Outdoor advertisement management system

Abstract

The invention belongs to the field of advertisement management, and discloses an outdoor advertisement management system, which comprises a partition module, a patrol path planning module, a patrol unmanned aerial vehicle and a management module, the zoning module is used for dividing the area where the outdoor advertising board to be patrolled is located into a plurality of patrolling areas; the path planning module is used for planning a patrol path of each patrol area; the patrol unmanned aerial vehicle is used for patrolling the outdoor advertising board in the patrol area based on the patrol path to obtain a patrol image; and the management module is used for managing the outdoor billboard based on the patrol image. According to the method, the existing partitioning mode is improved, and the patrol area is obtained based on the patrol coefficient, so that the finally obtained patrol area can be balanced among the number of the outdoor advertising boards, the patrol distance and the patrol difficulty, and the patrol efficiency of the outdoor advertising boards can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of advertising management, and in particular to an outdoor advertising management system. Background Art

[0002] Outdoor advertising management refers to checking the status of outdoor billboards after they are installed, so as to promptly discover billboards with safety risks or serious damage. The traditional inspection method is generally through manual inspection. Since billboards are generally located in high places, this brings great difficulties to manual inspection, making manual inspection efficiency relatively low. With the development of drone technology, using drones to inspect various high-altitude equipment has gradually become a common technology. Using drones to inspect outdoor billboards can significantly improve the inspection efficiency of billboards. Before the inspection, the inspection area is usually divided into zones, and then the path planning algorithm is used to calculate the best inspection order for each area to further improve the inspection efficiency. However, the existing partitioning method is generally directly divided into multiple areas of the same size, which also leads to some areas may have more billboards, so that the drone needs to go back and forth to the take-off point for battery replacement multiple times to complete the inspection, while some areas have fewer billboards, and the number of billboards that the drone can inspect in a single flight is too small, which will affect the inspection efficiency of outdoor billboards. Summary of the invention

[0003] The purpose of the present invention is to disclose an outdoor advertising management system to solve the technical problems raised in the background technology.

[0004] In order to achieve the above object, the present invention adopts the following technical solution:

[0005] The present invention provides an outdoor advertising management system, including a zoning module, a patrol path planning module, a patrol drone and a management module;

[0006] The partition module is used to divide the area where the outdoor billboards that need to be inspected are located into multiple inspection areas;

[0007] The path planning module is used to plan the inspection path for each inspection area;

[0008] The inspection drone is used to inspect outdoor billboards in the inspection area based on the inspection path and obtain inspection images;

[0009] The management module is used to manage outdoor billboards based on patrol images;

[0010] Among them, the area where the outdoor billboards that need to be inspected are located is divided into multiple inspection areas, including:

[0011] S1, use Area to represent the rectangular area containing all outdoor billboards, and initialize the integer c to 1;

[0012] S2, divide the area into N 2 temporary areas of equal size;

[0013] S3, calculate the inspection coefficient of each temporary area respectively;

[0014] S4, save the temporary area whose inspection coefficient is greater than the set inspection coefficient threshold to the set tempU c ;Save the temporary area whose inspection coefficient is less than or equal to the set inspection coefficient threshold to the set finalU;

[0015] S5, judge tempU c Whether the number of temporary areas in is greater than or equal to the set number threshold, if so, proceed to S6, if not, proceed to S8;

[0016] S6, respectively for tempU c Each temporary area in is processed as follows:

[0017] S61, for tempU c The elements tempu in tempu are divided into N 2 temporary areas of equal size;

[0018] S62, for all temporary areas obtained in S61, save the temporary areas whose inspection coefficients are greater than the set inspection coefficient threshold to the set tempU c+1 ;Save the temporary area whose inspection coefficient is less than or equal to the set inspection coefficient threshold to the set finalU;

[0019] S7, add 1 to the value of c and enter S5;

[0020] S8, use the temporary area in finalU as the inspection area.

[0021] Optionally, plan the inspection route for each inspection area, including:

[0022] The Bellman-Ford algorithm is used to plan the inspection path of the billboards in the inspection area to obtain the inspection path.

[0023] Optionally, outdoor billboards in the inspection area are inspected based on the inspection path to obtain inspection images, including:

[0024] Based on the inspection path, the surface of each outdoor billboard in the inspection area is photographed in sequence to obtain an inspection image.

[0025] Optionally, the management module includes an image recognition unit and a summary unit;

[0026] The image recognition unit is used to recognize the inspection image and obtain the preset type of defects existing in the inspection image;

[0027] The summarizing unit is used to summarize the defects contained in all the inspection images belonging to the same outdoor billboard to obtain the inspection result of the billboard.

[0028] Optionally, the process of obtaining Area is as follows:

[0029] Mark the coordinates of each outdoor advertising space that needs to be inspected on the map, including the X-axis coordinate and the Y-axis coordinate;

[0030] Get the maximum value X2 and the minimum value X1 of the X-axis coordinate, and the maximum value Y2 and the minimum value Y1 of the Y-axis coordinate of all coordinates of the outdoor billboard;

[0031] The X-axis coordinates of the points in the Area are in the range of [X1, X2], and the Y-axis coordinates are in the range of [Y1, Y2].

[0032] Optionally, divide Area into N 2 Temporary areas of equal size, including:

[0033] L1 and L2 are used to represent the length and width of Area respectively, then:

[0034]

[0035]

[0036] The length and width of the temporary area are bL1 and bL2 respectively.

[0037] Optionally, the calculation function of the patrol coefficient is:

[0038]

[0039] insp d represents the inspection coefficient of temporary area d, sumn d is the total number of outdoor billboards that need to be inspected in d, S d represents the area of ​​d, S Area represents the area of ​​Area, suml represents the total number of outdoor billboards that need to be inspected, ud represents the set of outdoor billboards that need to be inspected contained in d, and lens i It represents the planning coefficient of the outdoor billboard i that needs to be inspected in ud, lensm represents the maximum planning coefficient of the outdoor billboard that needs to be inspected in ud, Ads irepresents the surface area of ​​the outdoor billboard i that needs to be inspected in ud; Adsm represents the maximum surface area of ​​the outdoor billboard that needs to be inspected in ud; w1, w2 and w3 represent density weight, distance weight and area weight respectively.

[0040] Optional, lens i The calculation function is:

[0041]

[0042] niud represents the set obtained by deleting i from ud, dile i,j is the length of the straight line between i and j.

[0043] Optional, the values ​​of density weight, distance weight and area weight are and

[0044] Optionally, set the patrol coefficient threshold to

[0045] Beneficial effects:

[0046] The present invention improves the existing zoning method. It does not directly divide the area where the outdoor billboards that need to be inspected are located into multiple inspection areas of the same area, but obtains the inspection area based on the inspection coefficient, so that the inspection area finally obtained can achieve a balance between the number of outdoor billboards included, the inspection distance and the inspection difficulty, which can effectively improve the efficiency of inspecting outdoor billboards. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 The figure is a schematic diagram of an outdoor advertising management system of the present invention.

[0049] Figure 2 A schematic diagram of the filtering process of the present invention. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0051] like Figure 1 In one embodiment shown, the present invention provides an outdoor advertising management system, including a zoning module, a patrol path planning module, a patrol drone, and a management module;

[0052] The partition module is used to divide the area where the outdoor billboards that need to be inspected are located into multiple inspection areas;

[0053] The path planning module is used to plan the inspection path for each inspection area;

[0054] The inspection drone is used to inspect outdoor billboards in the inspection area based on the inspection path and obtain inspection images;

[0055] The management module is used to manage outdoor billboards based on patrol images;

[0056] Among them, the area where the outdoor billboards that need to be inspected are located is divided into multiple inspection areas, including:

[0057] S1, use Area to represent the rectangular area containing all outdoor billboards, and initialize the integer c to 1;

[0058] S2, divide the area into N 2 temporary areas of equal size;

[0059] S3, calculate the inspection coefficient of each temporary area respectively;

[0060] S4, save the temporary area whose inspection coefficient is greater than the set inspection coefficient threshold to the set tempU c ;Save the temporary area whose inspection coefficient is less than or equal to the set inspection coefficient threshold to the set finalU;

[0061] S5, judge tempU c Whether the number of temporary areas in is greater than or equal to the set number threshold, if so, proceed to S6, if not, proceed to S8;

[0062] S6, respectively for tempU c Each temporary area in is processed as follows:

[0063] S61, for tempU c The elements tempu in tempu are divided into N 2 temporary areas of equal size;

[0064] S62, for all temporary areas obtained in S61, save the temporary areas whose inspection coefficients are greater than the set inspection coefficient threshold to the set tempU c+1 ;Save the temporary areas whose inspection coefficient is less than or equal to the set inspection coefficient threshold to the set finalU;

[0065] S7, add 1 to the value of c and enter S5;

[0066] S8, use the temporary area in finalU as the inspection area.

[0067] The above zoning method improves the existing zoning method. It does not directly divide the area where the outdoor billboards that need to be inspected are located into multiple patrol areas of the same area, but obtains the patrol area based on the patrol coefficient, so that the final patrol area can achieve a balance between the number of outdoor billboards included, the patrol distance and the patrol difficulty, which can effectively improve the efficiency of patrolling outdoor billboards.

[0068] In the present invention, the quantity threshold value can be set to 1. The quantity threshold value here is mainly used to judge tempU c Whether there are still temporary areas that need to be further divided, so as to divide the Area into multiple inspection areas with different areas.

[0069] In the present invention, N=2n+1, where n is a positive integer greater than or equal to 2. For example, N may be 5.

[0070] Optionally, plan the inspection route for each inspection area, including:

[0071] The Bellman-Ford algorithm is used to plan the inspection path of the billboards in the inspection area to obtain the inspection path.

[0072] The Bellman-Ford algorithm is a classic algorithm for solving the single-source shortest path problem, especially for the case where there may be negative weight edges in the graph. Unlike the Dijkstra algorithm, the Bellman-Ford algorithm can handle the case where there are negative weight edges in the graph (but cannot handle negative weight cycles). Its basic idea is to gradually update the shortest path from the source point to each node through the "relaxation" operation until the shortest path is stable.

[0073] How the Bellman-Ford algorithm works:

[0074] The core idea of ​​the Bellman-Ford algorithm is to update the path estimate by relaxing the edges multiple times. The specific process is as follows:

[0075] Initialization: Set the distance of the source point to 0 and the distance of all other nodes to infinity.

[0076] Relaxation operation: Relax each edge in the graph, that is, check whether the shortest path from the source point to a node can be updated through a certain edge. If the path can be shortened through the current edge, update the path estimate.

[0077] Repeat step 2: relax all edges V-1 times, where V is the number of nodes in the graph. The reason is that the shortest path passes through at most V-1 edges (assuming there are no negative weight cycles).

[0078] Check for negative weight cycles: After performing V-1 relaxation operations, check all edges again. If the path length of an edge can still be updated, it means that there is a negative weight cycle in the graph.

[0079] After obtaining the inspection path, outdoor billboards in the inspection area can be inspected efficiently according to the connection order in the inspection path.

[0080] Optionally, outdoor billboards in the inspection area are inspected based on the inspection path to obtain inspection images, including:

[0081] Based on the inspection path, the surface of each outdoor billboard in the inspection area is photographed in sequence to obtain an inspection image.

[0082] Since the area of ​​an outdoor billboard may be very large, the inspection image obtained by a single shot of a drone may not be able to completely include the surface of the outdoor billboard while meeting the shooting distance for subsequent image recognition. Therefore, for such outdoor billboards, drones are required to perform partitioned shooting of the outdoor billboard at multiple shooting positions so that all the inspection images obtained cover all areas of the surface of the outdoor billboard.

[0083] The inspection drone can be transported to the inspection area by staff via vehicles.

[0084] After obtaining the inspection image, the inspection drone can transmit the inspection image to the management module via wireless transmission.

[0085] The inspection drone can be manually controlled to inspect outdoor billboards according to the inspection path, or the inspection path can be stored in the drone's memory chip and then the drone can adaptively inspect according to the inspection path.

[0086] Since the inspection path of the present invention is obtained based on a map, it is necessary to obtain the coordinates corresponding to the positions of the outdoor billboards in the inspection path in the real world through the scaling of the map.

[0087] Optionally, the management module includes an image recognition unit and a summary unit;

[0088] The image recognition unit is used to recognize the inspection image and obtain the preset type of defects existing in the inspection image;

[0089] The summarizing unit is used to summarize the defects contained in all the inspection images belonging to the same outdoor billboard to obtain the inspection result of the billboard.

[0090] Since the same outdoor billboard may correspond to multiple inspection images at the same time, the defects existing in the outdoor billboard can be more completely obtained through aggregation.

[0091] Optional, such as Figure 2 , identify the inspection image and obtain the preset types of defects in the inspection image, including:

[0092] Convert the inspection image into a grayscale image;

[0093] Filtering the grayscale image to obtain a filtered image;

[0094] The filtered image is input into the recognition model for recognition to obtain the preset type of defects existing in the inspection image.

[0095] Filtering is a common method to remove noise. Especially before image analysis and processing, denoising is very important and can improve image quality, extract important features, enhance visualization effects, etc.

[0096] Optionally, filtering the grayscale image to obtain a filtered image includes:

[0097] Use the following filtering function to calculate the filtered grayscale value of each pixel in the grayscale image and obtain the filtered image:

[0098]

[0099] pgy v represents the gray value of v after filtering, nvu represents the set of pixels in a rectangular area with length and width H centered on v, and gy zRepresents the grayscale value of pixel z, where z is the pixel in nvu, gy v represents the gray value of pixel v before filtering, gymx represents the maximum gray value of the pixel in nvu, ds v,z is the distance between v and z, dsmx represents the maximum distance between the pixel in nvu and v, sogymx and sogymi represent the average values ​​of the elements in the first set and the second set respectively obtained by clustering the elements in the set gNVU using the clustering algorithm; the elements in gNVU are the grayscale values ​​of the pixels in nvu; gy ave It represents the average gray value of the pixels in nvu; δ represents the filter weight.

[0100] In the filtering process, the present invention not only considers the difference in grayscale value between z and v, but also considers the difference in spatial position between z and v and the probability that v belongs to the edge of the image. Therefore, if the difference in grayscale value between z and v is greater, and the difference in spatial position between z and v is greater, the influence of z on the filtering result of v is greater; if the difference in grayscale value between z and v is smaller, and the difference in spatial position between z and v is smaller, the influence of z on the filtering result of v is smaller; thereby achieving a better edge preservation effect. In addition to the grayscale value and spatial position, the present invention also considers the probability that v belongs to the edge of the image. When other variables are the same, the greater the probability that v belongs to the edge of the image, the greater the grayscale value after it is filtered, and the smaller the probability that v belongs to the edge of the image, the smaller the grayscale value after it is filtered, thereby achieving the enhancement of the edge of the image, which is conducive to more effectively retaining the edge details in the image.

[0101] The probability that v belongs to the edge of the image is expressed by the difference between the average values ​​of the elements in the first set and the second set. If the difference between the average values ​​of the elements in the first set and the second set is larger, the grayscale boundary of the pixel points in nvu is more obvious, and the probability that v belongs to the edge of the image is greater.

[0102] In the present invention, the first set and the second set obtained by clustering the elements in the set gNVU using a clustering algorithm include:

[0103] Initialize the cluster center to 2;

[0104] Use the k-means clustering algorithm to cluster the elements in the combination gNVU to obtain two sets. The set with the larger mean of elements in the two sets is taken as the first set, and the other set is taken as the second set.

[0105] In the present invention, the value of the filtering weight may be 0.9.

[0106] In the present invention, the recognition model can be a YOLO model or a CNN model.

[0107] Taking the CNN model as an example, the process of training the CNN model is as follows:

[0108] The first step is data collection:

[0109] First, a large amount of billboard image data needs to be collected. These images should contain the types of defects that need to be identified. Billboard images can be obtained through actual shooting or public image datasets on the Internet.

[0110] The second step is data annotation:

[0111] Label each image individually, indicating the type of defect present in the image;

[0112] The third step is data preprocessing:

[0113] Image resizing:

[0114] Typically, the image size of CNN input is fixed (such as 224x224 or 256x256), so the image needs to be resized to a uniform size. This can be done by cropping or scaling the image.

[0115] Image Enhancement:

[0116] Image enhancement technology can help the model improve its generalization ability and reduce overfitting. Common image enhancement methods include random rotation and flipping.

[0117] Label format conversion:

[0118] For classification problems, the labels are usually integers representing the defect type.

[0119] Step 4: Model selection:

[0120] You can use classic convolutional neural network architectures such as VGG16, ResNet, Inception, etc., or you can use lighter network architectures such as MobileNet or EfficientNet.

[0121] Step 5: Train the CNN model

[0122] Loading a pre-trained model: If you use transfer learning, you can load a CNN model pre-trained on a large dataset such as ImageNet and fine-tune it with the billboard defect data.

[0123] Choose a loss function:

[0124] For classification tasks, the commonly used loss function is Cross Entropy Loss.

[0125] Select optimizer: You can choose Adam optimizer or SGD optimizer and set an appropriate learning rate.

[0126] Training and validation: Divide the data set into a training set and a validation set. Monitor the accuracy of the validation set during training to prevent overfitting. Use techniques such as early stopping to improve training results.

[0127] In the present invention, the preset type of defect may be breakage, discoloration, etc.

[0128] Optionally, the process of obtaining Area is as follows:

[0129] Mark the coordinates of each outdoor advertising space that needs to be inspected on the map, including the X-axis coordinate and the Y-axis coordinate;

[0130] Get the maximum value X2 and the minimum value X1 of the X-axis coordinate, and the maximum value Y2 and the minimum value Y1 of the Y-axis coordinate of all coordinates of the outdoor billboard;

[0131] The X-axis coordinates of the points in the Area are in the range of [X1, X2], and the Y-axis coordinates are in the range of [Y1, Y2].

[0132] Specifically, the X-axis and the Y-axis are two mutually perpendicular axes in a two-dimensional coordinate system established on a map. For example, the east direction of the map can be the positive direction of the X-axis.

[0133] Optionally, divide Area into N 2 Temporary areas of equal size, including:

[0134] L1 and L2 are used to represent the length and width of Area respectively, then:

[0135]

[0136]

[0137] The length and width of the temporary area are bL1 and bL2 respectively.

[0138] In the present invention, tempu is divided into N 2 The process of dividing Area into N temporary areas of the same area is the same as that of dividing Area into N 2 The process is the same for all temporary regions of equal size:

[0139] L3 and L4 are used to represent the length and width of tempu respectively, then:

[0140]

[0141]

[0142] The length and width of the temporary region obtained based on tempu are bL3 and bL4 respectively.

[0143] Optionally, the calculation function of the patrol coefficient is:

[0144]

[0145] insp d represents the inspection coefficient of temporary area d, sumn d is the total number of outdoor billboards that need to be inspected in d, S d represents the area of ​​d, S Area represents the area of ​​Area, suml represents the total number of outdoor billboards that need to be inspected, ud represents the set of outdoor billboards that need to be inspected contained in d, and lens i It represents the planning coefficient of the outdoor billboard i that needs to be inspected in ud, lensm represents the maximum planning coefficient of the outdoor billboard that needs to be inspected in ud, Ads i represents the surface area of ​​the outdoor billboard i that needs to be inspected in ud; Adsm represents the maximum surface area of ​​the outdoor billboard that needs to be inspected in ud; w1, w2 and w3 represent density weight, distance weight and area weight respectively.

[0146] The inspection coefficient is a comprehensive consideration of the distribution density of outdoor billboards in the temporary area d, the average distance between outdoor billboards, and the average surface area of ​​outdoor billboards.

[0147] If the distribution density of outdoor billboards is higher, the average distance between outdoor billboards is larger, and the surface area of ​​outdoor billboards is larger, the probability that temporary area d needs to be further divided is greater; if the distribution density of outdoor billboards is lower, the average distance between outdoor billboards is smaller, and the surface area of ​​outdoor billboards is smaller, the probability that temporary area d needs to be further divided is smaller.

[0148] This method of obtaining patrol areas can effectively reduce the probability of problems that may occur when the traditional method directly divides the Area into multiple patrol areas of the same size, which may cause the drone to need to travel back and forth to the take-off point multiple times and the number of billboards that can be patrolled in a single flight to be too small, thereby greatly improving patrol efficiency.

[0149] In the present invention, the surface area of ​​the outdoor billboard may be the sum of the areas of all surfaces of the outdoor billboard that can be photographed by the drone.

[0150] For example, general billboards are in the shape of a cube. If the outdoor billboard is fixed to a building, then except for the side that is in contact with the building, the remaining five sides can be photographed by the drone.

[0151] Optional, lens i The calculation function is:

[0152]

[0153] niud represents the set obtained by deleting i from ud, dile i,j is the length of the straight line between i and j.

[0154] Optional, the values ​​of density weight, distance weight and area weight are and

[0155] Optionally, set the patrol coefficient threshold to

[0156] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An outdoor advertising management system, characterized in that: Includes zoning module, patrol path planning module, patrol drone and management module; The partition module is used to divide the area where the outdoor billboards that need to be inspected are located into multiple inspection areas; The path planning module is used to plan the inspection path for each inspection area; The inspection drone is used to inspect outdoor billboards in the inspection area based on the inspection path and obtain inspection images; The management module is used to manage outdoor billboards based on patrol images; Among them, the area where the outdoor billboards that need to be inspected are located is divided into multiple inspection areas, including: S1, use Area to represent the rectangular area containing all outdoor billboards, and initialize the integer c to 1; S2, divide the area into N 2 temporary areas of equal size; S3, calculate the inspection coefficient of each temporary area respectively; S4, save the temporary area whose inspection coefficient is greater than the set inspection coefficient threshold to the set tempU c ;Save the temporary area whose inspection coefficient is less than or equal to the set inspection coefficient threshold to the set finalU; S5, judge tempU c Whether the number of temporary areas in is greater than or equal to the set number threshold, if so, proceed to S6, if not, proceed to S8; S6, respectively for tempU c Each temporary area in is processed as follows: S61, for tempU c The elements tempu in tempu are divided into N 2 temporary areas of equal size; S62, for all temporary areas obtained in S61, save the temporary areas whose inspection coefficients are greater than the set inspection coefficient threshold to the set tempU c+1 ;Save the temporary area whose inspection coefficient is less than or equal to the set inspection coefficient threshold to the set finalU; S7, add 1 to the value of c and enter S5; S8, use the temporary area in finalU as the inspection area.

2. An outdoor advertising management system according to claim 1, characterized in that: Plan the inspection route for each inspection area, including: The Bellman-Ford algorithm is used to plan the inspection path of the billboards in the inspection area to obtain the inspection path.

3. An outdoor advertising management system according to claim 1, characterized in that: Inspect outdoor billboards in the inspection area based on the inspection path to obtain inspection images, including: Based on the inspection path, the surface of each outdoor billboard in the inspection area is photographed in sequence to obtain an inspection image.

4. An outdoor advertising management system according to claim 1, characterized in that: The management module includes an image recognition unit and a summary unit; The image recognition unit is used to recognize the inspection image and obtain the preset type of defects existing in the inspection image; The summarizing unit is used to summarize the defects contained in all the inspection images belonging to the same outdoor billboard to obtain the inspection result of the billboard.

5. An outdoor advertising management system according to claim 1, characterized in that: The process of obtaining Area is as follows: Mark the coordinates of each outdoor advertising space that needs to be inspected on the map, including the X-axis coordinate and the Y-axis coordinate; Get the maximum value X2 and the minimum value X1 of the X-axis coordinate, and the maximum value Y2 and the minimum value Y1 of the Y-axis coordinate of all coordinates of the outdoor billboard; The X-axis coordinates of the points in the Area are in the range of [X1, X2], and the Y-axis coordinates are in the range of [Y1, Y2].

6. An outdoor advertising management system according to claim 1, characterized in that: Divide Area into N 2 Temporary areas of equal size, including: L1 and L2 are used to represent the length and width of Area respectively, then: The length and width of the temporary area are bL1 and bL2 respectively.

7. An outdoor advertising management system according to claim 1, characterized in that: The calculation function of the inspection coefficient is: insp d represents the inspection coefficient of temporary area d, sumn d is the total number of outdoor billboards that need to be inspected in d, S d represents the area of ​​d, S Area represents the area of ​​Area, suml represents the total number of outdoor billboards that need to be inspected, ud represents the set of outdoor billboards that need to be inspected contained in d, and lens i It represents the planning coefficient of the outdoor billboard i that needs to be inspected in ud, lensm represents the maximum planning coefficient of the outdoor billboard that needs to be inspected in ud, Ads i represents the surface area of ​​the outdoor billboard i that needs to be inspected in ud; Adsm represents the maximum surface area of ​​the outdoor billboard that needs to be inspected in ud; w1, w2 and w3 represent density weight, distance weight and area weight respectively.

8. An outdoor advertising management system according to claim 7, characterized in that: lens i The calculation function is: niud represents the set obtained by deleting i from ud, dile i,j is the length of the straight line between i and j.

9. An outdoor advertising management system according to claim 8, characterized in that: The values ​​of density weight, distance weight, and area weight are and 10. An outdoor advertising management system according to claim 9, characterized in that: The patrol coefficient threshold is set to

Images