A building inspection processing method and system based on drone

Abstract

The present invention provides a drone-based building inspection and processing method and system, which belongs to the field of drone technology. Specifically, the method and system include: determining the distribution data of buildings in a quality deviation area, determining the hidden danger building area in the quality deviation area by using the distribution data and the building composition data, determining the storage space requirement of the drone's building quality hidden danger image by using the hidden danger building area and the distribution data of the quality deviation area in the inspection route, determining the matching drone of the inspection route by using the storage space requirement, and using the matching drone to perform inspection processing on the buildings in the inspection route, thereby improving the reliability of the inspection processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles (UAVs), and in particular relates to a building inspection and processing method and system based on UAVs. Background Art

[0002] With the acceleration of urbanization, more and more buildings inevitably have various types of construction quality problems due to their long construction age. Existing technical solutions often use manual inspections, which not only have deviations in recognition accuracy, but also have difficulty in meeting the requirements in recognition processing efficiency.

[0003] To implement building inspections, the invention patent application CN202411595251.9, "Building Inspection Method, Device, and System Based on BIM Technology," uses the maximum distance to divide the overall route into multiple segments. By setting up a model building module and a path calculation module, it effectively saves inspection time and improves image quality and overall coverage. However, the following technical problems exist:

[0004] During the inspection process, drones often need to use nearby communication base stations to communicate with remote management platforms, so as to upload the building images obtained from the inspection for processing. However, during the inspection process of buildings, different buildings are located in different areas due to the differences in the distribution of communication base stations, which will lead to differences in communication quality. Therefore, how to use the differences in communication quality to generate differentiated drone inspection image upload management strategies and ensure the reliability of inspection image upload processing has become a technical problem that needs to be solved urgently.

[0005] In order to solve the above technical problems, the present application provides a building inspection and processing method and system based on drones. Summary of the Invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] Specifically, in a first aspect, the present application provides a drone-based building inspection and processing method, which specifically includes:

[0008] S1 determines the associated communication base stations of different inspection areas of the drone in the inspection route. When it is determined that there is a quality deviation area in the inspection route of the drone based on the distance between the inspection area and the associated communication base station and the historical communication data of the associated communication base station, proceed to the next step;

[0009] S2 determines distribution data of buildings in the quality deviation area, and determines a hidden danger building area in the quality deviation area based on the distribution data and building composition data;

[0010] S3: obtaining distribution data of quality deviation areas of different hazardous building areas in adjacent areas of the inspection route; determining, based on the distribution data of the quality deviation areas, that the communication processing reliability of the inspection route does not meet the requirements; and determining the storage space requirement of the drone's building quality hazard images based on the distribution data of the hazardous building areas and the quality deviation areas in the inspection route;

[0011] S4 uses the storage space requirement to determine a matching drone for the inspection route, and uses the matching drone to perform inspection processing on the buildings along the inspection route.

[0012] The beneficial effects of the present invention are:

[0013] Based on the distance between the inspection area and the associated communication base station and the historical communication data of the associated communication base station, it is determined whether there is a quality deviation area in the drone's inspection route. Not only the difference in signal quality caused by the difference in communication distance from the associated communication base station is taken into account, but also the difference in availability of the associated communication base station caused by the difference in the busyness of the historical communication data is taken into account, thereby realizing the screening of areas with deviations in communication quality, and also laying the foundation for differentiated matching of drones based on whether there is a quality deviation area, thereby ensuring the reliability of communication processing of images of building quality hazards.

[0014] The matching drones of the inspection routes are determined by utilizing storage space requirements, which ensures the reliability of storage of images of building quality hazards in areas with communication quality deviations and hidden dangers of building quality deviations, and performs communication upload processing in areas with normal communication quality, thereby ensuring the reliability of inspection processing of building quality and avoiding the influence of communication base stations with communication quality deviations.

[0015] A further technical solution is that the inspection area is divided according to the building areas using the same communication base station in the inspection route.

[0016] A further technical solution is that the associated communication base station is a communication base station used by the drone in the inspection area.

[0017] A further technical solution is that the historical communication data of the associated communication base station includes the historical communication data volume of the associated communication base station in different time periods.

[0018] A further technical solution is that the method for determining the mass deviation area is:

[0019] Determining, based on the location of the inspection area, an estimated time period for performing inspection processing of the inspection area using the drone;

[0020] Determining, based on the historical communication data of the associated communication base station during the estimation period, a date during the estimation period when the amount of historical communication data of the associated communication base station is greater than a preset data amount threshold, and using the date as the base station busy date;

[0021] Whether the inspection area is a quality deviation area is determined according to the proportion of the number of base station busy days of the associated communication base station in the estimated time period and the distance between the inspection area and the associated communication base station.

[0022] A further technical solution is that the estimated time period is determined according to the moving speed of the drone and the distance from the drone to the location of the inspection area.

[0023] A further technical solution is to determine whether the inspection area is a quality deviation area based on the proportion of busy days of the associated communication base station in the estimated time period and the distance between the inspection area and the associated communication base station, specifically including:

[0024] Determine the ratio of communication failures of the UAV at the distance between the inspection area and the associated communication base station;

[0025] The communication anomaly probability of the inspection area is determined according to the average value of the proportion of the communication failure times and the proportion of the number of busy days of the base station, and the communication anomaly probability is used to determine whether the inspection area is a quality deviation area.

[0026] A further technical solution is that the matching drone of the inspection route is a drone with a local image analysis function, which is larger than the storage space requirement and has the smallest deviation from the storage space requirement.

[0027] A further technical solution is that the local image analysis function is a function of the drone using an image recognition algorithm to identify and process images of building quality hazards.

[0028] A further technical solution is to use drones to carry out inspections of buildings along the inspection route, specifically including:

[0029] When it is in the quality deviation area, the matching drone is used to identify and process the building quality hidden danger image, and when it belongs to the building quality hidden danger image, the matching drone is used to store and process it;

[0030] When it is not in the quality deviation area, the building image collected by the matching drone and the image of the building quality hidden danger in the quality deviation area are uploaded to the remote management platform in real time.

[0031] In a second aspect, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned drone-based building inspection and processing method when running the computer program.

[0032] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0035] Figure 1 It is a flow chart of a drone-based building inspection processing method;

[0036] Figure 2 is a flow chart of a method for determining a quality deviation area;

[0037] Figure 3 is a flow chart of a method for determining a hazardous building area in a quality deviation area;

[0038] Figure 4 It is a flow chart to determine that the reliability of communication processing of the inspection route does not meet the requirements;

[0039] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0040] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0041] In this application, the distribution data of areas with building quality hazards and areas with abnormal communication quality are used to determine the storage requirements of drones' images of building quality hazards, and the storage requirements are used to determine matching drones, so that drones can be used for storage in areas with abnormal communication quality, avoiding the technical problem that the reliability of transmission and processing of images of building quality hazards cannot meet the requirements due to communication interference.

[0042] Example 1

[0043] like Figure 1 As shown, the present application provides a building inspection processing method based on drones, which specifically includes:

[0044] S1 determines the associated communication base stations of different inspection areas of the drone in the inspection route. When it is determined that there is a quality deviation area in the inspection route of the drone based on the distance between the inspection area and the associated communication base station and the historical communication data of the associated communication base station, proceed to the next step;

[0045] Based on the historical communication data of the associated communication base station, the date on which the historical communication data volume of the associated communication base station is greater than the preset data volume value is determined, and is used as the base station data abnormality date. The usage busy coefficient of the associated communication base station is determined based on the proportion of the number of base station data abnormality dates of the associated communication base station. When the product of the usage busy coefficient of the associated communication base station, the inspection area and the distance from the associated communication base station is greater than the preset value, the inspection area is determined to be a quality deviation area.

[0046] S2 determines distribution data of buildings in the quality deviation area, and determines a hidden danger building area in the quality deviation area based on the distribution data and building composition data;

[0047] The number of buildings of different construction ages in the quality deviation area is determined according to the building composition data, and the hidden danger weight values of different buildings are determined according to the preset hidden danger coefficients corresponding to the construction ages of different buildings. When the sum of the hidden danger weight values of the buildings in the quality deviation area is greater than the preset hidden danger weight threshold, the quality deviation area is determined to be a hidden danger building area.

[0048] S3: obtaining distribution data of quality deviation areas of different hazardous building areas in adjacent areas of the inspection route; determining, based on the distribution data of the quality deviation areas, that the communication processing reliability of the inspection route does not meet the requirements; and determining the storage space requirement of the drone's building quality hazard images based on the distribution data of the hazardous building areas and the quality deviation areas in the inspection route;

[0049] Determine the proportion of quality hidden danger areas in adjacent areas of different hidden danger building areas, and use it as the communication hidden danger impact weight value. Based on the sum of the communication hidden danger impact weight values of the hidden danger building areas in the inspection route, determine the comprehensive impact weight value. When the comprehensive impact weight value is greater than the preset impact weight threshold, it is determined that the communication processing reliability of the inspection route does not meet the requirements.

[0050] Determine the communication hazard impact weights of building quality hazard images of different hidden danger building areas using the proportion of the number of quality hazard areas in adjacent intervals, and determine the storage requirement coefficients of building quality hazard images of the hidden danger building areas using the proportion of the number of other hidden danger building areas in adjacent areas of the different hidden danger building areas;

[0051] Based on the communication hazard impact weight values and the average value of the storage requirement coefficient of the building quality hazard images in different hidden danger building areas, the storage requirement proportional factors of different hidden danger building areas are determined. Based on the product of the storage requirement proportional factor and the preset storage space, the storage space requirement of the building quality hazard images of the drone is determined.

[0052] S4 uses the storage space requirement to determine a matching drone for the inspection route, and uses the matching drone to perform inspection processing on the buildings along the inspection route.

[0053] Furthermore, the inspection area is divided according to the building areas using the same communication base station in the inspection route.

[0054] Specifically, the associated communication base station is a communication base station used by the drone in the inspection area.

[0055] Furthermore, the historical communication data of the associated communication base station includes the amount of historical communication data of the associated communication base station in different time periods.

[0056] It should be noted that if Figure 2 As shown, the method for determining the mass deviation area is:

[0057] Determining, based on the location of the inspection area, an estimated time period for performing inspection processing of the inspection area using the drone;

[0058] Determining, based on the historical communication data of the associated communication base station during the estimation period, a date during the estimation period when the amount of historical communication data of the associated communication base station is greater than a preset data amount threshold, and using the date as the base station busy date;

[0059] Whether the inspection area is a quality deviation area is determined according to the proportion of the number of base station busy days of the associated communication base station in the estimation period and the distance between the inspection area and the associated communication base station.

[0060] Furthermore, the estimated time period is determined based on the moving speed of the drone and the distance from the drone to the location of the inspection area.

[0061] It should be noted that determining whether the inspection area is a quality deviation area based on the proportion of the number of busy days of the associated communication base station in the estimated time period and the distance between the inspection area and the associated communication base station specifically includes:

[0062] Determine the ratio of communication failures of the UAV at the distance between the inspection area and the associated communication base station;

[0063] The communication anomaly probability of the inspection area is determined according to the average value of the proportion of the communication failure times and the proportion of the number of busy days of the base station, and the communication anomaly probability is used to determine whether the inspection area is a quality deviation area.

[0064] It can be understood that when the communication abnormality probability is greater than a preset abnormality probability threshold, the inspection area is determined to be a quality deviation area.

[0065] Specifically, when there is no quality deviation area in the inspection route, the drone without the local image analysis function and with the least communication failure times is selected as the matching drone.

[0066] In another possible embodiment, the method for determining the mass deviation area is:

[0067] Determine, based on the historical communication data of the associated communication base station, a date on which the amount of historical communication data of the associated communication base station is greater than a preset value of the amount of data, and use the date as a base station data abnormality date;

[0068] Determining a usage busy coefficient of the associated communication base station according to a proportion of abnormal base station data dates of the associated communication base station;

[0069] Whether the inspection area is a quality deviation area is determined by multiplying the usage busy coefficient of the associated base station by the distance between the inspection area and the associated communication base station.

[0070] Furthermore, when the product of the usage busy coefficient of the associated base station and the distance between the inspection area and the associated communication base station is greater than a preset value, the inspection area is determined to be a quality deviation area.

[0071] In another possible embodiment, the method for determining the mass deviation area is:

[0072] S11 determines the ratio of communication failures of the UAV at the distance between the inspection area and the associated communication base station, and determines the communication distance anomaly coefficient of the inspection area based on the ratio of communication failures and the number of communication failures at the distance;

[0073] S12: determining, based on the historical communication data of the associated communication base station, a date on which the amount of historical communication data of the associated communication base station is greater than a preset data amount value, and using the date as a base station data abnormality date; determining, based on the location of the inspection area, an estimated time period for performing inspection processing of the inspection area using the drone; determining, based on the historical communication data of the associated communication base station in the estimated time period, a date on which the amount of historical communication data of the associated communication base station is greater than a preset data amount threshold value in the estimated time period, and using the date as a base station busy date; and determining an available deviation coefficient of the communication base station based on a ratio of the number of base station busy dates to the number of base station data abnormal dates;

[0074] S13 determines the communication abnormality probability of the inspection area by the average value of the communication distance abnormality coefficient of the associated base station and the available deviation coefficient between the inspection area and the associated communication base station, and uses the communication abnormality probability to determine whether the inspection area is a quality deviation area.

[0075] Furthermore, the above step S11 includes the following contents:

[0076] S111 determines, based on the distance between the inspection area and the associated communication base station, that the distance between the inspection area and the associated communication base station is greater than a preset distance threshold, then determines that the inspection area is a quality deviation area; when the distance between the inspection area and the associated communication base station is not greater than the preset distance threshold, proceeds to step S112;

[0077] S112 determines that the number of communication failures of the UAV at the distance is greater than a preset failure number threshold, then determines that the inspection area is a quality deviation area; when it is determined that the number of communication failures of the UAV at the distance is not greater than the preset failure number threshold, proceeds to step S113;

[0078] S113 determines the proportion of communication failures of the UAV at the distance, and determines the communication distance anomaly coefficient of the inspection area based on the proportion of communication failures and in combination with the number of communication failures at the distance. When the communication distance anomaly coefficient of the inspection area is greater than the preset distance anomaly coefficient threshold, the inspection area is determined to be a quality deviation area. When the communication distance anomaly coefficient of the inspection area is not greater than the preset distance anomaly coefficient threshold, proceed to step S12.

[0079] Optionally, the above step S12 includes the following contents:

[0080] S121 determines, based on the historical communication data of the associated communication base station, a date on which the amount of historical communication data of the associated communication base station is greater than a preset data amount value, and uses the date as a base station data abnormality date; if the proportion of the number of base station data abnormality dates of the associated communication base station does not meet the requirement, the inspection area is determined to be a quality deviation area; if the proportion of the number of base station data abnormality dates of the associated communication base station meets the requirement, the process proceeds to step S122;

[0081] S122: If it is determined based on the historical communication data of the associated communication base station during the estimation period that there is no date during the estimation period when the amount of historical communication data of the associated communication base station is greater than a preset data amount threshold, then the inspection area is determined not to be a quality deviation area; if it is determined that there is a date during the estimation period when the amount of historical communication data of the associated communication base station is greater than the preset data amount threshold, then the process proceeds to step S123;

[0082] S123: Dates during the estimated period when the historical communication data volume of the associated communication base station is greater than a preset data volume threshold are considered as base station busy dates. If the percentage of the base station busy dates does not meet the requirement, the inspection area is determined to be a quality deviation area. If the percentage of the base station busy dates meets the requirement, the process proceeds to step S124.

[0083] S124 determines the available deviation coefficient of the communication base station based on the proportion of the number of busy dates of the base station and the number of abnormal dates of the base station data. When the available deviation coefficient of the communication base station is greater than the preset available deviation coefficient threshold, it is determined that the inspection area belongs to the quality deviation area. When the available deviation coefficient of the communication base station is not greater than the preset available deviation coefficient threshold, proceed to step S13.

[0084] Furthermore, the building distribution data includes the number of buildings in the quality deviation area.

[0085] Specifically, the building composition data includes the number of buildings of different construction ages in the quality deviation area.

[0086] Specifically, such as Figure 3 As shown, the method for determining the hidden danger building area in the quality deviation area is:

[0087] determining the number of buildings in the quality deviation area based on the distribution data of the buildings in the quality deviation area;

[0088] Determine the number of buildings of different construction ages in the quality deviation area according to the building composition data, and define buildings whose construction ages are within a preset range as buildings with quality hazards;

[0089] Based on the number of buildings in the quality deviation area and the number of buildings with quality hazards, it is determined whether the quality deviation area is a building area with quality hazards.

[0090] Furthermore, based on the number of buildings in the quality deviation area and the number of buildings with quality hazards, determining whether the quality deviation area is a building area with quality hazards specifically includes:

[0091] When the number of buildings in the quality deviation area is greater than the preset number of buildings or the number of buildings with quality hazards is greater than the preset number of buildings with quality hazards, the quality deviation area is determined to be a hidden danger building area.

[0092] In another possible embodiment, the method for determining the building area with hidden dangers in the quality deviation area is:

[0093] determining the number of buildings in the quality deviation area based on the distribution data of the buildings in the quality deviation area;

[0094] Determining the number of buildings of different construction ages in the quality deviation area according to the building composition data, and determining hidden danger weight values of different buildings according to preset hidden danger coefficients corresponding to the construction ages of different buildings;

[0095] Based on the sum of the hidden danger weight values of the buildings in the quality deviation area, it is determined whether the quality deviation area is a hidden danger building area.

[0096] Furthermore, the preset hidden danger coefficient corresponding to the construction age of the building is determined according to the proportion of quality hidden dangers in buildings of that construction age during historical inspections.

[0097] It can be understood that when the sum of the hidden danger weight values of the buildings in the quality deviation area is greater than a preset hidden danger weight threshold, the quality deviation area is determined to be a hidden danger building area.

[0098] In another possible embodiment, the method for determining the building area with hidden dangers in the quality deviation area is:

[0099] S21 determines the number of buildings in the quality deviation area based on the distribution data of the buildings in the quality deviation area, and determines the building distribution clustering factors of different quality deviation areas based on the building areas of different buildings;

[0100] S22 determines the number of buildings of different construction ages in the quality deviation area according to the building composition data, and determines the building quality abnormality factor of the quality deviation area based on the preset hidden danger coefficients corresponding to the construction ages of the different buildings and the building areas of the different buildings;

[0101] S23 determines the comprehensive abnormality factor of the quality deviation area based on the building quality abnormality factor and the building distribution clustering factor in the quality deviation area, and uses the comprehensive abnormality factor to determine whether the quality deviation area is a hidden danger building area.

[0102] Optionally, when the comprehensive abnormality factor of the quality deviation area is greater than a preset abnormality factor threshold, the quality deviation area is determined to be a hidden danger building area.

[0103] Optionally, the above step S21 includes the following contents:

[0104] S211 determines the number of buildings in the quality deviation area based on the distribution data of the buildings in the quality deviation area. When the number of buildings in the quality deviation area is greater than a preset number of buildings, the quality deviation area is determined to be a hidden danger building area. When the number of buildings in the quality deviation area is not greater than the preset number of buildings, the process proceeds to step S212.

[0105] S212: determining the total building area of the buildings in the quality deviation area based on the building areas of different buildings; if the total building area of the buildings in the quality deviation area does not meet the requirement, determining the quality deviation area as a hidden danger building area; if the total building area of the buildings in the quality deviation area meets the requirement, proceeding to step S213;

[0106] S213: When there is a building with a construction area larger than the preset construction area, the process proceeds to step S214; when there is no building with a construction area larger than the preset construction area, the process proceeds to step S215;

[0107] S214: When the number of buildings with a building area larger than the preset building area does not meet the requirement, the quality deviation area is determined to be a hidden danger building area; when the number of buildings with a building area larger than the preset building area meets the requirement, the process proceeds to step S215;

[0108] S215 determines the building distribution clustering factors of different quality deviation areas based on the number of buildings in the quality deviation area and the building areas of different buildings. When the building distribution clustering factor of the quality deviation area is greater than the preset distribution clustering factor threshold, the quality deviation area is determined to be a hidden danger building area. When the building distribution clustering factor of the quality deviation area is not greater than the preset distribution clustering factor threshold, the process proceeds to step S22.

[0109] Optionally, the above step S22 includes the following contents:

[0110] S221 determines the number of buildings of different construction ages in the quality deviation area based on the building composition data; if there are no buildings with construction ages within a preset age range, it is determined that the quality deviation area does not belong to a hidden danger building area; if there are buildings with construction ages within the preset age range, the process proceeds to step S222;

[0111] In step S222, buildings whose construction age falls within a preset range are considered as buildings with quality hazards. If either the number or the total building area of the buildings with quality hazards does not meet the requirements, the quality deviation area is determined to be a building area with quality hazards. If both the number and the total building area of the buildings with quality hazards meet the requirements, the process proceeds to step S223.

[0112] S223 determines the hidden danger weight values of different buildings based on the preset hidden danger coefficients corresponding to the construction ages of different buildings. When the sum of the hidden danger weight values of different buildings does not meet the requirement, the quality deviation area is determined to be a hidden danger building area. When the sum of the hidden danger weight values of different buildings meets the requirement, the process proceeds to step S224.

[0113] S224 determines the building quality anomaly factor of the quality deviation area based on the preset hidden danger coefficient corresponding to the construction age of different buildings and the building area of different buildings. When the building quality anomaly factor does not meet the requirements, the quality deviation area is determined to be a hidden danger building area. When the building quality anomaly factor meets the requirements, the process proceeds to step S23.

[0114] Furthermore, the adjacent area is an inspection area of the hidden danger building area within a preset inspection time in the inspection route.

[0115] Specifically, such as Figure 4 As shown, it is determined that the communication processing reliability of the inspection route does not meet the requirements, specifically including:

[0116] Obtaining the number of building areas with hidden dangers in the inspection route;

[0117] Based on the distribution data of quality risk areas in adjacent areas of different potential risk building areas, the proportion of quality risk areas in adjacent areas of different potential risk building areas is determined, and the proportion is used as the communication risk impact weight value;

[0118] Based on the sum of the communication hidden danger impact weight values of the hidden danger building areas in the inspection route, a comprehensive impact weight value is determined, and the comprehensive impact weight value is used to determine whether the communication processing reliability of the inspection route meets the requirements.

[0119] Furthermore, when the comprehensive impact weight value is greater than a preset impact weight threshold, it is determined that the communication processing reliability of the inspection route does not meet the requirements.

[0120] It should be noted that when the communication processing reliability of the inspection route meets the requirements, the drone with the least communication failure rate and the local image analysis function will be used as the matching drone.

[0121] Optionally, determining that the communication processing reliability of the inspection route does not meet the requirement specifically includes:

[0122] Obtaining the number of building areas with hidden dangers in the inspection route, and when the number of building areas with hidden dangers in the inspection route does not meet the requirement, determining that the communication processing reliability of the inspection route does not meet the requirement;

[0123] When the number of hazardous building areas in the inspection route meets the requirements:

[0124] Determine a basic communication impact coefficient based on the proportion of the quality risk areas in the inspection route, and when the basic communication impact coefficient does not meet the requirements, determine that the communication processing reliability of the inspection route does not meet the requirements;

[0125] When the basic communication impact coefficient meets the requirements:

[0126] Determine a hidden danger communication impact coefficient by multiplying the proportion of the number of quality hidden danger areas and the proportion of the number of hidden danger building areas in the inspection route; if the hidden danger communication impact coefficient does not meet the requirement, determine that the communication processing reliability of the inspection route does not meet the requirement;

[0127] When the hidden danger communication impact coefficient meets the requirements:

[0128] Based on the distribution data of quality risk areas in adjacent areas of different potential risk building areas, the proportion of quality risk areas in adjacent areas of different potential risk building areas is determined, and the proportion is used as the communication risk impact weight value. If there is a potential risk building area whose communication risk impact weight value does not meet the requirements, it is determined that the communication processing reliability of the inspection route does not meet the requirements.

[0129] When there are no hidden danger building areas where the communication hidden danger impact weight value does not meet the requirements:

[0130] Determining the number of inspection areas between different quality risk areas and the hazardous building areas based on distribution data of quality risk areas in adjacent areas of different hazardous building areas, determining a communication impact coefficient of the hazardous building areas based on the number of inspection areas between different quality risk areas and the hazardous building areas, and determining that the communication processing reliability of the inspection route does not meet the requirements if there is a hazardous building area whose communication impact coefficient does not meet the requirements;

[0131] When there are no hidden danger building areas where the communication impact coefficient does not meet the requirements:

[0132] Based on the communication impact coefficient of the hidden danger building area in the inspection route, and combined with the hidden danger communication impact coefficient, a comprehensive impact weight value is determined, and the comprehensive impact weight value is used to determine whether the communication processing reliability of the inspection route meets the requirements.

[0133] Furthermore, the method for determining the storage space requirement of the building quality hidden danger image of the drone is as follows:

[0134] Based on the distribution data of hidden danger building areas and quality deviation areas in the inspection route, the proportion of quality danger areas in the adjacent areas of different hidden danger building areas is determined, and the communication hazard impact weight value of the building quality hazard images of different hidden danger building areas is determined using the proportion of quality danger areas.

[0135] Determining a storage requirement coefficient of a building quality hazard image of a different hidden danger building area based on a ratio of the number of other hidden danger building areas in adjacent areas of the different hidden danger building areas;

[0136] Based on the communication hazard impact weight values and the average value of the storage requirement coefficient of the building quality hazard images of different hidden danger building areas, the storage requirement proportional factors of the different hidden danger building areas are determined, and the storage space requirements of the building quality hazard images of the drone are determined based on the storage requirement proportional factors.

[0137] Specifically, determining the storage space requirement of the building quality hazard image of the drone based on the storage requirement proportional factor specifically includes:

[0138] Based on the storage requirement proportional factor, the storage space requirement of the building quality hazard image of the UAV is determined based on the product of the storage requirement proportional factor and the preset storage space.

[0139] It should be noted that the preset storage space is determined according to the maximum storage space supported by different drones.

[0140] It can be understood that the matching drone of the inspection route is a drone with a local image analysis function that is larger than the storage space requirement and has the smallest deviation from the storage space requirement.

[0141] Furthermore, the local image analysis function is a function of the drone using an image recognition algorithm to identify and process images of building quality hazards.

[0142] Specifically, the inspection process of buildings using matching drones for inspection routes includes:

[0143] When it is in the quality deviation area, the matching drone is used to identify and process the building quality hidden danger image, and when it belongs to the building quality hidden danger image, the matching drone is used to store and process it;

[0144] When it is not in the quality deviation area, the building image collected by the matching drone and the image of the building quality hidden danger in the quality deviation area are uploaded to the remote management platform in real time.

[0145] Example 2

[0146] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned drone-based building inspection processing method when running the computer program.

[0147] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0148] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0149] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A building inspection and processing method based on drones, characterized in that: Specifically include: Determine the associated communication base stations of different inspection areas of the drone along the inspection route. If it is determined that there is a quality deviation area in the drone's inspection route based on the distance between the inspection area and the associated communication base station and the historical communication data of the associated communication base station, proceed to the next step. Determining distribution data of buildings in the quality deviation area, and determining a building area with hidden dangers in the quality deviation area based on the distribution data and building composition data; Obtaining distribution data of quality deviation areas of different hazardous building areas in adjacent areas of an inspection route; and determining, based on the distribution data of the quality deviation areas, that the communication processing reliability of the inspection route does not meet requirements, determining the storage space requirement of the drone's building quality hazard images based on the distribution data of the hazardous building areas and the quality deviation areas in the inspection route; Determining a matching drone for the inspection route using the storage space requirement, and using the matching drone to perform inspection processing on the buildings along the inspection route; The method for determining the mass deviation area is: Determining, based on the location of the inspection area, an estimated time period for performing inspection processing of the inspection area using the drone; Determining, based on the historical communication data of the associated communication base station during the estimation period, a date during the estimation period when the amount of historical communication data of the associated communication base station is greater than a preset data amount threshold, and using the date as the base station busy date; Determining whether the inspection area is a quality deviation area according to the proportion of busy days of the associated communication base station in the estimated time period and the distance between the inspection area and the associated communication base station; determining the number of buildings in the quality deviation area based on the distribution data of the buildings in the quality deviation area; Determine the number of buildings of different construction ages in the quality deviation area according to the building composition data, and define buildings whose construction ages are within a preset range as buildings with quality hazards; Determining whether the quality deviation area is a building area with hidden dangers based on the number of buildings in the quality deviation area and the number of buildings with hidden quality dangers; The method for determining the storage space requirement of the drone's building quality hidden danger images is as follows: Based on the distribution data of hidden danger building areas and quality deviation areas in the inspection route, the proportion of quality danger areas in the adjacent areas of different hidden danger building areas is determined, and the communication hazard impact weight value of the building quality hazard images of different hidden danger building areas is determined using the proportion of quality danger areas. Determining a storage requirement coefficient of a building quality hazard image of a different hidden danger building area based on a ratio of the number of other hidden danger building areas in adjacent areas of the different hidden danger building areas; Determining storage requirement scaling factors for different hazardous building areas based on communication hazard impact weight values and average values of storage requirement coefficients for images of building quality hazards in different hazardous building areas; and determining storage space requirements for the drone's images of building quality hazards based on the storage requirement scaling factors and the product of the storage requirement scaling factors and a preset storage space. The adjacent area is the inspection area of the hidden danger building area within the preset inspection time in the inspection route; Determining that the communication processing reliability of the inspection route does not meet the requirements includes: Obtaining the number of building areas with hidden dangers in the inspection route; Based on the distribution data of quality risk areas in adjacent areas of different potential risk building areas, the proportion of quality risk areas in adjacent areas of different potential risk building areas is determined, and the proportion is used as the communication risk impact weight value; Determining a comprehensive impact weight value based on the sum of the communication hidden danger impact weight values of the hidden danger building areas in the inspection route, and when the comprehensive impact weight value is greater than a preset impact weight threshold, determining that the communication processing reliability of the inspection route does not meet the requirements; Inspection processing of buildings using matching drones for inspection routes, specifically including: When it is in the quality deviation area, the matching drone is used to identify and process the building quality hidden danger image, and when it belongs to the building quality hidden danger image, the matching drone is used to store and process it; When it is not in the quality deviation area, the building image collected by the matching drone and the image of the building quality hidden danger in the quality deviation area are uploaded to the remote management platform in real time.

2. The drone-based building inspection method according to claim 1, wherein: The inspection area is divided according to the building area using the same communication base station in the inspection route.

3. The drone-based building inspection method according to claim 1, wherein: The associated communication base station is a communication base station used by the drone in the inspection area.

4. The drone-based building inspection method according to claim 1, wherein: The estimated time period is determined based on the moving speed of the drone and the distance from the drone to the location of the inspection area.

5. The drone-based building inspection method according to claim 1, wherein: Determining whether the inspection area is a quality deviation area according to the proportion of busy days of the associated communication base station in the estimated time period and the distance between the inspection area and the associated communication base station specifically includes: Determine the ratio of communication failures of the UAV at the distance between the inspection area and the associated communication base station; The communication anomaly probability of the inspection area is determined according to the average value of the proportion of the communication failure times and the proportion of the number of busy days of the base station, and the communication anomaly probability is used to determine whether the inspection area is a quality deviation area.

6. The drone-based building inspection method according to claim 1, wherein: The matching drone for the inspection route is a drone with a local image analysis function that is larger than the storage space requirement and has the smallest deviation from the storage space requirement.

7. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, it executes a drone-based building inspection processing method as described in any one of claims 1-6.

Images