A digital method and system for constructing a three-dimensional coverage demand heat map

Abstract

The application discloses a kind of digital methods and systems for constructing three-dimensional coverage demand heat map, so that it can face three-dimensional actual scene, generate digital coverage demand heat map.It is first to the layered discretization of three-dimensional space provided by the method;Second, based on interest point, detection direction and elevation level weight, heat map grid value quantization is carried out;Third, by proposing the concept of virtual interest point and environment partition, multiple coverage of interest point and stepwise coverage for detection direction are realized;Finally, by introducing pooling node, a relatively low-resolution coverage demand heat map is extracted, and the trade-off between calculation performance and calculation cost is realized.The method provided by the application can not only support decision-makers to intuitively grasp the coverage demand situation, but also provide numerical input for downstream optimization decision tasks, which is beneficial to many practical problems such as sensor network deployment.

Description

Technical Field

[0001] This invention relates to the field of situation assessment technology, specifically to a digital method for constructing a three-dimensional heat map of coverage demand, which can not only support decision-makers in intuitively grasping the coverage demand situation, but also provide numerical input for downstream optimization decision-making tasks. Background Technology

[0002] In practical applications such as target detection and environmental monitoring, deploying sensor networks to detect and cover areas of interest is crucial. However, in the information and intelligent era, the complexity of the actual environment and situation, the numerous influencing factors, and the large amount of information make it difficult to accurately measure and intuitively display coverage requirements. Coverage requirement analysis based on situation assessment technology provides important upstream input for tasks such as deployment optimization decisions.

[0003] There has been some research and progress in the field of situation assessment technology, including the analytic hierarchy process (AHP), principal component analysis (PCA), grey relational analysis, and Bayesian networks. These methods assign weights to different influencing factors based on their importance and then perform linear or nonlinear weighted combinations to assess the situation value. However, on the one hand, these methods cannot intuitively display the three-dimensional coverage demand situation; on the other hand, these methods do not provide targeted modeling for the key factors that are the focus of coverage demand analysis.

[0004] Currently, there is no technical solution that can generate digital heat maps of coverage demand for real-world 3D scenarios to help decision-makers intuitively grasp the status quo of coverage demand. Summary of the Invention

[0005] In view of this, the present invention provides a digital method and system for constructing a three-dimensional coverage demand heat map, which can generate a digital coverage demand heat map for real three-dimensional scenarios. This can not only support decision-makers to intuitively grasp the coverage demand situation, but also provide numerical input for downstream optimization decision-making methods.

[0006] To achieve the above objectives, the technical solution of the present invention includes the following steps:

[0007] Step 1: For the three-dimensional environment, the space is divided into multiple levels on the elevation, and each level is meshed to achieve the layered discretization of the three-dimensional environment space.

[0008] Step 2: Quantize grid values ​​based on the weights of points of interest, detection orientation, and elevation levels;

[0009] Step 3: To further simulate multiple coverage and tiered coverage, generate multiple sets of virtual points of interest and perform environmental zoning measurement;

[0010] Step 4: Extract a heatmap of coverage requirements by introducing pooled nodes;

[0011] Step 5: Display the 3D coverage demand heatmap based on the calculated values ​​and input it into the downstream optimization decision-making task.

[0012] Further, step one: For the three-dimensional environment, the space is divided into multiple levels based on elevation, and each level is meshed to achieve layered discretization of the three-dimensional environment space; specifically:

[0013] S101: For a three-dimensional environment, the space is divided into K levels in terms of elevation, with indexes k = 1, 2, ..., K. The value of K is set as needed, and is set to 3, which corresponds to low, medium and high altitudes.

[0014] S102: Divide each level into grids, with a total number of grids of I×J for each level, and indices i = 1, 2, ..., I; j = 1, 2, ..., J; construct the heatmap matrix F = (f ijk ) I×J×K The total number of elements in this heatmap matrix is ​​the same as the total number of all grid cells, where f ijk This represents the coverage requirement value for each element in the heatmap matrix, all of which are initialized to 0.

[0015] Further, step two: quantize the grid values ​​based on the weights of the points of interest, detection orientation, and elevation levels, specifically including the following steps:

[0016] S201: To address the coverage requirements of points of interest, a joint Gaussian-like distribution is designed to characterize the coverage requirement values. The Gaussian-like distribution is described by the following formula:

[0017]

[0018]

[0019] Where d is the distance calculated based on the L2 norm; σ represents the two-dimensional coordinates of the grid points, specifically the coordinates of each grid point with the center of the grid point where the point of interest is located as the origin; σ is a settable parameter used to adjust the shape of the Gaussian-like distribution.

[0020] S202: Traverse each level k, traverse the set of interest points M with indices m = 1, 2, ..., M, and construct a matrix with the same size as the heatmap matrix F. All elements are initialized to 0; during each iteration... The origin of the coordinate system is the grid where the center of the point of interest m is located, and all other grids have been translated compared to the grids in F.

[0021] Calculate according to the Gaussian distribution formula. The values ​​of each element in the set are calculated, and the result is displayed. The values ​​of the matrix are accumulated one-to-one into the heatmap matrix F;

[0022] S203: For the detection azimuth, define D azimuths, with indices d = 1, 2, ..., D; the angular range of each azimuth is... In the analysis of the coverage requirements for the detection azimuth, the element values ​​of the boundary column of the heat map matrix F corresponding to the detection azimuth are assigned the average value of all element values ​​of the matrix.

[0023] S204: Set different weights for different elevation levels.

[0024] Furthermore, in S202, the translation operation is specifically: in each level, the horizontal and vertical translation required to translate from the element at the top left corner (0,0) of the matrix to the grid where the center of the interest point m is located;

[0025] Further, step three: To further simulate multiple coverage and tiered coverage, multiple sets of virtual points of interest are generated and environmental zoning measurements are performed; specifically:

[0026] S301: Based on different detection directions, generate multiple sets of virtual points of interest, move them from the actual points of interest to the detection directions respectively, calculate the coverage requirement value near the virtual points of interest using the Gaussian distribution in step 2, and sum it with the coverage requirement value generated by the actual points of interest, so as to achieve multiple coverage of the points of interest and tiered coverage to cope with the detection directions.

[0027] Based on the above calculations, the actual coverage requirement for generating the m-th point of interest is:

[0028]

[0029] Among them, F (m) This represents the total coverage requirement for the m-th point of interest. This represents the coverage requirement value generated by the actual points of interest; This represents the coverage requirement value generated by the i-th virtual point of interest; n represents the number of detection directions.

[0030] S302: Perform environmental zoning measurement, considering the detection orientation and coverage requirements of each point of interest, divide the environmental area into U regions according to each orientation, and assign weights to the u-th region from farthest to nearest as follows: Where α max and α min Select 1 as the symmetrical value and ensure that the difference between the two does not exceed the set value;

[0031] The regional weight is multiplied by the value of each element in the heatmap matrix, and the combined effect of multiple directions yields the final element value of the heatmap matrix. If a grid in the heatmap matrix is ​​located in multiple partitions at the same time, its regional weight is the maximum value among the multiple partitions.

[0032] Further, step four: introduce pooling nodes to extract a heatmap covering the demand, achieving a trade-off between computational performance and computational cost; specifically:

[0033] Based on the heatmap matrix F calculated in the above steps, a series of discrete points are selected at equal intervals, called pooling nodes; the pooling nodes are downsampled, and the element values ​​of all grids within a certain range of their grid locations are aggregated to extract a heatmap that covers the required area.

[0034] The present invention also provides a digital system for constructing a three-dimensional heat map of coverage requirements, including a hierarchical discretization module, a grid value quantization module, a multi-coverage and tiered coverage simulation module, a heat map extraction module, and a heat map display module;

[0035] The hierarchical discretization module is used to divide the space into multiple layers on the elevation for a three-dimensional environment, and to perform meshing on each layer to achieve hierarchical discretization of the three-dimensional environment space.

[0036] The grid value quantization module is used to quantize grid values ​​based on the weights of interest points, detection orientation, and elevation levels.

[0037] The multi-coverage and tiered coverage simulation module is used to further simulate multi-coverage and tiered coverage, generate multiple sets of virtual points of interest, and perform environmental zoning measurement.

[0038] The heatmap extraction module is used to import pooled nodes to extract a heatmap that covers the required area.

[0039] The heatmap display module is used to display a three-dimensional coverage requirement heatmap based on the calculated values ​​and input it into the downstream optimization decision-making task.

[0040] Furthermore, the hierarchical discretization module specifically executes the following process:

[0041] For a three-dimensional environment, the space is divided into K levels in terms of elevation, with indices k = 1, 2, ..., K. The value of K is set as needed, and is set to 3, which corresponds to low, medium and high altitudes.

[0042] Each level is divided into grids, with a total number of grids of I×J in each level, and indices i = 1, 2, ..., I; j = 1, 2, ..., J; a heatmap matrix F = (f ijk ) I×J×K The total number of elements in this heatmap matrix is ​​the same as the total number of all grid cells, where f ijk This represents the coverage requirement value for each element in the heatmap matrix, all of which are initialized to 0.

[0043] Furthermore, the grid value quantization module executes as follows:

[0044] S201: To address the coverage requirements of points of interest, a joint Gaussian-like distribution is designed to characterize the coverage requirement values. The Gaussian-like distribution is described by the following formula:

[0045]

[0046]

[0047] Where d is the distance calculated based on the L2 norm; σ represents the two-dimensional coordinates of the grid points, specifically the coordinates of each grid point with the center of the grid point where the point of interest is located as the origin; σ is a settable parameter used to adjust the shape of the Gaussian-like distribution.

[0048] S202: Traverse each level k, traverse the set of interest points M with indices m = 1, 2, ..., M, and construct a matrix with the same size as the heatmap matrix F. All elements are initialized to 0; during each iteration... The origin of the coordinate system is the grid where the center of the interest point m is located. All other grids have undergone a translation operation compared to the grids in F. The translation operation is as follows: in each level, the horizontal and vertical translations required to translate from the element at the top left corner (0,0) of the matrix to the grid where the center of the interest point m is located.

[0049] Calculate one by one according to the Gaussian distribution formula. The values ​​of each element in the set are calculated, and the result is displayed. The values ​​of the matrix are accumulated one-to-one into the heatmap matrix F;

[0050] S203: For the detection azimuth, define D azimuths, with indices d = 1, 2, ..., D; the angular range of each azimuth is... In the analysis of the coverage requirements for the detection azimuth, the element values ​​of the boundary column of the heat map matrix F corresponding to the detection azimuth are assigned the average value of all element values ​​of the matrix.

[0051] S204: Set different weights for different elevation levels.

[0052] Furthermore, the multiple coverage and tiered coverage simulation module specifically executes the following process:

[0053] S301: Based on different detection directions, generate multiple sets of virtual points of interest, move them from the actual points of interest to the detection directions respectively, calculate the coverage requirement value near the virtual points of interest using the Gaussian distribution in step 2, and sum it with the coverage requirement value generated by the actual points of interest, so as to achieve multiple coverage of the points of interest and tiered coverage to cope with the detection directions.

[0054] Based on the above calculations, the actual coverage requirement for generating the m-th point of interest is:

[0055]

[0056] Among them, F (m) This represents the total coverage requirement for the m-th point of interest. This represents the coverage requirement value generated by the actual points of interest; This represents the coverage requirement value generated by the i-th virtual point of interest; n represents the number of detection directions.

[0057] S302: Perform environmental zoning measurement, considering the detection orientation and coverage requirements of each point of interest, divide the environmental area into U regions according to each orientation, and assign weights to the u-th region from farthest to nearest as follows: Where α max and α min Select 1 as the symmetrical value and ensure that the difference between the two does not exceed the set value;

[0058] The regional weights are multiplied by the value of each element in the heatmap matrix, and the combined effect of multiple directions yields the final element values ​​of the heatmap matrix. If a grid in the heatmap matrix is ​​located in multiple partitions at the same time, its regional weight is the maximum value among the multiple partitions.

[0059] The heatmap extraction module works as follows: Based on the heatmap matrix F mentioned above, a series of discrete points are selected at equal intervals, called pooling nodes; the pooling nodes are downsampled, and the element values ​​of all grids within a certain range of their grid positions are aggregated to extract a heatmap that covers the required area.

[0060] Beneficial effects:

[0061] This invention presents a digital method and system for constructing 3D coverage demand heatmaps, enabling the generation of digitized coverage demand heatmaps for real-world 3D scenarios. The method first discretizes the 3D space into layers; second, it quantizes the heatmap grid values ​​based on hierarchical weights of points of interest, detector orientation, and elevation; third, it introduces the concepts of virtual points of interest and environmental partitioning to achieve multiple coverage of points of interest and tiered coverage based on detector orientation; finally, it introduces pooling nodes to extract a relatively low-resolution coverage demand heatmap, achieving a trade-off between computational performance and computational cost. This method allows decision-makers to intuitively grasp the coverage demand situation and provides numerical input for downstream optimization decisions, benefiting many practical problems such as sensor network deployment. Attached Figure Description

[0062] Figure 1 A flowchart of the digital method for constructing a three-dimensional coverage requirement heatmap provided by the present invention.

[0063] Figure 2 A schematic diagram of the virtual point of interest generation method provided by the present invention.

[0064] Figure 3 This is a schematic diagram of the environmental zoning measurement method provided by the present invention. Detailed Implementation

[0065] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0066] Example 1:

[0067] This invention provides a digital method for constructing a three-dimensional heat map of coverage demand. This method can generate a digital heat map of coverage demand for real-world three-dimensional scenarios, which can not only help decision-makers intuitively grasp the coverage demand situation, but also provide numerical input for downstream optimization decision-making methods.

[0068] Step 1: Discretize the 3D space into layers. For the 3D environment, divide the space into multiple layers based on elevation, and then mesh each layer.

[0069] 1. For a three-dimensional environment, the space is divided into K levels based on elevation, with indices k = 1, 2, ..., K. The value of K can be set according to the decision-maker's needs; setting it to 3 corresponds to low, medium, and high altitudes.

[0070] 2. Divide each level into a grid, with each grid size being I×J and indices i = 1, 2, ..., I; j = 1, 2, ..., J. Construct a heatmap matrix F = (f... ijk ) I×J×K , where f ijk This represents the coverage requirement value for each element in the heatmap matrix, all of which are initialized to 0.

[0071] Step 2: Quantize grid values ​​based on the weights of points of interest, detection orientation, and elevation levels;

[0072] 1. To address the coverage requirements of points of interest (POIs), considering that the coverage requirement value should decrease as the distance from the center of the POI increases, a joint Gaussian-like distribution is designed to characterize the coverage requirement value. The Gaussian-like distribution is described by the following formula:

[0073]

[0074]

[0075] Where d is used to calculate the distance based on the L2 norm; σ represents the two-dimensional coordinates of the grid points, specifically the coordinates of each grid point with the center of the grid point containing the point of interest as the origin; σ is a settable parameter used to adjust the shape of the Gaussian-like distribution. The σ values ​​for the three points of interest are set to 3, 5, and 8, respectively.

[0076] 2. Traverse each level k, traverse the set of interest points M with indices m = 1, 2, ..., M, and construct a matrix with the same size as the heatmap matrix F. All elements are initialized to 0. In each traversal, the origin of F' is the grid containing the center of the interest point m, and all other grids are translated relative to the grids in F. The specific translation operation is defined as the horizontal and vertical translations required to move the element at the top-left corner (0,0) of the matrix to the grid containing the center of the interest point m at each level. This is calculated using the Gaussian distribution formula. The values ​​of each element in the set are calculated, and the result is displayed. The values ​​of the matrix are accumulated one-to-one into the heatmap matrix F;

[0077] 3. Regarding the detection orientation, eight main orientations are defined, with D = 8. Each orientation has an angle range of 45°, specifically "West," "Southwest," and "South." In the analysis of coverage requirements for the detection orientations, the element values ​​in the column corresponding to the boundary of the heatmap matrix F are assigned larger values, specifically the average of all element values ​​in the matrix. This approach helps to more accurately characterize the detection orientations of concern to decision-makers within the environment, thereby strengthening the monitoring and understanding of the environmental periphery.

[0078] 4. Different weights can be assigned to different elevation levels, ranging from 0 to 1, reflecting the decision-maker's emphasis on different elevations. For example, to better detect and cover high-altitude targets, the weight of the corresponding high-altitude level can usually be set to be larger. The weights for low, medium, and high altitudes are set to 0.3, 0.3, and 0.5, respectively.

[0079] Step 3: To further simulate multiple coverage and tiered coverage, generate multiple sets of virtual points of interest and perform environmental zoning measurement;

[0080] 1. Based on different detection directions, multiple sets of virtual points of interest are generated, and these virtual points of interest move from their actual locations toward the detection direction, such as... Figure 2 As shown. Figure 2In the context of the environment, a square represents the location of the actual point of interest (POI). To address the three detection directions of "West," "Southwest," and "South," three virtual POIs are generated by moving from their actual locations towards the detection directions, forming pentagonal shapes. The coverage requirement value near these virtual POIs is calculated using a Gaussian-like distribution as described in step 2, and then summed with the coverage requirement value generated from the actual POIs. This achieves multiple coverage of the POIs and tiered coverage for the detection directions. Based on the above calculations, the actual coverage requirement value generated for the m-th POI is:

[0081]

[0082] Among them, F (m) This represents the total coverage requirement for the m-th point of interest. This represents the coverage requirement value generated by the actual points of interest; represents the coverage requirement value generated by the i-th virtual point of interest; n represents the number of detection directions.

[0083] 2. Perform environmental zoning measurement, considering the detection orientation and coverage requirements of each point of interest, divide the environmental area into U regions according to each orientation, and assign weights to the u-th region from farthest to nearest as follows: Where α max and α min We choose a value symmetrical to 1, and the difference should not be too large. Here, we choose U as 3, and α... max and α min The values ​​are 1.2 and 0.8 respectively. The region weight is multiplied by each element value in the heatmap matrix; the combined effect of multiple orientations yields the final heatmap matrix element values. If a grid in the heatmap matrix falls within multiple partitions, its region weight is the maximum value among those partitions.

[0084] Step 4: If computational cost is limited, a pooling node is introduced to extract a relatively low-resolution heatmap of coverage demand, achieving a trade-off between computational performance and computational cost. If computational cost is sufficient, pooling nodes may not be introduced. If computational cost is limited, a series of discrete points, called pooling nodes, are selected at equal intervals based on the heatmap matrix F calculated in the above steps. The pooling nodes perform downsampling, aggregating the element values ​​of all grids within a certain range of their grid location to extract a relatively low-resolution heatmap of coverage demand.

[0085] Step 5: Display the 3D coverage demand heatmap based on the calculated values ​​and input it into the downstream optimization decision-making task.

[0086] Based on the current heatmap matrix F = (f ijk ) I×J×KA 3D heatmap of coverage requirements is generated. The heatmap primarily uses red and blue colors, with a gradual transition between the two colors to represent changes in the element values ​​of the heatmap matrix. Large element values ​​are represented in red, and small element values ​​are represented in blue.

[0087] Example 2:

[0088] Another embodiment of the present invention provides a digital system for constructing a three-dimensional heat map of coverage requirements, including a hierarchical discretization module, a grid value quantization module, a multi-coverage and tiered coverage simulation module, a heat map extraction module, and a heat map display module.

[0089] The hierarchical discretization module is used to divide the space into multiple layers on the elevation for a three-dimensional environment, and to perform meshing on each layer to achieve hierarchical discretization of the three-dimensional environment space.

[0090] The grid value quantization module is used to quantize grid values ​​based on the weights of interest points, detection orientation, and elevation levels.

[0091] The multi-coverage and tiered coverage simulation module is used to further simulate multi-coverage and tiered coverage, generate multiple sets of virtual points of interest, and perform environmental zoning measurement.

[0092] The heatmap extraction module is used to import pooled nodes to extract a heatmap that covers the required area.

[0093] The heatmap display module is used to display a three-dimensional coverage requirement heatmap based on the calculated values ​​and input it into the downstream optimization decision-making task.

[0094] The hierarchical discretization module performs the following process:

[0095] For a three-dimensional environment, the space is divided into K levels in terms of elevation, with indices k = 1, 2, ..., K. The value of K is set as needed, and is set to 3, which corresponds to low, medium and high altitudes.

[0096] Each level is divided into grids, with a total number of grids of I×J in each level, and indices i = 1, 2, ..., I; j = 1, 2, ..., J; a heatmap matrix F = (f ijk ) I×J×K The total number of elements in this heatmap matrix is ​​the same as the total number of all grid cells, where f ijk This represents the coverage requirement value for each element in the heatmap matrix, all of which are initialized to 0.

[0097] The grid value quantization module performs the following steps:

[0098] S201: To address the coverage requirements of points of interest, a joint Gaussian-like distribution is designed to characterize the coverage requirement values. The Gaussian-like distribution is described by the following formula:

[0099]

[0100]

[0101] Where d is the distance calculated based on the L2 norm; σ represents the two-dimensional coordinates of the grid points, specifically the coordinates of each grid point with the center of the grid point where the point of interest is located as the origin; σ is a settable parameter used to adjust the shape of the Gaussian-like distribution.

[0102] S202: Traverse each level k, traverse the set of interest points M with indices m = 1, 2, ..., M, and construct a matrix with the same size as the heatmap matrix F. All elements are initialized to 0; during each iteration... The origin of the coordinate system is the grid where the center of the interest point m is located. All other grids have undergone a translation operation compared to the grids in F. The translation operation is as follows: in each level, the horizontal and vertical translations required to translate from the element at the top left corner (0,0) of the matrix to the grid where the center of the interest point m is located.

[0103] Calculate according to the Gaussian distribution formula. The values ​​of each element in the set are calculated, and the result is displayed. The values ​​of the matrix are accumulated one-to-one into the heatmap matrix F;

[0104] S203: For the detection azimuth, define D azimuths, with indices d = 1, 2, ..., D; the angular range of each azimuth is... In the analysis of the coverage requirements for the detection azimuth, the element values ​​of the boundary column of the heat map matrix F corresponding to the detection azimuth are assigned the average value of all element values ​​of the matrix.

[0105] S204: Set different weights for different elevation levels.

[0106] The multi-coverage and tiered coverage simulation module executes the following process:

[0107] S301: Based on different detection directions, generate multiple sets of virtual points of interest, move them from the actual points of interest to the detection directions respectively, calculate the coverage requirement value near the virtual points of interest using the Gaussian distribution in step 2, and sum it with the coverage requirement value generated by the actual points of interest, so as to achieve multiple coverage of the points of interest and tiered coverage to cope with the detection directions.

[0108] Based on the above calculations, the actual coverage requirement for generating the m-th point of interest is:

[0109]

[0110] Among them, F (m) This represents the total coverage requirement for the m-th point of interest. This represents the coverage requirement value generated by the actual points of interest; This represents the coverage requirement value generated by the i-th virtual point of interest; n represents the number of detection directions.

[0111] S302: Perform environmental zoning measurement, considering the detection orientation and coverage requirements of each point of interest, divide the environmental area into U regions according to each orientation, and assign weights to the u-th region from farthest to nearest as follows: Where α max and α min Select 1 as the symmetrical value and ensure that the difference between the two does not exceed the set value;

[0112] The regional weights are multiplied by the value of each element in the heatmap matrix, and the combined effect of multiple directions yields the final element values ​​of the heatmap matrix. If a grid in the heatmap matrix is ​​located in multiple partitions at the same time, its regional weight is the maximum value among the multiple partitions.

[0113] The heatmap extraction module works as follows: Based on the heatmap matrix F mentioned above, a series of discrete points are selected at equal intervals, called pooling nodes; the pooling nodes are downsampled, and the element values ​​of all grids within a certain range of their grid positions are aggregated to extract a heatmap that covers the required area.

[0114] In summary, the above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A digital method for constructing a three-dimensional heat map of coverage demand, characterized in that, Includes the following steps: Step 1: For the three-dimensional environment, the space is divided into multiple levels on the elevation, and each level is meshed to achieve the layered discretization of the three-dimensional environment space. Step 2: Quantize grid values ​​based on the weights of points of interest, detection orientation, and elevation levels; Step 3: To further simulate multiple coverage and tiered coverage, multiple sets of virtual points of interest are generated and environmental zoning measurements are performed; specifically, Step 3 involves: S301: Based on different detection directions, generate multiple sets of virtual points of interest, move them from the actual points of interest to the detection directions respectively, calculate the coverage requirement value near the virtual points of interest using the Gaussian distribution in step 2, and sum it with the coverage requirement value generated by the actual points of interest, so as to achieve multiple coverage of the points of interest and tiered coverage to cope with the detection directions. Based on the above calculations, the first The actual coverage requirement value generated by each point of interest is: in, Indicates the first Total coverage requirement for each point of interest; This represents the coverage requirement value generated by the actual points of interest; Indicates the first Coverage requirement value generated by virtual points of interest; Indicates the number of detection azimuths; S302: Perform environmental zoning measurement, considering the detection orientation and coverage requirements of each point of interest, and divide the environmental area into zones according to each orientation. The first area, from farthest to nearest The weights of each region are respectively ,in and Select 1 as the symmetrical value and ensure that the difference between the two does not exceed the set value; The regional weights are multiplied by the value of each element in the heatmap matrix, and the combined effect of multiple directions yields the final element values ​​of the heatmap matrix. If a grid in the heatmap matrix is ​​located in multiple partitions at the same time, its regional weight is the maximum value among the multiple partitions. Step 4: Extract a heatmap of coverage requirements by introducing pooled nodes; Step 5: Display a 3D coverage requirement heatmap based on the calculated values ​​and input it into the downstream optimization decision-making task to determine the sensor network deployment.

2. The digital method for constructing a three-dimensional coverage demand heatmap as described in claim 1, characterized in that, Step one: For a three-dimensional environment, the space is divided into multiple levels based on elevation, and each level is meshed to achieve layered discretization of the three-dimensional environment space; specifically: S101: For a three-dimensional environment, space is divided into elevation sections. Each level, indexed as , The value is set as needed, and is set to 3, which corresponds to low, medium, and high altitudes; S102: Mesh each level, resulting in a total number of meshes for each level. The index is Constructing a heatmap matrix The total number of elements in this heatmap matrix is ​​the same as the total number of all grid cells, where This represents the coverage requirement value for each element in the heatmap matrix, all of which are initialized to 0.

3. The digital method for constructing a three-dimensional coverage demand heatmap as described in claim 1, characterized in that, Step two: Quantizing grid values ​​based on the weights of interest points, detection azimuth, and elevation levels, specifically includes the following steps: S201: To address the coverage requirements of points of interest, a joint Gaussian-like distribution is designed to characterize the coverage requirement values. The Gaussian-like distribution is described by the following formula: in, To calculate distance based on the L2 norm; These are the two-dimensional coordinates of the grid points, specifically the coordinates of each grid point with the center of the grid point where the point of interest is located as the origin. These are configurable parameters used to adjust the shape of the Gaussian-like distribution; S202: Traverse all levels Traverse the set of points of interest The index is Construction and heatmap matrix Matrix of the same size , All elements are initialized to 0; during each iteration... The origin of the coordinate system is the point of interest. The grid where the center is located, and the other grids relative to it. The grid in the image was translated once. Calculate according to the Gaussian distribution formula. The values ​​of each element in the set are calculated, and the result is displayed. ~ The values ​​of the matrix are accumulated one-to-one into the heatmap matrix. middle; S203: Delineate the detection azimuth. Location, index is The angular range for each direction is: In the analysis of coverage requirements for the detection azimuth, the heat map matrix will be used. The element values ​​of the boundary column corresponding to the detection azimuth are assigned the average value of all element values ​​in the matrix; S204: Set different weights for different elevation levels.

4. The digital method for constructing a three-dimensional coverage demand heatmap as described in claim 3, characterized in that, In S202, the translation operation specifically involves: in each level, shifting the matrix from its top left corner... Translate the element to the point of interest The required horizontal and vertical translations of the grid where the center is located.

5. The digital method for constructing a three-dimensional coverage demand heatmap as described in claim 1, characterized in that, Step four involves introducing pooling nodes to extract a heatmap of coverage requirements, achieving a trade-off between computational performance and computational cost; specifically: The heatmap matrix calculated in the above steps Based on this, a series of discrete points are selected at equal intervals, called pooling nodes; the pooling nodes are downsampled, and the element values ​​of all grids within a certain range of their grid locations are aggregated to extract a heat map of the coverage requirements.

6. A digital system for constructing a three-dimensional heat map of coverage demand, characterized in that, It includes a hierarchical discretization module, a grid value quantization module, a multi-coverage and tiered coverage simulation module, a heat map extraction module, and a heat map display module; The hierarchical discretization module is used to divide the space into multiple levels on the elevation for a three-dimensional environment, and to perform grid division on each level to achieve hierarchical discretization of the three-dimensional environment space. The grid value quantization module is used to quantize grid values ​​based on the weights of interest points, detection orientation, and elevation levels. The multi-coverage and tiered coverage simulation module is used to further simulate multi-coverage and tiered coverage, generate multiple sets of virtual points of interest, and perform environmental zoning measurement. The heatmap extraction module is used to introduce pooling nodes to extract a heatmap that covers the required area. The heat map display module is used to display a three-dimensional coverage requirement heat map based on the calculated values ​​and input it into the downstream optimization decision-making task.

7. A digital system for constructing a three-dimensional coverage demand heatmap as described in claim 6, characterized in that, The hierarchical discretization module specifically performs the following process: In a three-dimensional environment, space is divided into elevation sections. Each level, indexed as , The value is set as needed, and is set to 3, which corresponds to low, medium, and high altitudes; Each level is divided into grids, and the total number of grids in each level is... The index is Constructing a heatmap matrix The total number of elements in this heatmap matrix is ​​the same as the total number of all grid cells, where This represents the coverage requirement value for each element in the heatmap matrix, all of which are initialized to 0.

8. A digital system for constructing a three-dimensional coverage demand heat map as described in claim 6, characterized in that, The grid value quantization module performs the following specific actions: S201: To address the coverage requirements of points of interest, a joint Gaussian-like distribution is designed to characterize the coverage requirement values. The Gaussian-like distribution is described by the following formula: in, To calculate distance based on the L2 norm; These are the two-dimensional coordinates of the grid points, specifically the coordinates of each grid point with the center of the grid point where the point of interest is located as the origin. These are settable parameters used to adjust the shape of the Gaussian-like distribution; S202: Traverse all levels Traverse the set of points of interest The index is Construction and heatmap matrix Matrix of the same size , All elements are initialized to 0; during each iteration... The origin of the coordinate system is the point of interest. The grid where the center is located, and the other grids relative to it. Each grid in the matrix underwent a translation operation; the translation operation specifically involved shifting the matrix from its top left corner within each level. Translate the element to the point of interest The required horizontal and vertical translations of the grid containing the center; Calculate one by one according to the Gaussian distribution formula. The values ​​of each element in the set are calculated, and the result is displayed. ~ The values ​​of the matrix are accumulated one-to-one into the heatmap matrix. middle; S203: Delineate the detection azimuth. Location, index is The angular range for each direction is: In the analysis of coverage requirements for the detection azimuth, the heat map matrix will be used. The element values ​​of the boundary column corresponding to the detection azimuth are assigned the average value of all elements in the matrix. S204: Set different weights for different elevation levels.

9. A digital system for constructing a three-dimensional coverage demand heatmap as described in claim 6, characterized in that, The aforementioned multi-coverage and tiered coverage simulation module specifically executes the following process: S301: Based on different detection directions, generate multiple sets of virtual points of interest, move them from the actual points of interest to the detection directions respectively, calculate the coverage requirement value near the virtual points of interest using the Gaussian distribution in step 2, and sum it with the coverage requirement value generated by the actual points of interest, so as to achieve multiple coverage of the points of interest and tiered coverage to cope with the detection directions. Based on the above calculations, the first The actual coverage requirement value generated for each point of interest is: in, Indicates the first Total coverage requirement for each point of interest; This represents the coverage requirement value generated by the actual points of interest; Indicates the first Coverage requirement value generated by virtual points of interest; Indicates the number of detection azimuths; S302: Perform environmental zoning measurement, considering the detection orientation and coverage requirements of each point of interest, and divide the environmental area into zones according to each orientation. The first area, from farthest to nearest The weights of each region are respectively ,in and Select 1 as the symmetrical value and ensure that the difference between the two does not exceed the set value; The regional weights are multiplied by the value of each element in the heatmap matrix, and the combined effect of multiple directions yields the final element values ​​of the heatmap matrix. If a grid in the heatmap matrix is ​​located in multiple partitions at the same time, its regional weight is the maximum value among the multiple partitions. The heatmap extraction module specifically involves: extracting data from the aforementioned heatmap matrix. Based on this, a series of discrete points are selected at equal intervals, called pooling nodes; the pooling nodes are downsampled, and the element values ​​of all grids within a certain range of their grid locations are aggregated to extract a heat map of the coverage requirements.

Images