Low-altitude networking method, device, equipment, storage medium and program product

Abstract

The application relates to the technical field of low-altitude networking, and provides a low-altitude networking method, device, equipment, storage medium and program product, the method comprises the following steps: determining a candidate station set according to a multi-dimensional data set of a low-altitude area to be planned; the multi-dimensional data set comprises base station parameter data and a route of the low-altitude area; constructing an evaluation area of each candidate base station according to the candidate station set, determining a preferred object set of the candidate base station according to the evaluation area; extracting the spatial features of each preferred object in the preferred object set, identifying a backbone station according to the spatial features; and networking the low-altitude area based on the backbone station. Through the quantitative data and computational geometry of the low-altitude area, combined with the spatial features of the base station, the backbone station can be efficiently and accurately identified, the networking of the low-altitude area is realized, and the networking efficiency of the low-altitude private network is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of low-altitude networking, and in particular to a low-altitude networking method, device, equipment, storage medium and program product. BACKGROUND

[0002] With the development of the low-altitude field, the requirements for low-altitude communication and sensing capabilities are gradually increasing, but the low-altitude airspace is a brand-new signal coverage scenario, which faces problems of high networking cost, high low-altitude overlapping coverage and strong interference. The backbone site refers to a site with a wide coverage range and good quality, which can play a supporting role in the network. When low-altitude private network networking is performed, sites with high antenna hanging height (high tower sites or sites on high buildings) and less air blocking are used as the backbone sites of low-altitude private network networking to provide wide airspace coverage. In order to guarantee the coverage to the ground, after these sites perform low-altitude coverage, other sites in the coverage range can supplement the coverage areas of these sites, and the influence on the ground coverage is controlled within a threshold.

[0003] On the one hand, in terms of air coverage, the high sites can cover a large airspace due to high antenna height and less blocking, and the air coverage capability of other low sites is weak, which reduces the overlap and interference of the airspace; on the other hand, in terms of ground coverage, due to the dense ground base stations, the high sites provide coverage to the ground while also bringing high overlapping coverage and co-frequency interference, and using the high sites for air coverage can also reduce the interference to the ground.

[0004] Currently, the selection of the backbone sites for low-altitude networking mainly relies on expert experience for manual judgment based on antenna hanging height, the expert experience is affected by individual cognitive differences, subjective bias exists, there is a lack of unified quantitative standard, and the site selection is inconsistent; when the site scale is large, the time consumption of manual screening increases exponentially, and therefore, there are problems of low efficiency and accuracy. SUMMARY

[0005] The present application provides a low-altitude networking method, device, equipment, storage medium and program product, to solve the defects of low-altitude networking relying on expert experience for manual selection of backbone sites in the prior art, and to realize accurate and efficient identification of the backbone sites.

[0006] The present application provides a low-altitude networking method, comprising:

[0007] determining a candidate site set according to a multi-dimensional data set of a low-altitude area to be planned; the multi-dimensional data set comprises base station parameter data and a route of the low-altitude area;

[0008] constructing an evaluation area of each candidate base station according to the candidate site set, and determining a preferred object set of the candidate base station according to the evaluation area;

[0009] extract spatial features of each preferred object in the preferred object set, and identify backbone sites according to the spatial features;

[0010] network the low-altitude area based on the backbone sites.

[0011] In one embodiment, the constructing of the evaluation area of each candidate base station according to the candidate site set comprises:

[0012] determining a coverage distance of the candidate base station according to base station parameter data of each candidate base station in the candidate site set;

[0013] generating a circular coverage ring with the candidate base station as the center and the coverage distance as the radius;

[0014] constructing a triangular mesh corresponding to the candidate base station by using a triangulation algorithm with each candidate base station in the circular coverage ring as a node;

[0015] determining adjacent base stations of the candidate base station based on the adjacency relationship of the triangular mesh;

[0016] generating sectors according to the base station density of the adjacent base stations, screening out key base stations in each sector as boundary points, and constructing the evaluation area of the candidate base station.

[0017] In one embodiment, the base station parameter data comprises a coverage scenario; and the identifying of the backbone sites according to the spatial features comprises:

[0018] obtaining a site identification model corresponding to the coverage scenario of each candidate base station in the candidate site set;

[0019] inputting the spatial features into the site identification model, classifying each candidate base station, and obtaining a candidate set of backbone sites;

[0020] iteratively optimizing the candidate set to obtain the backbone sites.

[0021] In one embodiment, the multi-dimensional data further comprises measurement report data; and the iteratively optimizing the candidate set to obtain the backbone sites comprises:

[0022] based on each candidate backbone site in the candidate set, performing flight tests on the low-altitude area according to the flight route, and determining whether there is a coverage hole in the low-altitude area;

[0023] if there is a coverage hole and the coverage hole is within the coverage range of the candidate backbone site, obtaining a suboptimal base station of the candidate backbone site as a backbone site to optimize the candidate set;

[0024] After removing the sampling points of each backbone station in the candidate set from the measurement report data, evaluating the ground coverage of each base station;

[0025] According to the ground coverage, marking the backbone base stations affecting the ground coverage;

[0026] According to the candidate set, updating the candidate station set, returning and performing the step of constructing the evaluation area of each candidate base station according to the candidate station set until there is no coverage hole in the low-altitude area, and obtaining each backbone station in the candidate set.

[0027] In one embodiment, before the step of obtaining the station identification model corresponding to the coverage scenario of each candidate base station in the candidate station set, the method further comprises:

[0028] Obtaining an original data set; the original data set includes the antenna hanging height of a sample base station, a coverage scenario and height information of a geographic object;

[0029] Based on the distance between the geographic object and the receiving point of the sample base station and the height information, a space influence factor is constructed;

[0030] Comparing the height information and the antenna hanging height, and generating a label of the space influence factor according to the comparison result;

[0031] Based on the label and the space influence factor, a sample data set is constructed, and the sample data set is divided according to the coverage scenario to obtain a sample data subset;

[0032] Each of the sample data set subsets is used to iteratively train a preset support vector machine model to obtain a station identification model corresponding to each coverage scenario.

[0033] In one embodiment, the base station operating parameter data includes a base station position; and the candidate station set is determined according to the multi-dimensional data set of the low-altitude area to be planned, comprising:

[0034] A plurality of buffer zones are established on both sides of the flight path of the low-altitude area to be planned with a preset width;

[0035] The plurality of buffer zones are de-duplicated and merged to obtain a base station selection area;

[0036] According to the base station position of each base station in the base station operating parameter data, each candidate base station in the base station selection area is obtained to obtain a candidate station set.

[0037] The application also provides a low-altitude networking device, comprising the following modules:

[0038] The base station selection module is configured to determine a candidate station set according to a multi-dimensional data set of the low-altitude area to be planned, wherein the multi-dimensional data set comprises base station parameter data and a flight route of the low-altitude area.

[0039] The area construction module is configured to construct an evaluation area of each candidate base station according to the candidate station set, and determine a preferred object set of the candidate base station according to the evaluation area.

[0040] The station identification module is configured to extract spatial features of each preferred object in the preferred object set, and identify a backbone station according to the spatial features.

[0041] The low-altitude networking module is configured to network the low-altitude area based on the backbone station.

[0042] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the low-altitude networking method according to any one of the above when executing the computer program.

[0043] The application further provides a non-transitory computer-readable storage medium, which stores a computer program executable by a processor to implement the low-altitude networking method according to any one of the above.

[0044] The application further provides a computer program product, which includes a computer program executable by a processor to implement the low-altitude networking method according to any one of the above.

[0045] The low-altitude networking method, device, equipment, storage medium, and program product provided by the application determine candidate base stations through a multi-dimensional data set of a low-altitude area, construct evaluation areas of the candidate base stations through computational geometry, extract spatial features of preferred objects in the evaluation areas, identify a backbone station according to the spatial features of the preferred objects, and network the low-altitude area. Through quantitative data of the low-altitude area and computational geometry, combined with spatial features of base stations, the backbone station can be efficiently and accurately identified, the low-altitude area is networked, and the networking efficiency of the low-altitude private network is improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0047] Figure 1 is a flowchart of the low-altitude networking method provided by the embodiments of the application.

[0048] Figure 2 is a structural schematic diagram of a low-altitude networking device provided by the present application.

[0049] Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0051] An embodiment of the present application provides a low-altitude networking method, which can accurately and efficiently identify backbone sites in multiple scenarios through a dynamic decision mode of space-propagation-topology, and realize networking of a low-altitude airspace. Specifically, Figure 1 is a flowchart of a low-altitude networking method provided by an embodiment of the present application, as shown in Figure 1 the low-altitude networking method comprises the following steps:

[0052] Step 100, determining a candidate site set according to a multi-dimensional data set of a low-altitude region to be planned; the multi-dimensional data set comprises base station operating parameter data and a flight route of the low-altitude region;

[0053] Step 200, constructing an evaluation region of each candidate base station according to the candidate site set, and determining a preferred object set of the candidate base station according to the evaluation region;

[0054] Step 300, extracting a space feature of each preferred object in the preferred object set, and identifying a backbone site according to the space feature;

[0055] Step 400, networking the low-altitude region based on the backbone site.

[0056] According to a multi-dimensional data set of a low-altitude region to be planned, a candidate site set is determined, wherein the multi-dimensional data set comprises operating parameter data of each base station and a flight route of low-altitude region planning. Optionally, the operating parameter data of the base station specifically comprises a base station name, a base station identifier (base station ID), a longitude and latitude (base station position), a coverage type, an antenna hanging height, an antenna direction angle, a scene type of a coverage scene, a transmission power and a minimum access level, etc. Further, the coverage scene comprises multiple scenes such as low-altitude + urban cruise, low-altitude + firefighting and low-altitude + agriculture.

[0057] Optionally, one or more candidate base stations are determined by base station parameter data judgment to obtain a candidate site set. In an embodiment, the positions of the base stations are determined according to the base station parameters in the multidimensional data set, and one or more candidate base stations are determined as candidate sites according to the positions of the base stations to obtain the candidate site set.

[0058] An evaluation area of each candidate base station is constructed according to the determined candidate site set. Optionally, the evaluation area of each candidate base station in the candidate site set is constructed by means of calculation geometry, and the preferred object set of the candidate base station is determined according to the evaluation area. For any candidate base station in the candidate site set, the purpose of constructing the evaluation area is to determine a maximum reasonable coverage area of each base station under the existing network base station layout, which is the preferred range for comparison between the base station and other objects, and is also the range for evaluation of the influence of the base station on the ground coverage. The actual coverage of the base station is affected by factors such as parameter configuration and surrounding environment, and can be greater or less than the area.

[0059] Optionally, the multidimensional data set further includes feature information and distribution of geographic objects, including buildings and other structures, and the feature information of the geographic objects includes object position, object shape contour, object type, object name and object height. The distribution of the geographic objects is determined according to the object positions of the geographic objects, and the preferred object set of the candidate base station is composed of other base stations and geographic objects in the evaluation area.

[0060] The spatial features of each preferred object in the preferred object set are extracted, the preferred objects including base stations and geographic objects, and the spatial features of the preferred objects including height features. For the geographic objects in the preferred objects, the height features are determined according to the heights of the geographic objects, and for the base stations in the preferred objects, the height features are determined according to the antenna hanging height.

[0061] Optionally, the extracted spatial features of the preferred objects can further include the relative distances between different preferred objects. According to the extracted spatial features of the preferred objects, the backbone sites are identified. In an embodiment, the backbone sites are determined according to the antenna hanging height of each candidate base station in the preferred objects, combined with the heights of the geographic objects around the candidate base stations. Illustratively, the higher the antenna hanging height of the candidate base station, the lower the geographic objects around the candidate base station or the farther the distance between the candidate base station and the geographic objects, the greater the possibility of being a backbone site.

[0062] Further, the identified backbone sites include one or more, and the low-altitude area is networked based on the identified backbone sites to realize the airspace coverage of the low-altitude area.

[0063] In the embodiment, the candidate base stations are determined through the multi-dimensional data set of the low-altitude area, the evaluation area of the candidate base stations is constructed through computational geometry, the spatial features of the preferred objects in the evaluation area are extracted, the backbone sites are identified according to the spatial features of the preferred objects, and the networking of the low-altitude area is implemented. Through the quantitative data of the low-altitude area and the computational geometry, combined with the spatial features of the base stations, the backbone sites can be efficiently and accurately identified, the networking of the low-altitude area is implemented, and the networking efficiency of the low-altitude private network is improved.

[0064] In one embodiment, the base station parameter data in the multi-dimensional data set of the low-altitude area includes the base station position, and in step 100, the candidate site set is determined according to the multi-dimensional data set of the low-altitude area to be planned, including:

[0065] Step 101, a plurality of buffer zones are established on both sides of the flight line of the low-altitude area to be planned with a preset width;

[0066] Step 102, the plurality of buffer zones are de-duplicated and merged to obtain a base station selection area;

[0067] Step 103, according to the base station position of each base station in the base station parameter data, each candidate base station in the base station selection area is obtained to obtain the candidate site set.

[0068] Based on the flight line of the low-altitude area planning, a plurality of buffer zones are established on both sides of the flight line with a preset width D, the plurality of buffer zones may have overlapping areas, the plurality of buffer zones are de-duplicated and merged to obtain a base station selection area, and the base stations in the base station selection area are obtained as candidate base stations according to the positions of the base stations in the base station parameter data to obtain the candidate site set.

[0069] Optionally, the base station selection area can be a polygonal area, and the buffer zones are combined to remove the overlapping parts to synthesize a single polygonal area, which is the base station selection area.

[0070] Optionally, in step 200, the evaluation area of each candidate base station in the candidate site set is constructed through computational geometry, including:

[0071] Step 201, according to the base station parameter data of each candidate base station in the candidate site set, the coverage distance of the candidate base station is determined;

[0072] Step 202, a circular coverage circle is generated with the candidate base station as the center and the coverage distance as the radius;

[0073] Step 203, each candidate base station in the circular coverage circle is taken as a node, and a triangular mesh corresponding to the candidate base station is constructed by using a triangulation algorithm;

[0074] Step 204, based on the adjacency relationship of the triangular mesh, the adjacent base stations of the candidate base station are determined.

[0075] Step 205, generating sectors according to the base station density of the adjacent base station, screening out the key base stations in each sector as the boundary points, and constructing the evaluation area of the candidate base station.

[0076] According to the working parameter data of each candidate base station in the candidate site set, the coverage distance of the candidate base station is determined. In an embodiment, the coverage distance of the propagation model of the candidate base station is calculated according to the maximum access path loss of the candidate base station through the 3GPP channel model and the like. Among them, according to the coverage scenario in the working parameter data of the candidate base station, a suitable wireless propagation model is selected, such as the 3GPP channel model, to calculate the coverage distance of the propagation model of the candidate base station. In the 3GPP channel model, the path loss is the distance from the terminal to the base station and the sector frequency parameter. In this embodiment, the distance from the terminal to the base station corresponding to the maximum access path loss is the coverage distance of the candidate base station.

[0077] For any candidate base station B, a circle center coverage circle M is generated with the base station B as the center and the coverage distance of the base station B as the radius. Further, all candidate base stations within the circle center coverage circle M are taken as nodes, and a triangular mesh corresponding to the candidate base station is constructed by using a triangulation algorithm.

[0078] In an embodiment, all candidate base stations within a predetermined distance range around the base station B are taken as nodes, and all nodes are set as a vertex set V={v0, v1,..., v n}, wherein v0 is the base station B, n represents the number of nodes, and the predetermined distance range is, for example, less than or equal to the coverage distance Des x 1.5 of the base station B.

[0079] Further, a triangular mesh is constructed by using a triangulation algorithm, such as the Bowyer-Watson algorithm. The constructed triangular mesh is a Delaunay triangular mesh, which satisfies the empty circle characteristic, that is, the circumcircle of any triangle does not contain other vertices. A constraint condition is added: deleting the triangular edges with a length exceeding the coverage distance Des of the propagation model, to ensure that the network topology conforms to the actual coverage capability.

[0080] Based on the adjacency relationship of the triangular mesh, the adjacent base station of the candidate base station is determined, sectors are dynamically generated according to the base station density of the adjacent base station, key base stations within the sectors are screened out as boundary points, the screened boundary points are mapped, and the evaluation area of the candidate base station is constructed.

[0081] In an embodiment, an adjacency matrix is established through the adjacency relationship of the triangular mesh, adjacency_matrix[i][j]=1, v i and v jThere is a Delaunay edge connection; extract the direct adjacent base station set N = {n1, n2,..., n k} of base station B, wherein k≥3.

[0082] Based on the base station density, a dynamic sector generation algorithm is used to generate sectors, specifically, the relative azimuth and relative distance of each adjacent base station are calculated, and the adjacent base stations are sorted according to the calculated relative azimuth: θ1≤θ2≤...≤θ k , the difference and standard deviation of the relative azimuth of the adjacent two adjacent base stations are calculated according to the sorting order, and the number of sectors is dynamically divided in the following formula 2:

[0083] N = floor(360° / (median(θ i+1 -θ i )+3σ));(1)

[0084] Where N is the number of sectors, and σ is the standard deviation of the relative azimuth. According to the dynamically divided sector number, it can be ensured that the sector division adapts to the distribution density of the adjacent base stations.

[0085] Further, based on the dynamically divided sector number, the sector boundary angle is generated in the following formula 2:

[0086] Φ j =θ B +j×360° / N±Δθ,j=0,1,...,N-1;(2)

[0087] Where Δθ is an anti-overlapping buffer angle, which is optional, Δθ = 0.1×min(θ i+1 -θ i ).

[0088] In each sector, select a key base station as a boundary point, wherein for the selection of the key base station, specifically, filter the adjacent base stations n j that satisfy the condition: Φ i ≤θ j+1 <Φ i , and calculate the radial coverage weight W i : W i =α×r i +β×(h B / h i )+γ×(PL max / PL i ), wherein α, β and γ are configurable distance weight, height ratio weight and path loss ratio weight, PL i is the path loss value from base station B to adjacent base station n i , PL max is the maximum path loss, r iis the relative distance of base station B to adjacent base station n i is the antenna hanging height of base station B B is the antenna hanging height of base station B i is the antenna hanging height of base station B i is the antenna hanging height of base station B

[0089] According to the calculated radial coverage weight of each adjacent base station of base station B, the first m adjacent base stations with the largest weight are selected as the boundary points, the boundary points are projected, and the evaluation area of base station B is constructed. In an embodiment, an α-shape algorithm is used to construct an optimal polygon area to obtain the evaluation area of base station B. Specifically, all boundary points are projected into a polar coordinate system with base station B as the center, and the radius α r of the polar coordinate system is calculated. Optionally, α r = 0.8*Des, wherein 0.8 is a configurable coefficient, and Des is the maximum coverage distance of the propagation model of base station B.

[0090] Further, an α-hull polygon is generated, and after eliminating abnormal convex points, the α-hull is converted into geographic polygon coordinates to obtain the maximum evaluation area of base station B.

[0091] Optionally, the base station parameter data in the multidimensional data set includes a coverage scene of the base station; in step 300, the backbone site is identified according to the spatial features, including:

[0092] In step 301, a site identification model corresponding to the coverage scene of each candidate base station in the candidate site set is obtained.

[0093] In step 302, the spatial features are input into the site identification model, each candidate base station is classified, and a candidate set of backbone sites is obtained.

[0094] In step 303, the candidate set is iteratively optimized to obtain the backbone site.

[0095] The site identification model corresponding to the coverage scene of each candidate base station in the candidate site set is obtained, the extracted spatial features are input into the site identification model, the candidate set is classified, and it is determined whether the candidate site is a backbone site. For the candidate base station classified as a backbone site, a candidate set of backbone sites is obtained, and further, the candidate set is optimized to obtain the final backbone site.

[0096] Optionally, if the backbone site includes multiple sites, the backbone site set corresponding to the multiple backbone sites is obtained in the form of a set.

[0097] In an embodiment, whether a candidate set station is a backbone station is identified by a station identification model, and base stations classified as backbone stations are included in a new set, i.e., a candidate set of backbone stations. In the candidate set of backbone stations, the selection of the backbone stations for low-altitude area networking is optimized to remove super-close stations and ensure the optimization of station distribution. The distances between all adjacent base stations in the candidate set of backbone stations are calculated, and for the case where the distance between two adjacent base stations is less than a preset distance threshold, such as 200 meters, the station with the highest height is retained, and the base station with a lower height is removed, thereby optimizing the candidate set. This can avoid excessive station density and reduce signal interference and resource waste.

[0098] Further, in step 303, the iteration optimization of the candidate set to obtain the backbone stations can also include:

[0099] Step 313, based on each candidate backbone station in the candidate set, performing flight testing on the low-altitude area according to the flight route to determine whether there is a coverage hole in the low-altitude area;

[0100] Step 323, if there is a coverage hole and the coverage hole is within the coverage range of the candidate backbone station, obtaining a suboptimal base station of the candidate backbone station as a backbone station to optimize the candidate set;

[0101] Step 333, after removing the sampling points of each backbone station in the candidate set from the measurement report data, evaluating the ground coverage rate of each base station;

[0102] Step 343, marking the backbone stations affecting ground coverage according to the ground coverage rate;

[0103] Step 353, updating the candidate station set according to the candidate set, returning and performing the step of constructing the evaluation area of each candidate base station according to the candidate station set until there is no coverage hole in the low-altitude area, and obtaining each backbone station in the candidate set.

[0104] The iteration optimization of the candidate set is a joint evaluation of the air-ground coverage of the candidate backbone stations in the candidate set to form a set of backbone stations for the private network networking of the low-altitude area. Specifically, first, based on each candidate backbone station in the candidate set, flight testing is performed on the low-altitude area according to the flight route of the low-altitude area planning to determine whether there is a coverage hole in the low-altitude area based on the candidate backbone stations in the current candidate set. The coverage hole includes an uncovered area and a weakly covered area.

[0105] If there is a coverage hole, and the coverage hole is within the coverage of the candidate backbone site, the suboptimal base station of the candidate backbone site is obtained as a backbone site, so as to realize optimization of the candidate set. The suboptimal base station of the candidate backbone site can be a candidate base station adjacent to the candidate backbone site and having a lower antenna hanging height than the candidate backbone site.

[0106] In an embodiment, for the candidate set of backbone sites, higher sites are retained and lower sites are removed according to the distance between two adjacent candidate backbone sites. The removed candidate backbone sites are taken as a backup site set. On this basis, the candidate set is jointly evaluated for coverage of the ground and the air, the coverage holes of the candidate backbone sites in the candidate set are checked, and the suboptimal base stations in the backup site set are used to supplement the backbone site set of the low-altitude private network. Further, after the base station is used as a backbone site of the low-altitude network, the antenna angle needs to be adjusted for coverage of the air, which reduces the ground coverage capability of the base station. Therefore, the ground coverage of the backbone site needs to be evaluated to check whether the backbone site affects the ground coverage capability, and the backbone site affecting the ground coverage is marked.

[0107] Specifically, when checking the ground coverage of the backbone site, the sampling points of the backbone site are removed from the measurement report data of the base station evaluation area, and then the coverage rate in the evaluation area of the backbone site is re-evaluated to determine whether the ground coverage of the backbone site in the evaluation area is affected.

[0108] Optionally, if the coverage rate in the evaluation area is greater than or equal to a preset coverage rate threshold after the sampling points of the backbone site are removed, the ground coverage of the backbone site is not affected, otherwise, if the coverage rate is less than the preset coverage rate threshold, the backbone site is marked.

[0109] Then, the candidate site set is updated according to the optimized candidate set, the backbone sites in the candidate set are removed from the candidate site set, a new candidate site set is obtained, the evaluation area of each candidate site in the updated candidate site set is reconstructed by calculation geometry, new backbone sites are screened out, a supplement site set of the backbone sites in the candidate set for coverage holes is formed, the backbone sites in the supplement site set are merged into the candidate set, and the ground and air coverage is jointly evaluated until there is no coverage hole in the low-altitude area, and a final updated candidate set is obtained. The base stations in the candidate set are finally used as backbone sites for private network networking in the low-altitude area.

[0110] Optionally, the flight test of the low-altitude area can be performed by a UAV, which is not limited here.

[0111] Optionally, the candidate backbone station in the candidate set is obtained based on classification and identification of the candidate base station by a station identification model, and the station identification model is obtained based on sample data sets in different coverage scenarios, and can identify whether the candidate base station in the different coverage scenarios is a backbone station, or different coverage scenarios correspond to different station identification models, and the station identification model corresponding to any coverage scenario is obtained based on sample data sets in the coverage scenario, and based on the coverage scenario corresponding to the candidate base station, the station identification model corresponding to the coverage scenario is selected to classify and identify whether the candidate base station is a backbone station.

[0112] Before step 301, the following can also be included:

[0113] Step 310, obtaining an original data set; the original data set includes antenna hanging height of a sample base station, coverage scenario and height information of a geographic object;

[0114] Step 320, constructing a space influence factor based on the distance between the geographic object and the receiving point of the sample base station and the height information;

[0115] Step 330, comparing the height information and the antenna hanging height, and generating a label of the space influence factor according to the comparison result;

[0116] Step 340, constructing a sample data set based on the label and the space influence factor, and dividing the sample data set according to the coverage scenario to obtain a sample data subset;

[0117] Step 350, iteratively training a preset support vector machine model by using each sample data subset to obtain a station identification model corresponding to each coverage scenario.

[0118] In the model training phase, for the training of the station identification model, first, an original data set is obtained, which includes the height information of the sample base station and the height information of the geographic object, and the height information of the sample base station further includes the antenna hanging height and the coverage scenario.

[0119] Wherein, the geographic object includes buildings such as buildings, and different base stations in the sample base station are distinguished by base station ID, and each base station has a unique base station ID, which can be generated by a hash function.

[0120] According to the antenna hanging height of the sample base station and the height information of the geographic object, a space feature is constructed, which includes a height feature and a space influence factor, and the space influence factor is an index factor for quantifying the influence of the geographic object on signal propagation, which is calculated by the height of the geographic object and the distance between the geographic object and the base station receiving point, and the space influence factor The specific calculation method is shown in the following formula 3:

[0121] ; (3)

[0122] represents the height of the geographical object, and represents the distance between the geographical object and the base station receiving point, and is the number of geographical objects around the base station. In this way, the spatial influence factor of the base station signal propagation is calculated, which comprehensively considers the antenna hanging height of the base station and the height of the geographical object, ensuring that the closer and higher the geographical object, the greater the shielding effect of the base station signal. And it expands the data set for model training and increases the geographical factors affecting the base station coverage.

[0123] The height information of the geographical object and the antenna hanging height of the sample base station are compared, and the label of the spatial influence factor is constructed according to the comparison result. The height information of the geographical object and the antenna hanging height of the sample base station are compared, specifically, the antenna hanging height of the sample base station is compared with the height of the geographical object around it, if the antenna hanging height of a certain sample base station is higher than the antenna hanging height of the geographical object around it or other base stations, its label is the first characteristic value, otherwise it is the second label value. When a certain geographical object is higher than the antenna hanging height of the geographical object around it or the sample base station, its label is the first label value, otherwise it is the second label value. Exemplarily, the first label value is 1, and the second label value is -1. That is, the label of the spatial influence factor is used to represent

[0124] Based on the label and the constructed spatial influence factor, a sample data set is constructed, and the constructed sample data set is divided according to the coverage scene of each sample base station, to obtain a sample data subset under each coverage scene, and a scene-based sample data is constructed.

[0125] Optionally, the site identification model is constructed based on a support vector machine model, and the sample data subset under each coverage scene is used to iteratively train the preset support vector machine model to obtain the site identification model corresponding to the coverage scene.

[0126] When training the support vector machine model using the sample data subset, first, the sample data set is split by coverage scene, and each coverage scene is split into a sample data subset. Each sample data subset is further divided into a training set and a test set. The division of the training set and the test set is realized according to a preset split ratio, which can be determined according to the human demand and data characteristics of model training. Exemplarily, the split ratio is 8:2, 80% of the data in the sample data subset is divided into the training set, and 20% of the data is divided into the test set.

[0127] Further, a stratified sampling method is used to ensure that the distribution of data in each sample data subset is consistent with that of the original sample data set. Specifically, the sample data set is first sorted by category, and the sample data set is divided into two categories, including geographic objects and base stations, to facilitate separate processing of data in each category. For each category, the amount of data to be allocated to the training set and the test set is calculated, and a random sampling method is used to extract a corresponding proportion of samples from each category of data and add them to the training set and the test set to ensure that the samples in each sample data subset represent their respective categories as much as possible. Finally, the samples extracted from the data in each category are combined into the final training set, test set, and validation set, and the pre-set support vector machine model is iteratively trained using the divided training set, test set, and validation set.

[0128] In the model training of different scenarios, according to any one coverage scenario to be trained, the training set, test set, and validation set under the coverage scenario are selected for model training. Further, in the model training process under the coverage scenario, a grid search method is used for parameter optimization, and five-fold cross-validation is used to evaluate the performance of the model of each parameter combination, and finally the parameter combination with the highest F1-score (balanced mean) in cross-validation is selected as the final model parameter, to obtain the site recognition model under the coverage scenario.

[0129] The core of the support vector machine model (SVM) is to find a hyperplane to divide different categories of data points. Since classification is performed by high-level features in this embodiment, the number of feature items is small but the amount of data is large. Therefore, the radial basis function RBF (Radial Basis Function) is used, which is based on Gaussian distribution and can effectively handle nonlinear problems, and is particularly effective for cases with small sample dimensions but large sample sizes.

[0130] In the training process of the support vector machine model, the model parameters to be trained include the penalty parameter and the kernel function parameter. The penalty parameter C is a parameter that balances the complexity of the model and the training error. When C takes a large value, the model will try to reduce the training error, which may lead to overfitting. When C takes a small value, the model will tend to have a larger gap, which may ignore the misclassification of some training data points, leading to underfitting. The kernel function parameter determines the shape of the Gaussian kernel function. The larger the kernel function parameter value, the smaller the range of the kernel function, and the more complex the model, which is prone to overfitting. The smaller the kernel function parameter value, the larger the range of the kernel function, and the simpler the model, which may lead to underfitting.

[0131] In the iterative training process, after each iteration is completed, the trained model is verified by the validation set. Since the relatively high base station of the antenna belongs to a minority, the number of positive samples and negative samples in the sample data differs greatly. Therefore, F1-score (balanced average) is used as the performance evaluation index of the model parameter combination.

[0132] The parameter combination with the highest F1-score (balanced average) is selected as the best model parameter. The sample with relatively high antenna height is called positive sample, and the remaining sample is negative sample. The actual relatively high base station refers to the label label in the validation set being 1, and the model prediction label label being 1 when predicting as relatively high. The actual non-relatively high refers to the label label in the validation set being -1, and the model prediction label label being -1 when predicting as non-relatively high.

[0133] TP: The number of samples predicted as positive samples, i.e. the number of samples predicted as relatively high base stations; TN: The number of samples predicted as negative samples, i.e. the number of samples predicted as non-relatively high base stations; FP: The number of samples predicted as positive samples, i.e. the number of samples predicted as non-relatively high base stations; FN: The number of samples predicted as negative samples, i.e. the number of samples predicted as non-relatively high base stations;

[0134] F1-Score is calculated in the following formula 4:

[0135] ; (4)

[0136] The model is evaluated on the test set, and the parameter combination with F1-score greater than the preset threshold is a qualified model parameter in terms of performance index, and the parameter combination with the maximum F1-score is further selected. The model configured with the parameter combination is used as the site identification model of the antenna height of the corresponding coverage scenario.

[0137] According to the obtained multi-dimensional data set, the spatial influence factor of the candidate base station is constructed. Based on the spatial influence factor, the pre-trained candidate base station in the coverage scenario corresponding to the candidate base station is used to predict the spatial influence factor of the candidate base station. The spatial feature constructed by the antenna height is used for prediction. The prediction label label is 1 or -1, so as to determine whether the antenna height of the candidate base station belongs to a high site or a low site. The candidate base station predicted as a high site is used as a candidate backbone site, and a candidate set of backbone sites is obtained. Further iteration and optimization are performed on the candidate set to obtain the final backbone site, and a special network is constructed for the low-altitude area to realize the coverage of the low-altitude area.

[0138] In the embodiment, the candidate base stations are determined by the base station parameter data, the related information of the geographic object, and the planned route and other multi-dimensional data of the base station, the evaluation area of the base station is dynamically constructed based on the calculation set, the backbone station in the candidate base station is identified based on the station identification model trained in the scene, and the backbone station is iteratively optimized, thereby improving the scientificity and accuracy of the backbone station decision for low-altitude networking.

[0139] Further, the propagation model coverage distance of the base station is calculated, the triangular mesh of the base station is dynamically constructed based on the triangulation algorithm, and the sector is dynamically generated based on the base station density of the adjacent base station, the key base station is selected as the boundary point for projection based on the multi-dimensional weight, and the evaluation area of the base station is generated. The geographic object and the base station in the evaluation area are taken as the optimization objects, the backbone station identified by the station identification model trained in the scene is iteratively optimized, which is conducive to adapting to the networking demand in different scenes, and can improve the adaptability of the backbone station identification in different building density and height and other complex scenes.

[0140] In the iterative optimization process of the backbone station, the air-ground coverage is jointly evaluated, the coverage hole of the air coverage and the influence on the ground coverage are checked, the leakage of the backbone station of the air coverage is supplemented, and it is ensured that the final backbone station can not only fill all the coverage holes of the air coverage, but also ensure the quality and stability of the air network coverage. In the case of meeting the low-cost networking demand of air-ground cooperation, the evaluation area can be accurately determined, the backbone station can be iteratively evaluated and optimized, the network quality of the air coverage can be guaranteed while the existing network resources are maximally reused, and the low-altitude private network networking cost is effectively reduced.

[0141] The low-altitude networking device provided in the embodiments of the application is described below. The low-altitude networking device described below can be correspondingly referred to the low-altitude networking method described above.

[0142] Reference Figure 2 The low-altitude networking device provided in the embodiments of the application includes:

[0143] The base station selection module 10 is configured to determine a candidate station set according to a multi-dimensional data set of a low-altitude area to be planned, wherein the multi-dimensional data set includes base station parameter data and a route of the low-altitude area.

[0144] The area construction module 20 is configured to construct an evaluation area of each candidate base station according to the candidate station set, and determine an optimization object set of the candidate base station according to the evaluation area.

[0145] The station identification module 30 is configured to extract spatial features of each preferred object in the preferred object set, and identify a backbone station according to the spatial features.

[0146] The low-altitude networking module 40 is configured to network the low-altitude area based on the backbone station.

[0147] In an embodiment, the area construction module 20 is further configured to:

[0148] determine a coverage distance of each candidate base station in the candidate station set according to base station parameter data of the candidate base station;

[0149] generate a circular coverage ring with the candidate base station as the center and the coverage distance as the radius;

[0150] construct a triangular mesh corresponding to the candidate base station by using a triangulation algorithm with each candidate base station in the circular coverage ring as a node;

[0151] determine adjacent base stations of the candidate base station based on an adjacency relationship of the triangular mesh;

[0152] generate sectors according to a base station density of the adjacent base stations, filter out key base stations in each sector as boundary points, and construct an evaluation area of the candidate base station.

[0153] In an embodiment, the base station parameter data includes a coverage scenario; and the station identification module 30 is further configured to:

[0154] obtain a station identification model corresponding to the coverage scenario of each candidate base station in the candidate station set;

[0155] input the spatial features into the station identification model, classify each candidate base station, and obtain a candidate set of backbone stations;

[0156] iteratively optimize the candidate set to obtain a backbone station.

[0157] In an embodiment, the multi-dimensional data further includes measurement report data; and the station identification module 30 is further configured to:

[0158] determine whether there is a coverage hole in the low-altitude area according to the flight test of the low-altitude area by the route based on each candidate backbone station in the candidate set;

[0159] if there is a coverage hole and the coverage hole is within the coverage range of the candidate backbone station, obtain a suboptimal base station of the candidate backbone station as a backbone station to optimize the candidate set;

[0160] After removing the sampling points of each backbone station in the candidate set from the measurement report data, evaluating the ground coverage of each base station;

[0161] According to the ground coverage, marking the backbone base stations affecting the ground coverage;

[0162] According to the candidate set, updating the candidate station set, returning and performing the step of constructing the evaluation area of each candidate base station according to the candidate station set, until there is no coverage hole in the low-altitude area, obtaining each backbone station in the candidate set.

[0163] In one embodiment, the low-altitude networking device further comprises a model training module for:

[0164] Obtaining an original data set; the original data set comprises antenna hanging height of a sample base station, coverage scene and height information of geographical objects;

[0165] Based on the distance between the geographical objects and the receiving points of the sample base station and the height information, constructing a spatial influence factor;

[0166] Comparing the height information and the antenna hanging height, and generating a label of the spatial influence factor according to the comparison result;

[0167] Based on the label and the spatial influence factor, constructing a sample data set, and dividing the sample data set according to the coverage scene to obtain a sample data subset;

[0168] Using each sample data subset to iteratively train a preset support vector machine model respectively to obtain a station identification model corresponding to each coverage scene.

[0169] In one embodiment, the base station parameter data comprises base station positions; the base station selection module 10 is further configured to:

[0170] Establishing a plurality of buffer zones on both sides of the route of the low-altitude area to be planned with a preset width;

[0171] De-duplicating and merging the plurality of buffer zones to obtain a base station selection area;

[0172] According to the base station positions of each base station in the base station parameter data, obtaining each candidate base station in the base station selection area to obtain a candidate station set.

[0173] Figure 3 An example of an entity structure diagram of an electronic device is shown as Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 complete communications with each other through the communications bus 340. The processor 310 can invoke a logical instruction in the memory 330 to execute a low-altitude networking method, which includes:

[0174] determining a candidate site set according to a multi-dimensional data set of the low-altitude region to be planned; the multi-dimensional data set includes base station operating parameter data and air routes of the low-altitude region;

[0175] constructing an evaluation region of each candidate base station according to the candidate site set, and determining a preferred object set of the candidate base station according to the evaluation region;

[0176] extracting spatial features of each preferred object in the preferred object set, and identifying a backbone site according to the spatial features;

[0177] networking the low-altitude region based on the backbone site.

[0178] In addition, the logical instruction in the memory 330 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0179] On the other hand, the embodiments of the present application also provide a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the low-altitude networking method provided by the above-mentioned methods, which includes:

[0180] determining a candidate site set according to a multi-dimensional data set of the low-altitude region to be planned; the multi-dimensional data set includes base station operating parameter data and air routes of the low-altitude region;

[0181] constructing an evaluation area of each candidate base station according to the candidate station set, and determining a preferred object set of the candidate base station according to the evaluation area;

[0182] extracting spatial features of each preferred object in the preferred object set, and identifying a backbone station according to the spatial features;

[0183] networking the low-altitude area based on the backbone station.

[0184] In another aspect, the embodiments of the present application also provide a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the low-altitude networking method provided by the above method, and the method comprises:

[0185] determining a candidate station set according to a multi-dimensional data set of the low-altitude area to be planned, wherein the multi-dimensional data set comprises base station parameter data and air routes of the low-altitude area;

[0186] constructing an evaluation area of each candidate base station according to the candidate station set, and determining a preferred object set of the candidate base station according to the evaluation area;

[0187] extracting spatial features of each preferred object in the preferred object set, and identifying a backbone station according to the spatial features;

[0188] networking the low-altitude area based on the backbone station.

[0189] The apparatus embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place or distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments. Those skilled in the art can understand and implement without creative labor.

[0190] From the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0191] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some 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. A low-altitude networking method, characterized in that, include: The candidate site set is determined based on the multidimensional dataset of the low-altitude area to be planned; The multidimensional dataset includes base station operating parameter data and flight routes in the low-altitude area; An evaluation region for each candidate base station is constructed based on the candidate site set, and a set of preferred candidate base stations is determined based on the evaluation region. Extract the spatial features of each preferred object in the set of preferred objects, and identify backbone sites based on the spatial features; The low-altitude area is networked based on the backbone stations; The step of constructing the evaluation area for each candidate base station based on the candidate site set includes: The coverage distance of each candidate base station is determined based on the base station operating parameter data of each candidate base station in the candidate site set. A circular coverage area is generated with the candidate base station as the center and the coverage distance as the radius; Using each candidate base station within the circular coverage area as a node, a triangulation algorithm is used to construct a triangular mesh corresponding to the candidate base station. Based on the adjacency relationship of the triangular mesh, the neighboring base stations of the candidate base station are determined; Sectors are generated according to the base station density of the adjacent base stations, and key base stations in each sector are selected as boundary points to construct the evaluation area of ​​the candidate base stations.

2. The low-altitude networking method according to claim 1, characterized in that, The base station operating parameter data includes coverage scenarios; the identification of backbone sites based on the spatial features includes: Obtain the site identification model corresponding to the coverage scenario of each candidate base station in the candidate site set; The spatial features are input into the site identification model to classify each candidate base station and obtain a candidate set of backbone sites. The candidate set is iteratively optimized to obtain the backbone sites.

3. The low-altitude networking method according to claim 2, characterized in that, The multidimensional data also includes measurement report data; the iterative optimization of the candidate set to obtain backbone sites includes: Based on each candidate backbone site in the candidate set, flight tests are conducted in the low-altitude area according to the flight route to determine whether there are coverage holes in the low-altitude area. If a coverage hole exists and the coverage hole is within the coverage area of ​​the candidate backbone site and the candidate backbone site, the suboptimal base station of the candidate backbone site is obtained as the backbone site to optimize the candidate set. After removing the sampling points of each backbone site in the candidate set from the measurement report data, the ground coverage of each base station is evaluated; Based on the aforementioned ground coverage rate, backbone base stations that affect ground coverage are marked; The candidate site set is updated according to the candidate site set, and the step of constructing the evaluation area of ​​each candidate base station according to the candidate site set is returned and executed until there are no coverage holes in the low-altitude area, and the backbone sites in the candidate site set are obtained.

4. The low-altitude networking method according to claim 2, characterized in that, Before obtaining the site identification model corresponding to the coverage scenario of each candidate base station in the candidate site set, the method further includes: Obtain the original dataset; the original dataset includes the antenna height of the sample base station, the coverage scene, and the height information of geographical objects; Based on the distance between the geographic object and the receiving point of the sample base station and the height information, a spatial influence factor is constructed; The height information and the antenna mounting height are compared, and a label for the spatial influence factor is generated based on the comparison result; Based on the labels and the spatial influence factors, a sample dataset is constructed, and the sample dataset is divided according to the coverage scenarios to obtain sample data subsets; The preset support vector machine model is iteratively trained using each subset of the sample dataset to obtain the site identification model corresponding to each coverage scenario.

5. The low-altitude networking method according to claim 1, characterized in that, The base station operating parameter data includes the base station location; the process of determining the candidate site set based on the multidimensional dataset of the low-altitude area to be planned includes: Multiple buffer zones are established on both sides of the flight path in the low-altitude area to be planned, with a preset width; The multiple buffers are deduplicated and merged to obtain the base station selection area; Based on the base station location of each base station in the base station engineering parameter data, the candidate base stations within the selected area of ​​the base station are obtained, resulting in a candidate site set.

6. A low-altitude networking device, characterized in that, include: The base station selection module is used to determine a set of candidate sites based on a multidimensional dataset of the low-altitude area to be planned. The multidimensional dataset includes base station operating parameter data and flight routes in the low-altitude area; The region construction module is used to construct an evaluation region for each candidate base station based on the candidate site set, and to determine the set of preferred candidates for the candidate base stations based on the evaluation regions. The site identification module is used to extract the spatial features of each preferred object in the set of preferred objects, and to identify backbone sites based on the spatial features; A low-altitude networking module is used to network the low-altitude area based on the backbone stations; The step of constructing the evaluation area for each candidate base station based on the candidate site set includes: The coverage distance of each candidate base station is determined based on the base station operating parameter data of each candidate base station in the candidate site set. A circular coverage area is generated with the candidate base station as the center and the coverage distance as the radius; Using each candidate base station within the circular coverage area as a node, a triangulation algorithm is used to construct a triangular mesh corresponding to the candidate base station. Based on the adjacency relationship of the triangular mesh, the neighboring base stations of the candidate base station are determined; Sectors are generated according to the base station density of the adjacent base stations, and key base stations in each sector are selected as boundary points to construct the evaluation area of ​​the candidate base stations.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the low-altitude networking method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the low-altitude networking method as described in any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the low-altitude networking method as described in any one of claims 1 to 5.

Images