[0066] In practical applications, the drone AI self-management center uses a business matching module to assign matching scores to one or more pending business tasks and feeds the results back to the cloud platform (such as a centralized management platform). The cloud platform then determines the target business task based on the feedback information.

[0067] Based on this, in one embodiment, matching a target service to be executed suitable for the target drone based on the one or more services to be executed includes: determining a matching score corresponding to the one or more services to be executed, and sending the matching score to the cloud platform;

[0068] The matching score represents the degree of matching between the one or more services to be executed and the target drone, and the matching score is used by the cloud platform to determine the target service to be executed.

[0069] Here, the drone AI self-management center can select one or more pending tasks issued by the cloud platform based on the target drone's own location and communication capabilities, while also considering factors such as subsequent flight energy consumption and flight path. It can intelligently match the pending task most suitable for the current target drone, i.e., the target pending task, thereby improving the system's resource utilization efficiency and business execution efficiency.

[0070] Here, the drone AI self-management center matches one or more pending tasks issued by the cloud platform with the target drone based on the pending task identifier. The matching degree is used to determine the corresponding matching score. In other words, the matching degree score is assigned to one or more pending tasks according to the matching degree. For example, a_UAVID_match = 95 (representing the matching degree score between pending task a and the target drone UAVID) and b_UAVID_match = 85 (representing the matching degree score between pending task b and the target drone UAVID).

[0071] It should be noted that the process by which the cloud platform determines the target business to be executed based on the matching score can be understood by referring to the technical solution described in the cloud platform-side drone management method below, and will not be repeated here.

[0072] Step 103: Optimize the configuration of communication resources based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

[0073] In practical applications, since the communication goals of services in different application scenarios are different, such as high capacity, low latency, high reliability, wide coverage, high mobility, energy saving, etc., the drone AI self-management center can select the communication method and optimize the configuration of communication resources according to the target business to be executed by the target drone that is currently matched with the target drone.

[0074] Based on this, in one embodiment, optimizing the communication resource configuration based on the target service to be executed to achieve the communication objective of the target service to be executed includes: obtaining the execution service instruction corresponding to the target service to be executed; and optimizing the communication resource configuration of the target UAV in response to the execution service instruction to achieve the communication objective of the target service to be executed; the communication resource configuration includes one or more of the following: communication parameters; flight parameters.

[0075] Here, communication parameters include one or more of the following parameters: signal transmission power and bandwidth between the UAV and gNB; flight parameters include one or more of the following parameters: UAV direction, angle, and speed.

[0076] In practical applications, considering the changes in the drone's own parameters during its flight trajectory and the different capabilities of the base station, it is necessary to perform AI-distributed intelligent switching of multiple drones, that is, there may be a situation where a service may be executed alternately by different drones.

[0077] Based on this, in one embodiment, the method further includes: performing cell-level distributed service switching when it is determined that the target UAV meets the switching conditions.

[0078] Here, the target drone meeting the switching conditions means that the target drone's current communication capability with the base station or the changes in its own parameters during the flight trajectory make it unable to independently complete the target service to be performed. Therefore, the target service to be performed needs to be completed by different drones alternately. At this time, AI distributed intelligent switching of multiple drones is required.

[0079] In one embodiment, after the cell-level distributed service handover is performed, the method further includes: outputting the service handover result, and reporting the service handover result to the communication resource configuration module in the cloud platform and the UAV AI self-management center, so that the communication resource configuration module can re-optimize the communication resource configuration based on the service handover result.

[0080] Here, the communication resource configuration module can also be called the communication resource differentiation configuration module. In practical applications, when the service switching result indicates that the target service to be executed needs to be intelligently switched by multiple UAVs through AI distributed services, the UAV AI self-management center reports the service switching result to the communication resource configuration module. The communication resource configuration module then reconfigures the communication resources of the target UAV, that is, reconfigures one or more of the following parameters of the target UAV: ​​communication parameters; flight parameters. Among them, the communication parameters include one or more of the following parameters: signal transmission power and bandwidth between the target UAV and the gNB; the flight parameters include one or more of the following parameters: direction, angle, and speed of the target UAV.

[0081] Accordingly, this application also provides another method for controlling unmanned aerial vehicles (UAVs), which is applied to a cloud platform. Figure 2 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 2 ;like Figure 2 As shown, the method includes:

[0082] Step 201: Issue one or more pending services to the UAV AI self-management center, so that the UAV AI self-management center can match a target pending service suitable for the target UAV based on the one or more pending services; and optimize the communication resource configuration based on the target pending service to achieve the communication goal of the target pending service.

[0083] In this embodiment, the cloud platform can be a centralized management platform on the cloud side, which can be deployed on the SP. Here, the centralized management platform includes a service delivery module, a drone management module, and a visualization module. The service delivery module is responsible for delivering various services (i.e., one or more of the aforementioned services to be executed) to the airborne drone (i.e., the target drone). The drone management module is responsible for determining the target drone's services to be executed (i.e., the target services to be executed) based on the matching score and matching results, as well as the drone's take-off and landing control, etc. The visualization module is used to manage and record information such as the flight trajectories, completed services, and services in progress of multiple drones.

[0084] In this embodiment, the UAV AI self-management center is equipped on one or more UAVs. The target UAV represents the UAV in an idle state among the one or more UAVs, and can also be called an idle UAV. The target service to be executed satisfies the target UAV's needs for hybrid service assurance. That is to say, the UAV management method in this embodiment is no longer only for a single service need, but for more complex hybrid service assurance needs, such as two or more of the following: food delivery, logistics transmission, environmental monitoring, medical supply delivery, urban security, geographic surveying, VR live streaming, etc. Generally speaking, different UAV service application scenarios have different communication requirements such as low latency and high bandwidth, and different flight requirements such as speed, stability, trajectory periodicity, and intelligent trajectory planning.

[0085] In practical applications, after completing the previous pending task, the target drone reports its idle status to the cloud platform, such as the centralized management platform, and returns the identifier (ID, IDentity) of the base station it accessed.

[0086] Based on this, in one embodiment, before issuing one or more pending services to the drone AI self-management center, the method further includes: receiving the idle status sent by the target drone and the base station identifier to which the target drone is connected.

[0087] It should be noted that in related technologies, the trajectory of drones performing business is cyclical. For example, in the process of logistics delivery, the drone carries business items on the outbound journey, but the business is often empty on the return journey, resulting in the drone being unloaded. However, the embodiments of this application avoid the situation of the drone being unloaded by feeding back the idle status of the target drone to the cloud platform and executing the next business in a timely manner. At the same time, the drone's trajectory is planned more intelligently, instead of returning directly to the origin after reaching the destination.

[0088] In practical applications, after receiving the base station ID that the target drone has accessed, the cloud platform can determine the regional location of the target drone based on the base station ID, and send optional services to be executed to the target drone based on this.

[0089] Based on this, in one embodiment, the step of sending one or more pending services to the UAV AI self-management center includes: sending one or more pending services to the UAV AI self-management center based on the base station identifier accessed by the target UAV.

[0090] Specifically, the step of issuing one or more pending services to the drone AI self-management center based on the base station identifier accessed by the target drone includes: determining the regional location information of the target drone based on the base station identifier accessed by the target drone; and issuing the one or more pending services to the drone AI self-management center based on the regional location information of the target drone.

[0091] It should be noted that different drones may receive overlapping pending tasks due to geographical proximity. For example, drone A may receive pending tasks a, b, and c from the cloud platform, while drone B may receive pending tasks c, d, and e from the cloud platform. Thus, drones A and B may have overlapping pending task c due to their geographical proximity.

[0092] In practical applications, the drone AI self-management center uses a business matching module to assign matching scores to one or more pending business tasks and feeds the results back to the cloud platform (such as a centralized management platform). The cloud platform then determines the target business task based on the feedback information.

[0093] Based on this, in one embodiment, after the cloud platform issues one or more pending services to the UAV AI self-management center, the method further includes: receiving a matching score sent by the UAV AI self-management center; the matching score characterizes the score corresponding to the degree of matching between the one or more pending services and the target UAV; and determining the target pending service based on the matching score.

[0094] Here, the drone AI self-management center can select one or more pending tasks issued by the cloud platform based on the target drone's own location and communication capabilities, while also considering factors such as subsequent flight energy consumption and flight path. It can intelligently match the pending task most suitable for the current target drone, i.e., the target pending task, thereby improving the system's resource utilization efficiency and business execution efficiency.

[0095] In practical applications, in one embodiment, determining the target service to be executed based on the matching score includes: determining, based on the matching score, whether there is a situation where the same service to be executed is selected by multiple target drones; and determining the target service to be executed based on the determination result and the matching score.

[0096] The following sections will explain in detail the process of determining the target business to be executed from two aspects: single business with multiple scenarios and single terminal with multiple businesses.

[0097] For single-service, multi-scenario applications, the target drone has the capability to be used in multiple scenarios, but it is only responsible for handling one type of service at any given time. Furthermore, when facing services from different communication targets, the target drone needs to have the ability to adjust the communication method as needed.

[0098] In one embodiment, determining the target service to be executed based on the judgment result and the matching score includes:

[0099] If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the pre-matching result; the pre-matching result is obtained by determining the highest matching score based on the matching score of each target drone.

[0100] When the judgment result indicates that the same service to be executed is selected by multiple target drones, the target service to be executed suitable for each of the target drones is determined based on the comparison result of the pre-matching result and the matching degree score for the same service to be executed.

[0101] Here's an example: in a single-service, multi-scenario scenario, UAV A receives pending services a, b, and c from the cloud platform, while UAV B receives pending services c, d, and e from the cloud platform.

[0102] Assumption 1: The cloud platform receives the matching scores of pending services a, b, and c with UAV A from the UAV AI self-management center (e.g., a_UAV A_match = 90, b_UAV A_match = 80, c_UAV A_match = 70), and the matching scores of pending services c, d, and e with UAV B from the UAV AI self-management center (e.g., c_UAVB_match = 90, d_UAV B_match = 80, e_UAV B_match = 70). Based on the ranking of the matching scores of each UAV, it can be seen that the highest matching score of UAV A is 90, and the corresponding pending service is a (i.e., the pre-matching result of UAV A); the highest matching score of UAV B is 90, and the corresponding pending service is c (i.e., the pre-matching result of UAV B). At this time, based on the pre-matching results of each UAV, it can be determined that the target pending service suitable for UAV A is a, and the target pending service suitable for UAV B is c. There is no situation where the same service is selected by multiple UAVs.

[0103] Assumption 2: The cloud platform receives the matching scores of pending tasks a, b, and c with UAV A from the UAV AI self-management center (e.g., a_UAV A_match = 70, b_UAV A_match = 80, c_UAV A_match = 95), and the matching scores of pending tasks c, d, and e with UAV B from the UAV AI self-management center (e.g., c_UAVB_match = 90, d_UAV B_match = 80, e_UAV B_match = 70). Based on the ranking of the matching scores of each UAV, it can be seen that the highest matching score of UAV A is 95, corresponding to pending task c (i.e., the pre-matching result of UAV A); the highest matching score of UAV B is 90, corresponding to pending task c (i.e., the pre-matching result of UAV B). Therefore, it can be concluded that the pre-matching result of UAV A and UAV B are... The pre-matching results of B are all pending service c. At this time, there is a situation where the same service is selected by multiple drones. Then, for pending service c, the matching score between pending service c and UAV A (c_UAV A_match = 95) and the matching score between pending service c and UAV B (c_UAV B_match = 90) are compared. Since 95 > 90, it can be determined that the target pending service suitable for UAV A is c, and the target pending service suitable for UAV B is d.

[0104] Unlike single-service, multi-scenario deployments, single-terminal, multi-service deployments allow the target drone to simultaneously perform two types of services. For example, during logistics transportation, it can also simultaneously perform image or video transmission for urban security. Similarly, the target drone needs to be able to adjust its communication methods as needed to meet the diverse communication objectives.

[0105] In one embodiment, determining the target service to be executed based on the judgment result and the matching score includes:

[0106] If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the pre-matching result; the pre-matching result is obtained by ranking multiple target matching scores based on the matching score of each target drone, and the multiple target matching scores meet the matching score threshold.

[0107] When the judgment result indicates that the same service to be executed is selected by multiple target drones, the target service to be executed suitable for each of the target drones is determined based on the comparison result of the pre-matching result and the matching degree score for the same service to be executed.

[0108] Here's an example: in a single-terminal, multi-service scenario, UAV A receives pending services a, b, and c from the cloud platform, while UAV B receives pending services c, d, and e from the cloud platform.

[0109] Assumption 1: The cloud platform receives the matching scores of pending tasks a, b, and c with UAV A from the UAV AI self-management center (e.g., a_UAV A_match = 90, b_UAV A_match = 80, c_UAV A_match = 70), and the matching scores of pending tasks c, d, and e with UAV B from the UAV AI self-management center (e.g., c_UAVB_match = 90, d_UAV B_match = 80, e_UAV B_match = 70). Based on the matching scores of each UAV and the matching score threshold, it can be determined that multiple target matching scores for UAV A are 90 and 80. The matching score threshold can be preset according to actual needs. For example, setting the matching score threshold to 80 corresponds to pending tasks a and b (i.e., the pre-matching results of UAV A). Similarly, it can be determined that multiple target matching scores for UAV B are 90 and 80, corresponding to pending tasks c and d (i.e., the UAV B's matching results). (Pre-matching result of B) At this time, there is no situation where the same service is selected by multiple drones. The pre-matching results of UAV A and UAV B are directly issued. Then, based on the pre-matching results of each drone, the target services to be executed that are suitable for UAV A are a and b, and the target services to be executed that are suitable for UAV B are c and d.

[0110] Assumption 2: The cloud platform receives the matching scores of pending tasks a, b, and c with UAV A from the UAV AI self-management center (e.g., a_UAV A_match = 70, b_UAV A_match = 80, c_UAV A_match = 95), and the matching scores of pending tasks c, d, and e with UAV B from the UAV AI self-management center (e.g., c_UAVB_match = 90, d_UAV B_match = 80, e_UAV B_match = 70). Based on the matching scores of each UAV and the matching score threshold, it can be determined that multiple target matching scores for UAV A are 95 and 80. The matching score threshold can be preset according to actual needs. For example, setting the matching score threshold to 80 corresponds to pending tasks b and c (i.e., the pre-matching results of UAV A). Similarly, it can be determined that multiple target matching scores for UAV B are 90 and 80, corresponding to pending tasks c and d (i.e., the UAV B's matching results). From the pre-matching result of B, we can see that the pre-matching results of UAV A and UAV B are both for the service to be executed, c. There is a situation where the same service is selected by multiple UAVs. Then, for the service to be executed, we further compare the matching score between the service to be executed and UAV A (c_UAV A_match = 95) and the matching score between the service to be executed and UAV B (c_UAV B_match = 90). Since 95 > 90, we can determine that the target services to be executed for UAV A are c and b, and the target service to be executed for UAV B is d.

[0111] This application also provides another method for drone management, which is an interaction method between a drone AI self-management center and a cloud platform. Figure 3 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 3 ;like Figure 3 As shown, the method includes:

[0112] Step 301: The cloud platform issues one or more pending tasks to the drone AI self-management center.

[0113] In this embodiment of the application, the drone AI self-management center is equipped on one or more drones, and the cloud platform can be a centralized management platform on the cloud side, which can be deployed on the SP.

[0114] Step 302: The drone AI self-management center receives one or more pending tasks from the cloud platform.

[0115] Step 303: The UAV AI self-management center matches the target UAV with the target target service based on one or more of the pending services.

[0116] In this embodiment of the application, the target drone represents a drone that is in an unloaded state among the one or more drones, and the target service to be executed meets the requirements of the target drone for ensuring mixed services.

[0117] Step 304: The UAV AI self-management center optimizes the communication resource configuration based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

[0118] It should be noted that the specific process of drone AI self-management center and cloud platform completing drone control has been detailed above and will not be repeated here.

[0119] By adopting the technical solution of this application embodiment, the UAV AI self-management center equipped on the UAV can intelligently match the diverse services issued by the cloud platform with the target UAV's target services to be executed, and optimize the configuration of communication resources based on the target services to be executed, so as to achieve the communication goals of the target services to be executed. In this way, not only can the utilization efficiency of airspace resources be improved and the operational efficiency be increased, but also the intelligent and flexible adaptive adjustment needs in the face of diverse services can be met, that is, it can cope with more complex mixed service needs and improve service assurance capabilities.

[0120] To implement the drone control method of this application embodiment, this application embodiment also provides a drone control system. Figure 4 This is a schematic diagram of the composition structure of the unmanned aerial vehicle (UAV) control system according to an embodiment of this application, as shown below. Figure 4 As shown, the system includes: a cloud platform 41 and a drone AI self-management center 42, the drone AI self-management center 42 being equipped on one or more drones, and the drone AI self-management center 42 including a service matching module and a communication resource configuration module; wherein,

[0121] The service matching module is used to receive one or more pending services issued by the cloud platform 41, and match a suitable target pending service for the target drone based on the one or more pending services; the target drone represents the drone in the one or more drones that is in an empty state, and the target pending service meets the needs of the target drone for mixed service protection.

[0122] The communication resource configuration module is used to optimize the communication resource configuration based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

[0123] In one embodiment, the cloud platform 41 includes a drone management module and a service delivery module; wherein,

[0124] The drone management module is used to receive the idle status sent by the target drone and the base station identifier to which the target drone is connected;

[0125] The service delivery module is used to deliver one or more services to be executed to the target drone.

[0126] In one embodiment, the service delivery module is specifically used for:

[0127] Based on the base station identifier accessed by the target drone, the regional location information of the target drone is determined; based on the regional location information of the target drone, one or more services to be executed are sent to the target drone.

[0128] In one embodiment, the service matching module is specifically used for:

[0129] The matching score corresponding to the one or more pending services is determined, and the matching score is sent to the drone management module in the cloud platform; wherein, the matching score represents the score corresponding to the degree of matching between the one or more pending services and the target drone, and the matching score is used by the drone management module to determine the target pending service.

[0130] In one embodiment, the drone management module is further configured to:

[0131] The system receives the matching score sent by the service matching module; based on the matching score, it determines whether the same service to be executed is selected by multiple target drones; based on the determination result and the matching score, it determines the target service to be executed and sends the target service to be executed to the communication resource configuration module.

[0132] In one embodiment, the drone management module is specifically used for:

[0133] If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the pre-matching result; the pre-matching result is obtained by ranking the highest matching score among the matching scores of each target drone; if the judgment result indicates that a single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the comparison result between the pre-matching result and the matching score for the same service to be executed.

[0134] In another embodiment, the drone management module is further specifically used for:

[0135] If the judgment result indicates that no single service to be executed is selected by multiple target drones, a suitable target service to be executed for each target drone is determined based on the pre-matching result. The pre-matching result is obtained by ranking multiple target matching scores based on the matching scores of each target drone, and the multiple target matching scores meet the matching score threshold. If the judgment result indicates that a single service to be executed is selected by multiple target drones, a suitable target service to be executed for each target drone is determined based on the comparison result between the pre-matching result and the matching score for the same service to be executed.

[0136] In one embodiment, the communication resource configuration module is specifically used for:

[0137] Obtain the execution service instruction corresponding to the target service to be executed; in response to the execution service instruction, optimize the communication resource configuration of the target UAV to achieve the communication objective of the target service to be executed; the communication resource configuration includes one or more of the following: communication parameters; flight parameters.

[0138] In one embodiment, the drone AI self-management center 42 further includes a service switching module; wherein,

[0139] The service switching module is used to switch cell-level distributed services when it is determined that the target drone meets the switching conditions.

[0140] In one embodiment, the service switching module is further configured to output the service switching result and report the service switching result to the drone management module and communication resource configuration module in the cloud platform 41;

[0141] The communication resource configuration module is also used to re-optimize the communication resource configuration based on the service switching result.

[0142] It should be noted that the specific process of cloud platform 41 and drone AI self-management center 42 completing the control of drones has been detailed above and will not be repeated here.

[0143] The present application will now be described in detail with reference to application examples.

[0144] While existing drone service support solutions for related technologies ensure the completion of services under single business needs, they suffer from resource waste and are unable to cope with more complex mixed business needs. To address this technical problem, this application proposes a drone intelligent management and control system for mixed business support (corresponding to the aforementioned drone management and control system). Drones can readjust their communication parameters such as signal transmission power and bandwidth, as well as flight parameters such as direction, angle, and speed, based on different business needs and their own status information through the equipped drone AI self-management center. This improves the utilization efficiency of airspace resources, enhances operational efficiency, and meets the intelligent and flexible adaptive adjustment needs when facing diverse business needs.

[0145] In this application, the application scenarios of drones include logistics delivery, environmental monitoring, urban security, geographic surveying and mapping, VR live streaming, etc. Among them, different application scenarios have different communication requirements such as low latency and high bandwidth, and different flight requirements such as speed, stability, trajectory periodic circling, and intelligent trajectory planning.

[0146] In response to the diverse business needs in low-altitude networks, this application designs an AI-powered self-management center for unmanned aerial vehicles (UAVs) with inherent capabilities to achieve differentiated configuration based on business needs and intelligent control of UAV communication and flight strategies.

[0147] Figure 5 This is a schematic diagram of the architecture of the intelligent management and control system for hybrid service assurance according to an embodiment of this application, as shown below. Figure 5 As shown, the intelligent drone management and control system for hybrid business support in this application includes a centralized management platform (corresponding to the aforementioned cloud platform) and multiple drones equipped with drone AI self-management centers.

[0148] Centralized Management Platform: Deployable on SP, this centralized management platform includes a service delivery module, a drone management module, and a visualization module. The service delivery module is responsible for delivering various services (i.e., one or more of the aforementioned pending services) to airborne drones. The drone management module is responsible for determining the pending services of the target drone based on the matching score and matching results (i.e., the target pending services), as well as drone take-off and landing control, etc. The visualization module is used to manage and record information such as the flight trajectories of multiple drones (including different flight trajectories corresponding to different drone serial numbers), completed services, and services in progress.

[0149] The drone AI self-management center on the drone terminal side: Based on different application scenarios, different business needs, and its own battery power and business status information, the drone optimizes the target problem through the equipped drone AI self-management center, and inputs the optimization results into the communication module and flight control system to readjust the communication parameters such as signal transmission power and bandwidth between the drone and gNB, as well as its flight parameters such as direction, angle, and speed.

[0150] Among them, the drone AI self-management center is a key component of the drone intelligent control system, addressing issues such as mixed-service support. Figure 5 As shown, the drone AI self-management center can include the following functional modules:

[0151] 1. Intelligent Business Matching Module (corresponding to the aforementioned business matching module): Based on its own location and communication capabilities, and taking into account factors such as subsequent flight energy consumption and flight path, the UAV selects all or some of the pending business issued by the centralized management platform and intelligently matches the most suitable business to be executed for the current UAV (corresponding to the aforementioned target pending business), thereby improving the system's resource utilization efficiency and business execution efficiency.

[0152] 2. Differentiated Communication Resource Configuration Module (corresponding to the aforementioned Communication Resource Configuration Module): Since the communication objectives of services in different application scenarios are different, such as high capacity, low latency, high reliability, wide coverage, high mobility, energy saving, etc., UAVs should select communication methods and optimize communication resource configuration according to the current service.

[0153] 3. Cell-level service switching module (corresponding to the aforementioned service switching module): Based on the functions of the above two modules, considering the changes in the drone's own parameters during the flight trajectory and the different capabilities of the base station, it is necessary to perform AI distributed intelligent switching of services for multiple drones, that is, there may be a situation where a service may be executed alternately by different drones.

[0154] Furthermore, it should be noted that the drone AI self-management center can also possess intelligent path planning and obstacle avoidance capabilities, data sharing capabilities, etc. For example, it can use reinforcement learning technology to enable drones to autonomously plan optimal paths in complex environments and use sensors to perceive surrounding obstacles and avoid them. However, these are not capabilities unique to intelligent business support, and therefore will not be described in detail in this application.

[0155] The implementation process of the drone management method of this application will be illustrated below from two aspects: single service with multiple scenarios and single terminal with multiple services.

[0156] Application Example 1: Single Service, Multiple Scenarios

[0157] Drones are capable of applications in multiple scenarios, but they can only handle one type of task at a time. Taking logistics delivery and urban security as examples, the communication goal for logistics delivery is generally low latency, ensuring real-time command communication between the drone and the gNB (gear-based data unit) to guarantee the safety and stability of the transportation process. The communication goal for urban security is generally high-capacity communication, transmitting high-definition images or video data monitored. To meet the different communication goals of these tasks, drones need the ability to adjust their communication methods as needed.

[0158] Taking a cloud platform as a centralized management platform as an example, Figure 6 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 4 ,like Figure 6 As shown, the drone management method includes the following steps:

[0159] 1. After the UAV completes its previous service, it sends its idle status to the centralized management platform and returns the ID of the base station (gNB) it accessed.

[0160] 2. The centralized management platform determines the drone's location based on the base station ID and sends optional pending services to the drone based on this information (corresponding to the aforementioned sending one or more pending services to the drone's AI self-management center). Here, the pending services received by different drones may overlap due to their geographical proximity.

[0161] 3. The drone uses the business intelligent matching module to assign a matching score to the business, for example, a_UAVID_match=95, b_UAVID_match=85, and feeds the matching score results back to the centralized management platform.

[0162] 4. Based on the feedback information, the centralized management platform determines whether the same service is selected by multiple drones. If so, it sends a confirmation of service execution to the drones according to the comparison results of the matching scores of the same service with different drones. If not, it sends the service with the highest matching score for each drone.

[0163] 5. After receiving the business instruction, the UAV selects the appropriate communication method through the communication resource differentiation configuration module, and optimizes the flight parameters and communication parameters according to its remaining energy to achieve the communication goal of the current business.

[0164] 6. During the execution of this service by the UAV, before switching to the next gNB, the UAV obtains the communication capabilities of the currently accessed base station and surrounding base stations, as well as the services executed by the UAV accessing the surrounding base stations, through the Physical Downlink Control Channel (PDCCH) / Physical Downlink Shared Channel (PDSCH).

[0165] 7. Based on its own communication needs, it negotiates with surrounding drones on the selection of services and access base stations, and finally outputs whether to switch services.

[0166] 8. The drone reports the service switching results to the centralized management platform and the communication resource configuration module, and reconfigures the communication resources based on the new service through the communication resource configuration module.

[0167] It should be noted that since the business switching result is not determined by the centralized management platform based on information from all drones, but rather by information sharing among local drones, it is called distributed intelligent business switching.

[0168] Application Example 2: Single Terminal, Multiple Services

[0169] Unlike Application Example 1, in Application Example 2, the drone can perform two types of services simultaneously, such as transmitting images or videos for urban security during logistics transportation. However, this requires more complex strategies for service matching, communication resource configuration, and service switching.

[0170] Taking a cloud platform as a centralized management platform as an example, Figure 7 This is a flowchart illustrating the drone control method according to an embodiment of this application. Figure 5 ,like Figure 7 As shown, the drone management method includes the following steps:

[0171] 1. After the drone completes its previous operation, it sends its idle status to the centralized management platform and returns the ID of the base station it accessed.

[0172] 2. The centralized management platform determines the regional location of the drone based on the base station ID, and sends optional pending services to the drone based on this (corresponding to the aforementioned sending one or more pending services to the drone AI self-management center).

[0173] 3. The drone uses the business intelligent matching module to assign a matching score to the business and feeds the matching score results back to the centralized management platform.

[0174] 4. The centralized management platform outputs pre-matching results based on the matching scores in the feedback information, and determines whether the same service is selected by multiple drones. If not, the pre-matching results are issued directly; if so, the drone with the higher matching score is matched first.

[0175] It should be noted that the two logistics and transportation services cannot be executed simultaneously or dispatched.

[0176] 5. After receiving the execution command, the UAV selects an appropriate communication method through the communication resource differentiation configuration module to perform differentiated configuration of communication resources, thereby achieving a balance between multiple service communication objectives. Specifically, with the goal of maximizing the completion rate of multiple services, the power of each component is optimized, and the problem is modeled as follows:

[0177]

[0178] Where f1(p1,v) and f2(p2,v) represent the completion rates of different tasks; w1 and w2 represent the weights of different tasks. fly These represent the communication power of Service 1, the communication power of Service 2, and the flight power, respectively, and each should be greater than the minimum required power. At the same time, their sum cannot exceed the drone's maximum power limit. Constraint c5 represents the flight speed f of the UAV. v (p fly It cannot exceed the maximum speed V for consistently completing tasks. max This problem can be solved through optimization using AI deep learning.

[0179] 6. During the execution of this service by the drone, before switching to the next gNB, obtain the communication capabilities of the currently accessed base station and surrounding base stations, as well as the services executed by the drones accessing the surrounding base stations, through the PDCCH / PDSCH.

[0180] 7. Based on its own communication needs, it negotiates with surrounding drones on the selection of services and access base stations, and finally outputs whether to switch services.

[0181] It should be noted that in a single-service scenario, there are two outcomes: switching or not switching. In a multi-service scenario, there are more complex outcomes, such as switching one or multiple services. AI-based reinforcement learning can solve the problem of choosing different behaviors based on the current state of the drone.

[0182] 8. The UAV reports the service handover results to the centralized management platform and the communication resource configuration module, and issues flight control commands based on the cell handover results, and reconfigures communication resources based on the new service through the communication resource configuration module.

[0183] In response to the diverse business needs of low-altitude networks, this application designs an AI-powered self-management center for drones, which has the ability to intelligently match business needs and differentiate the configuration of communication resources, thereby improving the resource utilization efficiency and business execution efficiency of drones.

[0184] Compared with the solutions of related technologies, the solution of this application has the following advantages:

[0185] 1) Related technologies are designed only for a single service, which makes drones unable to carry other types of services. In contrast, this application has higher service compatibility, can flexibly handle multiple types of services, and can reasonably allocate drone resources through intelligent scheduling of different services, thereby improving overall operational efficiency.

[0186] 2) In related technologies, the trajectory of drones performing business is a periodic loop. However, this application avoids the situation of drones being idle by promptly executing the next business by feeding back the idle status. At the same time, it can perform trajectory planning more intelligently instead of returning directly to the origin after reaching the destination.

[0187] 3) This application improves the efficiency and economic benefits of drones, not only enhancing the practicality of drone management systems, but also bringing greater business opportunities and cost savings to service providers, and promoting the development of low-altitude networks.

[0188] To implement the drone control method at the drone AI self-management center in this application, this application also provides a drone control device. This device is installed on a drone AI self-management center, which is equipped on one or more drones. Figure 8 This is a schematic diagram of the composition and structure of the unmanned aerial vehicle (UAV) control device according to an embodiment of this application. Figure 1 ,like Figure 8 As shown, the drone control device includes:

[0189] The first receiving unit 81 is used to receive one or more pending services issued by the cloud platform;

[0190] Matching unit 82 is used to match a target service to be executed suitable for the target drone based on the one or more services to be executed; the target drone represents the drone in the one or more drones that is in an empty state, and the target service to be executed meets the requirements of the target drone for mixed service protection;

[0191] The optimization unit 83 is used to optimize the communication resource configuration based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

[0192] In one embodiment, the matching unit 82 is specifically used for:

[0193] The matching score corresponding to the one or more pending services is determined and sent to the cloud platform; wherein, the matching score represents the score corresponding to the degree of matching between the one or more pending services and the target drone, and the matching score is used by the cloud platform to determine the target pending service.

[0194] In one embodiment, the optimization unit 83 is specifically used for:

[0195] Obtain the execution service instruction corresponding to the target service to be executed; in response to the execution service instruction, optimize the communication resource configuration of the target UAV to achieve the communication objective of the target service to be executed; the communication resource configuration includes one or more of the following: communication parameters; flight parameters.

[0196] In one embodiment, the device further includes: a switching unit; wherein,

[0197] The switching unit is used to perform cell-level distributed service switching when it is determined that the target UAV meets the switching conditions.

[0198] In one embodiment, the device further includes: an output unit and a second transmitting unit; wherein,

[0199] The output unit is used to output the service handover result after the handover unit performs the cell-level distributed service handover.

[0200] The second sending unit is used to report the service switching result to the communication resource configuration module in the cloud platform and the UAV AI self-management center, so that the communication resource configuration module can re-optimize the communication resource configuration based on the service switching result.

[0201] In practical applications, the first receiving unit 81 can be implemented by the communication interface in the UAV control device, and the matching unit 82 and the optimization unit 83 can be implemented by the processor in the UAV control device.

[0202] To implement the cloud platform-side drone control method of this application embodiment, this application embodiment also provides another drone control device, which is installed on the cloud platform. Figure 9 This is a schematic diagram of the composition and structure of the unmanned aerial vehicle (UAV) control device according to an embodiment of this application. Figure 2 ,like Figure 9 As shown, the drone control device includes:

[0203] The first sending unit 91 is used to send one or more pending services to the UAV AI self-management center, so that the UAV AI self-management center can match a target pending service suitable for the target UAV based on the one or more pending services; and optimize the communication resource configuration based on the target pending service to achieve the communication target of the target pending service.

[0204] The drone AI self-management center is equipped on one or more drones, the target drone represents the drone in an empty state among the one or more drones, and the target service to be executed meets the needs of the target drone for hybrid service assurance.

[0205] In one embodiment, such as Figure 9 As shown, the device further includes: a second receiving unit 92; wherein,

[0206] The second receiving unit 92 is used to receive the idle status sent by the target drone and the base station identifier accessed by the target drone before the first sending unit 91 sends one or more services to be executed to the drone AI self-management center.

[0207] The first transmitting unit 91 is specifically used for:

[0208] Based on the base station identifier accessed by the target drone, one or more pending services are issued to the drone AI self-management center.

[0209] In one embodiment, the first transmitting unit 91 is specifically used for:

[0210] Based on the base station identifier accessed by the target drone, the regional location information of the target drone is determined; based on the regional location information of the target drone, one or more pending services are issued to the drone AI self-management center.

[0211] In one embodiment, the apparatus further includes: a third receiving unit and a determining unit; wherein,

[0212] The third receiving unit is used to receive the matching score sent by the UAV AI self-management center; the matching score represents the score corresponding to the degree of matching between the one or more services to be executed and the target UAV;

[0213] The determining unit is used to determine the target service to be executed based on the matching score.

[0214] In one embodiment, the determining unit includes a judging subunit and a determining subunit; wherein,

[0215] The judgment subunit is used to determine, based on the matching score, whether there is a situation where the same service to be executed is selected by multiple target drones;

[0216] The determining subunit is used to determine the target service to be executed based on the judgment result and the matching score.

[0217] In one embodiment, the determining subunit is specifically used for:

[0218] If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the pre-matching result; the pre-matching result is obtained by ranking the highest matching score among the matching scores of each target drone; if the judgment result indicates that a single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the comparison result between the pre-matching result and the matching score for the same service to be executed.

[0219] In another embodiment, the determining subunit is further specifically used for:

[0220] If the judgment result indicates that no single service to be executed is selected by multiple target drones, a suitable target service to be executed for each target drone is determined based on the pre-matching result. The pre-matching result is obtained by ranking multiple target matching scores based on the matching scores of each target drone, and the multiple target matching scores meet the matching score threshold. If the judgment result indicates that a single service to be executed is selected by multiple target drones, a suitable target service to be executed for each target drone is determined based on the comparison result between the pre-matching result and the matching score for the same service to be executed.

[0221] In practical applications, the first transmitting unit 91 and the second receiving unit 92 can be implemented by the communication interface in the UAV control device.

[0222] It should be noted that the drone control device provided in the above embodiments is only illustrated by the division of the above program modules when controlling drones. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the drone control device and the drone control method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0223] Based on the hardware implementation of the above program modules, and in order to implement the drone control method on the drone AI self-management center side of this application embodiment, this application embodiment also provides a drone AI self-management center, which is equipped on one or more drones. Figure 10 This is a schematic diagram of the hardware composition structure of the drone AI self-management center according to an embodiment of this application, as shown below. Figure 10 As shown, the drone AI self-management center 1000 includes:

[0224] The first communication interface 1001 is capable of exchanging information with the cloud platform;

[0225] The first processor 1002 is connected to the first communication interface 1001 to enable information interaction with the cloud platform. When running a computer program, it executes the methods provided by one or more technical solutions of the above-mentioned UAV AI self-management center side, and the computer program is stored on the first memory 1003.

[0226] It should be noted that the specific processing procedures of the first communication interface 1001 and the first processor 1002 can be understood by referring to the above-mentioned drone control method on the drone AI self-management center side.

[0227] Of course, in practical applications, the various components in the UAV AI self-management center 1000 are coupled together through the first bus system 1004. It can be understood that the first bus system 1004 is used to realize the connection and communication between these components. In addition to the data bus, the first bus system 1004 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 10 The general designated all buses as the first bus system 1004.

[0228] The first memory 1003 in this embodiment is used to store various types of data to support the operation of the UAV AI self-management center 1000. Examples of such data include any computer program used to operate on the UAV AI self-management center 1000.

[0229] The drone AI self-management center-side drone control method disclosed in the above embodiments of this application can be applied to the first processor 1002, or implemented by the first processor 1002. The first processor 1002 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above-mentioned drone AI self-management center-side drone control method can be completed by the hardware integrated logic circuit or software instructions in the first processor 1002. The first processor 1002 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The first processor 1002 can implement or execute the various drone AI self-management center-side drone control methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the drone AI self-management center-side drone control method disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the first memory 1003. The first processor 1002 reads the information in the first memory 1003 and combines it with its hardware to complete the steps of the aforementioned drone AI self-management center side drone control method.

[0230] In an exemplary embodiment, the UAV AI self-management center 1000 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to execute the aforementioned UAV control method on the UAV AI self-management center side.

[0231] Based on the hardware implementation of the above program modules, and in order to implement the cloud platform-side drone management method of this application embodiment, this application embodiment also provides a cloud platform. Figure 11 This is a schematic diagram of the hardware composition structure of the cloud platform according to an embodiment of this application, as shown below. Figure 11As shown, the cloud platform 1100 includes:

[0232] The second communication interface 1101 is capable of exchanging information with the drone AI self-management center;

[0233] The second processor 1102 is connected to the second communication interface 1101 to enable information interaction with the UAV AI self-management center. When running a computer program, it executes the methods provided by one or more technical solutions on the cloud platform side, and the computer program is stored on the second memory 1103.

[0234] It should be noted that the specific processing procedures of the second communication interface 1101 and the second processor 1102 can be understood by referring to the above-mentioned drone management method on the cloud platform side.

[0235] Of course, in practical applications, the various components in the cloud platform 1100 are coupled together through the second bus system 1104. It can be understood that the second bus system 1104 is used to realize the connection and communication between these components. In addition to the data bus, the second bus system 1104 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 11 The various buses are all labeled as the second bus system 1104.

[0236] The second memory 1103 in this embodiment is used to store various types of data to support the operation of the cloud platform 1100. Examples of such data include any computer program used to operate on the cloud platform 1100.

[0237] The cloud platform-side drone management method disclosed in the above embodiments of this application can be applied to, or implemented by, the second processor 1102. The second processor 1102 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the cloud platform-side drone management method can be completed by the integrated logic circuits in the hardware or by instructions in the software form of the second processor 1102. The second processor 1102 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The second processor 1102 can implement or execute the various cloud platform-side drone management methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the cloud platform-side drone management method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the second memory 1103. The second processor 1102 reads the information in the second memory 1103 and, in conjunction with its hardware, completes the steps of the aforementioned drone control method on the cloud platform side.

[0238] In an exemplary embodiment, the cloud platform 1100 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to execute the aforementioned drone control method on the cloud platform side.

[0239] It is understood that the memory (including the first memory 1003 and the second memory 1103) in the embodiments of this application can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0240] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a first memory 1003 storing a computer program, which can be executed by a first processor 1002 in the UAV AI self-management center 1000 to complete the steps of the aforementioned UAV control method on the UAV AI self-management center side; or, a second memory 1103 storing a computer program, which can be executed by a second processor 1102 in the cloud platform 1100 to complete the steps of the aforementioned UAV control method on the cloud platform side. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0241] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by a first processor 1002 in a drone AI self-management center 1000 to complete the steps of the aforementioned drone control method on the drone AI self-management center side, or the computer program can be executed by a second processor 1102 in a cloud platform 1100 to complete the steps of the aforementioned drone control method on the cloud platform side.

[0242] It should be noted that terms such as "first," "second," and "third" are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0243] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0244] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A drone control system, characterized in that, The system includes: a cloud platform and a drone AI self-management center, wherein the drone AI self-management center is equipped on one or more drones, and the drone AI self-management center includes a service matching module and a communication resource configuration module; wherein... The service matching module is used to receive one or more services to be executed from the cloud platform, and match a suitable target service to be executed for the target drone based on the one or more services to be executed; the target drone represents the drone in the one or more drones that is in an empty state, and the target service to be executed meets the requirements of the target drone for mixed service protection; The communication resource configuration module is used to optimize the communication resource configuration based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

2. The system according to claim 1, characterized in that, The cloud platform includes a drone management module and a service delivery module; wherein... The drone management module is used to receive the idle status sent by the target drone and the base station identifier to which the target drone is connected; The service delivery module is used to deliver one or more services to be executed to the target drone.

3. The system according to claim 2, characterized in that, The service delivery module is specifically used for: Based on the identifier of the base station accessed by the target drone, the regional location information of the target drone is determined; Based on the regional location information of the target drone, one or more services to be executed are sent to the target drone.

4. The system according to claim 1, characterized in that, The business matching module is specifically used for: Determine the matching score corresponding to the one or more services to be executed, and send the matching score to the drone management module in the cloud platform; The matching score represents the degree of matching between the one or more services to be executed and the target drone, and the matching score is used by the drone management module to determine the target service to be executed.

5. The system according to claim 4, characterized in that, The drone management module is also used for: Receive the matching score sent by the service matching module; Based on the matching score, determine whether there is a situation where the same pending service is selected by multiple target drones; Based on the judgment result and the matching score, the target service to be executed is determined and sent to the communication resource configuration module.

6. The system according to claim 5, characterized in that, The drone management module is specifically used for: If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target service to be executed suitable for each target drone is determined based on the pre-matching result. The pre-matching result is obtained based on the highest matching score determined by sorting the matching scores of each target UAV by size; When the judgment result indicates that the same service to be executed is selected by multiple target drones, the target service to be executed suitable for each of the target drones is determined based on the comparison result of the pre-matching result and the matching degree score for the same service to be executed.

7. The system according to claim 5, characterized in that, The drone management module is specifically used for: If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target service to be executed suitable for each target drone is determined based on the pre-matching result. The pre-matching result is obtained based on multiple target matching scores determined by sorting the matching scores of each target UAV by size, and the multiple target matching scores meet the matching score threshold. When the judgment result indicates that the same service to be executed is selected by multiple target drones, the target service to be executed suitable for each of the target drones is determined based on the comparison result of the pre-matching result and the matching degree score for the same service to be executed.

8. The system according to claim 1, characterized in that, The communication resource configuration module is specifically used for: Obtain the execution business instruction corresponding to the target business to be executed; In response to the execution service instruction, the communication resource configuration of the target UAV is optimized to achieve the communication objective of the target service to be executed; the communication resource configuration includes one or more of the following: communication parameters; flight parameters.

9. The system according to claim 1, characterized in that, The drone AI self-management center also includes a service switching module; wherein... The service switching module is used to switch cell-level distributed services when it is determined that the target drone meets the switching conditions.

10. The system according to claim 9, characterized in that, The service switching module is also used to output the service switching result and report the service switching result to the drone management module and communication resource configuration module in the cloud platform; The communication resource configuration module is also used to re-optimize the communication resource configuration based on the service switching result.

11. A method for controlling unmanned aerial vehicles (UAVs), characterized in that, An AI self-management center for unmanned aerial vehicles (UAVs), wherein the UAV AI self-management center is equipped on one or more UAVs, the method includes: Receive one or more pending business requests from the cloud platform; Based on the one or more pending services, a suitable target pending service is matched for the target drone; the target drone represents the drone in the one or more drones that is in an idle state, and the target pending service meets the requirements of the target drone for hybrid service assurance; Optimize the configuration of communication resources based on the target service to be executed, so as to achieve the communication objective of the target service to be executed.

12. The method according to claim 11, characterized in that, The matching of target services suitable for the target drone based on the one or more pending services includes: Determine the matching score corresponding to the one or more services to be executed, and send the matching score to the cloud platform; The matching score represents the degree of matching between the one or more services to be executed and the target drone, and the matching score is used by the cloud platform to determine the target service to be executed.

13. The method according to claim 11, characterized in that, The optimization of communication resource configuration based on the target service to be executed, in order to achieve the communication objective of the target service to be executed, includes: Obtain the execution business instruction corresponding to the target business to be executed; In response to the execution service instruction, the communication resource configuration of the target UAV is optimized to achieve the communication objective of the target service to be executed; the communication resource configuration includes one or more of the following: communication parameters; flight parameters.

14. The method according to claim 11, characterized in that, The method further includes: If the target drone meets the handover conditions, a cell-level distributed service handover is performed.

15. The method according to claim 14, characterized in that, After the cell-level distributed service handover is performed, the method further includes: Output the service switching result and report the service switching result to the communication resource configuration module in the cloud platform and the UAV AI self-management center, so that the communication resource configuration module can re-optimize the communication resource configuration based on the service switching result.

16. A method for controlling unmanned aerial vehicles (UAVs), characterized in that, Applied to a cloud platform, the method includes: One or more pending tasks are issued to the UAV AI self-management center, so that the UAV AI self-management center can match a target pending task suitable for the target UAV based on the one or more pending tasks; and optimize the configuration of communication resources based on the target pending task to achieve the communication goal of the target pending task. The drone AI self-management center is equipped on one or more drones, the target drone represents the drone in an empty state among the one or more drones, and the target service to be executed meets the needs of the target drone for hybrid service assurance.

17. The method according to claim 16, characterized in that, Before issuing one or more pending tasks to the drone AI self-management center, the method further includes: Receive the idle status sent by the target drone and the identifier of the base station to which the target drone is connected; The process of issuing one or more pending tasks to the drone AI self-management center includes: Based on the base station identifier accessed by the target drone, one or more pending services are issued to the drone AI self-management center.

18. The method according to claim 17, characterized in that, Based on the base station identifier accessed by the target drone, one or more pending services are issued to the drone AI self-management center, including: Based on the identifier of the base station accessed by the target drone, the regional location information of the target drone is determined; Based on the regional location information of the target drone, one or more pending tasks are issued to the drone AI self-management center.

19. The method according to claim 16, characterized in that, The method further includes: Receive the matching score sent by the drone AI self-management center; the matching score represents the score corresponding to the degree of matching between the one or more services to be executed and the target drone; Based on the matching score, the target service to be executed is determined.

20. The method according to claim 19, characterized in that, The step of determining the target service to be executed based on the matching score includes: Based on the matching score, determine whether there is a situation where the same pending service is selected by multiple target drones; Based on the judgment result and the matching score, the target service to be executed is determined.

21. The method according to claim 20, characterized in that, The step of determining the target service to be executed based on the judgment result and the matching score includes: If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the pre-matching result; the pre-matching result is obtained by determining the highest matching score based on the matching score of each target drone. When the judgment result indicates that the same service to be executed is selected by multiple target drones, the target service to be executed suitable for each of the target drones is determined based on the comparison result of the pre-matching result and the matching degree score for the same service to be executed.

22. The method according to claim 20, characterized in that, The step of determining the target service to be executed based on the judgment result and the matching score includes: If the judgment result indicates that no single service to be executed is selected by multiple target drones, the target services to be executed suitable for each target drone are determined based on the pre-matching result; the pre-matching result is obtained by ranking multiple target matching scores based on the matching score of each target drone, and the multiple target matching scores meet the matching score threshold. When the judgment result indicates that the same service to be executed is selected by multiple target drones, the target service to be executed suitable for each of the target drones is determined based on the comparison result of the pre-matching result and the matching degree score for the same service to be executed.

23. A drone control device, characterized in that, An AI self-management center for unmanned aerial vehicles (UAVs), wherein the UAV AI self-management center is equipped on one or more UAVs, the device comprising: The first receiving unit is used to receive one or more pending business operations issued by the cloud platform; The matching unit is used to match a target service to be executed that is suitable for the target drone based on the one or more services to be executed; the target drone represents the drone in the one or more drones that is in an idle state, and the target service to be executed meets the requirements of the target drone for hybrid service assurance; The optimization unit is used to optimize the configuration of communication resources based on the target service to be executed, so as to achieve the communication target of the target service to be executed.

24. A drone control device, characterized in that, The device, applied to a cloud platform, includes: The first sending unit is used to send one or more pending services to the UAV AI self-management center, so that the UAV AI self-management center can match a target pending service suitable for the target UAV based on the one or more pending services; and optimize the communication resource configuration based on the target pending service to achieve the communication target of the target pending service. The drone AI self-management center is equipped on one or more drones, the target drone represents the drone in an empty state among the one or more drones, and the target service to be executed meets the needs of the target drone for hybrid service assurance.

25. A drone AI self-management center, characterized in that, include: A first processor and a first memory for storing computer programs capable of running on the first processor; Wherein, when the first processor is used to run the computer program, it performs the steps of the method according to any one of claims 11 to 15.

26. A cloud platform, characterized in that, include: A second processor and a second memory for storing computer programs capable of running on the second processor; Wherein, when the second processor is used to run the computer program, it performs the steps of the method according to any one of claims 16 to 22.

27. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 11 to 22.

28. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 11 to 22.

Images