Logistics inspection unmanned aerial vehicle based on artificial intelligence

Abstract

The invention relates to the technical field of unmanned aerial vehicles, in particular to a logistics inspection unmanned aerial vehicle based on artificial intelligence. The inspection optimization module is used for judging an inspection optimization mode in response to an inspection condition; the inspection change module is used for judging an inspection change mode in response to a set condition; the inspection adjustment module is used for determining an inspection adjustment mode according to the inspection area category; the inspection and review module is used for collecting and storing inspection images and infrared thermal imaging images and determining whether the inspection areas need early warning or not according to danger trigger coefficients of the inspection images and thermal imaging coefficients of the infrared thermal imaging images; the inspection efficiency of the unmanned aerial vehicle can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a logistics inspection unmanned aerial vehicle based on artificial intelligence. Background Art

[0002] In the context of the rapid development of the current logistics and warehousing management industry, since there are a large number of production raw materials and product equipment in the logistics warehouse, the safety precautions in the warehouse area cannot be ignored. The use of logistics inspection drones can reduce the workload of staff inspection operations and reduce inspection costs. However, there are shortcomings such as the complexity of the logistics warehouse environment and the limited endurance of drones during the drone inspection process, resulting in poor drone inspection efficiency. Therefore, how to improve the inspection efficiency according to the actual status of the drone is a technical problem that technicians in this field need to solve urgently.

[0003] Chinese patent publication number CN113313852A discloses a drone inspection system, including: multiple position transmitters, drones and charging stations. Each position transmitter is suitable for installation on a meter or power equipment, and is used to transmit a position signal and a device identification, and one meter or power equipment corresponds to one device identification; the drone is used to receive the position signal and fly to the meter or power equipment corresponding to the device identification, as well as to collect the dial image of the meter, or detect the temperature of the power equipment; the charging station includes a charging platform for carrying the drone, a charging sensor for detecting the landing signal of the drone, and a charging module for charging the drone. It can be seen that the above technical solution has the following problems: inspection is only based on the position signal, the inspection method is single, and it is impossible to adaptively select different inspection methods according to the actual state of the drone when there are many position signals, and the inspection efficiency is poor. Summary of the invention

[0004] To this end, the present invention provides a logistics inspection drone based on artificial intelligence to overcome the problems in the prior art of a single inspection method, inability to adaptively select different inspection methods according to the actual state of the drone, and poor inspection efficiency.

[0005] To achieve the above objectives, the present invention provides a logistics inspection drone based on artificial intelligence, comprising: Information collection module, used to obtain basic information of logistics warehouses and drone flight information; An inspection optimization module, which is connected to the information collection module, and is used to respond to inspection conditions to determine an inspection optimization method, wherein the inspection optimization method is to determine an inspection change method according to set conditions, or to determine an inspection adjustment method according to an inspection area category; An inspection change module, which is connected to the information collection module and the inspection optimization module respectively, and is used to respond to the set conditions to determine the inspection change mode, and the inspection change mode is to determine the priority selection mode according to the change conditions, or to determine whether to inspect each uninspected area according to the information matching coefficient; The preferred selection method is to determine the inspection priority coefficient of each uninspected area according to the information matching coefficient, or to determine the inspection priority coefficient of the pre-inspected area corresponding to each associated combination according to the flight influence coefficient; An inspection adjustment module, which is connected to the information collection module and the inspection optimization module respectively, and is used to determine the inspection adjustment mode according to the inspection area category. The inspection adjustment mode is to determine the direction setting mode of each collection point according to the adjustment conditions or to set the collection direction of each collection point to the vertical direction; The inspection area category is determined according to the complexity of the area layout and the cargo stacking coefficient, and the direction setting method is to determine the collection direction according to the associated direction group or the direction evaluation coefficient; The inspection review module is connected to the inspection change module and the inspection adjustment module respectively, and is used to collect and store inspection images and infrared thermal imaging images, and determine whether each inspection area needs early warning based on the danger trigger coefficient of the inspection image and the thermal imaging coefficient of the infrared thermal imaging image.

[0006] Furthermore, the inspection optimization module responds to the inspection conditions to determine the inspection optimization mode, wherein: The inspection condition responded by the inspection optimization module is that the inspection area influence coefficient is less than the preset inspection area influence coefficient or the endurance reference value is less than the preset endurance reference value, and the inspection optimization mode is determined by determining the inspection change mode according to the set conditions; The inspection conditions responded by the inspection optimization module are that the inspection area influence coefficient is greater than or equal to the preset inspection area influence coefficient and the endurance reference value is greater than or equal to the preset endurance reference value. The inspection optimization method is determined by determining the inspection adjustment method according to the inspection area category.

[0007] Further, the inspection change module responds to the set conditions to determine the inspection change mode, wherein: The setting condition for the inspection change module response is that the inspection information degree is greater than or equal to the preset inspection information degree or the interactive correlation degree is greater than or equal to the preset interactive correlation degree, and the inspection change mode is determined by determining the priority selection mode according to the change condition; The setting conditions for the inspection change module response are that the inspection information degree is less than the preset inspection information degree and the interaction correlation degree is less than the preset interaction correlation degree. The inspection change determination method is to determine whether to inspect each uninspected area based on the information matching coefficient.

[0008] Furthermore, the inspection information is confirmed in the following manner: If the inspection offset value is greater than or equal to the preset inspection offset value, the inspection information degree is determined according to the trajectory characterization value and the inspection coefficient; If the inspection error value is less than the preset inspection error value, the inspection information degree is determined according to the inspection danger threshold and the inspection ratio.

[0009] Furthermore, the inspection change module responds to the change condition to determine the preferred selection method, wherein: The change condition of the inspection change module response is that the trajectory smoothness is greater than or equal to the preset trajectory smoothness or the area correlation coefficient is less than the preset area correlation coefficient. The priority selection method is to determine the inspection priority coefficient of each uninspected area according to the information matching coefficient; The change condition of the inspection change module response is that the trajectory smoothness is less than the preset trajectory smoothness and the area correlation coefficient is greater than or equal to the preset area correlation coefficient. The priority selection method is to determine the inspection priority coefficient of the pre-inspection area corresponding to each correlation combination according to the flight influence coefficient; The inspection priority coefficient of a single uninspected area is negatively correlated with the information matching coefficient of the uninspected area; The inspection priority coefficient of a single pre-inspection area is positively correlated with the flight impact coefficient corresponding to the pre-inspection area.

[0010] Furthermore, the confirmation method of the associated combination is: If the cross coefficient is greater than or equal to the preset cross coefficient, the associated combination is determined according to the cross similarity and the regional balance coefficient; If the cross coefficient is less than the preset cross coefficient, the associated combination is determined according to the regional similarity.

[0011] Furthermore, the inspection adjustment module determines the inspection adjustment mode according to the inspection area category, wherein: For a type of inspection area, the inspection adjustment method is to determine the direction setting method of each collection point according to the adjustment conditions; For the second type of inspection area, the inspection adjustment method is to set the collection direction of each collection point to the vertical direction.

[0012] Furthermore, the inspection area categories include: A type of inspection area where the regional layout complexity is greater than or equal to the preset regional layout complexity or the cargo stacking coefficient is greater than or equal to the preset cargo stacking coefficient; A second-class inspection area whose area layout complexity is less than the preset area layout complexity and whose cargo stacking coefficient is less than the preset cargo stacking coefficient.

[0013] Furthermore, the inspection adjustment module responds to the adjustment conditions to determine the direction setting mode of each collection point, wherein: For a single collection point, The adjustment condition of the patrol adjustment module response is that the mutual correlation coefficient is greater than or equal to the preset mutual correlation coefficient or the influence threshold is less than the preset influence threshold, and the determination direction setting method is to determine the collection direction according to the associated direction group; The adjustment condition of the patrol adjustment module response is that the mutual correlation coefficient is less than the preset mutual correlation coefficient and the influence threshold is greater than or equal to the preset influence threshold, and the direction setting method is to determine the collection direction according to the direction evaluation coefficient.

[0014] Furthermore, the inspection review module determines whether each inspection area needs an early warning according to the danger trigger coefficient of the inspection image and the thermal imaging coefficient of the infrared thermal imaging image, wherein: For a single inspection area, If the danger trigger coefficient is greater than or equal to the preset danger trigger coefficient or the thermal imaging coefficient is greater than or equal to the preset thermal imaging coefficient, an early warning is sent to the user terminal; If the danger trigger coefficient is less than the preset danger trigger coefficient and the thermal imaging coefficient is less than the preset thermal imaging coefficient, there is no need to send an early warning to the user end.

[0015] Compared with the prior art, the beneficial effect of the present invention lies in that, in the technical solution of the present invention, the inspection optimization module responds to the inspection conditions to determine the inspection optimization method, and effectively reflects the inspection difficulty of the logistics warehouse and the actual endurance status of the drone through the inspection conditions, and then adaptively selects different inspection optimization methods according to the inspection conditions, and can adjust the inspection optimization method in real time according to actual conditions, so that the selection of the inspection optimization method is more in line with the actual application scenario, thereby improving the inspection efficiency.

[0016] Furthermore, the inspection change module in the present invention determines the inspection change mode according to the set conditions, and effectively reflects the degree of correlation between the inspection areas that have been inspected and not inspected by the drone and the degree of danger of the inspection areas that have been inspected by the drone through the set conditions, and then adaptively selects different inspection change modes according to the set conditions, so that the selected inspection change mode can give priority to high-risk inspection areas, quickly identify potential safety hazards, and improve inspection efficiency.

[0017] Furthermore, the inspection adjustment module in the present invention determines the inspection area category according to the complexity of the regional layout and the cargo stacking coefficient, and effectively reflects the cargo status of the inspection area through the complexity of the regional layout and the cargo stacking coefficient, and then adaptively selects different inspection adjustment methods according to the inspection area category, so that the selected inspection adjustment method can improve the accuracy of the images collected by the drone, thereby improving the inspection efficiency and the accuracy of the inspection of the inspection area.

[0018] Furthermore, in the present invention, the direction setting method of each collection point is determined according to the adjustment conditions, and the correlation degree of each collection direction in the inspection area is effectively reflected through the adjustment conditions, and then different direction setting methods are adaptively selected according to the adjustment conditions, so that the selected direction setting method can collect more comprehensive and accurate data, thereby improving the accuracy of the inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a module connection diagram of the artificial intelligence-based logistics inspection drone of the present invention; Figure 2 This is a flow chart of the present invention for determining an inspection optimization method according to inspection conditions; Figure 3 This is a flow chart of the present invention for determining the inspection change mode according to the setting conditions; Figure 4 The present invention is a flow chart of determining a preferred selection method according to a change condition. DETAILED DESCRIPTION

[0020] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0022] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0023] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] See also Figures 1 to 4 As shown, the present invention provides a logistics inspection drone based on artificial intelligence, comprising: Information collection module, used to obtain basic information of logistics warehouses and drone flight information; An inspection optimization module, which is connected to the information collection module, and is used to respond to inspection conditions to determine an inspection optimization method, wherein the inspection optimization method is to determine an inspection change method according to set conditions, or to determine an inspection adjustment method according to an inspection area category; An inspection change module, which is connected to the information collection module and the inspection optimization module respectively, and is used to respond to the set conditions to determine the inspection change mode, and the inspection change mode is to determine the priority selection mode according to the change conditions, or to determine whether to inspect each uninspected area according to the information matching coefficient; The preferred selection method is to determine the inspection priority coefficient of each uninspected area according to the information matching coefficient, or to determine the inspection priority coefficient of the pre-inspected area corresponding to each associated combination according to the flight influence coefficient; An inspection adjustment module, which is connected to the information collection module and the inspection optimization module respectively, and is used to determine the inspection adjustment mode according to the inspection area category. The inspection adjustment mode is to determine the direction setting mode of each collection point according to the adjustment conditions or to set the collection direction of each collection point to the vertical direction; The inspection area category is determined according to the complexity of the area layout and the cargo stacking coefficient, and the direction setting method is to determine the collection direction according to the associated direction group or the direction evaluation coefficient; The inspection review module is connected to the inspection change module and the inspection adjustment module respectively, and is used to collect and store inspection images and infrared thermal imaging images, and determine whether each inspection area needs early warning based on the danger trigger coefficient of the inspection image and the thermal imaging coefficient of the infrared thermal imaging image.

[0025] The application scenario of the present invention is the inspection of drones in logistics warehouses. The basic information of the logistics warehouse includes but is not limited to the location of each cargo in the logistics warehouse and the cargo category corresponding to each inspection area. The cargo category includes but is not limited to matches, lighters and fireworks. The drone flight information is the flight trajectory of the drone, which is easy for technicians in this field to understand and will not be described in detail. The inspection area is confirmed by dividing the logistics warehouse into a number of rectangular areas of equal area and equal length and width, and taking the rectangular area with a cargo volume greater than the preset cargo volume as the inspection area. The number of divided rectangular areas is positively correlated with the area of ​​the logistics warehouse; The initial inspection method of the drone is to inspect each inspection area in order from large to small cargo volume, and the drone collects inspection images and infrared thermal imaging images at the collection points corresponding to each inspection area. The collection direction of each collection point is the vertical direction, and the vertical direction is the direction from the collection point corresponding to a single inspection area to the center point of the inspection area. The collection point corresponding to a single inspection area is a point that is 6m away from the center point of the inspection area and is located directly above the center point of the inspection area. The center point of a single inspection area is the center of the circumscribed circle of the inspection area. The cargo volume corresponding to a single inspection area is the total number of cargo in the inspection area. The value of the preset cargo volume can be determined by the user according to the actual application scenario. The greater the user's demand for improving the inspection accuracy of the logistics warehouse, the smaller the value of the preset cargo volume. A value of the preset cargo volume is provided, and the preset cargo volume is 100. The inspection image is an image taken by a high-definition camera carried by the drone, and the thermal infrared imaging image is an image obtained by measuring the thermal radiation of the inspection area by a thermal infrared imager carried by the drone. This is content that is easy for technicians in this field to understand and will not be described in detail. The present invention is provided with a continuously cyclic monitoring cycle, and the data status is determined once at the end of each monitoring cycle. The duration of the monitoring cycle can be set according to the needs of the user. The greater the user's demand for monitoring accuracy, the shorter the duration of the monitoring cycle. A value of the monitoring cycle is provided, and the monitoring cycle is 5 minutes.

[0026] In the present invention, several historical records are correspondingly set up, and any historical record records the inspection area influence coefficient, inspection information degree, interactive correlation degree, regional discreteness, information matching coefficient and inspection offset value, etc. in the historical process of at least one drone inspection in the logistics warehouse, and each historical record corresponds to a qualified mark, which records whether the waybill photo review process meets user needs. The qualified mark can be recorded manually. It can be understood that the user can determine whether the drone inspection process meets the needs based on self-set indicators. The self-set indicators can be but not limited to the number of missed inspections, which will not be elaborated here. The number of missed inspections is the number of times that it is incorrectly determined whether the inspection area needs an early warning.

[0027] Specifically, the inspection optimization module responds to the inspection conditions to determine the inspection optimization method, wherein: The inspection condition responded by the inspection optimization module is that the inspection area influence coefficient is less than the preset inspection area influence coefficient or the endurance reference value is less than the preset endurance reference value, and the inspection optimization mode is determined by determining the inspection change mode according to the set conditions; The inspection conditions responded by the inspection optimization module are that the inspection area influence coefficient is greater than or equal to the preset inspection area influence coefficient and the endurance reference value is greater than or equal to the preset endurance reference value. The inspection optimization method is determined by determining the inspection adjustment method according to the inspection area category.

[0028] Among them, the inspection conditions include a first inspection condition and a second inspection condition. The first inspection condition is that the inspection area influence coefficient is less than the preset inspection area influence coefficient or the endurance reference value is less than the preset endurance reference value. The second inspection condition is that the inspection area influence coefficient is greater than or equal to the preset inspection area influence coefficient and the endurance reference value is greater than or equal to the preset endurance reference value. The inspection area influence coefficient is confirmed by: If the area dispersion is greater than or equal to the preset area dispersion, the inspection area influence coefficient is determined according to the number of inspection areas and the influence mean, where the inspection area influence coefficient = the number of inspection areas - the influence mean; If the reference value of the number of inspection areas is less than the preset number of inspection areas, the inspection area impact coefficient is determined according to the historical accident frequency, wherein the inspection area impact coefficient is positively correlated with the historical accident frequency, and the inspection area impact coefficient = α × historical accident frequency. A value of α is provided, and α is 1.1; The number of inspection areas is the total number of inspection areas in the logistics warehouse; the impact mean is the average value of the sub-influence coefficients corresponding to each inspection area in the logistics warehouse. For a single inspection area, the inspection area is recorded as the target area, and the sub-influence coefficient corresponding to the target area = the number of inspection areas adjacent to the target area + the average value of the correlation coefficients corresponding to each inspection area adjacent to the target area; the correlation coefficient is confirmed by recording a single impact area adjacent to the target area as a reference area, and recording the number of cargo categories that exist in both the reference area and the target area as the impact mean; The historical accident frequency is the average number of warnings corresponding to each inspection area. The number of warnings corresponding to a single inspection area is the number of times that the inspection area needs warnings in the historical records that can meet user needs. Endurance reference value = remaining power of the drone in the current monitoring cycle / total power of the drone when fully charged; The area dispersion is the average value of the reference distances corresponding to each inspection area. For a single inspection area, the inspection area is recorded as the target inspection area, and the other inspection areas except the target inspection area are recorded as reference inspection areas. The shortest distance from the center point of the target inspection area to the center point of each reference inspection area is recorded as the reference distance. The values ​​of the preset inspection area influence coefficient, the preset endurance reference value and the preset area discreteness can be determined by the user according to the actual application scenario. The greater the user's demand for determining the inspection change method according to the set conditions, the smaller the values ​​of the preset inspection area influence coefficient and the preset endurance reference value. A value of the preset inspection area influence coefficient and the preset endurance reference value is provided, and the historical records of determining the inspection change method according to the set conditions are detected. The average value of the inspection area influence coefficient corresponding to the historical records that can meet the user's needs is recorded as the preset inspection area influence coefficient. The preset endurance reference value is 50%. The smaller the value of the preset area discreteness is, the greater the user's demand for determining the inspection area influence coefficient according to the number of inspection areas and the impact mean. A value of the preset area discreteness is provided, and the historical records of determining the inspection area influence coefficient according to the historical accident frequency are detected. The average value of the area discreteness corresponding to the historical records that can meet the user's needs is recorded as the preset area discreteness.

[0029] Specifically, the inspection change module responds to the set conditions to determine the inspection change mode, wherein: The setting condition for the inspection change module response is that the inspection information degree is greater than or equal to the preset inspection information degree or the interactive correlation degree is greater than or equal to the preset interactive correlation degree, and the inspection change mode is determined by determining the priority selection mode according to the change condition; The setting conditions for the inspection change module response are that the inspection information degree is less than the preset inspection information degree and the interaction correlation degree is less than the preset interaction correlation degree. The inspection change determination method is to determine whether to inspect each uninspected area based on the information matching coefficient.

[0030] The setting condition includes a first setting condition and a second setting condition. The first setting condition is that the inspection information degree is greater than or equal to the preset inspection information degree or the interactive correlation degree is greater than or equal to the preset interactive correlation degree. The second setting condition is that the inspection information degree is less than the preset inspection information degree and the interactive correlation degree is less than the preset interactive correlation degree. The method for confirming the degree of interaction is: If the similarity coefficient is greater than or equal to the preset similarity coefficient, the mutual correlation is determined according to the regional correlation, wherein the mutual correlation is positively correlated with the regional correlation, and the mutual correlation = regional correlation × β1, β1 is 1; If the similarity coefficient is less than the preset similarity coefficient, the mutual correlation is determined according to the similarity coefficient, wherein the mutual correlation is positively correlated with the similarity coefficient, and the mutual correlation = similarity coefficient × β2, β2 is 0.8; The inspection area that has been inspected by the drone in the current monitoring cycle is recorded as the inspected area, and the inspection area that has not been inspected by the drone in the current monitoring cycle is recorded as the uninspected area. The similarity coefficient = the number of cargo categories that exist in all inspected areas and all uninspected areas / A. The number of all cargo categories in all inspected areas is recorded as a1, and the number of all cargo categories in all uninspected areas is recorded as a2. The larger value of a1 and a2 is recorded as A; Area correlation = number of adjacent areas / total number of uninspected areas, where adjacent areas are uninspected areas adjacent to inspected areas; The values ​​of the preset inspection information degree, preset interactive correlation degree and preset similarity coefficient can be determined by the user according to the actual application scenario. The smaller the values ​​of the preset inspection information degree and the preset interactive correlation degree, the greater the user's need to determine the preferred selection method according to the change conditions. Provide a value of the preset inspection information degree and the preset interactive correlation degree, detect the historical records of the user determining the preferred selection method according to the change conditions, and record the average value of the inspection information degree corresponding to the historical records that can meet the user's needs as the preset inspection information degree, and record the average value of the interactive correlation corresponding to the historical records that can meet the user's needs as the preset interactive correlation. The larger the value of the preset similarity coefficient, the greater the user's need to determine the interactive correlation according to the similarity coefficient. Provide a value of the preset similarity coefficient, and the preset similarity coefficient is 60%; Determine whether to inspect each uninspected inspection area based on the information matching coefficient, where: For a single uninspected area, If the information matching coefficient is greater than or equal to the preset information matching coefficient, no inspection is performed on the uninspected area; If the information matching coefficient is less than the preset information matching coefficient, the uninspected area is inspected; The information matching coefficient is confirmed in the following way: for a single uninspected area, the uninspected area is recorded as the target uninspected area, and the inspected area closest to the target uninspected area is recorded as the target inspected area. The information matching coefficient = the number of cargo categories that exist in both the target uninspected area and the target inspected area - the shortest distance from the center point of the target uninspected area to the center point of the target inspected area; The value of the preset information matching coefficient can be determined by the user according to the actual application scenario. The higher the user's inspection accuracy requirement for the inspection area, the smaller the value of the preset information matching coefficient is. A value of the preset information matching coefficient is provided to detect the historical records of no inspection of the uninspected area, and the minimum value of the information matching coefficient corresponding to the historical records that can meet the user's needs is recorded as the preset information matching coefficient.

[0031] Specifically, the inspection information is confirmed in the following manner: If the inspection offset value is greater than or equal to the preset inspection offset value, the inspection information degree is determined according to the trajectory characterization value and the inspection coefficient; If the inspection error value is less than the preset inspection error value, the inspection information degree is determined according to the inspection danger threshold and the inspection ratio.

[0032] Among them, if the inspection offset value is greater than or equal to the preset inspection offset value, then the inspection information degree = trajectory representation value × inspection coefficient; If the inspection error value is less than the preset inspection error value, then the inspection information degree = inspection danger threshold × inspection ratio; The inspection offset value is the average value of the distance thresholds corresponding to each inspected area. For a single inspected area, the inspected area is recorded as the first area, and the other inspected areas except the first area are recorded as the second area. The distance threshold corresponding to the first area is the average value of the shortest distance from the center point of the first area to the center point of each second area. The value of the preset inspection offset value can be determined by the user according to the actual application scenario. The smaller the value of the preset inspection offset value is, the greater the user's demand for determining the inspection information degree according to the risk factor and the trajectory characterization value is. A value of the preset inspection offset value is provided, and the historical records of determining the inspection information degree according to the risk factor and the trajectory characterization value are detected, and the average value of the inspection offset value corresponding to the historical records that can meet the user's needs is recorded as the preset inspection offset value; The trajectory representation value is the average value of the inspection risk coefficient corresponding to each inspected area. The inspection risk coefficient is confirmed by recording a single inspected area as the target area. The inspection risk coefficient corresponding to the target area = the risk trigger coefficient corresponding to the target area + the thermal imaging coefficient corresponding to the target area. Inspection coefficient = a2 / a1, inspection ratio = (area of ​​the smallest rectangle that can contain all inspection areas - area of ​​the smallest rectangle that can contain each inspected area) / area of ​​the smallest rectangle that can contain each inspected area; inspection risk threshold is the maximum value of the inspection risk coefficients corresponding to each inspected area; The danger trigger coefficient is the average value of the sub-danger trigger coefficients of each inspection image corresponding to a single inspected area. For a single inspection image, the sub-danger trigger coefficient = personnel reference value + instability threshold, the personnel reference value is the total number of people in a single inspection image, and the instability threshold is the number of damaged goods in the inspection image. The damaged goods in the inspection image are determined by convolutional neural network technology, which is easy for technicians in this field to understand and will not be described in detail. The thermal imaging coefficient is the maximum value of the temperature reference values ​​corresponding to the infrared thermal imaging images corresponding to a single inspection area. The temperature reference value corresponding to a single infrared thermal imaging image is the highest value of the temperature corresponding to each pixel value in the infrared thermal imaging image. The temperature corresponding to a single pixel point is determined by infrared thermal imaging analysis software. This is content that is easy for technicians in this field to understand and will not be elaborated on in detail.

[0033] Specifically, the inspection change module responds to the change condition to determine the preferred selection method, wherein: The change condition of the inspection change module response is that the trajectory smoothness is greater than or equal to the preset trajectory smoothness or the area correlation coefficient is less than the preset area correlation coefficient. The priority selection method is to determine the inspection priority coefficient of each uninspected area according to the information matching coefficient; The change condition of the inspection change module response is that the trajectory smoothness is less than the preset trajectory smoothness and the area correlation coefficient is greater than or equal to the preset area correlation coefficient. The priority selection method is to determine the inspection priority coefficient of the pre-inspection area corresponding to each correlation combination according to the flight influence coefficient; The inspection priority coefficient of a single uninspected area is negatively correlated with the information matching coefficient of the uninspected area; The inspection priority coefficient of a single pre-inspection area is positively correlated with the flight impact coefficient corresponding to the pre-inspection area.

[0034] The change condition includes a first change condition and a second change condition, the first change condition is that the trajectory smoothness is greater than or equal to the preset trajectory smoothness or the regional correlation coefficient is less than the preset regional correlation coefficient, and the second change condition is that the trajectory smoothness is less than the preset trajectory smoothness and the regional correlation coefficient is greater than or equal to the preset regional correlation coefficient; The method for confirming the trajectory smoothness is to obtain the UAV movement trajectory, establish a three-dimensional rectangular coordinate system with the UAV position corresponding to the starting time point as the origin, record the UAV position in the UAV movement trajectory corresponding to each time point excluding the starting time point as a trajectory point, and detect the vector angle corresponding to each trajectory point. The method for confirming the vector angle corresponding to a single trajectory point is to record a trajectory point as the target trajectory point for a trajectory point, and record the vector angle corresponding to the trajectory point adjacent to the target trajectory point and located before the target trajectory point in the movement order. The vector corresponding to the target trajectory point The angle between Denoted as vector angle, ], the vector corresponding to each trajectory point is tangent to the moving trajectory and the direction of the vector is the same as the moving direction. The trajectory smoothness is the standard deviation of the vector angle corresponding to each trajectory point; the time point is set by the user, and a method for setting the time point is provided. According to the order of the drone inspection time from early to late, every 1s is recorded as a time point.

[0035] The regional correlation coefficient is the average value of the sub-correlation coefficients corresponding to each uninspected area. The method for confirming the sub-correlation coefficient is as follows: for a single uninspected area, the uninspected area is recorded as the target area, and the other uninspected areas except the target area are recorded as the reference area. The sub-correlation coefficient is the maximum value of the regional similarities between the target area and each reference area. For a single reference area, the reference area is recorded as the analysis reference area. The regional similarity between the analysis reference area and the target area = cargo similarity + distribution similarity. Cargo similarity = (the number of cargo categories existing in both the analysis reference area and the target area / the total number of cargo categories contained in the analysis reference area and the target area). Distribution similarity = the absolute value of the difference between the distribution thresholds corresponding to the analysis reference area and the target area / the larger value of the distribution thresholds corresponding to the analysis reference area and the target area. The distribution threshold is the average value of the cargo distances corresponding to each cargo in a single inspection area. The cargo distance corresponding to a single cargo is the average value of the shortest distances from the cargo to other cargoes in the inspection area where the cargo is located. The values ​​of the preset trajectory smoothness and the preset area correlation coefficient can be determined by the user according to the actual application scenario. The smaller the value of the preset trajectory smoothness is, the larger the value of the preset area correlation coefficient is, and the greater the user's demand for determining the inspection priority coefficient of each uninspected area according to the information matching coefficient is. A value of the preset trajectory smoothness and the preset area correlation coefficient is provided, and the historical records of determining the inspection priority coefficient of each uninspected area according to the information matching coefficient are detected, and the average value of the trajectory smoothness corresponding to the historical records that can meet the user's needs is recorded as the preset trajectory smoothness, and the average value of the area correlation coefficient corresponding to the historical records that can meet the user's needs is recorded as the preset area correlation coefficient; The flight impact coefficient corresponding to a single pre-inspection area = the shortest distance from the UAV to the pre-inspection area + the yaw coefficient, where the yaw coefficient is the angle between the first line segment and the second ray. The first line segment is the line connecting the trajectory point corresponding to the last time point of the UAV in the current monitoring cycle and the center point corresponding to the pre-inspection area. The second ray is a ray starting from the trajectory point corresponding to the last time point of the UAV in the current monitoring cycle and having the same direction as the vector corresponding to the trajectory point. When determining the inspection priority coefficient of each uninspected area according to the information matching coefficient, the smaller the information matching coefficient of the uninspected area is, the higher the priority of the inspection order is; When determining the inspection priority coefficient of the pre-inspection area corresponding to each associated combination according to the flight influence coefficient, each associated combination corresponds to a pre-inspection area, and any uninspected area is randomly selected as a pre-inspection area for a single associated combination. The smaller the flight influence coefficient of the pre-inspection area, the higher the priority of the inspection order; It should be noted that if the pre-inspection area meets the preset conditions, an early warning will be sent to the user end for each inspection area included in the associated combination corresponding to the pre-inspection area. The preset conditions are that the danger trigger coefficient is greater than or equal to the preset danger trigger coefficient or the thermal imaging coefficient is greater than or equal to the preset thermal imaging coefficient.

[0036] Specifically, the confirmation method of the association combination is: If the cross coefficient is greater than or equal to the preset cross coefficient, the associated combination is determined according to the cross similarity and the regional balance coefficient; If the cross coefficient is less than the preset cross coefficient, the associated combination is determined according to the regional similarity.

[0037] Among them, the cross coefficient is the average value of the cross reference values ​​corresponding to each uninspected area. For a single uninspected area, the uninspected area is recorded as the first target area, and each inspected area adjacent to the first target area is recorded as the first reference area. The cross reference value corresponding to the first target area = the number of first reference areas / cross angle; the line connecting the center point of each first reference area and the center point of the first target area is recorded as the reference line, and the angle that can contain the minimum angle of each reference line is recorded as the cross angle; it should be noted that if the number of first reference areas is 0 or 1, the cross reference value = the number of first reference areas; When determining the association combination according to the cross-similarity and the regional balance coefficient or determining the association combination according to the regional similarity, an association analysis is performed on each uninspected area. When performing an association analysis on a single uninspected area, the uninspected area is recorded as a first target uninspected area, and other uninspected areas that are not recorded in the association combination except the first target uninspected area are recorded as first reference uninspected areas. The set of the first reference uninspected area and the first target uninspected area that meet the benchmark condition is recorded as an association combination, and the association analysis is continued for the uninspected areas that are not recorded in the association combination until all uninspected areas are recorded in the association combination; Different confirmation methods correspond to different benchmark conditions, among which: If the confirmation method is to determine the associated combination according to the cross-similarity and the regional balance coefficient, the benchmark condition is that the cross-similarity with the first target inspection area is greater than the preset cross-similarity and the regional balance coefficient is greater than the preset regional balance coefficient; If the confirmation method is to determine the associated combination according to the regional similarity, the reference condition is that the regional similarity with the first target inspection area is greater than the preset regional similarity; Cross-similarity = 1-(the absolute value of the difference between the cross-reference values ​​corresponding to the two uninspected areas / the larger value of the cross-reference values ​​corresponding to the two uninspected areas). For any two uninspected areas, the regional balance coefficient is determined as follows: If the distance reference value is greater than or equal to the preset distance reference value, the area balance coefficient = the area of ​​the inspected area in the analysis rectangle / the area of ​​the analysis rectangle. The smallest rectangle that can contain two uninspected areas is recorded as the analysis rectangle. If the distance reference value is less than the preset distance reference value, the area balance coefficient is the larger value of the overlap ratios of the two uninspected areas; the smallest rectangle that can contain each inspected area is recorded as the first analysis rectangle, and the overlap ratio = the area where a single uninspected area overlaps with the first analysis rectangle / the area of ​​the uninspected area; The values ​​of the preset cross-coefficient, preset cross-similarity, preset regional balance coefficient and preset regional similarity can be determined by the user according to the actual application scenario. The larger the value of the preset cross-coefficient, the greater the user's demand for determining the associated combination based on the regional similarity. A value of the preset cross-coefficient is provided, and the historical records of determining the associated combination based on the cross-similarity and the regional balance coefficient are detected. The average value of the cross-coefficients corresponding to the historical records that can meet the user's needs is recorded as the preset cross-coefficient. The greater the user's demand for improving the inspection accuracy, the smaller the values ​​of the preset cross-similarity, the preset regional balance coefficient and the preset regional similarity. A value of the preset cross-similarity, the preset regional balance coefficient and the preset regional similarity is provided. The preset cross-similarity is 70%, the preset regional balance coefficient is 50%, and the preset regional similarity is 80%.

[0038] Specifically, the inspection adjustment module determines the inspection adjustment method according to the inspection area category, wherein: For a type of inspection area, the inspection adjustment method is to determine the direction setting method of each collection point according to the adjustment conditions; For the second type of inspection area, the inspection adjustment method is to set the collection direction of each collection point to the vertical direction.

[0039] Among them, the collection direction of each collection point is set to the vertical direction, wherein the collection direction is the direction in which the drone takes the inspection image and the infrared thermal imaging image; the vertical direction is the direction from the collection point corresponding to a single inspection area to the center point of the inspection area.

[0040] Specifically, the inspection area categories include: A type of inspection area where the regional layout complexity is greater than or equal to the preset regional layout complexity or the cargo stacking coefficient is greater than or equal to the preset cargo stacking coefficient; A second-class inspection area whose area layout complexity is less than the preset area layout complexity and whose cargo stacking coefficient is less than the preset cargo stacking coefficient.

[0041] Among them, for a single inspection area, the regional layout complexity = the area of ​​the area where goods are stacked in the inspection area / the area of ​​the inspection area; The cargo stacking coefficient is confirmed by recording the cargo category appearing in a single inspection area in the current monitoring period as the reference category, recording the smallest rectangle in the inspection area that can contain the cargo corresponding to a single reference category as the rectangle to be analyzed, each reference category corresponds to a rectangle to be analyzed, and recording the average value of the overlapping proportions corresponding to each rectangle to be analyzed as the cargo stacking coefficient; for a single rectangle to be analyzed, the rectangle to be analyzed is recorded as the target rectangle to be analyzed, and the overlapping proportion corresponding to the target rectangle to be analyzed = the area of ​​the area where the target rectangle to be analyzed overlaps with other rectangles to be analyzed / the area of ​​the target rectangle to be analyzed; The values ​​of the preset area layout complexity and the preset cargo stacking coefficient can be determined by the user according to the actual application scenario. The smaller the value of the preset area layout complexity and the larger the value of the preset cargo stacking coefficient, the greater the user's demand for determining the direction setting method of each collection point according to the adjustment conditions. A value of the preset area layout complexity and the preset cargo stacking coefficient is provided. The preset area layout complexity is 70%. The historical records of determining the inspection area as a Class II area are detected, and the average value of the cargo stacking coefficient corresponding to the historical records that can meet the user's needs is recorded as the preset cargo stacking coefficient.

[0042] Specifically, the inspection and adjustment module responds to the adjustment conditions to determine the direction setting mode of each collection point, wherein: For a single collection point, The adjustment condition of the patrol adjustment module response is that the mutual correlation coefficient is greater than or equal to the preset mutual correlation coefficient or the influence threshold is less than the preset influence threshold, and the determination direction setting method is to determine the collection direction according to the associated direction group; The adjustment condition of the patrol adjustment module response is that the mutual correlation coefficient is less than the preset mutual correlation coefficient and the influence threshold is greater than or equal to the preset influence threshold, and the direction setting method is to determine the collection direction according to the direction evaluation coefficient.

[0043] The adjustment condition includes a first adjustment condition and a second adjustment condition, the first adjustment condition is that the mutual correlation coefficient is greater than or equal to a preset mutual correlation coefficient or the influence threshold is less than a preset influence threshold, and the second adjustment condition is that the mutual correlation coefficient is less than the preset mutual correlation coefficient and the influence threshold is greater than or equal to the preset influence threshold; The confirmation method of the mutual correlation coefficient is as follows: for the center point of a single inspection area, the due north direction of the center point is recorded as the reference direction, and starting from the reference direction, the direction corresponding to each rotation of 30° is recorded as a direction to be analyzed, until the rotation is 360°, 12 directions to be analyzed can be obtained, and the average value of the sub-correlation means corresponding to each direction to be analyzed is recorded as the mutual correlation coefficient; The sub-correlation mean is the average value of the sub-correlations corresponding to a direction to be analyzed and other directions to be analyzed; For a single direction to be analyzed in a single inspection area, the inspection area is recorded as the second target inspection area, the direction to be analyzed is recorded as the target direction, a line segment with the center point of the second target inspection area as the starting point and a point on the boundary of the second target inspection area as the endpoint and the same as the target direction is recorded as a reference line, and an area in a circle with the midpoint of the reference line as the center and the length corresponding to the reference line as the diameter and overlapping with the second target inspection area is recorded as a radiation area corresponding to the target direction. It can be understood that each direction to be analyzed corresponds to a radiation area; For any two directions to be analyzed, the area where the radiation area corresponding to one direction to be analyzed does not overlap with the radiation area corresponding to the other direction to be analyzed is recorded as a non-overlapping reference area, and each of the two directions to be analyzed corresponds to a non-overlapping reference area; Sub-correlation = the area of ​​the area where the radiation area corresponding to one direction to be analyzed overlaps with the radiation area corresponding to another direction to be analyzed + the number of cargo categories that exist in both one non-overlapping reference area and another non-overlapping reference area; Direction evaluation coefficient = (the number of cargo categories contained in the radiation area corresponding to a single direction to be analyzed / the total number of cargo categories in the inspection area where the collection point is located) + the cargo density corresponding to a single direction to be analyzed; The cargo density is the average value of the distance coefficients corresponding to each cargo in the radiation zone corresponding to a single direction to be analyzed. The distance coefficient corresponding to a single cargo is the average value of the shortest distance from the cargo to other cargoes in the radiation zone where the cargo is located. Impact threshold = regional layout complexity + cargo stacking coefficient; Determining the collection direction according to the associated direction group includes: performing correlation analysis on each direction to be analyzed, for a single direction to be analyzed, recording the direction to be analyzed as a target direction to be analyzed, recording the directions to be analyzed other than the target direction to be collected and analyzed that are not recorded in the associated direction group as reference directions to be analyzed, recording the reference directions to be analyzed whose sub-correlation with the target direction to be analyzed is greater than a preset sub-correlation and the set of the target direction to be analyzed as an associated direction group, and continuing to perform correlation analysis on the directions to be analyzed that are not recorded in the associated direction group until all directions to be analyzed are recorded in the associated direction group; each associated direction group corresponds to an analysis direction, a single analysis direction is any randomly selected direction to be analyzed in a single associated direction group, and the direction from the drone to the center of the radiation area corresponding to the single analysis direction is taken as a collection direction; Determine the collection direction according to the direction evaluation coefficient, wherein the direction to be analyzed whose direction evaluation coefficient is greater than the preset direction evaluation coefficient is taken as the analysis direction, and the direction from the UAV to the center of the radiation area corresponding to a single analysis direction is taken as a collection direction, and each analysis direction corresponds to a collection direction; The values ​​of the preset mutual correlation coefficient, the preset impact threshold and the preset sub-correlation can be determined by the user according to the actual application scenario. The smaller the value of the preset mutual correlation coefficient and the larger the value of the preset impact threshold, the greater the user's demand for determining the collection direction according to the associated direction group. A value of the preset mutual correlation coefficient and the preset impact threshold is provided, and the historical records for determining the collection direction according to the associated direction group are recorded as reference historical records, and the average value of the mutual correlation coefficients corresponding to the reference historical records that can meet the user's needs is recorded as the preset mutual correlation coefficient, and the average value of the impact thresholds corresponding to the reference historical records that can meet the user's needs is recorded as the preset impact threshold; the greater the user's demand for improving the accuracy of warehouse inspections, the larger the value of the preset sub-correlation. A value of the preset sub-correlation is provided, and the average value of the sub-correlation corresponding to the reference historical records that can meet the user's needs is recorded as the preset sub-correlation.

[0044] Specifically, the inspection review module determines whether each inspection area needs an early warning based on the danger trigger coefficient of the inspection image and the thermal imaging coefficient of the infrared thermal imaging image, wherein: For a single inspection area, If the danger trigger coefficient is greater than or equal to the preset danger trigger coefficient or the thermal imaging coefficient is greater than or equal to the preset thermal imaging coefficient, an early warning is sent to the user terminal; If the danger trigger coefficient is less than the preset danger trigger coefficient and the thermal imaging coefficient is less than the preset thermal imaging coefficient, there is no need to send an early warning to the user end.

[0045] Among them, the values ​​of the preset danger trigger coefficient and the preset thermal imaging coefficient can be determined by the user according to the actual application scenario. The greater the user's demand for reducing the occurrence of logistics warehouse accidents, the smaller the values ​​of the preset danger trigger coefficient and the preset thermal imaging coefficient. A value of a preset danger trigger coefficient and a preset thermal imaging coefficient is provided, and the historical records of sending warnings to the user end are detected. The average value of the danger trigger coefficient corresponding to the historical records that can meet the user's needs is recorded as the preset danger trigger coefficient, and the average value of the thermal imaging coefficient corresponding to the historical records that can meet the user's needs is recorded as the preset thermal imaging coefficient.

[0046] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A logistics inspection drone based on artificial intelligence, characterized in that: include: Information collection module, used to obtain basic information of logistics warehouses and drone flight information; An inspection optimization module, which is connected to the information collection module, and is used to respond to inspection conditions to determine an inspection optimization method, wherein the inspection optimization method is to determine an inspection change method according to set conditions, or to determine an inspection adjustment method according to an inspection area category; An inspection change module, which is connected to the information collection module and the inspection optimization module respectively, and is used to respond to the set conditions to determine the inspection change mode, and the inspection change mode is to determine the priority selection mode according to the change conditions, or to determine whether to inspect each uninspected area according to the information matching coefficient; The preferred selection method is to determine the inspection priority coefficient of each uninspected area according to the information matching coefficient, or to determine the inspection priority coefficient of the pre-inspected area corresponding to each associated combination according to the flight influence coefficient; An inspection adjustment module, which is connected to the information collection module and the inspection optimization module respectively, and is used to determine the inspection adjustment mode according to the inspection area category. The inspection adjustment mode is to determine the direction setting mode of each collection point according to the adjustment conditions or to set the collection direction of each collection point to the vertical direction; The inspection area category is determined according to the complexity of the area layout and the cargo stacking coefficient, and the direction setting method is to determine the collection direction according to the associated direction group or the direction evaluation coefficient; The inspection review module is connected to the inspection change module and the inspection adjustment module respectively, and is used to collect and store inspection images and infrared thermal imaging images, and determine whether each inspection area needs early warning based on the danger trigger coefficient of the inspection image and the thermal imaging coefficient of the infrared thermal imaging image.

2. The artificial intelligence-based logistics inspection drone according to claim 1 is characterized in that: The inspection optimization module responds to the inspection conditions to determine the inspection optimization method, wherein: The inspection condition responded by the inspection optimization module is that the inspection area influence coefficient is less than the preset inspection area influence coefficient or the endurance reference value is less than the preset endurance reference value, and the inspection optimization mode is determined by determining the inspection change mode according to the set conditions; The inspection conditions responded by the inspection optimization module are that the inspection area influence coefficient is greater than or equal to the preset inspection area influence coefficient and the endurance reference value is greater than or equal to the preset endurance reference value. The inspection optimization method is determined by determining the inspection adjustment method according to the inspection area category.

3. The artificial intelligence-based logistics inspection drone according to claim 2 is characterized in that: The inspection change module responds to the set conditions to determine the inspection change mode, wherein: The setting condition for the inspection change module response is that the inspection information degree is greater than or equal to the preset inspection information degree or the interactive correlation degree is greater than or equal to the preset interactive correlation degree, and the inspection change mode is determined by determining the priority selection mode according to the change condition; The setting conditions for the inspection change module response are that the inspection information degree is less than the preset inspection information degree and the interaction correlation degree is less than the preset interaction correlation degree. The inspection change determination method is to determine whether to inspect each uninspected area based on the information matching coefficient.

4. The artificial intelligence-based logistics inspection drone according to claim 3 is characterized in that: The inspection information is confirmed in the following manner: If the inspection offset value is greater than or equal to the preset inspection offset value, the inspection information degree is determined according to the trajectory characterization value and the inspection coefficient; If the inspection error value is less than the preset inspection error value, the inspection information degree is determined according to the inspection danger threshold and the inspection ratio.

5. The artificial intelligence-based logistics inspection drone according to claim 3 is characterized in that: The inspection change module responds to the change condition to determine the preferred selection method, wherein: The change condition of the inspection change module response is that the trajectory smoothness is greater than or equal to the preset trajectory smoothness or the area correlation coefficient is less than the preset area correlation coefficient. The priority selection method is to determine the inspection priority coefficient of each uninspected area according to the information matching coefficient; The change condition of the inspection change module response is that the trajectory smoothness is less than the preset trajectory smoothness and the area correlation coefficient is greater than or equal to the preset area correlation coefficient. The priority selection method is to determine the inspection priority coefficient of the pre-inspection area corresponding to each correlation combination according to the flight influence coefficient; The inspection priority coefficient of a single uninspected area is negatively correlated with the information matching coefficient of the uninspected area; The inspection priority coefficient of a single pre-inspection area is positively correlated with the flight impact coefficient corresponding to the pre-inspection area.

6. The artificial intelligence-based logistics inspection drone according to claim 5 is characterized in that: The confirmation method of the association combination is: If the cross coefficient is greater than or equal to the preset cross coefficient, the associated combination is determined according to the cross similarity and the regional balance coefficient; If the cross coefficient is less than the preset cross coefficient, the associated combination is determined according to the regional similarity.

7. The artificial intelligence-based logistics inspection drone according to claim 5 is characterized in that: The inspection adjustment module determines the inspection adjustment mode according to the inspection area category, wherein: For a type of inspection area, the inspection adjustment method is to determine the direction setting method of each collection point according to the adjustment conditions; For the second type of inspection area, the inspection adjustment method is to set the collection direction of each collection point to the vertical direction.

8. The artificial intelligence-based logistics inspection drone according to claim 7, characterized in that: The inspection area categories include: A type of inspection area where the regional layout complexity is greater than or equal to the preset regional layout complexity or the cargo stacking coefficient is greater than or equal to the preset cargo stacking coefficient; A second-class inspection area whose area layout complexity is less than the preset area layout complexity and whose cargo stacking coefficient is less than the preset cargo stacking coefficient.

9. The artificial intelligence-based logistics inspection drone according to claim 7, characterized in that: The inspection and adjustment module responds to the adjustment conditions to determine the direction setting mode of each collection point, wherein: For a single collection point, The adjustment condition of the patrol adjustment module response is that the mutual correlation coefficient is greater than or equal to the preset mutual correlation coefficient or the influence threshold is less than the preset influence threshold, and the determination direction setting method is to determine the collection direction according to the associated direction group; The adjustment condition of the patrol adjustment module response is that the mutual correlation coefficient is less than the preset mutual correlation coefficient and the influence threshold is greater than or equal to the preset influence threshold, and the direction setting method is to determine the collection direction according to the direction evaluation coefficient.

10. The artificial intelligence-based logistics inspection drone according to claim 9, characterized in that: The inspection review module determines whether each inspection area needs an early warning based on the danger trigger coefficient of the inspection image and the thermal imaging coefficient of the infrared thermal imaging image, wherein: For a single inspection area, If the danger trigger coefficient is greater than or equal to the preset danger trigger coefficient or the thermal imaging coefficient is greater than or equal to the preset thermal imaging coefficient, an early warning is sent to the user terminal; If the danger trigger coefficient is less than the preset danger trigger coefficient and the thermal imaging coefficient is less than the preset thermal imaging coefficient, there is no need to send an early warning to the user end.

Images