An intelligent UAV inspection system

Abstract

Multiple embodiments of this specification relate to the field of automation technology, and specifically relate to an intelligent unmanned aerial vehicle (UAV) inspection system. An intelligent UAV inspection system, the system performs the following steps: reading a target area range to be inspected and historical inspection records; generating an event heat map of the target area range according to the historical inspection records, the event heat map recording the probability distribution of events occurring at each position within the target area range; dividing the target area range into a number of sub-areas according to the event heat map, the sub-areas being areas where the difference in the probability of events occurring is less than a preset threshold; generating an inspection route set and an inspection frequency for each sub-area, the inspection route set including a number of inspection routes; generating an airport location according to the inspection route set, and controlling the UAV to sequentially and cyclically execute the inspection routes in the inspection route set according to the inspection frequency.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of automation technology, and more particularly to an intelligent unmanned aerial vehicle (UAV) inspection system. Background Art

[0002] An intelligent UAV inspection system is an advanced integrated management system that integrates modern UAV technology, sensor technology, and data processing and analysis tools. It is specifically designed to efficiently and accurately monitor and inspect specific areas or facilities. This system utilizes the latest flight control technology, enabling the UAV to autonomously fly along a preset path and flexibly adjust the flight mode according to mission requirements. By carrying advanced sensor devices such as high-definition cameras, infrared thermal imagers, and lidar, the intelligent UAV can capture information about the target area. During the mission execution, the UAV transmits the collected data back to the ground control center in real time through wireless communication technology. Due to its efficient and convenient characteristics, UAV inspection is widely used in various fields, including urban inspections, to detect illegal vehicle parking, illegal garbage stacking, etc., and help deal with emerging problems in a timely and rapid manner. Summary of the Invention

[0003] Multiple embodiments of this specification describe an intelligent UAV inspection system.

[0004] In a first aspect, embodiments of this specification provide an intelligent UAV inspection system, which performs the following steps:

[0005] Read the target area range to be inspected and historical inspection records;

[0006] Generate an event heat map of the target area range based on the historical inspection records, where the event heat map records the probability distribution of events occurring at each location within the target area range;

[0007] Divide the target area range into several sub-areas according to the event heat map, where the sub-areas are areas where the difference in the probability of events occurring is less than a preset threshold;

[0008] Generate an inspection route set and an inspection frequency for each sub-area, where the inspection route set includes several inspection routes;

[0009] Generate an airport location according to the inspection route set, and control the UAV to sequentially and cyclically execute the inspection routes in the inspection route set according to the inspection frequency.

[0010] In a second aspect, embodiments of this specification provide another intelligent UAV inspection system, including:

[0011] A reading module that reads the target area range to be inspected and historical inspection records;

[0012] A reading module that generates an event heat map of the target area range based on historical inspection records, where the event heat map records the probability distribution of events occurring at each location within the target area range;

[0013] A partitioning module that partitions the target area range into several sub - areas according to the event heat map, where the sub - areas are areas where the difference in the probability of events occurring is less than a preset threshold;

[0014] A generating module that generates an inspection route set and an inspection frequency for each sub - area, where the inspection route set includes several inspection routes;

[0015] An execution module that generates airport positions according to the inspection route set, and controls the drone to sequentially and cyclically execute the inspection routes in the inspection route set according to the inspection frequency.

[0016] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory;

[0017] The processor is connected to the memory;

[0018] The memory is used to store executable program code;

[0019] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any of the above aspects.

[0020] In a fourth aspect, an embodiment of this specification provides a computer - readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0021] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented.

[0022] The beneficial effects brought by the technical solutions provided in some embodiments of this specification at least include:

[0023] In multiple embodiments of this specification, the provided intelligent drone inspection system realizes differentiated inspection of areas with different event probabilities by means of the control of the event heat map and the inspection frequency, which helps to detect events earlier during inspections and improve the efficiency of event handling; through the division of grids, an event heat map can be quickly obtained based on historical inspection records, and by means of equivalent values, the contingency of historical inspection records can be compensated.

[0024] Other features and advantages of multiple embodiments of this specification will be further revealed in the following detailed implementation manners and drawings. Brief Description of the Drawings

[0025] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 It is a schematic diagram of the event heat map provided by the embodiments of this specification.

[0027] Figure 2 It is a schematic diagram of the system architecture of the embodiments of this specification.

[0028] Figure 3 It is a schematic diagram of the interaction interface of the embodiments of this specification.

[0029] Figure 4 It is a schematic diagram of the flow of the drone inspection method provided by the embodiments of this specification.

[0030] Figure 5 It is an event schematic diagram provided by the embodiments of this specification.

[0031] Figure 6 It is a schematic diagram of the event heat map generation process provided by the embodiments of this specification.

[0032] Figure 7 It is a schematic diagram of obtaining approximate surrounding squares in the embodiments of this specification.

[0033] Figure 8 It is a schematic diagram of the process of generating an inspection route set in the embodiments of this specification.

[0034] Figure 9 It is a schematic diagram of the drone inspection system in the embodiments of this specification.

[0035] Figure 10 It is an example picture of the airport of the drone in the embodiments of this specification.

[0036] Figure 11 It is a schematic diagram of the electronic device provided by the embodiments of this specification. Detailed Embodiments

[0037] The following will explain and illustrate the technical solutions in the embodiments of this specification in conjunction with the drawings of the embodiments of this specification. However, the following embodiments are only the preferred embodiments of this specification, not all of them. Based on the embodiments in the embodiments, other embodiments obtained by those of ordinary skill in the art without creative efforts all fall within the protection scope of this specification.

[0038] In the description, claims and the above drawings of this specification, the terms "first", "second", "third", etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0039] In the following description, the use of terms such as "inside", "outside", "above", "below", "left", "right", etc. to indicate orientation or positional relationship is only for the convenience of describing embodiments and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this specification.

[0040] The data involved in this application are all information and data authorized by users or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0041] Before introducing the technical solutions described in this specification, the application scenarios and related technologies of the technical solutions are introduced.

[0042] The application of the intelligent unmanned aerial vehicle (UAV) inspection system in urban appearance management can greatly improve urban management efficiency, reduce the cost of manual inspection, and can quickly respond to various emergencies. For example, through the UAV 10 equipped with a high-definition camera, it can patrol various blocks of the city regularly or irregularly, and monitor the cleanliness of the streets in real time, including phenomena such as garbage stacking and illegal advertisement posting. Once a problem is found, it can quickly notify the relevant departments for handling. The UAV 10 can fly over areas such as parks and green belts, and use a multi-spectral camera to monitor the health status of vegetation, identify early signs of pests and diseases, and evaluate the green coverage. This helps to take timely measures to protect and improve the urban greening environment.

[0043] Taking advantage of the high-altitude shooting capabilities of the drone 10, it is possible to conduct a detailed inspection of the exterior of high-rise buildings to identify potential safety hazards such as cracks and loose materials. At the same time, it can also detect unauthorized building expansions or renovations, assisting urban planning and management departments in law enforcement. During peak hours or large events, the drone 10 can be used to monitor traffic flow at major roads and transportation hubs, helping to optimize traffic signal settings and alleviate congestion. In addition, in the event of a traffic accident, the drone 10 can quickly reach the scene for aerial reconnaissance and provide real-time video support to the command center for faster emergency decision-making. The drone 10 can quickly enter dangerous areas for search and rescue operations after natural disasters (such as floods and earthquakes), providing key information support to ground rescue teams. The drone 10 can also be used for night patrols to enhance the security of public places.

[0044] Currently, the drone 10 has become an important auxiliary tool for modern urban management, capable of helping to improve urban management and service levels. However, existing technologies lack an automatic planning method for the drone inspection route 11. Instead, it relies on manual pilots to fly according to requirements and then adjusts the flight trajectory as the inspection route 11. The inspection route 11 obtained in this way lacks pertinence. Therefore, it is necessary to study the control system of the drone 10 and the method for generating the inspection route 11. Please refer to the appendix Figure 1 For the intelligent drone inspection system provided in this specification, the inspection route 11 is generated based on historical inspection records, along with the probability distribution of different events 12, where different colors represent different events. Airports are set on or near the inspection route 11. The drone 10 flies along the inspection route 11 at a basically fixed speed and altitude, capturing images below. Exemplarily, the drone 10 is capable of capturing a range of 3 km on both sides of the inspection route 11.

[0045] The system provided in this application has the Figure 2 system architecture as shown, Figure 2 which is a schematic diagram of the system architecture in an embodiment of this application. As shown in Figure 2 it, the system architecture includes a server 20 and a client 30, and the client 30 is deployed with an interactive interface. Please refer to the appendix Figure 3, the interaction interface is used for functions such as uploading the target area range, historical inspection records, viewing real-time inspection captured images, controlling the takeoff or return of the drone 10, and viewing the drone status. Among them, the interaction interface can run on the terminal device in the form of a browser, or can also run on the terminal device in the form of an independent application (APP), etc. For the specific display form of the client 30, it is not limited here. The server 20 involved in this application can be an independent physical server 20, or a server cluster or distributed system composed of multiple physical servers, or can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. The terminal device can be a smart phone, tablet computer, laptop computer, handheld computer, personal computer, smart speaker, smart TV, smart watch, in-vehicle device, wearable device, etc., but is not limited thereto. The terminal device and the server 20 can be directly or indirectly connected through wired or wireless communication methods, and this application does not limit this here. The number of the server 20 and the terminal device is also not limited.

[0046] An intelligent drone inspection system, please refer to the appendix Figure 4 , perform the following steps:

[0047] Step S101) Read the target area range to be inspected and historical inspection records.

[0048] Step S102) Generate an event heat map of the target area range according to the historical inspection records, and the event heat map records the probability distribution of events occurring at each location within the target area range. Exemplarily, please refer to the appendix Figure 5 , the events are related to urban management such as accumulated construction waste, exposed garbage, vehicle illegal parking, building illegal construction, traffic jams, etc.

[0049] Please refer to the appendix Figure 6 , the method for the system to generate the event heat map of the target area range according to the historical inspection records includes:

[0050] Step S201) Divide the target area range into grids of a preset size, and mark the number of events occurring in each grid according to the historical inspection records.

[0051] Step S202) Traverse each grid marked with the number of events in turn, read the geographical description information and building information of the grid, and obtain the surrounding grids similar to the geographical description information and building information of the grid, which are recorded as the set of similar grids.

[0052] Step S203) Calculate the maximum value and the average value of the number of events marked in each square in the set of similar squares, obtain an equivalent value according to the maximum value and the average value, and set the number of events marked in each square in the set of similar squares to the equivalent value.

[0053] Step S204) After obtaining the equivalent values of all the squares, calculate the probability of an event occurring in each square according to the equivalent values of all the squares, and obtain an event heat map.

[0054] The number of events occurring in each square can be directly obtained from the historical inspection records. However, the occurrence of events recorded in the historical inspection records is somewhat accidental. In this embodiment, in order to enable each square to more accurately reflect the probability of an event occurring, a set of similar squares is obtained based on the geographical description information and the building information. Calculate the maximum value and the average value of the number of events in all the sets of similar squares. Obtain an equivalent value according to the maximum value and the average value. Exemplarily, the weighted mean of the maximum value and the average value is used as the equivalent value. For example, the equivalent value = 0.3 × maximum value + 0.2 × average value. Further, different weights are used according to the numerical ranges of the maximum value and the average value. For example, when the maximum value and the average value are greater than 30, the weight used is 0.45; when the maximum value and the average value are between 20 and 30, the weight used is 0.35; when the maximum value and the average value are between 10 and 20, the weight used is 0.2; when the maximum value and the average value are between 0 and 10, the weight used is 0.15.

[0055] Among them, please refer to the appendix Figure 7 , the method by which the system obtains the surrounding squares similar to the geographical description information and the building information of the square includes:

[0056] Step S301) Calculate the similarity of the geographical description information within the preset surrounding range of the square, denoted as the geographical similarity;

[0057] Step S302) Identify the images of the squares within the preset surrounding range, and obtain the number of building elements in the images;

[0058] Step S303) Calculate the correlation degree between every two of the building elements, and obtain the average correlation degree according to the correlation degree between every two;

[0059] Step S304) Calculate the weighted mean of the geographical similarity and the average correlation degree, and the squares whose difference from the weighted mean of the square is greater than the preset lower limit value are classified as the surrounding squares similar to the square.

[0060] Exemplarily, the geographical description information includes landforms, climate conditions, vegetation cover, human geography features, and address descriptions. The method for calculating the similarity of the geographical description information is to calculate the similarity of the texts of the fields of landforms, climate conditions, vegetation cover, human geography features, and address descriptions respectively, and the average value of the similarities of these texts is used as the average value of the geographical description information. For blocks with similar geographical description information, the probabilities of the occurrence of the same type of event are relatively close. Exemplarily, one block is a dry, flat, hard, bare, and idle ground. Adjacent to it, or another block with a similar dry, flat, hard, bare, and idle ground at a relatively close distance, the probabilities of the occurrence of accumulated construction waste in the two blocks are similar. Assume the geographical similarity between the two is 0.9. Since they are idle grounds and the number of building elements in both is 0, the correlation degree is 0, and the average correlation degree is also 0. If in the historical inspection records, there are 4 occurrences of accumulated construction waste in the first block A, while there has been no occurrence of accumulated construction waste in the other block B. However, in this embodiment, the weighted average value of the geographical similarity and the average correlation degree between block A and block B will be calculated. Assume the calculation result of the weighted average value is 0.72 and the lower limit value is 0.7, then block B will be classified as an approximate surrounding block of block A. After obtaining the equivalent value through the calculation of block A, block B, and other blocks, the number of events of block B is set to this equivalent value. At this time, even though the number of occurrences of the event of accumulated construction waste in block B is 0, after the calculation of this embodiment, the final number of occurrences of the event of accumulated construction waste set for block B will not be 0, but the calculated equivalent value.

[0061] Among them, the method for the system to calculate the correlation degree between two building elements includes:

[0062] Read a sample building image, identify the building elements in the sample building image, and the building elements belong to a pre-configured set of building elements;

[0063] Combine the building elements in pairs to obtain the probability that each pair of building elements appears in the same sample building image;

[0064] Obtain the correlation degree between two building elements according to the probability.

[0065] Building elements include buildings, walls, columns, balconies, courtyards, landscapes, ground, drainage facilities, etc. The probability that a wall and a courtyard appear in the same sample building image is relatively high. Exemplarily, it is 0.85, then the correlation degree between the wall and the courtyard can be set to 0.85.

[0066] Step S103) Divide the target area range into several sub - areas according to the event heat map. The sub - areas are areas where the difference in the probability of an event occurring is less than a preset threshold. Exemplarily, considering only the event of accumulated construction waste, the probability of this event occurring in most areas is 0. Therefore, most areas are classified as one sub - area, and the probability of this event occurring in this sub - area is 0 or close to 0. Among the remaining partial areas, several sub - areas are divided according to the rule that the probabilities of this event occurring are similar. The sub - areas are not necessarily continuous areas. To avoid forming too many sub - areas, the threshold for determining the difference in the probability of this event should be set to a relatively large value. Exemplarily, for a single type of event, it is a relatively recommended implementation method to form 2 - 4 sub - areas. On the other hand, generating multiple sub - areas for each type of event will result in too many sub - areas. Therefore, in this embodiment, the average value of the probabilities of all types of events is used as the basis for dividing sub - areas. That is, after superimposing the event heat maps of all types of events into one event heat map, it is used for the division of sub - areas. It means that when the total probability of multiple types of events occurring in an area is relatively large, it will be divided into one sub - area.

[0067] Step S104) Generate a set of inspection routes 11 and inspection frequencies for each sub - area. The set of inspection routes 11 includes several inspection routes 11.

[0068] Please refer to the appendix Figure 8 , the method for the system to generate a set of inspection routes 11 and inspection frequencies for each sub - area includes:

[0069] Step S401) Calculate the average probability of the probability of an event occurring in all squares of the sub - area, and arrange all the sub - areas in descending order according to the average probability.

[0070] Step S402) Set the inspection frequency of each sub - area according to the average probability.

[0071] Step S403) Read the sub - areas in sequence, generate a curve of a preset length, and place the curve within the sub - area.

[0072] Step S404) Calculate the average probability of the squares passed by the curve, and the set of squares in the sub - area covered by extending a preset length along the normal direction of the curve, and calculate the weighted sum of the average probability and the number of squares in the square set.

[0073] Step S405) Adjust the curve until the weighted sum corresponding to the curve is the largest.

[0074] Step S406) Determine whether the curve extends a preset length along the normal direction and covers the sub - area.

[0075] Step S407) If the sub-region is not covered, generate a new curve and place the new curve in the part of the sub-region that is not covered by the normal extension of the curve by a preset length.

[0076] Step S408) Calculate the average probability of the squares passed by the new curve and the set of squares in the sub-region covered by the normal extension of the new curve by a preset length, and calculate the weighted sum of the average probability and the number of squares in the square set.

[0077] Step S409) Adjust the new curve until the weighted sum corresponding to the new curve is maximized.

[0078] Step S410) Continuously generate new curves according to the foregoing steps until all the curves' normal extensions by a preset length cover the sub-region.

[0079] Arrange all the sub-regions in descending order according to the average probability, and the priority is given to the sub-regions with higher average probability. The average probability sets the inspection frequency of each sub-region. Exemplarily, when the average probability is greater than 0.5, the daily inspection frequency is 3 times; when the average probability is greater than 0.2 and less than 0.5, the daily inspection frequency is 2 times; when the average probability is less than 0.2, the daily inspection frequency is 1 time.

[0080] On the other hand, in another embodiment, the method for the system to generate the inspection route set and inspection frequency for each sub-region further includes:

[0081] Whenever a new curve is generated, adjust all the generated curves to maximize the weighted sum value.

[0082] When generating a curve of a preset length for a sub-region, select one from multiple preset lengths according to the size of the sub-region. The maximum length of the curve is the flight range of the drone 10. The maximum lengths of the curves corresponding to different types of drones 10 are different. The maximum length of the generated curve is the flight range of the drone 10. The length of the generated curve can be selected from 1 / 8, 1 / 6, 1 / 4, 1 / 2, 2 / 3, 3 / 4, and 1 of the maximum length. The specific selection method can be carried out in the manner already disclosed in the art, and this process does not require creative labor.

[0083] Step S105) Generate the airport location according to the inspection route set 11, and control the drone 10 to sequentially and circularly execute the inspection routes 11 in the inspection route set 11 according to the inspection frequency.

[0084] In this embodiment, the inspection route 11 centrally includes several inspection routes 11, and one of the inspection routes 11 is sequentially selected for each inspection. When the sub-region is large, it is difficult for a single inspection route 11 to cover the sub-region. Therefore, multiple inspection routes 11 are used for coverage. Just appropriately increase the inspection frequency.

[0085] The method for the system to generate the inspection route set 11 and inspection frequency for each sub-region further includes:

[0086] Whenever a new curve is generated, all the generated curves are adjusted to maximize the weighted sum value. When a new curve is added, all the curves are adjusted to optimize the combination of multiple curves.

[0087] On the other hand, please refer to the appendix Figure 9 , in this embodiment, an intelligent UAV inspection system includes:

[0088] A reading module 100 that reads the target area range to be inspected and the historical inspection records;

[0089] A heat map module 200 that generates an event heat map of the target area range according to the historical inspection records, and the event heat map records the probability distribution of events occurring at each position within the target area range;

[0090] A division module 300 that divides the target area range into several sub-regions according to the event heat map, and the sub-region is an area where the difference in the probability of events occurring is less than a preset threshold;

[0091] A generation module 400 that generates an inspection route set 11 and inspection frequency for each sub-region, and the inspection route set 11 includes several inspection routes 11;

[0092] An execution module 500 that generates an airport location according to the inspection route set 11, and controls the UAV to sequentially and cyclically execute the inspection routes 11 in the inspection route set 11 according to the inspection frequency.

[0093] Please refer to the appendix Figure 10 which is a real-time image at an exemplary airport. The airport has charging facilities to charge the UAV.

[0094] Please refer to Figure 11 which shows a schematic structural diagram of an electronic device provided by an embodiment of this specification.

[0095] As Figure 11As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned various components. Among them, the user interface 1103 may include buttons, and the optional user interface may further include a standard wired interface and a wireless interface. Among them, the network interface 1104 may, but is not limited to, include a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 connects various parts within the entire electronic device 1100 through various interfaces and lines, and executes various functions of the routing device 1100 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1105, and by calling the data stored in the memory 1105. Optionally, the processor 1101 may be implemented in at least one of the hardware forms of DSP, FPGA, and PLA. The processor 1101 may integrate one or a combination of several of CPU, GPU, and modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0096] It can be understood that the above-mentioned modem may not be integrated into the processor 1101 and may be implemented separately by a single chip.

[0097] Among them, the memory 1105 may include RAM and may also include ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1105 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 1105 may further be at least one storage device located far from the aforementioned processor 1101. The memory 1105, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 can be used to call the application programs stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0098] The embodiments of this specification also provide a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When it runs on a computer or a processor, the computer or the processor is caused to execute multiple steps in the above embodiments. If each component module of the above electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the computer-readable storage medium.

[0099] The embodiments of this specification also provide a computer program product, including a computer program. When the computer program is executed by a processor, multiple steps in the above embodiments are implemented.

[0100] Without conflict, the technical features in this embodiment and the implementation solutions can be combined arbitrarily.

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes multiple computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this specification are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that integrates multiple available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, Digital Versatile Disc (DVD)), or a semiconductor medium (for example, Solid State Disk (SSD)), etc.

[0102] When implemented by hardware or firmware, the foregoing method flow is programmed into a hardware circuit to obtain a corresponding hardware circuit structure and implement corresponding functions. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logic function is determined by a user's programming of the device. A designer can program on their own to "integrate" a digital system on a PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL), and there are not only one but many kinds of HDLs. Those skilled in the art should also be clear that as long as the method flow is slightly logically programmed in the above-mentioned several hardware description languages and programmed into an integrated circuit, it is easy to obtain a hardware circuit that implements the logic method flow.

[0103] The embodiments described above are merely described in the preferred embodiment mode of this specification and do not limit the scope of this specification. Without departing from the design spirit of this specification, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of this specification shall fall within the protection scope determined by the claims of this specification.

Claims

1. An intelligent drone inspection system, characterized in that: The system performs the following steps: Read the target area to be inspected and historical inspection records; Generate an event heat map of the target area based on historical inspection records, where the event heat map records the probability distribution of events occurring at each location within the target area; Dividing the target area into a plurality of sub-areas according to the event heat map, wherein the sub-areas are areas where the difference in probability of an event occurring is less than a preset threshold; Generate an inspection route set and an inspection frequency for each sub-area, wherein the inspection route set includes a plurality of inspection routes; Generate an airport location according to the inspection route set, and control the drone to cyclically execute the inspection routes in the inspection route set in sequence according to the inspection frequency; The method for the system to generate an event heat map of the target area according to historical inspection records includes: Divide the target area into grids of preset size, and mark the number of events occurring in each grid according to the historical inspection records; Traverse each square marked with the number of events in turn, read the geographic description information and building information of the square, obtain surrounding squares with similar geographic description information and building information to the square, and record them as a set of similar squares; Calculating the maximum value and the average value of the number of events marked in each square in the set of similar squares, obtaining an equivalent value according to the maximum value and the average value, and setting the number of events marked in each square in the set of similar squares as the equivalent value; After obtaining the equivalent values ​​of all the squares, the probability of an event occurring in each square is calculated according to the equivalent values ​​of all the squares to obtain an event heat map.

2. The intelligent unmanned aerial vehicle inspection system according to claim 1, characterized in that: The method for the system to obtain surrounding grids with similar geographic description information and building information to the grid includes: Calculate the similarity of the geographic description information within the preset surrounding range of the grid, which is recorded as geographic similarity; Recognize the image of the squares within the preset surrounding range to obtain the number of building elements in the image; Calculating the correlation between the building elements in pairs, and obtaining an average correlation according to the correlation between the building elements in pairs; The weighted mean of the geographic similarity and the average correlation is calculated, and the squares whose difference with the weighted mean of the square is greater than a preset lower limit are classified as approximate surrounding squares of the square.

3. The intelligent unmanned aerial vehicle inspection system according to claim 2, characterized in that: The method for the system to calculate the correlation between the building elements comprises: Reading a sample building image, identifying a building element in the sample building image, wherein the building element belongs to a preconfigured building element set; Combine the architectural elements in pairs and obtain the probability that each pair of architectural elements appears in the same sample architectural image; The correlation between each pair of building elements is obtained according to the probability.

4. An intelligent drone inspection system according to any one of claims 1 to 3, characterized in that: The method for the system to generate an inspection route set and inspection frequency for each sub-area includes: Calculate the average probability of the event occurring in all the squares of the sub-region, and arrange all the sub-regions in descending order according to the average probability; Setting the inspection frequency of each of the sub-areas according to the average probability; Reading the sub-regions in sequence, generating a curve of a preset length, and placing the curve in the sub-region; Calculate the average probability of the blocks that the curve passes through, and the set of blocks in the sub-area that are extended along the normal direction of the curve and covered by a preset length, and calculate the weighted sum of the average probability and the number of blocks in the set of blocks; Adjusting the curve until the weighted sum corresponding to the curve is maximum; Determine whether the preset length of the normal extension of the curve covers the sub-area; If the sub-region is not covered, a new curve is generated, and the new curve is placed in the portion of the sub-region that is not covered by the preset length of the normal extension of the curve; Calculate the average probability of the blocks that the new curve passes through, and the set of blocks in the sub-area that are extended along the normal direction of the new curve and covered by a preset length, and calculate the weighted sum of the average probability and the number of blocks in the set of blocks; Adjusting the new curve until the weighted sum corresponding to the new curve is the largest; New curves are continuously generated according to the above steps until all the curves are normally extended to a preset length to cover the sub-region.

5. The intelligent unmanned aerial vehicle inspection system according to claim 4, characterized in that: The method for the system to generate an inspection route set and an inspection frequency for each sub-area also includes: Whenever a new curve is generated, all the generated curves are adjusted to maximize the weighted sum.

6. An intelligent drone inspection system, characterized in that: include: Reading module, reads the target area to be inspected and historical inspection records; A heat map module generates an event heat map of the target area based on historical inspection records, wherein the event heat map records the probability distribution of events occurring at each location within the target area; A division module, which divides the target area into a plurality of sub-areas according to the event heat map, wherein the sub-areas are areas where the difference in the probability of an event occurring is less than a preset threshold; A generation module generates an inspection route set and an inspection frequency for each sub-area, wherein the inspection route set includes a plurality of inspection routes; An execution module generates an airport location according to the inspection route set, and controls the drone to cyclically execute the inspection routes in the inspection route set in sequence according to the inspection frequency; The method for the system to generate an event heat map of the target area according to historical inspection records includes: Divide the target area into grids of preset size, and mark the number of events occurring in each grid according to the historical inspection records; Traverse each square marked with the number of events in turn, read the geographic description information and building information of the square, obtain surrounding squares with similar geographic description information and building information to the square, and record them as a set of similar squares; Calculating the maximum value and the average value of the number of events marked in each square in the set of similar squares, obtaining an equivalent value according to the maximum value and the average value, and setting the number of events marked in each square in the set of similar squares as the equivalent value; After obtaining the equivalent values ​​of all the squares, the probability of an event occurring in each square is calculated according to the equivalent values ​​of all the squares to obtain an event heat map.

7. An electronic device, characterized in that including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method executed by the system as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method executed by the system according to any one of claims 1 to 5 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method executed by the system as claimed in any one of claims 1 to 5 is implemented.

Images