Unmanned aerial vehicle inspection management method and system based on artificial intelligence

Abstract

The invention discloses an unmanned aerial vehicle inspection management method, system and device based on artificial intelligence and a medium. Performing flight inspection by using the unmanned aerial vehicle based on the user task, and obtaining traffic image data on the inspection line; transmitting the acquired traffic image data to a data processing terminal; performing data analysis on the acquired traffic image data based on an artificial intelligence technology to obtain a traffic condition analysis result; and determining a corresponding processing scheme according to the analysis result based on an artificial intelligence technology, and feeding back the processing scheme to the control terminal. According to the invention, the unmanned aerial vehicle is used for carrying out traffic inspection, the obtained image is processed in real time based on the artificial intelligence technology, the current traffic condition is accurately and intelligently analyzed, the characteristic traffic condition is obtained, the corresponding processing scheme is scientifically selected, and the specific processing information is rapidly and automatically generated and fed back to the control personnel. The traffic guidance pressure is greatly reduced, the intelligent process is optimized, and the intelligence of traffic dispersion and the overall working efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of drone applications, and particularly to an unmanned aerial vehicle inspection management method, system, computing device, and computer storage medium based on artificial intelligence. Background Art

[0002] With the development of the social and economic level and the improvement of people's living standards, the vehicle ownership in each region has continuously reached new highs, resulting in increasing traffic pressure in various places, and more effective guidance and management are required.

[0003] The most common current traffic command method is based on cameras installed along the road to collect road condition information at the location, and after summarization, obtain the general road condition information of the overall road network, and further arrange police officers to conduct command or control in key areas. However, the basis for making accurate command and management lies in the accuracy of obtaining traffic information. And this method obtains information based on several points on the road, that is, the information obtained by traffic cameras. The information obtained is discontinuous. For traffic problems that occur in locations not covered by the cameras, such as traffic accidents, additional police officers have to be arranged to reach the scene to obtain relevant information. This leads to discontinuous and inaccurate traffic information content, affecting the rationality of subsequent traffic command and management, greatly increasing labor costs and time costs, and reducing the timeliness of traffic command and the overall work efficiency. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides an unmanned aerial vehicle inspection management method based on artificial intelligence and a corresponding unmanned aerial vehicle inspection management system, computing device, and computer storage medium based on artificial intelligence.

[0005] According to one aspect of the present invention, an unmanned aerial vehicle inspection management method based on artificial intelligence is provided. The method includes:

[0006] Using an unmanned aerial vehicle to perform flight inspections based on user tasks and obtain traffic image data on the inspection route;

[0007] Transmitting the obtained traffic image data to a data processing terminal;

[0008] Performing data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result;

[0009] Determining a corresponding processing plan based on artificial intelligence technology according to the analysis result and feeding it back to a control terminal.

[0010] In the above solution, the step of using an unmanned aerial vehicle to perform flight inspections based on user tasks and obtain traffic image data on the inspection route further includes:

[0011] The task objectives at least include performing flight inspections according to a preset inspection route or performing flight inspections for a specific target area; among them,

[0012] If performing flight inspections according to a preset inspection route, traffic image data on the inspection route is obtained in real time;

[0013] If performing flight inspections for a specific target area, after arriving at the specific target area, fly around the area and obtain traffic image data in real time.

[0014] In the above solution, the traffic condition analysis result is obtained by performing data analysis on the obtained traffic image data based on artificial intelligence technology, which further includes:

[0015] Performing image recognition on the obtained traffic image data based on artificial intelligence technology to identify characteristic traffic conditions from it;

[0016] Selecting a corresponding feature information extraction method for the characteristic traffic conditions to complete the extraction of feature information;

[0017] Generating a corresponding traffic condition analysis result based on artificial intelligence based on the characteristic traffic conditions and the corresponding feature information.

[0018] In the above solution, the traffic condition analysis result is obtained by performing data analysis on the obtained traffic image data based on artificial intelligence technology, which further includes:

[0019] The characteristic traffic conditions at least include: road construction, road maintenance, traffic accidents, traffic congestion, occupation of the emergency lane, and temporary road risks;

[0020] Extracting the corresponding feature information for different characteristic traffic conditions; among them,

[0021] For road construction and road maintenance, at least obtain the range information of the operation section of the corresponding construction and maintenance operations and the lane occupation information;

[0022] For traffic accidents, at least obtain accident scene photos, accident location information, accident vehicle license plate information, information on injured persons, lane occupation information, and congestion range information;

[0023] For traffic congestion, at least obtain congestion range information;

[0024] For the occupation of the emergency lane, at least obtain the occupation location information, the license plate information of the occupied vehicle, and the occupation photo;

[0025] For temporary road risks, at least obtain risk location information and risk photos.

[0026] In the above solution, based on artificial intelligence technology, determining a corresponding processing solution according to the analysis result and feeding it back to the control terminal further includes:

[0027] For road construction and road maintenance, generating a construction and / or maintenance notice based on the obtained feature information and feeding it back to the control terminal;

[0028] For traffic accidents, generating an alarm message and a detour message in combination with the obtained feature information and feeding them back to the control terminal;

[0029] For traffic congestion, generating congestion information and a detour message based on the obtained feature information and feeding them back to the control terminal;

[0030] For the occupation of the emergency lane, generating an alarm message based on the obtained feature information and generating an avoidance prompt message based on the occupation position information and feeding them back to the control terminal;

[0031] For temporary road risks, generating a risk prompt message based on the obtained feature information and feeding it back to the control terminal.

[0032] In the above solution, based on artificial intelligence technology, performing data analysis on the obtained traffic image data to obtain a traffic condition analysis result further includes:

[0033] Performing object recognition on the target object for the traffic image data to obtain an object recognition result;

[0034] Judging the object type based on the object recognition result, and judging whether there is a risk according to the object type and its location in the traffic image data; among them,

[0035] If the target object in the traffic image data is in a safe position, it is determined that there is no risk;

[0036] If the target object in the traffic image data is in an unsafe position, judge whether its object type belongs to an abnormal type;

[0037] If the object type belongs to an abnormal type, it is determined that the current characteristic traffic condition belongs to a temporary road risk.

[0038] In the above solution, the method further includes:

[0039] If the object type belongs to a normal type, obtain the moving speed and moving direction of the target object, and judge whether its moving type belongs to an abnormal moving type based on the conventional motion parameters corresponding to the position of the target object;

[0040] If the target object does not belong to an abnormal moving type, it is determined that there is no risk, and the determination process ends;

[0041] If the target object belongs to the abnormal movement type, it is determined that the current characteristic traffic condition belongs to the temporary road risk.

[0042] According to another aspect of the present invention, there is provided an artificial intelligence-based drone inspection and management system, including: a data acquisition module, a transmission module, a data analysis module, and a processing information generation module; wherein,

[0043] The data acquisition module is used to use the drone to perform flight inspections based on user tasks and acquire traffic image data on the inspection route;

[0044] The transmission module is used to transmit the acquired traffic image data to the data processing terminal;

[0045] The data analysis module is used to perform data analysis on the acquired traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result;

[0046] The processing information generation module is used to determine a corresponding processing plan based on artificial intelligence technology according to the analysis result and feedback it to the control terminal.

[0047] According to yet another aspect of the present invention, there is provided a computing device, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete mutual communication through the communication bus;

[0048] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform the operations corresponding to an artificial intelligence-based drone inspection and management method as described above.

[0049] According to still another aspect of the present invention, there is provided a computer storage medium, and at least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to perform the operations corresponding to an artificial intelligence-based drone inspection and management method as described above.

[0050] According to the technical solution provided by the present invention, a drone is used to perform flight inspections based on user tasks and obtain traffic image data on the inspection route; the obtained traffic image data is transmitted to a data processing terminal; data analysis is performed on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result; based on artificial intelligence technology, a corresponding processing solution is determined according to the analysis result and fed back to a control terminal. By using the drone to perform flight inspections according to the tasks set by the user and obtaining traffic image data from the inspection route, the continuity of data acquisition is ensured, the current traffic condition information can be clearly learned, the entire congestion range, repair and maintenance range or specific accident occurrence points can be accurately determined, and the drone can replace police officers to quickly reach the scene of the accident or risk point and obtain the image information of the scene as early as possible, which helps to conduct traffic guidance and processing as soon as possible in the follow-up; different inspection methods can be selected based on different information acquisition requirements, namely specific route inspection or specific target inspection, so as to meet the acquisition of complete traffic information on the route or the rapid and accurate acquisition of specific target information; artificial intelligence technology is used to perform intelligent analysis and recognition on traffic image data, scientifically determine the current characteristic traffic condition type, obtain corresponding characteristic information from the image data according to different types, quickly obtain the relevant information most urgently needed for different traffic condition types, and generate processing information for feedback based on specific types and their corresponding relevant information for relevant personnel to release information or execute specific processing methods, thereby greatly improving the intelligent level of traffic command and the timeliness of information acquisition and subsequent processing, effectively reducing the impact caused by abnormal traffic conditions, avoiding many risks, improving safety, and also enhancing the scientificity and efficiency of traffic command. In addition, based on artificial intelligence technology, type judgment, position judgment and motion type judgment are performed on the target objects in the traffic image data to scientifically determine whether the target object has caused a temporary road risk, so as to obtain relevant information in time to issue a prompt and avoid the occurrence of traffic accidents.

[0051] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written specification and the drawings.

[0052] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0053] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0054] Figure 1 Shows a schematic flow chart of an artificial intelligence-based UAV inspection management method according to an embodiment of the present invention;

[0055] Figure 2 Shows a schematic flow chart of an artificial intelligence-based traffic condition analysis method according to an embodiment of the present invention;

[0056] Figure 3 Shows a schematic flow chart of an artificial intelligence-based road temporary risk identification method according to an embodiment of the present invention;

[0057] Figure 4 Shows a structural block diagram of an artificial intelligence-based UAV inspection management system according to an embodiment of the present invention;

[0058] Figure 5 Shows a schematic structural diagram of a computing device according to an embodiment of the present invention. Detailed implementation manners

[0059] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0060] Figure 1 Shows a schematic flow chart of an artificial intelligence-based UAV inspection management method according to an embodiment of the present invention. The method includes the following steps:

[0061] Step S101: Use a UAV to perform flight inspections based on user tasks and obtain traffic image data on the inspection route.

[0062] Specifically, the task objectives at least include performing flight inspections according to a preset inspection route or performing flight inspections on a specific target area; among them,

[0063] If performing flight inspections according to a preset inspection route, obtain traffic image data on the inspection route in real time;

[0064] If performing flight inspections on a specific target area, perform circular flight on the area after flying to the specific target area and obtain traffic image data in real time.

[0065] Preferably, the specific target area may be accurate location information; it may also be a traffic event within a general area, which is further confirmed during the inspection. For example, based on other information sources, it is determined that there is a traffic accident at a certain kilometer on a certain road in a certain direction, and this accurate location information is used as the specific target area for flight inspection; or, based on other information sources, it is determined that there is a traffic accident between Bridge A and Bridge B on a certain road, and this area is inspected, and the specific target area is determined during the flight inspection.

[0066] Step S102: Transmit the obtained traffic image data to the data processing terminal.

[0067] Preferably, the data transmission is carried out using mobile communication technology.

[0068] Step S103: Perform data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result.

[0069] Step S104: Determine a corresponding processing plan based on the analysis result based on artificial intelligence technology and feedback it to the control terminal.

[0070] In addition, the transmission of control instructions for the unmanned aerial vehicle is also based on 5G mobile communication technology; and during the inspection process, the task corresponding to the control instruction is preferably completed based on the user's control instruction; wherein, the task may be other tasks unrelated to the currently executed task, or it may be a new task based on the currently executed task. For example, during the flight inspection according to the normal preset inspection route, a traffic accident occurs at another location, and according to the control instruction, it flies to the accident location first to obtain information; or, during the flight inspection according to the normal preset inspection route, relevant data on the temporary risk of the road caused by road spillage is additionally obtained on this inspection route.

[0071] According to the UAV inspection management method based on artificial intelligence provided by this embodiment, by using the UAV to perform flight inspections according to the tasks set by the user and obtaining traffic image data from the inspection route, the continuity of data acquisition is ensured, the current traffic condition information can be clearly obtained, the entire congestion range, repair and maintenance range or specific accident occurrence points can be accurately determined, and the UAV can replace the police officers to quickly reach the scene of the accident or risk point, and obtain the image information of the scene as early as possible, which helps to conduct traffic guidance and processing as soon as possible in the follow-up; different inspection methods can be selected based on different information acquisition requirements, that is, specific route inspection or specific target inspection, so as to meet the acquisition of complete traffic information on the route or the rapid and accurate acquisition of specific target information; the artificial intelligence technology is used to perform intelligent analysis and recognition on the traffic image data, scientifically determine the current characteristic traffic condition, and obtain the relevant information of the most priority requirements of different traffic condition types, and generate processing information for feedback accordingly, for relevant personnel to release information or execute specific processing methods, thereby greatly improving the intelligence level of traffic command and the timeliness of information acquisition and subsequent processing, effectively reducing the impact caused by abnormal traffic conditions, avoiding many risks, improving safety, and also improving the scientificity and efficiency of traffic command.

[0072] The data analysis is carried out based on the traffic image data according to the following method flow.

[0073] Figure 2 The flow chart of a traffic condition analysis method based on artificial intelligence according to an embodiment of the present invention is shown;

[0074] As Figure 2 shown, the method includes the following steps:

[0075] Step S201, perform image recognition on the obtained traffic image data based on artificial intelligence technology, and identify the characteristic traffic condition from it.

[0076] Preferably, the characteristic traffic condition at least includes: road construction, road maintenance, traffic accident, traffic congestion, occupation of the emergency lane and temporary road risks.

[0077] Step S202, select the corresponding characteristic information extraction method for the characteristic traffic condition to complete the extraction of characteristic information.

[0078] Preferably, based on different characteristic traffic conditions, extract the corresponding characteristic information; among them,

[0079] For road construction and road maintenance, at least obtain the information of the operation section range and the lane occupation information of the corresponding construction and maintenance operations;

[0080] For traffic accidents, at least obtain accident scene photos, accident location information, accident vehicle license plate information, personnel injury information, lane occupancy information, and congestion range information;

[0081] For traffic congestion, at least obtain congestion range information;

[0082] For emergency lane occupancy, at least obtain occupancy location information, occupied vehicle license plate information, and occupancy photos;

[0083] For temporary road risks, at least obtain risk location information and risk photos.

[0084] Step S203: Generate corresponding traffic condition analysis results based on artificial intelligence based on the characteristic traffic conditions and corresponding characteristic information.

[0085] Furthermore, based on artificial intelligence technology, determine corresponding treatment plans according to the analysis results and feedback them to the control terminal.

[0086] Preferably, for road construction and road maintenance, generate construction and / or maintenance notices based on the obtained characteristic information and feedback them to the control terminal; among them, the construction and / or maintenance notices should be combined with the corresponding in-road work notices, and at least include information such as the sections, directions, lanes, and times of construction and maintenance, so that drivers can fully and comprehensively understand the relevant road administration work information, optimize their own trips, and reduce the possibility of congestion.

[0087] For traffic accidents, generate warning information and detour information based on the obtained characteristic information and feedback them to the control terminal; among them, obtain the same-direction lines adjacent to the accident location information, and based on the current road congestion information, screen the routes with a smooth road congestion level from them to generate detour information, so as to optimize their own trips.

[0088] For traffic congestion, generate congestion information and detour information based on the obtained characteristic information and feedback them to the control terminal;

[0089] For emergency lane occupancy, generate warning information based on the obtained characteristic information, and generate avoidance prompt information based on the occupancy location information and feedback it to the control terminal;

[0090] For temporary road risks, generate risk prompt information based on the obtained characteristic information and feedback it to the control terminal.

[0091] Preferably, after the above various different traffic management information is fed back to the control terminal, it can be automatically published with the existing traffic information control system or a third-party electronic map software that has completed networking, or a prompt message can be generated before publishing to prompt the control personnel to complete the manual control information release.

[0092] According to the above method, artificial intelligence technology can be used to intelligently analyze and identify traffic image data, scientifically determine the current type of characteristic traffic conditions, obtain corresponding characteristic information from the image data according to different types, quickly obtain relevant information on the most urgent needs of different traffic condition types, and generate processing information for feedback based on specific types using their corresponding relevant information, for relevant personnel to release information or execute specific processing methods. This greatly improves the intelligence level of traffic command, as well as the timeliness of information acquisition and subsequent processing, effectively reduces the impact caused by abnormal traffic states, avoids many risks, improves safety, and also enhances the scientific nature and efficiency of traffic command.

[0093] Figure 3 Fig. shows a schematic flowchart of a method for identifying temporary road risks based on artificial intelligence according to an embodiment of the present invention;

[0094] As Figure 3 shown, the method includes the following steps:

[0095] Step S301, perform object recognition on the target object for traffic image data to obtain an object recognition result.

[0096] Specifically, before the rail manipulator, the indicator, and the intelligent tool basket perform their respective operations, measure the third weight of the intelligent tool basket; wherein, the third weight is usually the empty bin weight of the intelligent tool basket without placing any items.

[0097] Preferably, a vision self-attention neural network model (Vision Transformer, ViT) based on the transformer architecture is used as the image recognition model to perform object recognition on traffic image data. Further, during the training process of the image recognition model, focal loss is used as the loss function to reduce the situation of class imbalance; wherein, the focal loss function is

[0098] FL(p t ) = -α(1 - p t ) γ log(p t )

[0099] wherein, p t is the probability value predicted by the image recognition model; α is the class balance factor; γ is the adjustment factor.

[0100] Preferably, γ ∈ [0, 5], and when p t →1, γ = 0.

[0101] Step S302: Based on the object recognition result, determine the object type, and judge whether there is a risk according to the object type and its location in the traffic image data.

[0102] Specifically, if the target object in the traffic image data is in a safe position, it is determined that there is no risk, and step S307 is executed.

[0103] If the target object in the traffic image data is in an unsafe position, step S303 is executed.

[0104] Step S303: Judge whether the object type of the target object belongs to an abnormal type.

[0105] Specifically, if so, it is determined that the current characteristic traffic condition belongs to a temporary road risk, and step S309 is executed.

[0106] If not, that is, the object type of the target object belongs to a normal type, step S304 is executed.

[0107] Step S304: Obtain the moving speed and moving direction of the target object, based on the conventional motion parameters corresponding to the location of the target object.

[0108] Step S305: Judge whether the motion type of the target object belongs to an abnormal motion type.

[0109] Specifically, if the target object belongs to an abnormal motion type, step S306 is executed.

[0110] If the target object does not belong to an abnormal motion type, it is determined that there is no risk, and step S307 is executed.

[0111] Step S306: Determine that the current characteristic traffic condition belongs to a temporary road risk.

[0112] Step S307: End the determination process.

[0113] Preferably, the above judgment process can use the FCMAE (Fully Convolutional Masked Auto Encoder) framework based on the convolutional neural network to construct an image recognition model to complete image recognition; among them, the masked auto encoder (MAE) and the decoder are used to form an asymmetric encoding-decoding architecture to realize the function of self-supervised learning, and the feature collapse is alleviated based on the feature cosine distance analysis and global response normalization to generate an image recognition model. Further use the historical traffic image data, screen out the images of various characteristic traffic conditions from it to construct a training set and a test set, train and test the model, and finally generate an identification model for the traffic image data.

[0114] According to the above method, based on artificial intelligence technology, it is possible to determine the type, position, and movement type of the target object in traffic image data, scientifically determine whether the target object has caused a temporary road risk, improve the accuracy of the determination, so as to timely obtain relevant information to issue a prompt and avoid the occurrence of traffic accidents.

[0115] Figure 4 Fig. 5 shows a structural block diagram of an unmanned aerial vehicle (UAV) inspection management system based on artificial intelligence according to an embodiment of the present invention;

[0116] As Figure 4 shown, the system includes: a data acquisition module 401, a transmission module 402, a data analysis module 403, and a processing information generation module 404; wherein,

[0117] The data acquisition module 401 is configured to use a UAV to perform flight inspections based on a user task and acquire traffic image data on the inspection route.

[0118] Specifically, the data acquisition module 401 is further configured to,

[0119] The task objective at least includes performing flight inspections according to a preset inspection route or performing flight inspections on a specific target area; wherein,

[0120] If performing flight inspections according to a preset inspection route, then acquire traffic image data on the inspection route in real time;

[0121] If performing flight inspections on a specific target area, then perform circular flight on the area after flying to the specific target area and acquire traffic image data in real time.

[0122] The transmission module 402 is configured to transmit the acquired traffic image data to a data processing terminal.

[0123] The data analysis module 403 is configured to perform data analysis on the acquired traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result.

[0124] Specifically, the data analysis module 403 is further configured to,

[0125] Perform image recognition on the acquired traffic image data based on artificial intelligence technology to identify characteristic traffic conditions therefrom;

[0126] Select a corresponding feature information extraction method for the characteristic traffic conditions to complete the extraction of feature information;

[0127] Generate a corresponding traffic condition analysis result based on artificial intelligence based on the characteristic traffic conditions and the corresponding feature information.

[0128] Preferably, the data analysis module 403 is further configured to

[0129] The characteristic traffic conditions at least include: road construction, road maintenance, traffic accidents, traffic congestion, occupation of the emergency lane, and temporary road risks;

[0130] Based on different characteristic traffic conditions, extract the corresponding characteristic information; among them,

[0131] For road construction and road maintenance, at least obtain the range information of the operation section and the lane occupation information of the corresponding construction and maintenance operations;

[0132] For traffic accidents, at least obtain accident scene photos, accident location information, accident vehicle license plate information, personnel injury information, lane occupation information, and congestion range information;

[0133] For traffic congestion, at least obtain congestion range information;

[0134] For the occupation of the emergency lane, at least obtain the occupation location information, the license plate information of the occupied vehicle, and the occupation photos;

[0135] For temporary road risks, at least obtain risk location information and risk photos.

[0136] Preferably, the data analysis module 403 is further configured to

[0137] Perform object recognition on the target object for traffic image data to obtain an object recognition result;

[0138] Based on the object recognition result, judge the object type, and judge whether there is a risk according to the object type and its location in the traffic image data; among them,

[0139] If the target object in the traffic image data is in a safe position, it is determined that there is no risk;

[0140] If the target object in the traffic image data is in an unsafe position, then judge whether its object type belongs to an abnormal type;

[0141] If the object type belongs to an abnormal type, it is determined that the current characteristic traffic condition belongs to a temporary road risk;

[0142] If the object type belongs to a normal type, obtain the moving speed and moving direction of the target object, and judge whether its movement type belongs to an abnormal movement type based on the conventional movement parameters corresponding to the position of the target object;

[0143] If the target object does not belong to an abnormal movement type, it is determined that there is no risk, and the determination process ends;

[0144] If the target object belongs to the abnormal movement type, it is determined that the current characteristic traffic condition belongs to a temporary road risk.

[0145] The processing information generation module 404 is configured to determine a corresponding processing solution based on the analysis result according to artificial intelligence technology and feedback it to the control terminal.

[0146] Preferably, the processing information generation module 404 is further configured to

[0147] generate a construction and / or maintenance notice based on the obtained characteristic information for road construction and road maintenance and feedback it to the control terminal;

[0148] generate an alarm message and a detour message based on the obtained characteristic information for traffic accidents and feedback them to the control terminal;

[0149] generate a congestion message and a detour message based on the obtained characteristic information for traffic congestion and feedback them to the control terminal;

[0150] generate an alarm message based on the obtained characteristic information for the occupation of the emergency lane, and generate an avoidance prompt message based on the occupation position information and feedback it to the control terminal;

[0151] generate a risk prompt message based on the obtained characteristic information for the temporary road risk and feedback it to the control terminal.

[0152] The unmanned aerial vehicle (UAV) inspection management system based on artificial intelligence provided by this embodiment includes: a data acquisition module, a transmission module, a data analysis module, and a processing information generation module. Among them, the data acquisition module is used to use the UAV to perform flight inspections based on user tasks and acquire traffic image data on the inspection route; the transmission module is used to transmit the acquired traffic image data to the data processing terminal; the data analysis module is used to perform data analysis on the acquired traffic image data based on artificial intelligence technology to obtain traffic condition analysis results; the processing information generation module is used to determine corresponding processing plans based on artificial intelligence technology according to the analysis results and feedback them to the control terminal. Through the UAV inspection management system based on artificial intelligence provided by this embodiment, by using the UAV to perform flight inspections according to the tasks set by the user and acquiring traffic image data from the inspection route, the continuity of data acquisition is ensured, the current traffic condition information is clearly known, the entire congestion range, repair and maintenance range, or specific accident occurrence points are accurately determined, and the UAV can replace police officers to quickly reach the scene of accidents and risk points to obtain image information of the scene as early as possible, which helps to quickly conduct traffic guidance and processing subsequently; different inspection methods can be selected based on different information acquisition requirements, that is, specific route inspection or specific target inspection, so as to meet the acquisition of complete traffic information on the route or the rapid and accurate acquisition of specific target information; the traffic image data is intelligently analyzed and recognized using artificial intelligence technology to scientifically determine the current characteristic traffic condition type, and the corresponding characteristic information is obtained from the image data according to different types, quickly obtaining the relevant information most urgently needed for different traffic condition types, and generating processing information based on the specific type and its corresponding relevant information to complete the feedback for relevant personnel to release information or execute specific processing methods, thereby greatly improving the intelligence level of traffic command and the timeliness of information acquisition and subsequent processing, effectively reducing the impact caused by abnormal traffic conditions, avoiding many risks, improving safety, and also enhancing the scientificity and efficiency of traffic command. In addition, based on artificial intelligence technology, type judgment, position judgment, and motion type judgment are performed on the target objects in the traffic image data to scientifically determine whether the target objects pose temporary road risks, so as to obtain relevant information in a timely manner to issue prompts and avoid traffic accidents.

[0153] The present invention also provides a non-volatile computer storage medium, and the computer storage medium stores at least one executable instruction, and the executable instruction can execute a method for managing UAV inspection based on artificial intelligence in any of the above method embodiments.

[0154] Figure 5 The structural schematic diagram of a computing device according to an embodiment of the present invention is shown, and the specific implementation of the computing device is not limited in the specific embodiments of the present invention.

[0155] As Figure 5 shown, the computing device may include: a processor 502, a communications interface 504, a memory 506, and a communication bus 508.

[0156] Wherein:

[0157] The processor 502, the communications interface 504, and the memory 506 communicate with each other via the communication bus 508.

[0158] The communications interface 504 is used to communicate with network elements of other devices such as clients or other servers.

[0159] The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned embodiments of the method for unmanned aerial vehicle inspection management based on artificial intelligence.

[0160] Specifically, the program 510 may include program code, and the program code includes computer operation instructions.

[0161] The processor 502 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0162] The memory 506 is used to store the program 510. The memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0163] The program 510 is specifically used to cause the processor 502 to execute a method for unmanned aerial vehicle inspection management based on artificial intelligence in any of the above method embodiments. For the specific implementation of each step in the program 510, reference may be made to the corresponding steps and units in the above-mentioned embodiments of the method for unmanned aerial vehicle inspection management based on artificial intelligence, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices and modules can refer to the corresponding process descriptions in the foregoing method embodiments, which will not be repeated here.

[0164] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems can also be used in conjunction with the teachings based hereon. The structure required to construct such systems will be apparent from the above description. In addition, the present invention is not directed to any particular programming language. It should be appreciated that the present invention as described herein can be implemented using various programming languages, and the description of specific languages above is for the purpose of disclosing the best mode of the present invention.

[0165] In the specification provided herein, numerous specific details are set forth. However, it can be understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0166] Similarly, it should be understood that in order to streamline this disclosure and assist in understanding one or more of the various inventive aspects, in the foregoing description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the claims reflect, the inventive aspects lie in less than all of the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0167] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0168] In addition, those skilled in the art can understand that although some embodiments described herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0169] Each component embodiment of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (such as a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0170] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. An unmanned aerial vehicle (UAV) inspection management method based on artificial intelligence, comprising: Using a UAV to perform flight inspections based on user tasks and obtaining traffic image data on the inspection route; Transmitting the obtained traffic image data to a data processing terminal; Performing data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result; Determining a corresponding processing plan based on the analysis result according to artificial intelligence technology and feeding it back to the control terminal.

2. The method according to claim 1, wherein The step of using a UAV to perform flight inspections based on user tasks and obtaining traffic image data on the inspection route further includes: The task objectives at least include flying for inspections according to a preset inspection route or flying for inspections in a specific target area; wherein, If flying for inspections according to a preset inspection route, traffic image data on the inspection route is obtained in real time; If flying for inspections in a specific target area, after arriving at the specific target area, fly around the area and obtain traffic image data in real time.

3. The method according to claim 1, characterized in that, The step of performing data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result further includes: Performing image recognition on the obtained traffic image data based on artificial intelligence technology to identify characteristic traffic conditions; Selecting a corresponding feature information extraction method for the characteristic traffic conditions to complete the extraction of feature information; Generating a corresponding traffic condition analysis result based on artificial intelligence based on the characteristic traffic conditions and the corresponding feature information.

4. The method according to claim 3, wherein The step of performing data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result further includes: The characteristic traffic conditions at least include: road construction, road maintenance, traffic accidents, traffic congestion, emergency lane occupancy, and temporary road risks; Based on different characteristic traffic conditions, extracting corresponding characteristic information; wherein, For road construction and road maintenance, at least obtain the range information of the operation section of the corresponding construction and maintenance operations and the lane occupancy information; For traffic accidents, at least obtain accident scene photos, accident location information, accident vehicle license plate information, information on injured persons, lane occupancy information, and congestion range information; For traffic congestion, at least obtain congestion range information; For emergency lane occupancy, at least obtain the occupancy location information, the license plate information of the occupied vehicle, and the occupancy photo; For temporary road risks, at least obtain the risk location information and the risk photo.

5. The method according to claim 1, characterized in that, The step of determining a corresponding processing plan based on the analysis result according to artificial intelligence technology and feeding it back to the control terminal further includes: For road construction and road maintenance, generating a construction and / or maintenance notice based on the obtained characteristic information and feeding it back to the control terminal; For traffic accidents, generating an alarm message and a detour message based on the obtained characteristic information and feeding them back to the control terminal; For traffic congestion, generating a congestion message and a detour message based on the obtained characteristic information and feeding them back to the control terminal; For emergency lane occupancy, generating an alarm message based on the obtained characteristic information, and generating an avoidance prompt message based on the occupancy location information and feeding it back to the control terminal; For temporary road risks, risk warning information is generated based on the obtained feature information and fed back to the control terminal.

6. The method according to claim 1, characterized in that, The method of performing data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result further includes: Performing object recognition on the target object for the traffic image data to obtain an object recognition result; Judging the object type based on the object recognition result, and judging whether there is a risk according to the object type and its location in the traffic image data; where If the target object in the traffic image data is in a safe position, it is determined that there is no risk; If the target object in the traffic image data is in an unsafe position, then it is judged whether the object type belongs to an abnormal type; If the object type belongs to an abnormal type, it is determined that the current characteristic traffic condition belongs to a temporary road risk.

7. The method according to claim 6, wherein The method further includes: If the object type belongs to a normal type, obtain the moving speed and moving direction of the target object, and judge whether its movement type belongs to an abnormal movement type based on the conventional movement parameters corresponding to the location of the target object; If the target object does not belong to an abnormal movement type, it is determined that there is no risk and the determination process ends; If the target object belongs to an abnormal movement type, it is determined that the current characteristic traffic condition belongs to a temporary road risk.

8. An unmanned aerial vehicle inspection management system based on artificial intelligence, comprising: A data acquisition module, a transmission module, a data analysis module, and a processing information generation module; where The data acquisition module is used to perform flight inspections based on user tasks using an unmanned aerial vehicle and obtain traffic image data on the inspection route; The transmission module is used to transmit the obtained traffic image data to the data processing terminal; The data analysis module is used to perform data analysis on the obtained traffic image data based on artificial intelligence technology to obtain a traffic condition analysis result; The processing information generation module is used to determine a corresponding processing solution based on artificial intelligence technology according to the analysis result and feed it back to the control terminal.

9. A computing device, comprising: A processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to a method for unmanned aerial vehicle inspection management based on artificial intelligence as described in any one of claims 1-7.

10. A computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to a method for unmanned aerial vehicle inspection management based on artificial intelligence as described in any one of claims 1-7.

Images