Unmanned aerial vehicle global AI inspection intelligent management and control method

Abstract

The invention relates to an unmanned aerial vehicle global AI inspection intelligent management and control method, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: determining a target region and first association information of the target region, dividing the target region, and generating a plurality of subregions; acquiring second associated information of the target partition, determining the inspection type and priority of the target partition based on the second associated information, and generating an unmanned aerial vehicle inspection task request; in response to the received unmanned aerial vehicle inspection task request, acquiring state information and environment information of the unmanned aerial vehicle in the standby queue, and determining a target unmanned aerial vehicle associated with the target partition and cut-in and cut-out information of the target unmanned aerial vehicle in the target partition; and determining a communication link of the target unmanned aerial vehicle according to the cut-in and cut-out information of the unmanned aerial vehicles corresponding to the plurality of partitions, and controlling the target unmanned aerial vehicle to execute an inspection task corresponding to the unmanned aerial vehicle inspection task request. According to the invention, the inspection efficiency, precision and safety are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle global AI inspection intelligent management and control method. BACKGROUND

[0002] With the rapid development of unmanned aerial vehicle technology, it has been widely used in power lines, oil pipelines, wind power plants, photovoltaic power stations, rail transit, smart parks and emergency rescue and many other fields of inspection work due to its high flexibility, low cost, high efficiency and other advantages. The traditional periodic manual inspection method has the problems of high labor intensity, high safety risk, low efficiency, geographical environment limitation and difficulty in finding hidden defects. Unmanned aerial vehicle inspection effectively overcomes these problems and becomes an important means of modern infrastructure operation and maintenance. Although the current unmanned aerial vehicle inspection technology has replaced traditional manual inspection, there are still problems such as difficulty in realizing large-scale global coverage in single-machine operation mode, information lag and data island caused by separation of data collection and analysis, insufficient automation and AI recognition intelligence level, and reduced safety and reliability in complex environments. Therefore, it is necessary to propose an unmanned aerial vehicle global AI inspection intelligent management and control method that can solve the problems of multi-machine cooperation, real-time intelligent analysis and centralized management, in order to realize safe, efficient and accurate global inspection. SUMMARY

[0003] Therefore, it is necessary to provide an unmanned aerial vehicle global AI inspection intelligent management and control method that can realize safe, efficient and accurate global inspection.

[0004] In a first aspect, an unmanned aerial vehicle global AI inspection intelligent management and control method is provided, which comprises: determining a target area and first associated information of the target area, dividing the target area based on the first associated information, and generating a plurality of partitions, wherein the associated information is at least task attribute data used to describe the AI inspection task of the area; obtaining second associated information of a target partition, determining the inspection type and priority of the target partition based on the second associated information, and generating an unmanned aerial vehicle inspection task request based on the second associated information, the inspection type and the priority; in response to receiving the unmanned aerial vehicle inspection task request, obtaining state information and environmental information of the unmanned aerial vehicle in the standby queue, determining a target unmanned aerial vehicle associated with the target partition and cut-in and cut-out information of the target unmanned aerial vehicle in the target partition based on the unmanned aerial vehicle inspection task request, the state information and the environmental information, and the cut-in and cut-out information at least includes time and position; According to the cut-in and cut-out information of the plurality of sub-regions corresponding to the unmanned aerial vehicle, a communication link of the target unmanned aerial vehicle is determined, and based on the cut-in and cut-out information of the target unmanned aerial vehicle in the target sub-region and the communication link, the target unmanned aerial vehicle is controlled to perform an inspection task corresponding to the unmanned aerial vehicle inspection task request.

[0005] Optionally, determining the target region and the first associated information of the target region comprises: receiving an inspection request of a user terminal, the inspection request of the user terminal at least comprising a geographical region range; determining the target region based on the geographical region range; extracting the first associated information of the target region from a database according to the target region, the first associated information at least comprising an inspection object, an inspection accuracy and an inspection key target.

[0006] Optionally, based on the first associated information, the target region is divided to generate a plurality of sub-regions, comprising: determining a first division rule of the target region according to an object attribute of the inspection object, comprising: in response to the first object attribute of the inspection object being a geographical feature, dividing the target region based on a boundary of the geographical feature to generate a first sub-region; in response to the first object attribute of the inspection object being a non-geographical feature, dividing the target region based on an area balance mechanism to generate a second sub-region; in response to the second sub-region having been divided, determining a second division rule of the target region based on the inspection accuracy and the inspection key target, comprising: obtaining a level corresponding to the inspection accuracy and an attribute of the inspection key target, and determining a task amount of the second sub-region based on the level and the attribute; adjusting a division result of the second sub-region based on a task amount balance mechanism and the task amount of the second sub-region to generate a third sub-region; defining the first sub-region and / or the third sub-region as the plurality of sub-regions generated by dividing the target region.

[0007] Optionally, obtaining second associated information of a target sub-region, and determining an inspection type and a priority of the target sub-region based on the second associated information comprises: obtaining second associated information of a target sub-region, the second associated information at least comprising an inspection object; determining an inspection type of the target sub-region based on a second object attribute of the inspection object, the second object attribute at least comprising an inspection method, an inspection frequency and an inspection accuracy; According to the inspection type of the target partition, a factor affecting the execution order of the target partition inspection task is determined, and a comprehensive evaluation value is determined according to the factor; Based on the comprehensive evaluation value, the priority of the target partition is determined.

[0008] Optionally, based on the second association information, the inspection type and the priority, the UAV inspection task request is generated, including: The second association information of the target partition, the inspection type and the priority are obtained; The second association information, the inspection type and the priority are mapped to generate a mapping relationship including a unique identifier, and the mapping relationship is filled into the corresponding field of the task request template to generate the UAV inspection task request.

[0009] Optionally, in response to receiving the UAV inspection task request, the state information and the environment information of the UAV in the standby queue are obtained, including: In response to receiving the UAV inspection task request, a UAV in an idle state and / or with a remaining task execution time less than a first preset threshold is determined, and the UAV identifier corresponding to the UAV is sequentially arranged in the standby queue according to the task execution state; The state information of the UAV in the standby queue is obtained, and the state information at least includes a health state, an equipment state, a task execution state and a real-time running state; The environment information of the target partition is obtained, and the environment information at least includes meteorological information, geographical information, airspace information and electromagnetic information; The state information and the environment information of the UAV in the standby queue are mapped to generate a mapping relationship and saved.

[0010] Optionally, according to the UAV inspection task request, the state information and the environment information, a target UAV associated with the target partition and the target UAV in the target partition are determined, including: According to the environment information of the target partition, a first UAV set associated with the target partition is determined; According to the inspection type, the priority and the state information, a second UAV set associated with the target partition is selected from the first UAV set; The UAVs in the second UAV set are defined as target UAVs associated with the target partition; Based on the spatiotemporal coordination mechanism and the inspection type, the target UAV in the target partition is determined.

[0011] Optionally, the communication link of the target UAV is determined based on the entering and exiting information of the UAVs in the plurality of sub-zones. The path point sequence of the target UAV in the target sub-zone is determined based on the entering and exiting information of the target UAV. The communication link reachability degree of the target UAV at a target path point with a first target communication base station is determined based on the path point sequence. In response to the communication link reachability degree not meeting a preset standard, the first target communication base station of the target UAV at the target path point is switched to a second target communication base station, so that the communication link reachability degree meets the preset standard. The communication load and the interference degree of the communication link in a target time period are obtained based on the entering and exiting information of the UAVs in the plurality of sub-zones, the target time period being determined based on the entering time and the exiting time. In response to a cooperative optimization value corresponding to the communication load and the interference degree being greater than a first preset threshold value, the second target communication base station of the target UAV at the target path point is switched to a third target communication base station, so that the communication link reachability degree meets the preset standard and the cooperative optimization value is less than or equal to the first preset threshold value. The communication link of the target UAV at the target path point with the third target communication base station is defined as a target communication link. A set of communication links generated by the plurality of target communication links is defined as the communication link of the target UAV.

[0012] Optionally, the target UAV is controlled to perform the inspection task corresponding to the UAV inspection task request based on the entering and exiting information of the target UAV in the target sub-zone and the communication link. The target UAV is controlled to perform the inspection task corresponding to the UAV inspection task request based on the entering and exiting information of the target UAV in the target sub-zone. Image data generated by the target UAV performing the inspection task is transmitted back to a data receiving end based on the communication link.

[0013] Optionally, the method further comprises: Image data transmitted back by the target UAV is obtained, and the image data is analyzed to determine whether there is an abnormal situation in the target sub-zone. In response to the existence of an abnormal situation, alarm information is generated and pushed.

[0014] In a second aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: determine a target region and first association information of the target region, divide the target region based on the first association information, and generate a plurality of partitions, wherein the association information is at least task attribute data used to describe a regional AI inspection task; obtain second association information of a target partition, determine an inspection type and a priority of the target partition based on the second association information, and generate a UAV inspection task request based on the second association information, the inspection type, and the priority; in response to receiving the UAV inspection task request, obtain state information and environmental information of a UAV in a standby queue, determine a target UAV associated with the target partition and entry and exit information of the target UAV in the target partition based on the UAV inspection task request, the state information, and the environmental information, wherein the entry and exit information at least includes time and position; determine a communication link of the target UAV based on entry and exit information of a plurality of partitions corresponding to the UAV, and control the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the entry and exit information of the target UAV in the target partition and the communication link In a third aspect, a computer readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the following steps are implemented: determine a target region and first association information of the target region, divide the target region based on the first association information, and generate a plurality of partitions, wherein the association information is at least task attribute data used to describe a regional AI inspection task; obtain second association information of a target partition, determine an inspection type and a priority of the target partition based on the second association information, and generate a UAV inspection task request based on the second association information, the inspection type, and the priority; in response to receiving the UAV inspection task request, obtain state information and environmental information of a UAV in a standby queue, determine a target UAV associated with the target partition and entry and exit information of the target UAV in the target partition based on the UAV inspection task request, the state information, and the environmental information, wherein the entry and exit information at least includes time and position; determine a communication link of the target UAV based on entry and exit information of a plurality of partitions corresponding to the UAV, and control the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the entry and exit information of the target UAV in the target partition and the communication link In a fourth aspect, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the following steps are implemented: determine a target region and first associated information of the target region, divide the target region based on the first associated information, and generate a plurality of partitions, wherein the associated information is at least task attribute data used to describe a regional AI inspection task; obtain second associated information of a target partition, determine an inspection type and a priority of the target partition based on the second associated information, and generate a UAV inspection task request based on the second associated information, the inspection type, and the priority; In response to receiving the UAV inspection task request, obtain state information and environmental information of a UAV in a standby queue, determine a target UAV associated with the target partition and entry and exit information of the target UAV in the target partition based on the UAV inspection task request, the state information, and the environmental information, wherein the entry and exit information at least includes time and location; determine a communication link of the target UAV based on the entry and exit information of the UAV corresponding to the plurality of partitions, and control the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the entry and exit information of the target UAV in the target partition and the communication link The above-mentioned UAV global AI inspection intelligent management and control method comprises the following steps: determining a target region and first associated information of the target region, dividing the target region based on the first associated information, and generating a plurality of partitions, wherein the associated information is at least task attribute data used to describe a regional AI inspection task; obtaining second associated information of a target partition, determining an inspection type and a priority of the target partition based on the second associated information, and generating a UAV inspection task request based on the second associated information, the inspection type, and the priority; in response to receiving the UAV inspection task request, obtaining state information and environmental information of a UAV in a standby queue, determining a target UAV associated with the target partition and entry and exit information of the target UAV in the target partition based on the UAV inspection task request, the state information, and the environmental information, wherein the entry and exit information at least includes time and location; determining a communication link of the target UAV based on the entry and exit information of the UAV corresponding to the plurality of partitions, and controlling the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the entry and exit information of the target UAV in the target partition and the communication link. Through decomposition of global tasks, multi-machine collaborative planning, and real-time AI analysis, the application improves the inspection efficiency, accuracy, and safety. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 An application environment diagram of the UAV global AI inspection intelligent management and control method in one embodiment; Figure 2A flowchart of a global AI inspection intelligent management and control method of a UAV in an embodiment is shown in the figure. Figure 3 An internal structure diagram of a computer device in an embodiment is shown in the figure. DETAILED DESCRIPTION

[0016] To make the purposes, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0017] It should be understood that, in the description of the present application, unless the context clearly requires otherwise, the terms "comprise", "comprise", and the like in the entire description should be interpreted as inclusive rather than exclusive or exhaustive meaning; that is, as "including but not limited to".

[0018] It should also be understood that the terms "first", "second", and the like are only for the purpose of description, and should not be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise stated, the meaning of "multiple" is two or more.

[0019] It should be noted that the terms "S1", "S2", and the like are only for the purpose of describing the steps, and do not specifically refer to the order or position, nor are they used to limit the present application. They are only used to facilitate the description of the method of the present application, and should not be understood as indicating the order of the steps. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the fact that a person of ordinary skill in the art can realize it. When the combination of technical solutions contradicts each other or cannot be realized, it should be considered that the combination of technical solutions does not exist, nor is it within the scope of protection required by the present application.

[0020] The global AI inspection intelligent management and control method of the UAV provided by the present application can be applied to the application environment as shown in Figure 1 . Among them, the terminal 102 communicates with the data processing platform set on the server 104 through the network, wherein the terminal 102 can be but not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 can be realized by an independent server or a server cluster composed of multiple servers.

[0021] In an embodiment, as shown in Figure 2 , a global AI inspection intelligent management and control method of a UAV is provided, and the method is applied to Figure 1The terminal in the system is taken as an example for illustration, including the following steps: S1: determining a target area and first associated information of the target area, dividing the target area based on the first associated information, and generating a plurality of partitions, wherein the associated information is at least task attribute data for describing an AI inspection task of the area.

[0022] It should be noted that the target area refers to an area that needs to be inspected according to a user request, which is determined by longitude and latitude coordinates, geographical boundaries, or imported GIS map data. The first associated information can include an inspection object, an inspection accuracy, and an inspection key target. The inspection object refers to a specific asset that needs to be checked, which can be a power line, a photovoltaic panel, a pipeline, etc. The inspection accuracy is a specified flight height, image resolution, etc. for ensuring that the collected image data can meet the analysis requirements. The inspection key target refers to an area or equipment point that needs special attention, such as equipment with known hidden dangers. A target area can include multiple inspection key targets.

[0023] S2: obtaining second associated information of the target partition, determining an inspection type and a priority of the target partition based on the second associated information, and generating a UAV inspection task request based on the second associated information, the inspection type, and the priority.

[0024] It should be noted that the inspection type can be determined by an inspection method, an inspection frequency, and an inspection accuracy. For example, the inspection method can include thermal imaging, multispectral, and other special payloads. The inspection frequency can be periodic inspection or special inspection. For example, periodic inspection is performed according to a pre-prepared operation and maintenance calendar, such as monthly, seasonal, or annual inspection of power lines. Special inspection is triggered after a specific event, such as special inspection after a typhoon or heavy rain, which focuses on disaster impact inspection. The inspection accuracy can be determined according to the attributes of the inspection object. For example, key core equipment (such as main transformers of substations, pipeline valves, etc.) needs high-frequency and fine inspection or detection type inspection (such as using thermal imaging, multispectral, and other special payloads).

[0025] S3: in response to receiving the UAV inspection task request, obtaining state information and environmental information of a UAV in a standby queue, and determining a target UAV associated with the target partition and cut-in and cut-out information of the target UAV in the target partition based on the UAV inspection task request, the state information, and the environmental information, wherein the cut-in and cut-out information at least includes time and location.

[0026] It should be noted that the state information can include health status, equipment status, task execution status and real-time running status, wherein the health status can be determined by the self-checking status of the core components (such as motors and the like), historical maintenance records, remaining life prediction, the equipment status includes the type of carried load (such as visible light, infrared, laser radar), load working state, the task execution status includes whether the unmanned aerial vehicle is in an idle state or the remaining time length of executing a task, and the real-time running status can include the current power, running height, speed, heading and the like; the environmental information can include meteorological information, geographic information, airspace information and electromagnetic information, wherein the meteorological information includes real-time forecasted wind speed, wind direction, precipitation, visibility, temperature and the like, the geographic information includes high-precision digital elevation model (DEM) of the target area, distribution of obstacles (such as buildings, mountains and the like) and the like, the airspace information can include real-time no-fly zone, restricted area and other air traffic activities and the like, and the electromagnetic information mainly includes the interference intensity distribution diagram of the communication frequency band and the like; the cut-in and cut-out information includes cut-in time, cut-out time, cut-in position and cut-out position, wherein one target subarea can have multiple associated target unmanned aerial vehicles, which can execute the inspection task in the same time period or in different time periods.

[0027] S4: determining the communication link of the target unmanned aerial vehicle according to the cut-in and cut-out information of the unmanned aerial vehicle corresponding to the multiple subareas, and controlling the target unmanned aerial vehicle to execute the inspection task corresponding to the unmanned aerial vehicle inspection task request based on the cut-in and cut-out information of the target unmanned aerial vehicle in the target subarea and the communication link.

[0028] It should be noted that the communication link is constructed between the target unmanned aerial vehicle and the communication base station, the target unmanned aerial vehicle enters the target subarea according to the cut-in time and the cut-in position, and exits the target subarea according to the cut-out position and the cut-out time, and inspects the target subarea in the time period between the cut-in time and the cut-out time, wherein multiple target subareas can be simultaneously inspected by multiple unmanned aerial vehicles.

[0029] In some embodiments, determining the target area and the first associated information of the target area comprises: receiving an inspection request of a user end, the inspection request of the user end at least including a geographic area range, wherein the inspection request of the user end can be input in real time by a user or can be issued by the system at a fixed time, and the geographic area range refers to a target area range to be inspected determined by longitude and latitude coordinates, geographic boundaries or imported GIS map data; determining the target area based on the geographic area range, and the target area can be a linear pipeline corresponding area or a regularly arranged photovoltaic panel square array for example; According to the target area, first association information of the target area is extracted from a database, the first association information at least including a patrol object, a patrol precision and a patrol key target, wherein the database is used to save task attribute data of a plurality of target areas, such as the first association information and second association information.

[0030] In some embodiments, based on the first association information, the target area is divided to generate a plurality of partitions, including: According to the object attribute of the patrol object, a first division rule of the target area is determined, including: In response to the first object attribute of the patrol object being a geographical feature, the target area is divided based on the boundary of the geographical feature to generate a first partition, wherein the geographical feature refers to a region containing natural barriers (such as rivers, ridges) or obvious geographical separation, and these regions are preferentially divided into regions with these features as boundaries to ensure the geographical continuity of each partition; In response to the first object attribute of the patrol object being a non-geographical feature, the target area is divided based on an area balance mechanism to generate a second partition, wherein the non-geographical feature refers to a region within the target area without obvious geographical separation, i.e., a region with uniform distribution of topography and patrol targets, and the target area is divided into a plurality of sub-partitions with equal areas according to the set partition size, and the sub-partition is defined as the second partition; In response to the second partition being divided, a second division rule of the target area is determined based on the patrol precision and the patrol key target, including: The level corresponding to the patrol precision and the attribute of the patrol key target are obtained, and the task amount of the second partition is determined based on the level and the attribute, wherein the level corresponding to the patrol precision is determined by a pre-set mapping relationship, the mapping relationship is used to describe the corresponding relationship between the patrol precision and the patrol level, generally, the higher the patrol precision, the larger the patrol level, the attribute of the patrol key target includes the number of key targets and the patrol time length of key targets, the patrol level, the number of key targets and the patrol time length of key targets are normalized, and based on the normalized data, the task amount of the second partition is determined through a task amount evaluation function, wherein the task amount evaluation function is R = w1X1 + w2X2 + w3X3, wherein R represents a task amount evaluation value, w1, w2 and w3 all represent weight coefficients, X1 represents the patrol level, X2 represents the number of key targets, and X3 represents the patrol time length of key targets; adjust the division result of the second partition based on a task quantity balancing mechanism and the task quantity of the second partition, to generate a third partition, wherein the task quantity balancing mechanism comprises: determining a task quantity evaluation value of a plurality of second partitions, and performing difference processing on the task quantity evaluation values of any two partitions to obtain a difference absolute value, based on a plurality of difference processing processes, a plurality of difference absolute values are obtained, in response to the plurality of difference absolute values being less than a second preset threshold or the number of difference absolute values greater than or equal to the second preset threshold in the plurality of difference absolute values being less than or equal to a third preset threshold, the second partition is not adjusted, at this time, the first partition and / or the second partition are defined as a plurality of partitions generated by dividing the target region, in response to the number of difference absolute values greater than or equal to the second preset threshold in the plurality of difference absolute values being greater than the third preset threshold, the second partition is adjusted according to the task quantity evaluation value until the number of difference absolute values greater than or equal to the second preset threshold in the plurality of difference absolute values is less than or equal to the third preset threshold, wherein the second preset threshold and the third preset threshold can be set according to actual needs; define the first partition and / or the third partition as a plurality of partitions generated by dividing the target region.

[0031] In some embodiments, the second association information of the target partition is obtained, and based on the second association information, the inspection type and the priority of the target partition are determined. Obtain the second association information of the target partition, and the second association information at least includes the inspection object; Based on the second object attribute of the inspection object, the inspection type of the target partition is determined, and the second object attribute at least includes the inspection method, the inspection frequency and the inspection accuracy; According to the inspection type of the target partition, the factors affecting the execution order of the target partition inspection task are determined, and the comprehensive evaluation value is determined according to the factors, wherein the influencing factors can include the risk determined based on the inspection type, the key degree of the inspection object in the industry chain, the timeliness requirement and the task dependency relationship, for example, the risk refers to emergency inspection, targeted inspection, etc., such as post-disaster evaluation, the risk level is high, and the priority is high, the targeted inspection of hidden danger information, the risk level is medium, and the priority is medium, the higher the key degree of the inspection object in the industry chain, the higher the priority, the higher the timeliness requirement, the higher the priority, and the subsequent task depends on the current task inspection result, then the priority of the current task is higher, based on this, the expert assignment method is used to assign values to the above influencing factors, and standardization processing is performed, and the comprehensive evaluation value is calculated based on the result after standardization processing, and the calculation method is: wherein, indicates the comprehensive evaluation value, m indicates the number of influencing factors, a weight coefficient representing an nth influencing factor, an nth influencing factor; based on the comprehensive evaluation value, determining the priority of the target partition, wherein the larger the comprehensive evaluation value, the higher the priority of the target partition, and the priority of the target partition is determined according to the ranking result, for example, if the comprehensive evaluation value is the largest, the ranking is the first, and the priority is the largest, and so on.

[0032] In some embodiments, based on the second association information, the inspection type and the priority, generating the UAV inspection task request comprises: obtaining the second association information, the inspection type and the priority of the target partition; mapping the second association information, the inspection type and the priority, generating a mapping relationship including a unique identifier, and filling the mapping relationship into the corresponding field of the task request template to generate the UAV inspection task request, wherein the unique identifier refers to a unique ID, which is used to represent the related information of the target partition, and the task request template is a pre-set inspection task request template.

[0033] In some embodiments, in response to receiving the UAV inspection task request, obtaining the state information and the environmental information of the UAV in the standby queue comprises: In response to receiving the UAV inspection task request, determining the UAV in an idle state and / or with a remaining task execution time less than a first preset threshold, and arranging the UAV identifier corresponding to the UAV in the standby queue in order according to the task execution state, wherein the first preset threshold can be set according to actual needs, and generally, the working time of the UAV in the idle state can be determined, for example, if the working time of the UAV in the idle state is 2.5 hours, the first preset threshold needs to be less than 2.5 hours, and so on. obtaining the state information of the UAV in the standby queue, the state information at least including health status, equipment status, task execution status and real-time running status; obtaining the environmental information of the target partition, the environmental information at least including meteorological information, geographical information, airspace information and electromagnetic information; mapping the state information and the environmental information of the UAV in the standby queue to generate a mapping relationship and save it.

[0034] In some embodiments, according to the UAV inspection task request, the state information and the environmental information, determining the target UAV associated with the target partition and the in-out information of the target UAV in the target partition comprises: According to the environment information of the target partition, a first set of unmanned aerial vehicles associated with the target partition is determined, wherein a matching degree of an unmanned aerial vehicle and the environment information of the target partition is determined based on a matching degree evaluation function, and the matching degree evaluation function is: wherein, represents the matching degree, represents the number of environment parameters, represents the weight coefficient of the i th environment parameter, represents the standardized value of the i th environment parameter, represents the conversion coefficient of the i th environment parameter corresponding to the unmanned aerial vehicle function, represents the standardized value of the i th environment parameter corresponding to the unmanned aerial vehicle function, for example, the standardized value of the unmanned aerial vehicle function can be the standardized value of wind resistance, the standardized value of load penetration, etc., and the corresponding environment parameter standardized value can be wind speed, visibility, etc., and the standardized value is assigned by an expert and standardized, and the standardization method is a common method, and the specific process is not described here; In response to the matching degree being greater than a fourth preset threshold, the unmanned aerial vehicle is associated with the target partition, wherein the fourth preset threshold can be set according to actual needs; According to the inspection type, the priority, and the state information, a second set of unmanned aerial vehicles associated with the target partition is selected from the first set of unmanned aerial vehicles, specifically, the first set of unmanned aerial vehicles is preliminarily screened according to the inspection type to determine the unmanned aerial vehicles matched with the inspection type, and the unmanned aerial vehicles in the preliminary screening result are secondarily screened according to the priority and the state information to obtain the second set of unmanned aerial vehicles, wherein a state evaluation value of the unmanned aerial vehicle is calculated based on the state information, and the calculation method includes: wherein, represents the state evaluation value of the unmanned aerial vehicle, represents the number of state parameters, represents the weight coefficient of the b th state parameter, represents the b th state parameter; According to the state evaluation value, a corresponding partition priority is matched, for example, the higher the state evaluation value, the higher the matched priority partition, and so on, which is not described here; The unmanned aerial vehicles in the second set of unmanned aerial vehicles are defined as target unmanned aerial vehicles associated with the target partition; Based on the spatiotemporal coordination mechanism and the inspection type, the entry and exit information of the target UAV in the target partition is determined. Specifically, based on parameters such as the partition boundary of the target partition, the 3D model of the inspection object, and the required resolution, the UAV flight altitude is calculated using the formula H = (D × f) / d, where H is the flight altitude, D represents the sampling distance (determined by the required resolution), f represents the focal length of the camera sensor, and d represents the size of a single pixel of the camera sensor. All parameters are in meters. Furthermore, based on the flight altitude and overlap rate, adjacent image acquisition nodes are calculated using the formula... ,in, The image acquisition spacing is represented by L, and the image scaling ratio is represented by L. This indicates the camera's field of view angle corresponding to the heading. The overlap rate is used to determine the acquisition path points. These path points are then connected and smoothed. Local adjustments are made to the smoothed path based on environmental data such as obstacles to ensure a safe distance between the path and obstacles, thus generating the corresponding UAV inspection path. The path smoothing method uses a polynomial curve to connect the path points, a common method; the specific connection process is not detailed here. The path start point is the node closest to the UAV nest in the partition, i.e., the UAV's entry point in the target partition. The UAV's exit point in the target partition is the intersection of the UAV inspection path and the partition boundary. The entry time is the time from the path start point to the node closest to the UAV nest in the partition. Furthermore, the smoothed path is divided into multiple segments, and an optimal speed profile is generated for each segment, including acceleration, deceleration, and cruising segments. Based on the acceleration, deceleration, and cruising segments, as well as the dwell time at each acquisition path point, the entire inspection task time is determined. Based on this time and the entry time, the final exit time is determined. The calculation method for the entire inspection task time is as follows: in, This indicates the total time of the inspection task. Indicates the number of line segments. Indicates the first The inspection time corresponding to each line segment. Indicates the number of data collection path points. Indicates the first The dwell time at each data collection path point; in, The calculation method is as follows: in, Indicates cruising speed. Indicates the maximum acceleration. Indicates the length of the line segment; In some embodiments, determining the communication link of the target UAV based on the cut-in and cut-out information of the plurality of sub-regions corresponding to the UAVs comprises: determining a path point sequence of the target UAV in the target sub-region based on the cut-in and cut-out information of the target UAV, i.e., the path point sequence generated by the above-mentioned collection of path points; determining the degree of accessibility of the communication link of the target UAV with the first target communication base station at the target path point based on the path point sequence, wherein the degree of accessibility of the communication link is determined by whether there is an obstacle between the target UAV and the first target communication base station and the degree of obstruction, and the two are inversely proportional, i.e., the greater the obstruction range, the smaller the degree of accessibility of the communication link; in response to the degree of accessibility of the communication link not meeting the preset standard, switching the first target communication base station of the target UAV at the target path node to a second target communication base station so that the degree of accessibility of the communication link meets the preset standard, wherein the preset standard is that the degree of accessibility of the communication link is within a preset range, which can be set according to actual needs, such as the occurrence of a communication blind area, etc. obtaining the communication load and the degree of interference of the communication link in a target time period based on the cut-in and cut-out information of the plurality of sub-regions corresponding to the UAVs, the target time period being determined based on the cut-in time and the cut-out time, the communication load referring to the amount of communication bandwidth resources used by a communication link in a time period, and the degree of interference referring to the degree of communication interference between multiple UAVs, such as co-frequency interference and adjacent frequency interference, etc. in response to the cooperative optimization value corresponding to the communication load and the degree of interference being greater than a first preset threshold, switching the second target communication base station of the target UAV at the target path node to a third target communication base station so that the degree of accessibility of the communication link meets the preset standard and the cooperative optimization value is less than or equal to the first preset threshold, wherein the calculation method of the cooperative optimization value is B = w4X4 + w5X5, wherein B represents the cooperative optimization value, w4 and w5 represent weight coefficients, X4 represents the communication load, X5 represents the degree of interference, and the first preset threshold can be set according to actual needs; defining the communication link generated by the target UAV at the target path node and the third target communication base station as a target communication link; defining a set of communication links generated by a plurality of target communication links as the communication link of the target UAV.

[0035] In some embodiments, based on the cut-in and cut-out information of the target UAV in the target sub-region and the communication link, controlling the target UAV to perform the inspection task corresponding to the UAV inspection task request comprises: According to the cut-in and cut-out information of the target UAV in the target subzone, the target UAV is controlled to perform the corresponding inspection task of the UAV inspection task request; Based on the communication link, the image data generated by the target UAV performing the inspection task is transmitted back to the data receiving end.

[0036] In some embodiments, the method further comprises: The image data transmitted back by the target UAV is acquired, and the image data is analyzed to determine whether there is an abnormal situation in the target subzone, wherein the image analysis process is performed by a central processor according to a pre-set code, and the specific analysis method is a commonly used method such as similarity matching, and the specific process is not described here. In response to the existence of an abnormal situation, an alarm information is generated and pushed, which is pushed to the user end to timely remind the user.

[0037] In the above-mentioned global AI inspection intelligent management and control method of the UAV, the method comprises: determining a target region and first associated information of the target region, dividing the target region based on the first associated information to generate a plurality of subzones, wherein the associated information is at least task attribute data used to describe the AI inspection task of the region; acquiring second associated information of the target subzone, determining the inspection type and priority of the target subzone based on the second associated information, generating a UAV inspection task request based on the second associated information, the inspection type and the priority; in response to receiving the UAV inspection task request, acquiring state information and environmental information of the UAV in the standby queue, determining a target UAV associated with the target subzone and cut-in and cut-out information of the target UAV in the target subzone according to the UAV inspection task request, the state information and the environmental information, the cut-in and cut-out information at least including time and position; determining the communication link of the target UAV according to the cut-in and cut-out information of the UAV corresponding to the plurality of subzones, and controlling the target UAV to perform the corresponding inspection task of the UAV inspection task request based on the cut-in and cut-out information of the target UAV in the target subzone and the communication link, the present application improves the inspection efficiency, accuracy and safety through decomposition of global task, multi-machine cooperative planning and real-time AI analysis.

[0038] It should be understood that, although Figure 2 The steps in the flowchart of the method are displayed in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figure 2At least one of the steps in the method can include a plurality of sub-steps or a plurality of stages, which are not necessarily performed at the same time, but can be performed at different times, and the order of the execution of the sub-steps or stages is not necessarily sequential, but can be performed in rotation or alternation with other steps or sub-steps or stages of other steps.

[0039] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram thereof can be as shown in Figure 3 The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a method for globally intelligent management and control of unmanned aerial vehicle inspection. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0040] Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0041] In one embodiment, a computer device is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1: determining a target area and first association information of the target area, dividing the target area based on the first association information, and generating a plurality of partitions, wherein the association information is at least task attribute data used to describe an AI inspection task of the area; S2: obtaining second association information of a target partition, determining an inspection type and a priority of the target partition based on the second association information, and generating an unmanned aerial vehicle inspection task request based on the second association information, the inspection type and the priority; S3: in response to receiving the UAV inspection task request, obtaining state information and environment information of a UAV in a standby queue, determining a target UAV associated with the target partition and cut-in and cut-out information of the target UAV in the target partition according to the UAV inspection task request, the state information and the environment information, the cut-in and cut-out information at least including time and position; S4: determining a communication link of the target UAV according to the cut-in and cut-out information of the UAV corresponding to the multiple partitions, and controlling the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the cut-in and cut-out information of the target UAV in the target partition and the communication link.

[0042] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps: S1: determining a target area and first associated information of the target area, dividing the target area based on the first associated information to generate multiple partitions, wherein the associated information is at least task attribute data used to describe an AI inspection task of the area; S2: obtaining second associated information of a target partition, determining an inspection type and a priority of the target partition based on the second associated information, and generating a UAV inspection task request based on the second associated information, the inspection type and the priority; S3: in response to receiving the UAV inspection task request, obtaining state information and environment information of a UAV in a standby queue, determining a target UAV associated with the target partition and cut-in and cut-out information of the target UAV in the target partition according to the UAV inspection task request, the state information and the environment information, the cut-in and cut-out information at least including time and position; S4: determining a communication link of the target UAV according to the cut-in and cut-out information of the UAV corresponding to the multiple partitions, and controlling the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the cut-in and cut-out information of the target UAV in the target partition and the communication link.

[0043] In one embodiment, a computer program product is provided, and the computer program product includes a computer program, and the computer program is executed by a processor to implement the following steps: S1: determining a target area and first associated information of the target area, dividing the target area based on the first associated information to generate multiple partitions, wherein the associated information is at least task attribute data used to describe an AI inspection task of the area; S2: obtaining second association information of the target partition, determining an inspection type and a priority of the target partition based on the second association information, and generating a UAV inspection task request based on the second association information, the inspection type, and the priority; S3: in response to receiving the UAV inspection task request, obtaining state information and environment information of a UAV in a standby queue, and determining a target UAV associated with the target partition and in-out information of the target UAV in the target partition according to the UAV inspection task request, the state information, and the environment information, the in-out information at least including time and position; S4: determining a communication link of the target UAV according to in-out information of a plurality of partitions corresponding to UAVs, and controlling the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the in-out information of the target UAV in the target partition and the communication link.

[0044] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0045] Each technical feature of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present disclosure.

[0046] The above embodiments only express several implementation ways of the present application, and the description is more specific and detailed, but it should not be understood as a limitation to the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which are all within the scope of protection of the present application.

Claims

1. A global AI inspection intelligent management and control method for a UAV, characterized in that, The method comprises: determining a target area and first associated information of the target area, dividing the target area based on the first associated information, and generating a plurality of partitions, wherein the associated information is at least task attribute data for describing an AI inspection task of the area; obtaining second associated information of a target partition, determining an inspection type and a priority of the target partition based on the second associated information, and generating a UAV inspection task request based on the second associated information, the inspection type, and the priority; in response to receiving the UAV inspection task request, obtaining state information and environmental information of a UAV in a standby queue, determining a target UAV associated with the target partition and entry and exit information of the target UAV in the target partition based on the UAV inspection task request, the state information, and the environmental information, the entry and exit information at least including time and position; determining a communication link of the target UAV based on the entry and exit information of the UAV corresponding to the plurality of partitions, and controlling the target UAV to perform an inspection task corresponding to the UAV inspection task request based on the entry and exit information of the target UAV in the target partition and the communication link. 2.The method of claim 1, wherein, Determining a target area and first associated information of the target area comprises: receiving an inspection request of a user terminal, the inspection request of the user terminal at least including a geographical area range; determining the target area based on the geographical area range; extracting first associated information of the target area from a database according to the target area, the first associated information at least including an inspection object, an inspection accuracy, and an inspection focus target. 3.The method of claim 2, wherein, Dividing the target area based on the first associated information to generate a plurality of partitions comprises: determining a first division rule of the target area according to an object attribute of the inspection object, including: in response to a first object attribute of the inspection object being a geographical feature, dividing the target area based on a boundary of the geographical feature to generate a first partition; in response to the first object attribute of the inspection object being a non-geographical feature, dividing the target area based on an area balance mechanism to generate a second partition; in response to the second partition having been divided, determining a second division rule of the target area based on the inspection accuracy and the inspection focus target, including: obtaining a level corresponding to the inspection accuracy and an attribute of the inspection focus target, and determining a task amount of the second partition based on the level and the attribute; adjusting a division result of the second partition based on a task amount balance mechanism and the task amount of the second partition to generate a third partition; defining the first partition and / or the third partition as the plurality of partitions generated by dividing the target area. 4.The method of claim 3, wherein, Obtaining second associated information of a target partition and determining an inspection type and a priority of the target partition based on the second associated information comprises: obtaining second associated information of a target partition, the second associated information at least including an inspection object; determine, based on the second object attribute of the inspection object, an inspection type of the target partition, the second object attribute including at least an inspection manner, an inspection frequency, and an inspection accuracy; determine, according to the inspection type of the target partition, a factor affecting an execution order of the target partition inspection task, and determine a comprehensive evaluation value according to the factor; determine, based on the comprehensive evaluation value, a priority of the target partition. 5.The method of claim 4, wherein, generating the UAV inspection task request based on the second correlation information, the inspection type, and the priority includes: obtaining the second correlation information, the inspection type, and the priority of the target partition; mapping the second correlation information, the inspection type, and the priority, generating a mapping relationship including a unique identifier, and filling the mapping relationship into a corresponding field of a task request template to generate the UAV inspection task request. 6.The method of claim 5, wherein, in response to receiving the UAV inspection task request, obtaining state information and environment information of a UAV in a standby queue includes: in response to receiving the UAV inspection task request, determining a UAV in an idle state and / or having a remaining task execution time less than a first preset threshold, and arranging, according to a task execution state, UAV identifiers corresponding to the UAVs in the standby queue in order; obtaining state information of the UAVs in the standby queue, the state information including at least a health state, an equipment state, a task execution state, and a real-time running state; obtaining environment information of the target partition, the environment information including at least meteorological information, geographical information, airspace information, and electromagnetic information; mapping the state information and the environment information of the UAVs in the standby queue to generate a mapping relationship and save the mapping relationship. 7.The method of claim 6, wherein, determining, according to the UAV inspection task request, the state information, and the environment information, a target UAV associated with the target partition and cut-in and cut-out information of the target UAV in the target partition includes: determining, according to the environment information of the target partition, a first set of UAVs associated with the target partition; screening, according to the inspection type, the priority, and the state information, a second set of UAVs associated with the target partition from the first set of UAVs; defining the UAVs in the second set of UAVs as target UAVs associated with the target partition; determining, based on a space-time coordination mechanism and the inspection type, cut-in and cut-out information of the target UAV in the target partition. 8.The method of claim 7, wherein, determining, according to cut-in and cut-out information of a plurality of partition corresponding UAVs, a communication link of the target UAV includes: determining, based on the cut-in and cut-out information of the target UAV, a path point sequence of the target UAV in the target partition; determining, according to the path point sequence, a communication link accessibility degree of the target UAV to a first target communication base station at a target path point; in response to the communication link accessibility degree not meeting a preset standard, switching the first target communication base station at the target path point to a second target communication base station to make the communication link accessibility degree meet the preset standard; According to the cut-in and cut-out information of the unmanned aerial vehicle corresponding to the multiple partitions, communication load and interference degree of the communication link in a target time period are obtained, the target time period being determined based on the cut-in time and the cut-out time; In response to a cooperative optimization value corresponding to the communication load and the interference degree being greater than a first preset threshold, a second target communication base station of the target unmanned aerial vehicle at a target path node is switched to a third target communication base station, so that the communication link reachability degree meets a preset standard and the cooperative optimization value is less than or equal to the first preset threshold; A communication link generated by the target unmanned aerial vehicle at the target path node and the third target communication base station is defined as a target communication link; A set of communication links generated by the multiple target communication links is defined as a communication link of the target unmanned aerial vehicle. 9.The method of claim 8, wherein, Based on the cut-in and cut-out information of the target unmanned aerial vehicle in the target partition and the communication link, the target unmanned aerial vehicle is controlled to perform an inspection task corresponding to the unmanned aerial vehicle inspection task request, which includes: According to the cut-in and cut-out information of the target unmanned aerial vehicle in the target partition, the target unmanned aerial vehicle is controlled to perform an inspection task corresponding to the unmanned aerial vehicle inspection task request; Based on the communication link, image data generated by the target unmanned aerial vehicle performing the inspection task is transmitted back to a data receiving end. 10.The method of claim 9, wherein, The method further includes: Obtaining the image data transmitted back by the target unmanned aerial vehicle, and analyzing the image data to determine whether there is an abnormal situation in the target partition; In response to the existence of an abnormal situation, alarm information is generated and pushed.

Images