Intelligent inspection method and device based on risk heat map and electronic equipment

Abstract

The application provides an intelligent inspection method and device based on a risk heat map and electronic equipment. The intelligent inspection method based on the risk heat map comprises the following steps: obtaining a static risk heat map of a scene to be inspected; generating a dynamic risk heat map according to the static risk heat map; creating an inspection path to be inspected according to each heat value point in a region corresponding to a different heat value in the dynamic risk heat map; inspecting the scene to be inspected based on the inspection path to be inspected to obtain an inspection result, wherein the inspection result comprises an inspected path and a risk region found in an inspection process; updating the dynamic risk heat map according to the inspected path contained in the inspection result; and updating the heat value of the static risk heat map according to the risk region found in the inspection process contained in the inspection result. The intelligent inspection method based on the risk heat map improves the reliability of the inspection result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular to an intelligent inspection method and device based on a risk heat map and an electronic device. BACKGROUND

[0002] With the increasing emphasis on safety issues, many scenarios require inspection robots to supervise and prevent the surrounding environment accordingly. For example, in places such as shopping malls and hospitals, inspection robots are needed to respond to unsafe incidents in a timely manner; for places where dangerous flammable goods are stored, inspection robots are needed to promptly investigate potential safety hazards.

[0003] In the prior art, many inspection tasks simply focus on path planning tasks, and although full-area coverage is achieved, this inspection method ignores the focus on high-risk areas, so that the inspection system spends more time in safe areas.

[0004] Therefore, the inspection method in the prior art has low reliability of the inspection result. SUMMARY

[0005] Therefore, the present application provides an intelligent inspection method and device based on a risk heat map and an electronic device to solve the above problems.

[0006] According to a first aspect of the present application, an intelligent inspection method based on a risk heat map is provided, comprising: obtaining a static risk heat map of a scene to be inspected; generating a dynamic risk heat map according to the static risk heat map; creating a path to be inspected according to each heat value point in the region corresponding to different heat values in the dynamic risk heat map; based on the path to be inspected, inspecting the scene to be inspected to obtain an inspection result, wherein the inspection result contains the inspected path and the risk area found in the inspection process; updating the dynamic risk heat map according to the inspected path contained in the inspection result, wherein the updated dynamic risk heat map is used as the basis for the next inspection path planning and the initial map of the inspected path record; updating the heat value of the static risk heat map according to the risk area found in the inspection process contained in the inspection result.

[0007] In another implementation manner of the present application, obtaining a static risk heat map of a scene to be inspected comprises: obtaining prior information and a scene map of the scene to be inspected; determining the probability of accidents occurring in each region of the scene map according to the prior information of the scene to be inspected; modeling based on the probability of accidents occurring in each region of the scene map to obtain a static risk heat map.

[0008] In another implementation manner of the present application, the to-be-inspected path is created according to each heat value point in the region corresponding to different heat values in the dynamic risk heat map, comprising: creating a temporary heat value map according to the dynamic risk heat map, wherein the heat values of each heat value point in the region corresponding to different heat values in the temporary heat value map are adjusted according to a preset heat value adjustment condition; selecting an inspection target point in the temporary heat value map according to a preset number of inspection target points; connecting each inspection target point in the temporary heat value map to obtain the to-be-inspected path.

[0009] In another implementation manner of the present application, the temporary heat value map is created according to the dynamic risk heat map, comprising: creating an initial temporary heat value map according to an initial dynamic risk heat map; selecting an inspection target point for the first time inspection based on the initial temporary heat value map; establishing a set of inspection target points according to each selected inspection target point; updating the temporary heat value map of the last time to obtain each temporary heat value map according to each set of inspection target points.

[0010] In another implementation manner of the present application, the dynamic risk heat map is updated according to the inspected route contained in the inspection result, comprising: updating the dynamic risk heat map of the last time to obtain each dynamic risk heat map according to the inspected route contained in each inspection result.

[0011] In another implementation manner of the present application, the heat value of the static risk heat map is updated according to the risk region found in the inspection process contained in the inspection result, comprising: determining the corresponding region of the risk region found in the inspection process contained in the inspection result in the static risk heat map; increasing the heat value of the corresponding region.

[0012] In another implementation manner of the present application, the intelligent inspection method based on the risk heat map further comprises: if the inspection result indicates that there is no risk region in the inspection region, reducing the heat value of the inspection region in the corresponding region of the dynamic risk heat map.

[0013] According to a second aspect of the present application, there is provided an intelligent inspection device based on a risk heat map, comprising: an acquisition module configured to acquire a static risk heat map of a scene to be inspected; a first processing module configured to generate a dynamic risk heat map according to the static risk heat map, and create an inspection path to be inspected according to each heat value point in a region corresponding to a different heat value in the dynamic risk heat map; an inspection module configured to inspect the scene to be inspected based on the inspection path to be inspected, and obtain an inspection result, wherein the inspection result comprises an inspected path and a risk region found in the inspection process; and a second processing module configured to update the dynamic risk heat map according to the inspected path in the inspection result, wherein the updated dynamic risk heat map is used as a basis for planning a next inspection path and an initial map for recording the inspected path, and update a heat value of the static risk heat map according to the risk region found in the inspection process in the inspection result.

[0014] According to a third aspect of the present application, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the intelligent inspection method based on a risk heat map according to any one of the above aspects when executing the computer program.

[0015] According to a fourth aspect of the present application, there is provided a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program implements the steps of the intelligent inspection method based on a risk heat map according to any one of the above aspects when executed by a processor.

[0016] In the intelligent inspection method based on a risk heat map according to the present application, the static risk heat map is acquired, so that the region in the scene to be inspected where a risk is likely to occur and the probability of the risk occurring can be determined intuitively, the inspection path to be inspected is created based on each heat value point in the dynamic risk heat map, so that the inspection path to be inspected is targeted and the high-risk region can be inspected more accurately, the dynamic risk heat map is updated according to the inspection result, so that the user can observe the inspection result and the inspection region more intuitively, and the static risk heat map and the dynamic risk heat map are updated in real time according to the inspection result, so that the inspection target point selected for the next inspection is more accurate and the reliability of the inspection result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, brief descriptions will be given to the drawings needed in the embodiments or prior art descriptions. The advantages and benefits of the solutions will become clear to those skilled in the art by reading the following detailed description of the embodiments. The drawings are only used for the purpose of illustrating the preferred embodiments and are not considered as limiting the present application. In the drawings:

[0018] Figure 1A step flow chart of the intelligent inspection method based on the risk heat map for an embodiment of the present application.

[0019] Figure 2 A schematic diagram of the static risk heat map for another embodiment of the present application.

[0020] Figure 3 A schematic diagram of the temporary heat map for another embodiment of the present application.

[0021] Figure 4 A schematic diagram of the dynamic risk heat map for another embodiment of the present application.

[0022] Figure 5 A schematic diagram of the inspection path for another embodiment of the present application.

[0023] Figure 6 A schematic diagram of the inspection times of each target point for another embodiment of the present application.

[0024] Figure 7 A schematic diagram of the dynamic risk heat map for another embodiment of the present application.

[0025] Figure 8 A schematic diagram of the inspection path for another embodiment of the present application.

[0026] Figure 9 A schematic diagram of the inspection times of each target point for another embodiment of the present application.

[0027] Figure 10 A schematic diagram of the static risk heat map for another embodiment of the present application.

[0028] Figure 11 A schematic diagram of the dynamic risk heat map for another embodiment of the present application.

[0029] Figure 12 A schematic diagram of the inspection path for another embodiment of the present application.

[0030] Figure 13 A schematic diagram of the inspection times of each target point for another embodiment of the present application.

[0031] Figure 14 A structure block diagram of the intelligent inspection device based on the risk heat map for another embodiment of the present application.

[0032] Figure 15 A structure schematic diagram of the electronic device for another embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make personnel in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art should belong to the scope of protection of the embodiments of the present application.

[0034] Figure 1 A step flow chart of an intelligent inspection method based on a risk heat map provided by the embodiments of the present application is shown in Figure 1 The present embodiment mainly includes the following steps:

[0035] S101, obtaining a static risk heat map of a scene to be inspected.

[0036] Exemplarily, a scene map is generated according to scene information to be inspected, a static risk heat map of the scene to be inspected is constructed according to a prior probability of sending an accident in each region in the scene to be inspected, and the static risk heat map does not change under the condition that no risk is found in the inspection process and the actual scene does not change. The way of constructing the risk heat map can be completed by using a gas diffusion model according to the properties of gas diffusion, constructing the risk heat map, focusing on inspection of high-risk areas where gas leakage may occur, and the like. The present application does not make specific limitations on the construction method of the risk heat map.

[0037] It should be understood that the static risk heat map is obtained by some prior information to get the relative size of the accident probability, and the weight a r is set. The probability information is modeled by a Gaussian model. Assuming that the risk probability p r of several key monitoring points has been evaluated, the static heat map can be regarded as a mixture of k single Gaussian models, which is expressed by the following formula

[0038]

[0039] wherein k represents the kth single Gaussian model in the GMM (Gaussian Mixture Model), is the weight of the corresponding Gaussian model, K is the total number of Gaussian models, m ij is any point in the temporary heat map. A single component in the Gaussian mixture model simulates the probability of finding a target at a specific location. The distribution of p

[0040]

[0041] wherein the initial value is the risk probability of the key monitoring point.

[0042] S102. Generate a dynamic risk heat map based on the static risk heat map.

[0043] For example, such as Figure 2 As shown, in a static risk heat map, larger heat values ​​are represented by warmer colors, and smaller heat values ​​by cooler colors. It can be seen that corresponding points exhibit different degrees of warmth based on their heat values, where different heat values ​​represent different risk probabilities. Based on the static risk heat map, a model like the one shown is generated. Figure 4 The dynamic risk heat map shown.

[0044] S103. Create inspection paths based on the heat value points in the regions corresponding to different heat values ​​in the dynamic risk heat map.

[0045] For example, inspection target points are selected from the regions corresponding to each heat value point in the dynamic risk heat map and connected to generate an inspection path. Inspection path planning can be accomplished using more direct methods, such as obtaining the optimal path distance between any two points through other path planning algorithms, obtaining the inspection order by solving user problems, and then obtaining the path planning for a single inspection, etc. This invention does not impose specific limitations on the method of inspection path planning.

[0046] S104. Based on the path to be inspected, inspect the scene to be inspected and obtain the inspection results. The inspection results include the inspected path and the risk areas found during the inspection.

[0047] For example, the inspection robot follows the path to be inspected to inspect the scene to be inspected and obtains the inspection results, which include the inspected path and whether there are any risk areas during the inspection process.

[0048] S105. Update the dynamic risk heat map based on the inspected routes included in the inspection results. The updated dynamic risk heat map serves as the basis for the next inspection route planning and as the initial map for the inspected route records.

[0049] For example, the updated dynamic heatmap records which areas the inspection robot has traversed and which areas have not been inspected for a long time. By recording the grid along the inspection path, which is the grid for the sensor to collect information, the scene map M(l×w) is divided by the sensor search radius r. s Divide the length of each cell into (l / r) s )×(w / r s ) area, i.e. l h ×w hThe grid, since the generated path is composed of nodes and edges between nodes, only needs to traverse all nodes and edges to obtain all grids passed by the inspection path.

[0050] First, the node m1(x1, y1) and the node m2(x2, y2) are converted into grid coordinates, that is, the coordinate values are divided by the sensor search radius r s , to obtain grid coordinates and

[0051] The maximum and minimum values of the line segment on the x-axis and y-axis are taken respectively, the minimum value of the coordinate on the x-axis is rounded down, the maximum value is rounded up, the integer value of the x-axis from small to large is taken, and the value of the corresponding longitudinal coordinate on the same straight line with the grid coordinates and is calculated; the minimum value of the coordinate on the y-axis is rounded down, the maximum value is rounded up, the integer value of the y-axis from small to large is taken, and the value of the corresponding transverse coordinate on the same straight line with the grid coordinates and is calculated, to obtain the set of all intersection points with the grid

[0052] The intersection point set is sorted, it is judged which grids are passed through by the adjacent two coordinates, and the single inspection record R is updated.

[0053] For the single inspection record R:

[0054]

[0055] That is, the single inspection record R of all passed grids is recorded as 1.

[0056] For multiple inspections, we assume that a total of T inspections are performed, among which, a total of t ij inspections are performed to a point m ij , and T ij inspections are experienced from the last time the point m ij is inspected, in other words, the last time the point x ij is inspected is the T-T ij time, then we can obtain:

[0057]

[0058]

[0059] In the above formula, α dy is a weight parameter, the greater the value, the greater the influence of the static risk heat map on the update of the subsequent dynamic risk heat map, and appropriately increasing the value of the weight α dy can achieve the effect of multiple inspections of high-risk areas. pobs (m ij ) is a point m ij whether the point m ij on the obstacle, p obs (m ij ) = 1, the dynamic risk heat map heat value

[0060] It should be understood that the dynamic risk heat map is updated according to each inspection path, for embodying the number of inspections of each point and the inspection interval from the last inspection, and can also consider the actual trajectory of the robot, the frame rate and radius of the sensor and other information to update the dynamic risk heat map.

[0061] S106, according to the risk area found in the inspection process contained in the inspection result, the static risk heat map is updated.

[0062] Exemplarily, according to the risk area found in the inspection process contained in the inspection result, the static risk heat map is updated, and the static risk heat map is constructed according to prior information, and when the risk or the surrounding environment changes, the static risk heat map is updated.

[0063] In the intelligent inspection method based on the risk heat map of the present application, by obtaining the static risk heat map, the area prone to risk in the scene to be inspected and the probability of risk occurrence can be determined intuitively, and the dynamic risk heat map is created based on each heat value point, so that the to-be-inspected path is targeted and the high-risk area can be inspected more accurately, and the dynamic risk heat map is updated according to the inspection result, so that the user can more intuitively observe the inspection result and the inspection area, and the static risk heat map and the dynamic risk heat map are updated in real time according to the inspection result, so that the inspection target point selected for the next inspection is more accurate, and the reliability of the inspection result is improved.

[0064] In another implementation manner of the present application, the static risk heat map of the scene to be inspected is obtained, comprising: obtaining the prior information and the scene map of the scene to be inspected; determining the probability of each area in the scene map to occur an accident according to the prior information of the scene to be inspected; and modeling based on the probability of each area in the scene map to occur an accident, to obtain the static risk heat map.

[0065] In another implementation of the present invention, creating an inspection path based on each heat value point in the region corresponding to different heat values ​​in the dynamic risk heat map includes: creating a temporary heat value map based on the dynamic risk heat map, wherein the heat values ​​of each heat value point in the region corresponding to different heat values ​​in the temporary heat value map are adjusted according to preset heat value adjustment conditions; selecting inspection target points in the temporary heat value map according to a preset number of inspection target points; and connecting each inspection target point in the temporary heat value map to obtain the inspection path.

[0066] For example, such as Figure 2 As shown, let m ij The risk probabilities p corresponding to the values ​​in [30,240], [470,100], [480,280], [150,80], [300,30], [160,200], [200,260], [330,170], and [240,150] are respectively. r The values ​​are set to 0.8, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0.7, and 0.6 respectively. Based on the areas corresponding to different heat values ​​in the dynamic risk heat map, each heat value point is determined. Based on the different preset number of inspection target points, inspection target points are selected from each heat value point. The method for selecting inspection target points is as follows:

[0067] First, a temporary heatmap with the same initial values ​​as the initial dynamic risk heatmap is constructed. exist Figure 2 Tests were conducted on a static risk heat map, with α set. obj =0.001, setting different values ​​for n obj Values, each temporary heat map as shown Figure 3 As shown, the number of target points n selected as needed. obj Determine the number of iterations, and each time select the point m with the highest heat value on the map. max (x max ,y max Add to the set M of inspection target points obj Afterwards, the temporary heatmap was modified to obtain the following result: Figure 3 The temporary heatmaps shown apply the following weighting to each heat value on the temporary heatmap:

[0068]

[0069]

[0070] in, For temporary heat map any point m ij Thermodynamic value, weight ω(x) max ,ymax )Reference is made to the hyperbolic tangent (Tanh) activation function:

[0071]

[0072] It should be understood that the patrol target points are selected on the dynamic risk heat map, and each time is determined according to the initial risk probability value from large to small, and there is no situation that the patrol target points are relatively densely concentrated in a certain area due to a value being too large. Taking point [20, 20] as the starting point, points [30, 240], [470, 100], [480, 280], [150, 80], [300, 30], [160, 200], [200, 260], [330, 170], and [240, 150] are set as initial marked high-risk points, and the risk probabilities thereof are set as 0.8, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0.7, and 0.6 respectively.

[0073] As shown in Figure 5 , the various patrol target points in the temporary heat value map are connected to obtain a to-be-patrolled path, the number of target points n obj = 20, the sensor search radius r s = 20, and finally, 9 times of patrol are experienced to complete the patrol task. The preset heat value adjustment condition can include reducing the size of the risk value around the selected point or increasing the weight of the unselected position. The way of finding the target point for single patrol can also be replaced by other weight functions, and the formula used by the application for calculating the weight is not specifically limited. Based on the heat values of various regions of the dynamic risk heat map, the various patrol target points are determined, thereby ensuring the accuracy of the risk area of the patrol.

[0074] It should be understood that the application can still achieve the same effect when reducing the number of risk points. Taking point [20, 20] as the starting point, points (30, 240) and (150, 80) are set as initial marked high-risk points, and the risk probabilities thereof are set as 0.8 and 0.6 respectively. The static risk heat map obtained by GMM (Gaussian Mixture Model) is as shown in Figure 10 , the number of target points n obj = 20, the sensor search radius r s = 20, finally, 8 times of patrol are experienced to complete the patrol task, the dynamic risk heat map is as shown in Figure 11 , the patrol path is as shown in Figure 12 , and the number of patrols t ij of each point is plotted, and the result is as shown in Figure 13The left lower corner point in the figure is the starting point, and the other two points are the high-risk areas initially set. Since the high-risk areas initially set are less, it can be seen that the key inspection areas are concentrated on the left side, especially near the two high-risk areas and the starting point. The full coverage task is divided into multiple inspections, which reduces the repeated path of each inspection while ensuring global coverage after multiple inspections. The high-risk areas are inspected multiple times, and the key inspection is improved, thereby improving the inspection efficiency.

[0075] In another implementation mode of the present application, according to the dynamic risk heat map, a temporary heat value map is created, including: according to the initial dynamic risk heat map, an initial temporary heat map is created; based on the initial temporary heat map, the inspection target point of the first time is selected; according to each selected inspection target point, the inspection target point set is established; according to each inspection target point set, the last temporary heat map is updated to obtain each temporary heat map.

[0076] In another implementation mode of the present application, according to the dynamic risk heat map, a temporary heat value map is created, including: according to the initial dynamic risk heat map, an initial temporary heat map is created; based on the initial temporary heat map, the inspection target point of the first time is selected; according to each selected inspection target point, the inspection target point set is established; according to each inspection target point set, the last temporary heat map is updated to obtain each temporary heat map.

[0077] Exemplarily, according to the static risk heat map, an initial dynamic risk heat map is created, as shown in Figure 4 According to the dynamic risk heat map, a temporary heat value map is created, including: according to the initial dynamic risk heat map, an initial temporary heat map is created; based on the initial temporary heat map, the inspection target point of the first time is selected; according to each selected inspection target point, the inspection target point set is established; according to each inspection target point set, the last temporary heat map is updated to obtain each temporary heat map.

[0078] In another implementation mode of the present application, according to the dynamic risk heat map, a temporary heat value map is created, including: according to the initial dynamic risk heat map, an initial temporary heat map is created; based on the initial temporary heat map, the inspection target point of the first time is selected; according to each selected inspection target point, the inspection target point set is established; according to each inspection target point set, the last temporary heat map is updated to obtain each temporary heat map.

[0079] Exemplarily, if the inspection result indicates that there is a risk area, the heat value of the corresponding area of the risk area in the static risk heat map is increased.

[0080] It should be understood that the inspection times t ij The result is shown in Figure 6 The left lower corner point in the figure is the starting point, and the other two points are the high-risk areas initially set. Since the high-risk areas initially set are less, it can be seen that the key inspection areas are concentrated on the left side, especially near the two high-risk areas and the starting point. The full coverage task is divided into multiple inspections, which reduces the repeated path of each inspection while ensuring global coverage after multiple inspections. The high-risk areas are inspected multiple times, and the key inspection is improved, thereby improving the inspection efficiency.

[0081] In another implementation of the present application, the intelligent inspection method based on the risk heat map further comprises: if the inspection result indicates that there is no risk area in the inspection area, reducing the heat value of the inspection area in the corresponding area of the dynamic risk heat map.

[0082] For example, if the inspection result indicates that there is no risk area in the inspection area, the heat value of the inspection area in the corresponding area of the dynamic risk heat map is reduced, as shown in FIG. 6. Figure 4 Figure 4 The color of the inspection path in FIG. 6 is darker in some areas and lighter in some areas. The lighter area indicates that there is no risk area.

[0083] In another implementation of the present application, if we replace the formula:

[0084]

[0085] The static risk heat map in FIG. 5 Corresponding heat value With the dynamic risk heat map Corresponding heat value The following formula:

[0086]

[0087] Heat value The dynamic risk heat map generated in this way can avoid selecting the target point repeatedly as much as possible. Let the number of target points n obj = 20, the sensor search radius r s = 20, and the global inspection task is completed after 7 inspections. The risk heat map changes in winter as shown in FIG. 8, and the inspection path is as shown in FIG. 9. The inspection times t ij of each point are plotted, and the plotting result is as shown in FIG. 10. Figure 7 Figure 8 Figure 9

[0088] It should be understood that although the inspection times are relatively small, there is no obvious multiple inspection effect at the key inspection points. Compared with the use of the static risk heat map, the key attention to the marked high-risk areas is lacking, and it is better to directly plan the full coverage inspection path than to achieve the global coverage task by multiple inspections.

[0089] Figure 14 The structure block diagram of an intelligent inspection device 1400 based on a risk heat map provided by an embodiment of the present application is as shown in FIG. 11. The embodiment mainly comprises: Figure 14

[0090] ​​​​​The acquisition module 1401 is configured to acquire a static risk heat map of a scene to be inspected.

[0091] The first processing module 1402 is configured to generate a dynamic risk heat map according to the static risk heat map, and create an inspection path to be inspected according to each heat value point in a region corresponding to a different heat value in the dynamic risk heat map.

[0092] The inspection module 1403 is configured to inspect the scene to be inspected based on the inspection path to be inspected, to obtain an inspection result, wherein the inspection result includes an inspected path and a risk region found in an inspection process.

[0093] The second processing module 1404 is configured to update the dynamic risk heat map according to the inspected path included in the inspection result, wherein the updated dynamic risk heat map is used as a basis for planning a next inspection path and an initial map for recording the inspected path, and update the static risk heat map according to the risk region found in the inspection process included in the inspection result.

[0094] In the intelligent inspection device based on the risk heat map, the static risk heat map is acquired, so that the region prone to risks in the scene to be inspected and the probability of risk occurrence can be determined intuitively, the inspection path to be inspected is created based on each heat value point in the dynamic risk heat map, so that the inspection path to be inspected is targeted and the high-risk region can be inspected more accurately, the dynamic risk heat map is updated according to the inspection result, so that the user can observe the inspection result and the inspection region more intuitively, the static risk heat map and the dynamic risk heat map are updated in real time according to the inspection result, so that the inspection target point selected for the next inspection is more accurate, and the reliability of the inspection result is improved.

[0095] In another implementation manner of the present application, the acquisition module 1401 is further configured to acquire prior information and a scene map of the scene to be inspected, determine the probability of an accident occurring in each region in the scene map according to the prior information of the scene to be inspected, and model the probability of an accident occurring in each region in the scene map to obtain the static risk heat map.

[0096] In another implementation manner of the present application, the first processing module 1402 is further configured to create a temporary heat value map according to the dynamic risk heat map, adjust the heat value of each heat value point in a region corresponding to a different heat value in the temporary heat value map according to a preset heat value adjustment condition, select an inspection target point in the temporary heat value map according to a preset number of inspection target points, and connect each inspection target point in the temporary heat value map to obtain the inspection path to be inspected.

[0097] In another implementation manner of the present application, the first processing module 1402 is further configured to create an initial temporary heat map according to the initial dynamic risk heat map; select a target point for the first inspection based on the initial temporary heat map; establish a set of target points for inspection according to each selected target point for inspection; and update the temporary heat map of the last time according to each set of target points for inspection to obtain each temporary heat map.

[0098] In another implementation manner of the present application, the second processing module 1404 is further configured to update the dynamic risk heat map of the last time according to the inspected route contained in each inspection result to obtain each dynamic risk heat map.

[0099] In another implementation manner of the present application, the second processing module 1404 is further configured to determine the corresponding area of the risk area found in the inspection process in the static risk heat map contained in the inspection result; and increase the heat value of the corresponding area.

[0100] In another implementation manner of the present application, the second processing module 1404 is further configured to reduce the heat value of the corresponding area of the inspection area in the dynamic risk heat map if the inspection result indicates that there is no risk area in the inspection area.

[0101] As shown in Figure 15 The electronic device 1500 can include a processor 1501, a memory 1503, and a communication bus 1504, a communication interface 1505.

[0102] Among them:

[0103] The processor 1501, the memory 1503 and the communication interface 1505 complete the communication among each other through the communication bus 1504.

[0104] The communication interface 1505 is configured to communicate with other electronic devices or servers.

[0105] The processor 1501 is configured to execute the program 1502, and specifically can execute the steps of the intelligent inspection method based on the risk heat map in any of the above embodiments.

[0106] Specifically, the program 1502 can include program code including computer operation instructions.

[0107] The processor 1501 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the application. The one or more processors included in the smart device can be of the same type or different types, such as one or more CPUs and one or more ASICs.

[0108] The memory 1503 is configured to store the program 1502. The memory 1503 can include a high-speed RAM memory, and can further include a non-volatile memory such as at least one disk memory.

[0109] The program 1502 can be specifically configured to cause the processor 1501 to perform the steps of any of the risk heat map based intelligent inspection methods described in the embodiments. The specific implementation of each step in the program 1502 can refer to the corresponding description of the steps and units performed by any of the risk heat map based intelligent inspection methods described above, and will not be described here. It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, the specific working processes of the devices and modules described above can refer to the corresponding process descriptions in the foregoing method embodiments.

[0110] The exemplary embodiments of the present application further provide a non-transitory computer readable storage medium having computer instructions stored therein, wherein the computer instructions are used to cause a computer to execute the method of the embodiments of the present application.

[0111] The method according to the embodiments of the present application described above can be implemented in hardware, firmware, or as software or computer code stored in a recording medium such as a CD ROM, a RAM, a floppy disk, a hard disk, or an optical disk, or downloaded from a network and stored in a local recording medium, so that the method described herein can be processed by such software using a general purpose computer, a special purpose processor, or programmable or special purpose hardware such as an ASIC or an FPGA. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component (for example, a RAM, a ROM, a flash memory, etc.) that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method described herein is implemented. In addition, when a general purpose computer accesses the code for implementing the method shown herein, the execution of the code will convert the general purpose computer into a special purpose computer for executing the method shown herein.

[0112] To this end, particular embodiments of the application have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0113] It should be noted that all directional indications, such as upper, lower, left, right, front, back, rear, etc., are merely used for convenience of description and are not intended to limit the application to a particular orientation.

[0114] In the description of the present application, the terms "first", "second", etc., are used only for convenience and are not intended to imply or represent the order of importance, the relative significance or the implied direction of the technical features indicated. Therefore, the features defined as "first", "second" can explicitly or implicitly include at least one of the features.

[0115] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0116] It should be noted that, although the specific embodiments of the present application are described in detail with reference to the accompanying drawings, it should not be understood as limiting the scope of protection of the present application. Various modifications and variations of the embodiments described in the claims are still within the scope of protection of the present application without creative labor.

[0117] The examples of the embodiments of the present application are intended to simply illustrate the technical features of the embodiments of the present application, so that those skilled in the art can intuitively understand the technical features of the embodiments of the present application, and are not improper limitations of the embodiments of the present application.

[0118] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent inspection method based on a risk heat map, characterized in that, include: Obtain a static risk heat map of the scene to be inspected, including: Obtain prior information and scene map of the scene to be inspected; Based on the prior information of the scene to be inspected, determine the probability of an accident occurring in each area of ​​the scene map; A static risk heat map is obtained by modeling the probability of accidents occurring in each area of ​​the scene map. This static risk heat map is... A mixture of single Gaussian models is represented as: in, In the Gaussian mixture model, the first... A single Gaussian model, These correspond to the weights of the Gaussian model. This is the total number of Gaussian models. For any point in the temporary heatmap; A dynamic risk heat map is generated based on the static risk heat map. Based on the heat value points in the regions corresponding to different heat values ​​in the dynamic risk heat map, create a path to be inspected; Based on the path to be inspected, the scene to be inspected is inspected to obtain inspection results, wherein the inspection results include the inspected path and the risk areas found during the inspection. Based on the inspected routes included in the inspection results, the dynamic risk heat map is updated. The updated dynamic risk heat map serves as the basis for planning the next inspection route and as the initial map for the recorded inspected routes, including: For single inspection records : The single inspection record of all grids passed through. Recorded as 1; For multiple inspections, the dynamic risk heat map heat value is: in, These are weight parameters; Second inspection completed. The last inspection Experienced Secondary inspection; Point Whether it is obstructed by an obstacle, point When on an obstacle, , ; The static risk heat map is updated with heat values ​​based on the risk areas discovered during the inspection process, as included in the inspection results.

2. The method according to claim 1, characterized in that, The step of creating an inspection path based on the heat value points in the regions corresponding to different heat values ​​in the dynamic risk heat map includes: Based on the dynamic risk heat map, a temporary heat value map is created, wherein the heat values ​​of each heat value point in the region corresponding to different heat values ​​in the temporary heat value map are adjusted according to preset heat value adjustment conditions; Select the inspection target points from the temporary heat map based on the preset number of inspection target points; Connect the various inspection target points in the temporary heat map to obtain the inspection path.

3. The method according to claim 2, characterized in that, The step of creating a temporary heat map based on the dynamic risk heat map includes: Create an initial temporary heat map based on the initial dynamic risk heat map; Based on the initial temporary heat map, select the inspection target point for the first inspection; Based on the selected inspection target points each time, establish a set of inspection target points; Based on the set of each inspection target point, the previous temporary heat map is updated to obtain each temporary heat map.

4. The method according to claim 3, characterized in that, The step of updating the dynamic risk heat map based on the inspected routes included in the inspection results includes: Based on the inspected routes included in each inspection result, the previous dynamic risk heat map is updated to obtain various dynamic risk heat maps.

5. The method according to claim 1, characterized in that, The step of updating the heat map of static risk based on the risk areas discovered during the inspection process, as included in the inspection results, includes: Determine the corresponding areas in the static risk heat map for the risk areas discovered during the inspection process included in the inspection results; Increase the thermal value of the corresponding region.

6. The method according to claim 1, characterized in that, Also includes: If the inspection results indicate that the risk area does not exist in the inspection area, then the heat value of the inspection area in the corresponding area of ​​the dynamic risk heat map is reduced.

7. An intelligent inspection device based on a risk heat map, characterized in that, include: Acquisition module: Acquires static risk heat map of the scene to be inspected; The first processing module generates a dynamic risk heat map based on the static risk heat map, including: acquiring prior information and a scene map of the scene to be inspected; determining the probability of an accident occurring in each area of ​​the scene map based on the prior information of the scene to be inspected; and modeling based on the probability of an accident occurring in each area of ​​the scene map to obtain a static risk heat map. A mixture of single Gaussian models is represented as: in, In the Gaussian mixture model, the first... A single Gaussian model, These correspond to the weights of the Gaussian model. This is the total number of Gaussian models. For any point in the temporary heat map; create an inspection path based on the heat value points in the regions corresponding to different heat values ​​in the dynamic risk heat map; Inspection module: Based on the path to be inspected, the inspection module performs an inspection on the scene to be inspected and obtains the inspection results, wherein the inspection results include the inspected path and the risk areas found during the inspection. The second processing module updates the dynamic risk heat map based on the inspected routes included in the inspection results. The updated dynamic risk heat map serves as the basis for the next inspection route planning and as the initial map for the inspected route records. It includes: For single inspection records : The single inspection record of all grids passed through. Recorded as 1; For multiple inspections, the dynamic risk heat map heat value is: in, These are weight parameters; Second inspection completed. The last inspection Experienced Secondary inspection; Point Whether it is obstructed by an obstacle, point When on an obstacle, , Based on the risk areas discovered during the inspection process included in the inspection results, the static risk heat map is updated with heat values.

8. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the intelligent inspection method based on a risk heat map as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of the intelligent inspection method based on a risk heat map as described in any one of claims 1 to 6.

Images