A communication site planning method, device, equipment and readable storage medium

Abstract

The embodiment of the present invention relates to the field of communication technology, and discloses a communication site planning method, device, equipment and readable storage medium. The planning method includes: rasterizing the area to be planned to obtain the index data information of each grid; performing weak coverage screening on the grid; performing the first clustering processing on the grid after weak coverage screening to obtain the planning demand cluster in the area to be planned; respectively obtaining the number of demand sites of each planning demand cluster; outputting the planned location of each demand site in the planning demand cluster according to the number of demand sites. Through the above method, the embodiment of the present invention can improve the scientificity and rationality of the selection of communication sites, improve the adaptability of the algorithm and the accuracy of site planning, and realize the automatic planning of the number and location of communication sites, thereby improving planning efficiency.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of communication technology, and in particular to a communication site planning method, device, equipment and readable storage medium. Background Art

[0002] In recent years, with the development of big data technology and positioning technology, operators can more accurately obtain the location information of sampling points where terminals connect to the network for business. These location information combined with user business data and performance data can provide strong data support for network planning and optimization. However, the existing communication network site planning methods do not make full use of these data, and often rely only on coverage simulation data for planning, resulting in a significant difference between the planning results and actual needs.

[0003] Among them, the existing communication network site planning method is to sort out the initial site of the communication according to the existing site resources, use the planning software to perform coverage simulation, analyze the coverage simulation results, find out the weak coverage area, add stations to the weak coverage area points manually or through a simple convergence method, and output the site planning list.

[0004] However, the existing communication network site planning has the following problems: 1. The analyzed data samples are all simulation data generated by the wireless propagation model, which is greatly affected by the accuracy of the existing site engineering parameters. The engineering parameter data is static data and its accuracy cannot be guaranteed. At the same time, the simulation data itself is simulated non-actual data; 2. The existing technology only uses the simulated signal strength as the only analysis data for site planning, without considering multiple dimensions, and the basis for site selection is too one-sided; 3. The location and number of site planning are mainly determined by the subjective judgment of the operator, and its quality is largely determined by the professional quality of the operator, and it is inefficient. Summary of the invention

[0005] In view of the above problems, the embodiments of the present invention provide a communication site planning method, device, equipment and readable storage medium, which are used to solve the problems existing in the prior art of communication network site planning, such as the accuracy of analysis data samples using simulation data cannot be guaranteed, the basis for site selection is too one-sided, and the inefficiency of site planning caused by manual operation.

[0006] According to one aspect of an embodiment of the present invention, a communication site planning method is provided, the planning method comprising: performing rasterization processing on a planned area to obtain indicator data information of each grid; performing weak coverage screening on the grid; performing a first clustering processing on the grid after the weak coverage screening to obtain a planned demand cluster in the planned area; respectively obtaining the number of demand sites of each of the planned demand clusters; and outputting the planned location of each demand site in the planned demand cluster according to the number of demand sites.

[0007] In an optional manner, the rasterization processing of the area to be planned to obtain the index data information of each grid further includes: when it is determined that each of the grids has precisely positioned sampling point data, the sampling point data of the precise positioning system in the area to be planned is obtained, and the index data information of the grid is calculated based on the sampling point data of the precise positioning system; when it is determined that each of the grids does not have precisely positioned sampling point data, the simulation signal strength data of each grid in the simulation planning system is obtained, and the index data information of the grid is calculated based on the simulation signal strength data of the grid.

[0008] In an optional manner, the separately obtaining the number of demand sites of each of the planned demand clusters further includes: obtaining a value coefficient of each of the planned demand clusters; normalizing the value coefficient of each of the planned demand clusters; and calculating the number of demand sites of each of the planned demand clusters based on the normalized value coefficient of each of the planned demand clusters.

[0009] In an optional manner, the normalizing the value coefficients of each of the planned demand clusters further includes: obtaining the maximum and minimum values ​​of the value coefficients of each of the planned demand clusters; calculating the normalized coefficients according to the maximum and minimum values; and calculating the normalized value coefficients of each of the planned demand clusters according to the normalized coefficients.

[0010] In an optional method, the number of required sites of each planned demand cluster is calculated based on the value coefficient of each planned demand cluster after normalization, further including: respectively obtaining parameter information of each planned demand cluster and the coverage index of the communication site; combining the parameter information, the coverage index and the value coefficient of each planned demand cluster after normalization to calculate the number of required sites of each planned demand cluster.

[0011] In an optional manner, the output of the planned location of each demand site in the planned demand cluster further includes: when it is determined that the number of demand sites in the planned demand cluster is equal to 1, obtaining the longitude and latitude of the first center point of the area where the planned demand cluster is located, and using the longitude and latitude of the first center point as the planned location of the demand site in the planned demand cluster; when it is determined that the number of demand sites in the planned demand cluster is greater than 1, performing a second clustering processing on each of the grids in the planned demand cluster to form multiple sub-clusters; and respectively obtaining the longitude and latitude of multiple second center points of the area where the multiple sub-clusters are located, and using the multiple second center point longitudes and latitudes as the planned locations of the demand sites in the planned demand cluster.

[0012] In an optional manner, the indicator data information of the grid includes at least signal strength data, traffic volume data and value data of the grid.

[0013] According to another aspect of an embodiment of the present invention, a communication site planning device is provided, the planning device comprising: a rasterization processing module, used to perform rasterization processing on a planned area to obtain indicator data information of each grid; a weak coverage screening module, used to perform weak coverage screening on the grid; a clustering module, used to cluster the grids after weak coverage screening to obtain planning demand clusters in the planned area; an acquisition module, used to respectively obtain the number of demand sites of each of the planned demand clusters; and an output module, used to output the planned position of each demand site in the planned demand cluster according to the number of demand sites.

[0014] According to another aspect of an embodiment of the present invention, a communication site planning device is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of any one of the communication site planning methods described above.

[0015] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores at least one executable instruction, wherein the executable instruction enables a communication site planning device / apparatus to perform the operation of any one of the communication site planning methods described above.

[0016] The embodiments of the present invention can improve the scientificity and rationality of communication site selection by rasterizing the planning area and combining the indicator parameters of the grid; combining a customized machine learning algorithm can improve the adaptability of the algorithm and the accuracy of site planning; establishing a complete communication site planning process from data collection, data analysis, solution output to solution execution can realize the automated planning of the number and location of communication sites, greatly improving planning efficiency.

[0017] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0019] Figure 1 A schematic diagram showing a flow chart of a communication site planning method provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a process flow of an implementation method of step 100 of the present invention is shown;

[0021] Figure 3 A schematic diagram showing an implementation method of planning demand clusters according to the present invention;

[0022] Figure 4 A schematic diagram showing a flow chart of an implementation of step 400 of the present invention;

[0023] Figure 5 A schematic diagram showing a flow chart of an embodiment of step 420 of the present invention

[0024] Figure 6 A schematic diagram showing a flow chart of an implementation of step 430 of the present invention;

[0025] Figure 7 A schematic diagram showing a flow chart of an embodiment of step 500 of the present invention

[0026] Figure 8 A schematic diagram showing the structure of an embodiment of a communication site planning device of the present invention;

[0027] Fig. 9 A schematic structural diagram of an embodiment of a communication site planning device of the present invention is shown. DETAILED DESCRIPTION

[0028] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0029] Figure 1 The flowchart of the communication site planning method embodiment of the present invention is shown. It can be understood that the communication site planning of the present invention is described in detail by taking the planning of 5G site as an example. Of course, the communication site planning method of the present invention can also be applied to the planning of other sites, such as the planning of 4G site, etc., which is not specifically limited here. Specifically, Figure 1 As shown, the communication site planning method of the present invention includes the following steps:

[0030] Step 100: rasterize the area to be planned to obtain indicator data information of each grid.

[0031] First, the planned area is gridded, that is, the area where communication site planning is required is gridded (5G site planning in the embodiment of the present invention) and divided into multiple s meters * s meters grids, where each grid is a geographical area.

[0032] Furthermore, the indicator data information of each grid is obtained respectively, and the indicator data information of each grid in the embodiment of the present invention includes at least the signal strength data, business volume data and value data of the grid. Among them, the signal strength data of the grid is used to evaluate the coverage of the area, which is a basic indicator of 5G site planning (areas with poor coverage need to supplement site coverage); the number of resident users in the grid area reflects the business data volume of the area, and the average monthly income reflects the value data.

[0033] In the above implementation, communication site planning is performed by mining data in multiple dimensions, that is, combining grid signal strength data, business volume data, and value data. Compared with the prior art that only uses simulated signal strength as the only analytical data for site planning, the present invention can improve the scientificity and rationality of the basis for site selection.

[0034] Optionally, the acquisition of indicator data information of each grid is divided into the following two cases:

[0035] 1. A grid with precise positioning sampling point data, that is, using the precise positioning data of the terminal;

[0036] 2. For grids without precise positioning data, simulated signal strength data is used;

[0037] The present invention mainly uses the terminal's precise positioning data and uses the simulated signal strength data as an auxiliary analysis data sample system, which can improve the accuracy of the data. The above two situations of the present invention are described in detail below.

[0038] Please further combine Figure 2 , Figure 2 A schematic diagram of the process of implementing step 100 of the present invention is shown, as shown in FIG. Figure 2 , step 100 of the present invention further includes the following sub-steps:

[0039] Step 110: When it is determined that each grid has sampling point data of precise positioning, the sampling point data of the precise positioning system in the area to be planned is obtained, and the index data information of the grid is calculated according to the sampling point data of the precise positioning system.

[0040] Optionally, when it is determined that each grid has sampling point data with precise positioning, that is, there is a precise positioning system in the area to be planned, and the precise positioning sampling point data means that there are at least Vm sampling points from the precise positioning system in the grid. Further, the sampling point data of the precise positioning system in the area to be planned in the last e days (e≥3) are extracted. Among them, the sampling point data of the precise positioning system all carry longitude and latitude information, and the longitude and latitude information of the sampling point data carry signal strength. The longitude and latitude information of the sampling point data is attributed to each grid, and the signal strength of each sampling point in the grid is the signal strength of the grid. The indicator data information of the calculation grid can be calculated, as follows:

[0041] The average signal strength of the grid (signal strength data) = sum (signal strength of sampling points in the grid - δi) / total number of sampling points in the grid, where δi is the strength compensation value of sampling points in different frequency bands of 4G and 5G frequency bands;

[0042] Number of grid resident users (traffic data) = count (users who appear in the grid for at least e-1 days)

[0043] Grid income (value data) = sum (average monthly cost of grid regular users).

[0044] Step 120: When it is determined that there is no precisely located sampling point data for each grid, the simulated signal strength data of each grid in the simulation planning system is obtained, and the index data information of the grid is calculated based on the simulated signal strength data of the grid.

[0045] Optionally, when it is determined that there is no precisely located sampling point data for each grid, the simulated signal strength data of each geographical location of the 5G simulation planning system is extracted, and the simulated signal strength data also carries latitude and longitude information, and the latitude and longitude information carries the simulated signal strength, which is attributed to each grid, and the simulated signal strength in the grid is the signal strength data of the grid, thereby calculating the indicator data information of the calculation grid, as follows:

[0046] Grid average signal strength (signal strength data) = the mean value of the simulated signal strength within the grid;

[0047] Among them, the number of grid resident users (traffic volume data) and grid income (value data) are both set to 0.

[0048] In the above implementation, the actual data is mainly used and the simulated data is supplemented. The actual precise positioning data of the terminal is combined with the analysis data sample system of the simulated signal strength data, which can improve the accuracy of the data.

[0049] Step 200: Perform weak coverage screening on the grid.

[0050] Furthermore, the grids in the planned area are screened for weak coverage, and the grids whose average signal strength is less than the minimum reference signal receiving power (RSRP) are used for DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering.

[0051] Step 300: Perform a first clustering process on the grid after weak coverage screening to obtain a planning demand cluster in the area to be planned.

[0052] It is understandable that the present invention uses the DBSCAN clustering algorithm to perform the first clustering process on the grid after weak coverage screening. The DBSCAN clustering algorithm is a density-based clustering algorithm. Unlike the partitioning and hierarchical clustering methods, it defines a cluster as the maximum set of density-connected points, can divide areas with sufficiently high density into clusters, and can find clusters of any shape in a noisy spatial database.

[0053] Optionally, the DBSCAN clustering algorithm in the present invention is a clustering based on the geographical location of each grid, so the implementation of the DBSCAN algorithm needs to match this situation, and the customized modification mainly includes:

[0054] 1. Model input

[0055] The model only inputs two variables, longitude and latitude, and clusters the samples based on these two variables.

[0056] 2. Calculation of distance between grid samples

[0057] The method for calculating the distance between grid samples in the DBSCAN clustering algorithm is modified to an algorithm for calculating the distance between two points based on the longitude and latitude of the two points.

[0058] The DBSCAN clustering algorithm of the present invention is described in detail below:

[0059] Among them, the grids clustered by DBSCAN are grids obtained after screening weak coverage grids, and the variables input to the model are the central longitude and latitude of each grid. In a specific application scenario of the present invention, the central longitude and latitude of the grid can be (106.23223, 38.745443).

[0060] Specifically, DBSCAN contains two parameters, eps and min_samples. Among them, eps defines the distance, and min_samples defines the minimum number of grid samples. If there are min_samples other grid data samples whose distance to the current grid sample is eps, the current grid sample is considered to be the core grid sample, and the other min_samples grid samples are regarded as neighbors of this core grid sample. It can be understood that if there are no min_samples other grid data samples whose distance to the current grid sample is eps, it means that the above-mentioned weakly covered grids do not form a cluster, and the problem of weak coverage is relatively scattered. From the perspective of coverage, there is no value in planning new 5G sites, and the area does not need to be planned.

[0061] Furthermore, a series of core grid samples are grouped into a cluster, and recursively a core grid sample is used to find all its neighbors, which can also be core grid samples, and so on. A cluster can have non-core grid samples, which are neighbors of core grid samples but are not core grid samples themselves. Intuitively, these non-core grid samples are all at the edge of the cluster. A large min_samples and a small eps indicate that only grid samples with a large density can form a cluster.

[0062] Furthermore, since the distance algorithm has been modified to the longitude and latitude geographic distance algorithm in the above text, the setting of the eps parameter can be measured by the geographic distance requirement, so the system sets eps = t*s, where t is an integer ≥ 1, and s is the side length of the grid. The system sets min_samples = floor(N*t^2), where t is the t value in the eps setting, N ranges from [1, 3], and floor means rounding down. When N is set to 1, the required density is small, and when N is set to 3, the density requirement is large.

[0063] Please further combine Figure 3 , Figure 3 A schematic diagram of an implementation of a planning demand cluster of the present invention is shown. Optionally, a planning demand cluster is formed based on the clusters obtained by clustering the weak coverage grids and the non-weak coverage grids within the cluster range obtained by clustering. The cluster range refers to the area formed by connecting the boundary points of the cluster.

[0064] Step 400: Obtain the number of demand sites of each planned demand cluster respectively.

[0065] Please further combine Figure 4 , Figure 4 FIG. 4 is a flow chart showing an implementation of step 400 of the present invention. Figure 4 Step 400 further includes the following sub-steps:

[0066] Step 410: Obtain the value coefficient of each planning demand cluster.

[0067] Optionally, parameter information of each planned demand cluster can be calculated based on each planned demand cluster, and the parameter information at least includes the area, number of resident users and income of each planned demand cluster. The calculation formula is as follows:

[0068] Planning demand cluster area Vi = sum (the area of ​​each grid in the planning demand cluster);

[0069] The number of resident users in the planned demand cluster Pi = count (the sum of resident users of each grid in the planned demand cluster without duplicates);

[0070] Planning demand cluster income Ii = sum (average monthly expenses of users who are resident in each grid within the planning demand cluster, excluding duplicates).

[0071] Further, the relevant parameter information of the area to be planned is calculated, and the relevant parameter information of the area to be planned at least includes the total area of ​​the area to be planned, the total number of resident users and the total income. The calculation formula is as follows:

[0072] The total area of ​​the area to be planned is U;

[0073] The total number of resident users in the area to be planned R = count (the total number of resident users in each grid in the area to be planned, excluding duplicates);

[0074] The total income of the area to be planned J=sum (the average monthly expenses of the users who are resident in each grid in the area to be planned, excluding duplicates).

[0075] Optionally, the value coefficient of each planning demand cluster is defined as Qi, and the value coefficient of the planning demand cluster is Qi, which is the value per unit area of ​​each planning demand cluster divided by the value per unit area of ​​the entire area to be planned, and the expression is as follows:

[0076] Qi=(Ii / Vi) / (J / U).

[0077] Step 420: Normalize the value coefficients of each planning demand cluster.

[0078] Further, combined with Figure 5 , Figure 5 FIG. 4 is a flow chart showing an implementation of step 420 of the present invention. Figure 5 , step 420 further includes the following sub-steps:

[0079] Step 421: Obtain the maximum and minimum values ​​of the value coefficients of each planning demand cluster.

[0080] First, the minimum value Qmin and the maximum value Qmax of the value coefficient Qi of each planning demand cluster are obtained.

[0081] Step 422: Calculate a normalization coefficient based on the maximum value and the minimum value.

[0082] Furthermore, the value coefficient Qi of the planned demand cluster is mapped to the interval [a, b], so that excessive resource tilting due to value differences can be avoided. The interval [a, b] can refer to the range of values. For example, in a specific embodiment of the present invention, the interval [a, b] can be set to [0, 2]. Specifically, for clusters with Qi values ​​of 0 to 1, the number of planned sites will be reduced due to insufficient value coefficients; while for clusters with Qi values ​​of 1 to 2, more sites will be planned and more resources will be obtained due to high value coefficients. Of course, in other embodiments of the present invention, the interval [a, b] can also be set to [0, 3], etc., so that the value coefficient Qi will have a greater impact on site planning; of course, the interval [a, b] can also be set to [0.5, 1.5], so that the value coefficient Qi will have a smaller impact on site planning. In a preferred embodiment of the present invention, the recommended value range of a is [0, 0.5], and the recommended value range of b is [1.5, 3]. Of course, in actual application scenarios, the value of the interval [a, b] can be set according to the actual situation, and no specific limitation is made here.

[0083] Furthermore, the normalization coefficient is calculated based on the maximum and minimum values. The normalization coefficient expression is as follows:

[0084] c = (ba) / (Qmax-Qmin).

[0085] Step 423: Obtain the normalized value coefficient of each planning demand cluster according to the normalization coefficient.

[0086] Optionally, the normalized value coefficient of each planning demand cluster is obtained according to the normalization coefficient, and the expression is as follows:

[0087] Qnew(i)=a+c(Qi-Qmin).

[0088] Step 430: Obtain the number of demand sites of each planned demand cluster according to the normalized value coefficient of each planned demand cluster.

[0089] Please further combine Figure 6 , Figure 6 FIG. 4 is a flow chart showing an implementation of step 430 of the present invention. Figure 6 , step 430 further includes the following sub-steps:

[0090] Step 431: Obtain parameter information of each planning demand cluster and coverage index of the communication site respectively.

[0091] Optionally, step 410 can obtain parameter information of each planned demand cluster that can be calculated based on each planned demand cluster, and the parameter information at least includes the area, number of resident users and income of each planned demand cluster. In this embodiment, the parameter information uses the planned demand cluster area Vi and the planned demand cluster number of resident users Pi, and the calculation formula is as follows:

[0092] Planning demand cluster area Vi = sum (the area of ​​each grid in the planning demand cluster);

[0093] The number of resident users in the planned demand cluster Pi=count (the sum of resident users of each grid in the planned demand cluster after removing duplicates).

[0094] Furthermore, the coverage indicators of the communication site are obtained, wherein for 5G site planning, the coverage indicators include at least the coverage area and the number of users carried, that is, the maximum coverage area W of the planned 5G single site and the number of users carried G of the planned 5G single site.

[0095] Step 432: Calculate the number of demand sites for each planned demand cluster by combining parameter information, coverage indicators and the normalized value coefficient of each planned demand cluster.

[0096] Optionally, the percentage of each planned demand cluster area in the planned maximum coverage area of ​​the single 5G site and the percentage of the number of resident users of each planned demand cluster in the number of users carried by the single 5G site are calculated respectively.

[0097] Among them, the maximum coverage area W of the planned 5G single site and the maximum number of users G carried by the planned 5G single site are known parameters in the present invention. The planned demand cluster area Vi is compared with the maximum coverage area W of the planned 5G single site to obtain the percentage Vi / W of each planned demand cluster area in the maximum coverage area of ​​the planned 5G single site; further, the number of resident users Pi of each planned demand cluster is compared with the number of users carried by the planned 5G single site to obtain the percentage Pi / G of the number of resident users of each planned demand cluster in the number of users carried by the planned 5G single site.

[0098] Furthermore, the product of the larger percentage of the two and the normalized value coefficient Qnew(i) of each planning demand cluster is selected to obtain the number of demand sites Ki of each planning demand cluster, which is expressed as follows:

[0099] Ki=max(Vi / W,Pi / G)*Qnew(i)

[0100] Optionally, in the present invention, when it is judged that Ki<0.5, it is considered that the planning demand cluster is insufficient for planning the site, and Ki is 0; if it is judged that Ki≥0.5, Ki=ceiling(Ki), where ceiling means rounding up.

[0101] Optionally, the planning process in the above-mentioned implementation mode of the present invention comprehensively considers multiple factors such as coverage, number of users, regional value, etc., and realizes multi-dimensional quantitative planning of communication sites in combination with the communication site's own coverage indicators (coverage area, number of users carried).

[0102] Step 500: Output the planned location of each demand site in the planned demand cluster according to the number of demand sites.

[0103] Please further combine Figure 7 , Figure 7 FIG. 5 is a flow chart showing an implementation of step 500 of the present invention. Figure 7 , step 500 further includes the following sub-steps:

[0104] Step 510: When it is determined that the number of demand sites in the planned demand cluster is equal to 1, the longitude and latitude of the first center point of the area where the planned demand cluster is located are obtained, and the longitude and latitude of the first center point are used as the planned position of the demand site in the planned demand cluster.

[0105] Optionally, in the present invention, when it is determined that the number of demand sites Ki of the planned demand cluster is equal to 1, the longitude and latitude of the first center point of the area where the planned demand cluster is located is directly calculated, and the longitude and latitude of the first center point is used as the planned location of the demand site in the planned demand cluster. The longitude and latitude of the first center point are calculated as follows:

[0106] Longitude = mean (longitude of all weak coverage grids in the planning demand cluster);

[0107] Latitude = mean (latitude of all weak coverage grids in the planning demand cluster;

[0108] Among them, the grid longitude and grid latitude are the longitude and latitude of the first center point.

[0109] Step 520: When it is determined that the number of demand sites in the planned demand cluster is greater than 1, a second clustering process is performed on each grid in the planned demand cluster to form a plurality of sub-clusters.

[0110] Further, if it is determined that the number of demand sites Ki of the planned demand cluster is greater than 1, then in step 520, it is necessary to perform clustering processing on the weak coverage grids in each planned demand cluster, and Kmeans clustering algorithm (k-means clustering algorithm) is adopted in the embodiment of the present invention. Among them, Kmeans clustering is an iterative clustering analysis algorithm, and its steps are to randomly select K objects as the initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. The cluster centers and the objects assigned to them represent a cluster. For each sample assigned, the cluster center of the cluster will be recalculated according to the existing objects in the cluster. This process will be repeated until a certain termination condition is met. The termination condition can be that no (or the minimum number) of objects are reallocated to different clusters, no (or the minimum number) of cluster centers change again, and the error square sum is locally minimized.

[0111] Furthermore, since the existing distance algorithms of Kmeans and DBSCAN include Euclidean distance, Manhattan distance, etc., which cannot accurately measure the distance on geographic information, the present invention customizes the Kmeans clustering algorithm to the distance on geographic information, as follows:

[0112] Kmeans clustering is to input the longitude and latitude of the weak coverage grid of a certain planning demand cluster into Kmeans, and set the number of output categories to K for modeling. The model outputs the category to which each weak coverage grid belongs. For each category, by calculating the central longitude and latitude of all the weak coverage grids in the category, the center point of the category can be obtained, that is, the location of the 5G site to be planned for the category. Therefore, for the planning demand cluster, the K sites planned can all find accurate locations.

[0113] Specifically, Kmeans clustering is performed on each grid according to its longitude and latitude in the planning requirement cluster. The Kmeans algorithm needs to set the parameter K, that is, the number of converged subclusters, that is, to form multiple subclusters.

[0114] Step 530: respectively obtain the longitudes and latitudes of multiple second center points in the areas where the multiple sub-clusters are located, and use the longitudes and latitudes of the multiple second center points as the planned positions of the demand sites in the planned demand cluster.

[0115] Further, the edge points of the multiple sub-clusters formed in step 520 are connected to form multiple sub-areas, and the latitude and longitude of multiple second center points of the areas where the multiple sub-clusters are located are respectively obtained, so as to use the latitude and longitude of the multiple second center points as the planned location of the demand site Ki in the planned demand cluster. The second center point calculation method is:

[0116] Longitude = mean (longitude of all weak coverage grids of this category in the planning demand cluster);

[0117] Latitude = mean (latitude of all weakly covered grids of this category in the planning demand cluster).

[0118] Optionally, a customized two-layer machine learning algorithm is applied in the embodiment of the present invention, the first layer is the DBSCAN clustering algorithm, and the second layer is the Kmeans clustering algorithm, and the parameter setting method of the two machine learning algorithm models is specifically given, which improves the adaptability of the algorithm and the accuracy of site planning. And the communication site planning method of the present invention establishes a complete set of method flows from data collection, data analysis, solution output to solution execution, which greatly improves the planning efficiency of communication sites.

[0119] In the above implementation mode, by rasterizing the planned area and combining the index parameters of the grid, the scientificity and rationality of the communication site selection can be improved; combining with a customized machine learning algorithm can improve the adaptability of the algorithm and the accuracy of site planning; establishing a complete communication site planning process from data collection, data analysis, solution output to solution execution can realize the automated planning of the number and location of communication sites, greatly improving planning efficiency.

[0120] Figure 8 FIG. 1 is a schematic diagram showing a structure of an embodiment of a communication site planning device of the present invention. Figure 8 As shown, the communication site planning device includes: a rasterization processing module 310, a weak coverage screening module 320, a first clustering processing module 330, an acquisition module 340 and an output module 350.

[0121] In an optional manner, the grid processing module 310 is used to perform grid processing on the planned area to obtain index data information of each grid, wherein the index data information of the grid at least includes signal strength data, traffic volume data and value data of the grid.

[0122] In an optional manner, the rasterization processing module 310 further includes a first acquisition unit 311 , a first calculation unit 312 , a second acquisition unit 313 and a second calculation unit 314 .

[0123] The first acquisition unit 311 is used to acquire the sampling point data of the precise positioning system in the planned area when it is determined that each grid has the sampling point data of the precise positioning system. The first calculation unit 312 is used to calculate the index data information of the grid according to the sampling point data of the precise positioning system.

[0124] The second acquisition unit 313 is used to acquire the simulation signal strength data of each grid in the simulation planning system when it is determined that there is no accurately located sampling point data for each grid. The second calculation unit 314 is used to calculate the index data information of the grid according to the simulation signal strength data of the grid.

[0125] In an optional manner, the weak coverage screening module 320 is used to perform weak coverage screening on the grid.

[0126] In an optional manner, the first clustering processing module 330 is used to perform a first clustering process on the grid after the weak coverage screening to obtain a planning demand cluster in the area to be planned.

[0127] In an optional manner, the acquisition module 340 is used to respectively acquire the number of demand sites of each planned demand cluster. The acquisition module 340 further includes a third acquisition unit 341, a normalization processing unit 342, and a third calculation unit 343. The third acquisition unit 341 is used to acquire the value coefficient of each planned demand cluster, the normalization processing unit 342 is used to normalize the value coefficient of each planned demand cluster, and the third calculation unit 343 is used to calculate the number of demand sites of each planned demand cluster according to the value coefficient of each planned demand cluster after normalization.

[0128] In an optional manner, the normalization processing unit 342 is also used to obtain the maximum and minimum values ​​of the value coefficients of each planning demand cluster; calculate the normalization coefficient based on the maximum and minimum values; and obtain the normalized value coefficients of each planning demand cluster based on the normalization coefficient.

[0129] In an optional manner, the third calculation unit 343 is also used to obtain parameter information of each planned demand cluster and coverage indicators of communication sites respectively; the number of required sites of each planned demand cluster is calculated by combining the parameter information, coverage indicators and the value coefficient of each planned demand cluster after normalization.

[0130] In an optional manner, the output module 350 is used to output the planned location of each demand site in the planned demand cluster. And the output module 350 further includes a fourth acquisition unit 351, a second clustering processing unit 352 and a fifth acquisition unit 353. Among them, the fourth acquisition unit 351 is used to obtain the longitude and latitude of the first center point of the area where the planned demand cluster is located when it is determined that the number of demand sites in the planned demand cluster is equal to 1, so as to use the longitude and latitude of the first center point as the planned location of the demand site in the planned demand cluster. The second clustering processing unit 352 is used to perform a second clustering process on each grid in the planned demand cluster to form a plurality of sub-clusters when it is determined that the number of demand sites in the planned demand cluster is greater than 1. The fifth acquisition unit 353 is used to respectively obtain the longitude and latitude of multiple second center points in the areas where the multiple sub-clusters are located, so as to use the longitude and latitude of the multiple second center points as the planned locations of the demand sites in the planned demand cluster.

[0131] In the above implementation mode, by rasterizing the planned area and combining the indicator parameters of the grid, the scientificity and rationality of the communication site selection can be improved; combining with a customized machine learning algorithm can improve the adaptability of the algorithm and the accuracy of site planning; establishing a complete communication site planning process from data collection, data analysis, solution output to solution execution can realize the automated planning of the number and location of communication sites, greatly improving planning efficiency.

[0132] Fig. 9 The schematic diagram of the structure of the communication site planning device embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the communication site planning device.

[0133] like Fig. 9 As shown, the communication site planning device may include: a processor (processor) 402, a communication interface (Communications Interface) 404, a memory (memory) 406, and a communication bus 408.

[0134] Wherein: the processor 402, the communication interface 404, and the memory 406 communicate with each other through the communication bus 408. The communication interface 404 is used to communicate with other devices such as a client or other server network elements. The processor 402 is used to execute the program 409, which can specifically execute the relevant steps in the above-mentioned embodiment of the planning method for 5G site.

[0135] Specifically, the program 409 may include program codes, which include computer-executable instructions.

[0136] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the communication site planning device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0137] The memory 406 is used to store the program 409. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0138] Program 409 may be specifically called by processor 402 to enable the communication station device to perform the following operations:

[0139] The planned area is rasterized to obtain the index data information of each grid; the grids are weakly covered; the grids after weakly covered are first clustered to obtain the planned demand clusters in the planned area; the number of demand sites in each planned demand cluster is obtained respectively; and the planned location of each demand site in the planned demand cluster is output.

[0140] For the specific implementation of each step in this embodiment, please refer to the specific description of step 100 to step 500 in the above embodiment, which will not be repeated here.

[0141] In the above implementation mode, by rasterizing the planned area and combining the index parameters of the grid, the scientificity and rationality of the communication site selection can be improved; combining with a customized machine learning algorithm can improve the adaptability of the algorithm and the accuracy of site planning; establishing a complete communication site planning process from data collection, data analysis, solution output to solution execution can realize the automated planning of the number and location of communication sites, greatly improving planning efficiency.

[0142] An embodiment of the present invention provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is executed on a communication site planning device / apparatus, the communication site planning device / apparatus executes the communication site planning method in any of the above-mentioned method embodiments.

[0143] The executable instructions may be specifically used to enable the communication site planning device / apparatus to perform the following operations:

[0144] The planning area is rasterized to obtain the index data information of each grid; the grids are weakly covered; the grids after weak coverage screening are clustered to obtain the planning demand clusters in the planning area; the number of demand sites of each planning demand cluster is obtained respectively; and the planning position of each demand site in the planning demand cluster is output according to the number of demand sites.

[0145] For the specific implementation of each step in this embodiment, please refer to the specific description of step 100 to step 500 in the above embodiment, which will not be repeated here.

[0146] In the above implementation mode, by rasterizing the planned area and combining the indicator parameters of the grid, the scientificity and rationality of the communication site selection can be improved; combining with a customized machine learning algorithm can improve the adaptability of the algorithm and the accuracy of site planning; establishing a complete communication site planning process from data collection, data analysis, solution output to solution execution can realize the automated planning of the number and location of communication sites, greatly improving planning efficiency.

[0147] An embodiment of the present invention provides a communication site planning device, which is used to execute the above communication site planning method.

[0148] An embodiment of the present invention provides a computer program, which can be called by a processor to enable a communication site planning device to execute the communication site planning method in any of the above method embodiments.

[0149] An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed on a computer, the computer executes the communication site planning method in any of the above method embodiments.

[0150] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other equipment. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description made to specific languages ​​above is for disclosing the best mode of the present invention.

[0151] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0152] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0153] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0154] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0155] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for planning a communication site, characterized in that: The planning method includes: The area to be planned is subjected to rasterization processing. When it is determined that each grid has sampling point data of precise positioning, the sampling point data of the precise positioning system in the area to be planned is obtained, and the index data information of the grid is calculated according to the sampling point data of the precise positioning system; when it is determined that each grid does not have sampling point data of precise positioning, the simulation signal strength data of each grid in the simulation planning system is obtained, and the index data information of the grid is calculated according to the simulation signal strength data of the grid; Performing weak coverage screening on the grid; Performing a first clustering process on the grid after weak coverage screening to obtain a planning demand cluster in the area to be planned; Obtaining the value coefficient of each of the planned demand clusters; normalizing the value coefficient of each of the planned demand clusters; calculating the number of demand sites of each of the planned demand clusters according to the value coefficient of each of the planned demand clusters after normalization; wherein the value coefficient is the value per unit area of ​​each of the planned demand clusters divided by the value per unit area of ​​the entire area to be planned; When it is determined that the number of demand sites in the planned demand cluster is equal to 1, the longitude and latitude of the first center point of the area where the planned demand cluster is located is obtained, and the longitude and latitude of the first center point is used as the planned position of the demand site in the planned demand cluster; when it is determined that the number of demand sites in the planned demand cluster is greater than 1, a second clustering process is performed on each of the grids in the planned demand cluster to form a plurality of sub-clusters; and the longitudes and latitudes of the plurality of second center points of the areas where the plurality of sub-clusters are located are respectively obtained, and the plurality of second center point longitudes and latitudes are used as the planned positions of the demand sites in the planned demand cluster.

2. The planning method according to claim 1, characterized in that: The normalizing the value coefficients of the planning demand clusters further includes: Obtaining the maximum and minimum values ​​of the value coefficients of each of the planning demand clusters; Calculating the normalization coefficient according to the maximum value and the minimum value; The normalized value coefficient of each of the planned demand clusters is calculated according to the normalization coefficient.

3. The planning method according to claim 1, characterized in that: Calculating the number of demand sites of each planned demand cluster according to the value coefficient of each planned demand cluster after normalization further includes: Respectively obtain parameter information of each of the planned demand clusters and coverage indicators of the communication site; wherein the parameter information at least includes the area, number of resident users and income of each of the planned demand clusters; the coverage indicator at least includes the coverage area and the number of carried users; The number of demand sites of each planned demand cluster is calculated by combining the parameter information, the coverage index and the value coefficient of each planned demand cluster after the normalization process.

4. The planning method according to claim 1, characterized in that: The indicator data information of the grid includes at least signal strength data, traffic volume data and value data of the grid.

5. A communication site planning device, characterized in that: The planning device comprises: A rasterization processing module is used to perform rasterization processing on the area to be planned. When it is determined that each grid has accurately positioned sampling point data, the sampling point data of the accurate positioning system in the area to be planned is obtained, and the index data information of the grid is calculated based on the sampling point data of the accurate positioning system; when it is determined that each grid does not have accurately positioned sampling point data, the simulation signal strength data of each grid in the simulation planning system is obtained, and the index data information of the grid is calculated based on the simulation signal strength data of the grid; A weak coverage screening module, used for performing weak coverage screening on the grid; A first clustering processing module, used for performing a first clustering processing on the grid after the weak coverage screening, so as to obtain a planning demand cluster in the area to be planned; An acquisition module is used to acquire the value coefficient of each of the planned demand clusters; normalize the value coefficient of each of the planned demand clusters; and calculate the number of demand sites of each of the planned demand clusters according to the value coefficient of each of the planned demand clusters after normalization; wherein the value coefficient is the value per unit area of ​​each of the planned demand clusters divided by the value per unit area of ​​the entire area to be planned; The output module is used to obtain the longitude and latitude of the first center point of the area where the planned demand cluster is located when it is determined that the number of demand sites in the planned demand cluster is equal to 1, so as to use the longitude and latitude of the first center point as the planned position of the demand site in the planned demand cluster; when it is determined that the number of demand sites in the planned demand cluster is greater than 1, perform a second clustering process on each of the grids in the planned demand cluster to form a plurality of sub-clusters; and respectively obtain the longitude and latitude of the plurality of second center points of the areas where the plurality of sub-clusters are located, so as to use the plurality of second center point longitudes and latitudes as the planned positions of the demand sites in the planned demand cluster.

6. A communication site planning device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of the communication site planning method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction. When the executable instruction is executed on the communication site planning device / apparatus, the communication site planning device / apparatus executes the operation of the communication site planning method as described in any one of claims 1 to 4.

Images