CN111918298A

CN111918298A - Clustering-based site planning method and device, electronic equipment and storage medium

Info

Publication number: CN111918298A
Application number: CN202010795633.1A
Authority: CN
Inventors: 高智涛; 朱光军; 祁彭泳; 任阔; 王辉; 李雪雷; 庞松涛; 杨丁一; 赵雪莹; 王玲敏
Original assignee: Henan Information Consulting Design And Research Co ltd
Current assignee: Henan Information Consulting Design And Research Co ltd
Priority date: 2020-08-10
Filing date: 2020-08-10
Publication date: 2020-11-10
Anticipated expiration: 2040-08-10
Also published as: CN111918298B

Abstract

The embodiment of the application provides a clustering-based site planning method and device, electronic equipment and a storage medium, and relates to the field of equipment management of mobile communication. The site planning method comprises the following steps: acquiring raster data obtained after rasterization processing is carried out on data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of sampling points; clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid; and taking the planning site to be determined matched with the planning requirement of the user as a target site. Compared with the traditional manual site planning, the site planning method provided by the application can reduce manpower, greatly improve the work efficiency of network analysis and site planning, simultaneously save the expenses of cost of a notebook computer, data analysis software and the like, and reduce the limit on personnel capacity.

Description

Clustering-based site planning method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of device management for mobile communications, and in particular, to a method and an apparatus for site planning based on clustering, an electronic device, and a storage medium.

Background

The existing site planning is mainly manual operation, workers use a notebook computer in combination with data analysis software to analyze network coverage data of operators, and meanwhile, manually add planning sites and add information such as site names, site positions, site longitude and latitude and the like for the planning sites.

The existing site planning is based on manual analysis and has the following defects: the number of workers to be invested is large: 3 workers are usually needed to complete the planning of 1 operator in 1 second-line city, and 5 workers are needed in the first-line city; the work efficiency is low: generally, 1 week is needed for completing the planning of 1 operator in 1 city, and when large data volume analysis is carried out, longer time is often needed due to the performance limitation of a notebook computer; the resource investment is large: each worker needs to configure a notebook computer, analysis software and the like to complete data analysis.

Disclosure of Invention

In view of the above, an object of the present application is to provide a method, an apparatus, an electronic device and a storage medium for site planning based on clustering.

In order to achieve the above purpose, the embodiments of the present application employ the following technical solutions:

in a first aspect, an embodiment of the present application provides a method for site planning based on clustering, where the method includes: acquiring raster data obtained after rasterization processing is carried out on data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of the sampling points; clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid; and taking the planning site to be determined matched with the planning requirement of the user as a target site.

In an optional embodiment, the preset clustering parameters include grid topic information, a first clustering window and a preset grid threshold; clustering the grid data according to preset clustering parameters to obtain a planned site to be determined, wherein the method comprises the following steps: acquiring a plurality of first clustering grids matched with the grid thematic information in the grid data; sliding the first clustering window, and judging whether the first number of the first clustering grids in the first clustering window is greater than or equal to the preset grid threshold; if the first number is smaller than the preset grid threshold, marking a first clustering grid in the first clustering window as a discrete clustering grid; if the first number is larger than or equal to the preset grid threshold, marking the first clustering grid in the first clustering window as a dense clustering grid, and acquiring the planning site to be determined according to all the dense clustering grids.

In an optional embodiment, the preset clustering parameters further include a second clustering window and a preset clustering ratio threshold, where the second clustering window is larger than the first clustering window; acquiring the planning site to be determined according to all the dense clustering grids, wherein the acquiring comprises the following steps: sliding the second clustering window, and judging whether the dense grid ratio of the second clustering window is greater than or equal to the preset clustering ratio threshold; wherein the dense grid ratio is a ratio of the number of dense clustering grids to a total number of grids in the second clustering window, the total number of grids being a sum of the number of discrete clustering grids and the number of dense clustering grids; and if the dense grid ratio is greater than or equal to the preset clustering occupation ratio threshold, taking the clustering center of the second clustering window as the planning site to be determined.

In an optional embodiment, the step of taking the planning site to be determined, which matches with the planning requirement of the user, as a target site includes: determining the grid attribute of a target clustering window according to the planning requirement; fusing second clustering windows corresponding to the plurality of planning sites to be determined according to the grid attributes to obtain target clustering windows and clustering area boundaries; and taking the clustering center of the target clustering window as a target site in the boundary of the clustering area.

In an optional embodiment, acquiring raster data obtained by rasterizing data to be planned includes: deleting invalid data in the data to be planned to obtain first data; the invalid data is data reported by mistake when the data to be planned is decoded; and rasterizing the first data to acquire the raster data.

In an alternative embodiment, the method further comprises: adding key information to the target site; the key information includes site names, location information, and the number of clustering grids.

In a second aspect, an embodiment of the present application provides a site planning apparatus based on clustering, where the apparatus includes: the acquiring module is used for acquiring raster data obtained by rasterizing the data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of the sampling points; the processing module is used for clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid; the processing module is further used for taking the planning site to be determined matched with the planning requirement of the user as a target site.

In an optional embodiment, the preset clustering parameters include grid topic information, a first clustering window and a preset grid threshold; the processing module is further used for acquiring a plurality of first clustering grids matched with the grid thematic information in the grid data; the processing module is further configured to slide the first clustering window, and determine whether a first number of first clustering grids in the first clustering window is greater than or equal to the preset grid threshold; the processing module is further configured to mark a first clustering grid in the first clustering window as a discrete clustering grid if the first number is smaller than the preset grid threshold; the processing module is further configured to mark the first clustering grid in the first clustering window as a dense clustering grid if the first number is greater than or equal to the preset grid threshold, and obtain the planned site to be determined according to all the dense clustering grids.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the method of any one of the foregoing embodiments.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method of any one of the foregoing embodiments.

Compared with the prior art, the embodiment of the application provides a site planning method and device based on clustering, electronic equipment and a storage medium, and relates to the field of equipment management of mobile communication. The site planning method comprises the following steps: acquiring raster data obtained after rasterization processing is carried out on data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of the sampling points; clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid; and taking the planning site to be determined matched with the planning requirement of the user as a target site. Compared with the traditional manual site planning, the site planning method provided by the application can reduce manpower, greatly improve the work efficiency of network analysis and site planning, simultaneously save the expenses of cost of a notebook computer, data analysis software and the like, and reduce the limit on personnel capacity.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic flowchart of a site planning method based on clustering according to an embodiment of the present application;

fig. 2 is a schematic flow chart of another clustering-based site planning method according to an embodiment of the present application;

fig. 3 is a schematic flow chart of another clustering-based site planning method according to an embodiment of the present application;

fig. 4 is a schematic flowchart of another method for planning a site based on clustering according to an embodiment of the present application;

FIG. 5 is a clustering diagram of a mean-shift clustering algorithm;

fig. 6 is a schematic flow chart of another clustering-based site planning method according to an embodiment of the present application;

fig. 7 is a schematic flowchart of another method for planning a site based on clustering according to an embodiment of the present application;

fig. 8 is a thematic map layer output according to RSRP coverage mean attribute value in the embodiment of the present application;

FIG. 9 is a schematic view of a sliding window provided in an embodiment of the present application;

FIG. 10 is a schematic view of a grid marker provided in an embodiment of the present application;

fig. 11 is a schematic diagram of a clustering region provided in an embodiment of the present application;

fig. 12 is a schematic diagram of another clustering region provided in the embodiment of the present application;

fig. 13 is a schematic diagram of a clustering result of a site plan according to an embodiment of the present application;

fig. 14 is a schematic diagram of another clustering region provided in the embodiment of the present application;

fig. 15 is a schematic block diagram of a station planning apparatus according to an embodiment of the present application;

fig. 16 is a block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

In order to solve at least the drawbacks of the background art, an embodiment of the present application provides a method for planning a site based on clustering, please refer to fig. 1, where fig. 1 is a schematic flow diagram of the method for planning a site based on clustering according to the embodiment of the present application, and the method for planning a site may include the following steps:

and S31, acquiring raster data obtained by rasterizing the data to be planned.

The data to be planned is sampling points of a layout site, and the grid data is a grid including a plurality of sampling points. For example, The data to be planned may be ott (over The top) data acquired through an "internet big data analysis platform", and The grid data may be processed according to grids of two sizes, 38m × 19m and 25m × 25m, or may be adjusted according to actual requirements of site planning.

It should be understood that, in one possible embodiment, the above S31 may include: deleting invalid data in the data to be planned to acquire first data, wherein the invalid data is data reporting errors when the data to be planned is decoded; the first data is rasterized to obtain raster data. For example, original OTT data (data to be planned) is filtered, invalid data in the OTT data is deleted, the filtered OTT data is imported into an "internet OTT big data analysis platform", and original point data is rasterized, and the "internet OTT big data analysis platform" supports 2 raster forms, which are respectively: the GeoHash code grid 38m 19m and the regular grid 25m in order to rasterize the OTT data to obtain the grid data.

And S32, clustering the grid data according to the preset clustering parameters to obtain the planning site to be determined.

The planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid. It should be understood that, in the site planning method for the communication industry, a scene, a site coverage radius, the number of clustering samples and the like need to be considered comprehensively, and meanwhile, with the continuous expansion of the network building scale of the communication network, the above conditions need to support dynamic adjustment, and the preset clustering parameters can be adjusted according to different scenes, site coverage radii and the like so as to obtain the planned site to be determined.

And S33, taking the planning site to be determined matched with the planning requirement of the user as a target site.

It should be understood that, in order to implement the planning of the target site, the site planning method may further include: and adding key information for the target site. The key information may include, but is not limited to, site name, location information, number of clustering grids, and the like. It is foreseeable that, in order to adapt to different planning requirements of users, the key information of the target site may also be edited, such as site name modification, longitude and latitude change, and the like.

It should be noted that, for different service cells or scenes, the communication networks required by the devices are different, and the actual requirements of the users are different, so that different planning requirements are generated, and the site to be planned is matched with the planning requirements of the users to obtain the target site meeting the actual planning requirements.

In an optional embodiment, in order to obtain a to-be-determined planned site, on the basis of fig. 1, taking an example that a preset clustering parameter includes grid topic information, a first clustering window, and a preset grid threshold, please refer to fig. 2, where fig. 2 is a schematic flow diagram of another site planning method based on clustering provided in an embodiment of the present application, where the above-mentioned S32 may include:

s321, obtaining a plurality of first clustering grids matched with the grid thematic information in the grid data.

For example, the grid topic information may include, but is not limited to, five topics including Reference Signal Receiving Power (RSRP) coverage mean, RSRP weak coverage ratio, sampling density, value area, and weak coverage area of 2/3/4/5G network Reference Signal Receiving Power (RSRP) of each operator in the communication industry.

S322, sliding the first clustering window, and judging whether the first number of the first clustering grids in the first clustering window is larger than or equal to a preset grid threshold.

The first clustering window can be set to be square, the side length of the square can be customized according to requirements, for example, the side length of the square is set to be any value within 50-200m, the preset grid threshold can be set to be 10, and the preset grid threshold can be set according to actual requirements. In one possible embodiment, the sliding first clustering window may be: moving the grid to the right (38m) in sequence from the top left corner vertex position of the area to be planned as the starting position to the rightmost side boundary, wherein the grid moves to the right (vertical position is unchanged) one grid width (38m) at a time in the horizontal direction; after the boundary reaches the rightmost side, the sliding window starts from the left side boundary again, moves downwards in the vertical direction by one grid height (19m) as a starting point, and shifts rightmost sequentially; sequentially moving downwards to the lowest boundary of the region in the vertical direction; and finally, the sliding window is shifted to the end of the lower right corner of the area.

If the first number is smaller than the preset grid threshold, executing S323; if the first number is greater than or equal to the predetermined grid threshold, S324 is performed.

And S323, marking the first clustering grid in the first clustering window as a discrete clustering grid.

It should be understood that the smaller the number of first clustering grids in the first clustering window, the more dispersed the first clustering grids are, and thus, they are labeled as discrete clustering grids. For example, according to the preset clustering parameter setting, in a square filtering window (first clustering window) of 190m × 190m, there is a total space of 50 grids in the filtering window range (first clustering window), if the number of grids in the filtering window (first clustering window) is less than 10, the number of grids in the region is considered to be less, the grid samples in the region are determined to be discrete samples, and the grids are defined as discrete clustering grids.

And S324, marking the first clustering grid in the first clustering window as a dense clustering grid, and acquiring the planning site to be determined according to all the dense clustering grids.

It should be understood that, in the polling calculation process of the sliding first clustering window, the number of grids in the first clustering window may be recorded, each first clustering window in the area to be planned is sorted according to the number of grids, and the center point of the sliding window of the grid number sorting draft may be used as the starting point position for acquiring the site to be determined.

In an optional embodiment, on the basis of fig. 2, in order to obtain a planned site to be determined, taking as an example that the preset clustering parameters further include a second clustering window and a preset clustering ratio threshold, where the second clustering window is larger than the first clustering window, please refer to fig. 3, where fig. 3 is a schematic flow diagram of another site planning method based on clustering provided in the embodiment of the present application, where the above S324 may include:

s3241, sliding the second cluster window, and judging whether the dense grid ratio of the second cluster window is larger than or equal to a preset cluster occupation ratio threshold.

And the dense grid ratio is the ratio of the number of dense clustering grids to the total number of grids in the second clustering window, and the total number of grids is the sum of the number of discrete clustering grids and the number of dense clustering grids. For example, the preset cluster occupancy threshold may be set to 30%.

If the dense grid ratio is greater than or equal to the preset clustering ratio threshold, executing S3242; if the dense grid ratio is smaller than the preset clustering ratio threshold, S3243 is performed.

And S3242, taking the cluster center of the second cluster window as a planning site to be determined.

It should be understood that when clustering is performed on the second clustering window, the grids that have been accessed may be marked as "accessed" and belonging to the same clustering region until all grids in the region to be planned are marked as "accessed" state. For example, the process of obtaining the clustering center may be to determine a "clustering center" of the clustering region when the clustering region corresponding to the second clustering window is used, and the calculation method of the "clustering center" may be a center longitude and latitude average value of dense grids in the clustering region.

S3243, it is determined that the grid in the current region corresponding to the second cluster window is marked as "noise".

In the site planning work, the concerned region is a region where target grids (dense clustering grids) are gathered, the site planning needs to be carried out on the region where the target grids (dense clustering grids) reach a certain number, and for the sporadic target grids (dense clustering grids), secondary filtering needs to be carried out, and the clustering of the site planning region is not involved; after filtering the discrete clustering grids, marking target grids (dense clustering grids) meeting conditions (preset clustering grid ratio threshold) as effective grids, setting a corresponding grid clustering threshold and a merging threshold of a clustering area according to working requirements, and finally completing clustering analysis of effective grid data (dense clustering grids) so as to take the clustering center of a second clustering window as a planning site to be determined.

In an alternative embodiment, in order to obtain a target site, a possible implementation is given on the basis of fig. 1, please refer to fig. 4, fig. 4 is a flowchart of another method for planning a site based on clustering according to an embodiment of the present application, and the above S33 may include:

and S331, determining the grid attribute of the target clustering window according to the planning requirement.

For example, in actual OTT data, an "internet OTT big data analysis platform" outputs different special data according to specific attributes, such as: outputting the RSRP mean coverage topic of each communication operator 2/3/4/5G network according to the RSRP mean in the grid attribute; outputting a special problem of the density of the sampling points according to the quantity of the sampling points in the grid attribute; outputting a weak coverage proportion topic according to the proportion of the RSRP < -105dbm sampling points in the grid attribute to the total sampling points; meanwhile, there are other "weak coverage topics", "value area topics", "convergence service topics", "network competition versus topics", "broadband topics", and "terminal topics", etc.

And S332, fusing second clustering windows corresponding to the plurality of to-be-determined planning sites according to the grid attributes to obtain a target clustering window and a clustering area boundary.

For example, the boundary of the clustering region may be an irregular polygon, the line width, color and transparency of the polygon may be modified, and the target clustering window is a target clustering region meeting the planning requirements of the user.

And S333, taking the clustering center of the target clustering window as a target site in the clustering area boundary.

The planning site information of the target site may include key information such as site name, longitude and latitude, clustering grid number, and the like, and meanwhile, the planning site is supported to be edited, for example: site name modification, longitude and latitude change and the like.

In order to facilitate understanding of the site planning method provided by the foregoing embodiment, the present application provides a possible specific embodiment: the existing site planning is based on manual analysis, and a clustering analysis technology is not applied to the site planning, because the existing clustering technology is not suitable for being applied to the site planning work, the reasons are as follows:

first, clustering analysis, also called cluster analysis, is a statistical analysis method for studying (sample or index) classification problems, and is also an important algorithm for data mining. Clustering (Cluster) analysis is composed of several patterns (patterns), which are typically vectors of a metric (measure) or a point in a multidimensional space. Cluster analysis is based on similarity, with more similarity between patterns in one cluster than between patterns not in the same cluster.

The clustering algorithm is an algorithm related to grouping data in machine learning: in a given data set, the electronic device may divide it into several different groups by a clustering algorithm. In theory, data in the same group has the same attribute or characteristic, and the attribute or characteristic of data in different groups is greatly different. The existing cluster analysis mainly has the following modes: K-Means clustering, mean shift clustering, density-based clustering method (DBSCAN).

It should be noted that the K-means has the disadvantage that the number of clusters to be clustered must be determined first; ideally, for a clustering algorithm, for a target problem, the clustering algorithm aims to obtain some insights from data; the k-means starts with randomly selecting a clustering center, so it is possible to produce different clustering results in different runs of the algorithm; therefore, the results of K-means clustering are not reproducible and lack consistency.

As shown in fig. 5, fig. 5 is a clustering diagram of a mean shift clustering algorithm, which has a disadvantage that the selection of the sliding window size/radius "r" needs to be considered carefully; the following problems exist in an internet OTT big data analysis platform: (1) using a mean shift clustering algorithm, points outside the target area of the set A, B, C shown in fig. 2 cannot be filtered, and these discrete points are considered as invalid points in the internet OTT big data analysis platform and do not need to be clustered; (2) the points in the special area 1 are considered to belong to the set B and the points in the special area 2 belong to the set C, which is determined by the radius r, and the actual requirement in the internet OTT big data analysis platform is to draw the points in the special area 1 and the special area 2 into the set a, because the points are "connected areas" from the set a in a visual sense.

The biggest disadvantage of DBSCAN is that when the density of clusters varies, the threshold of distance and minPoints for determining neighbor points will also change, which also occurs in very high dimensional data, as the distance threshold becomes difficult to estimate.

That is, the existing clustering technology cannot realize: (1) filtering zero star points on the edge of the clustering area; (2) changing the size of the clustering area according to the scene and the requirement; (3) and generating a frame for the clustering area to form a closed area, wherein the clustering area cannot have an overlapping condition.

In contrast, with the site planning method provided in the embodiment of the present application, please refer to fig. 6, where fig. 6 is a schematic flow chart of another cluster-based site planning method provided in the embodiment of the present application, and the site planning method may include the following steps:

a1, OTT data preparation: and filtering the original OTT data, deleting invalid data, and importing the filtered OTT data into an Internet OTT data analysis platform to prepare for subsequent analysis.

A2, OTT data rasterization processing: rasterization processing is carried out on original point data, and an internet OTT big data analysis platform supports 2 grid forms, which are respectively as follows: a GeoHash code grid 38m 19m and a regular grid 25 m.

A3, selecting clustering analysis topics: the internet OTT data analysis platform supports cluster analysis on five topics including an 2/3/4/5G network RSRP coverage mean value, an RSRP weak coverage ratio, sampling density, a value area, a weak coverage area and the like of operators in the communication industry at present.

A4, setting cluster analysis conditions: and setting parameters such as a convergence target grid, a primary convergence range, the number of primary convergence grids, a secondary convergence range, a merging area range, a grid ratio and the like.

A5, area convergence: and performing cluster analysis according to the related cluster analysis parameters set in the process A4 to generate a convergence result of the cluster analysis. And if the region convergence result meets the planning requirement, outputting the result, and if the region convergence result does not meet the planning requirement, modifying the clustering analysis condition setting to finish region convergence again.

A6, outputting a target site planning result: and outputting the area convergence result to finish the automatic output of the planning base station.

For the above processes corresponding to A3-a 5, please refer to fig. 7, where fig. 7 is a schematic flow chart of another clustering-based site planning method provided in the embodiment of the present application, and a new clustering algorithm flow in the present application is introduced by taking a GeoHash code grid 38m × 19m as an example for description.

i. Screening grids meeting the conditions: in the process of screening the grids meeting the condition, a, screening the clustering target grids according to the grid attributes needs to be finished. In the application process of the Internet OTT data analysis platform, the screening work of the clustering target grid is completed according to the special subject attributes in the first step. As shown in fig. 8, fig. 8 is a thematic map layer output according to RSRP coverage mean attribute values in the embodiment of the present application, where (a) in fig. 8 totals grid data of types 4, and assuming that a grid with RSRP < -105dbm is a target grid that needs to be subjected to cluster analysis, in a first step of cluster analysis, first step of data screening is performed according to conditions, and a screening result is shown in (b) in fig. 8.

After the first data screening is finished, taking the grid data meeting the screening condition as 'clustering grid' data, and carrying out subsequent clustering analysis; and taking the grid data which does not meet the screening condition as a non-clustering grid.

And the non-clustering grid is used as the denominator data of the total quantity of grids in the flow of ' e ' and setting the grid clustering proportion threshold ' and does not participate in the presentation of the final grid clustering result.

ii. Filtering the discrete grid: in the process of filtering the discrete grid, 2 filtering conditions need to be set, which are respectively: b. setting the size of a discrete grid filtering window, c, and setting a discrete grid filtering quantity threshold.

The filtering windows in the filtering condition ' b ' and the size of the discrete grid filtering window ' are set to be square, and the side length of the square can be customized according to requirements. Since the process focuses on deleting discrete points, the recommended configuration of the filtering window is 50m-200m, and the specific configuration can be set according to the size of the grid.

The threshold value in the filtering condition "c" and the threshold value of the discrete grid filtering quantity is an integer larger than or equal to 1, the numerical value can be customized according to requirements, and the specific configuration can be configured according to the grid size and the filtering window.

For example: b. setting the discrete grid filter window size to "190 m by 190 m";

c. the discrete grid filter number threshold is set to "10".

According to the above filtering condition setting, in a square filtering window of 190m × 190m, there is a total space of 50 grids within the filtering window, if the number of grids in the filtering window is less than 10, the number of grids in the region is considered to be less, the grid samples in the region are determined to be discrete samples, and the grids are defined as discrete grids. Referring to fig. 9, fig. 9 is a schematic view of a sliding window according to an embodiment of the present application, where (a): sequentially sliding for one grid width in the horizontal direction by taking the fixed point at the upper left corner as a starting point, and keeping the grid width unchanged in the vertical direction until the boundary at the rightmost side is finished; (b) the method comprises the following steps And moving downwards by one grid height in the vertical direction, and sequentially sliding by one grid width in the horizontal direction until the rightmost boundary is finished.

In the process of the sliding window polling calculation, all grid data are marked in sequence and are respectively marked as 2 types of discrete clustering grids and dense clustering grids. Referring to fig. 10, fig. 10 is a schematic diagram of a grid marker provided in the embodiment of the present application, in which "dense clustering grid" data is used as target grid data to perform secondary clustering analysis. In the sliding window polling calculation process, the number of grids in the sliding window is recorded, sorting is carried out according to the number of the grids, and the center point of the sliding window with the high-grade grid number is used as the starting point position of the quadratic clustering analysis.

The discrete clustering grid generated in the process participates in the calculation of the number of the clustering grids in the subsequent process of e and setting the grid clustering ratio threshold, and does not participate in the presentation of the final grid clustering result and the drawing of the boundary of the clustering area.

iii, target grid clustering: in the process of filtering the discrete grid, 2 filtering conditions need to be set, which are respectively: d. setting the size of a grid clustering window, e and setting a grid clustering ratio threshold.

Setting a filtering window in the filtering condition'd' and setting the size of a grid clustering window 'as a square, wherein the side length of the square can be customized according to requirements, and suggesting that the value is configured to be more than 100m, and' b 'and setting the size of a discrete grid filtering window', and meanwhile, considering the problem of the coverage capability of a base station in the communication industry, suggesting that the value is configured to be less than or equal to 500 m;

and (3) filtering the condition ' e ', and setting the percentage threshold value in the grid cluster percentage threshold ' as percentage (%), wherein the numerical value can be self-defined according to requirements. For example: b. setting the discrete grid filter window size to "380 m by 380 m"; c. the discrete grid filter number threshold is set to "30%".

The target grid clustering process is as follows: (1) taking the highest-ranking position in the process of filtering the discrete grids according to the 'ii' as a starting point, wherein the size of a filtering window is a square with the side length of 380m, and the grids in the filtering window are taken as target grids; (2) and if the ratio of the number of the target grids in the filtering window to the total grid number is more than or equal to 30%, the clustering process is started, and the target grids in the filtering window become new clustering areas. Otherwise, the grid in the filter window is marked as "noise", and the grid which is already accessed is marked as "accessed"; (3) this process is repeated until all points are marked as visited. All points are visited at the end, and each point is marked as belonging to a clustering area; (4) and after the clustering areas are marked, determining the center of each clustering area, wherein the center calculation method is the average value of the longitude and latitude of the center of the target grid in the clustering area. As shown in fig. 11, fig. 11 is a schematic diagram of a clustering region provided in this embodiment, a region enclosed by a square frame in (a) of fig. 11 is a clustering region determined by a grid, and a pentagon in (b) of fig. 11 is a center of the clustering region, that is, the clustering center described above.

iv, merging clustering areas: and in the merging process of the clustering regions, mainly finishing f and setting the size of a merging window of the clustering regions.

The merging window in the filtering condition ' f ' and the size of the merging window in the clustering area ' is set to be square, the side length of the square can be customized according to requirements, and the value configuration is proposed to combine the coverage scene and the coverage capability of the base station in consideration of the problem of the coverage capability of the base station in the communication industry.

The size of the f and the cluster region merging window can be set to be more than 2 times of the size of the d and the grid cluster window, and adjacent cluster regions can be merged. The merging of the clustering regions can be regarded as clustering in which the center of the clustering region in the process iii is used as a sample point and the window is 'f' and the size of a merging window of the clustering regions is set. The merging principle may be: (1) the areas with the number as much as possible are preferably combined; (2) and if the number of the convergence areas is the same, combining the areas which need to be combined and are closer to the center of the convergence area. Fig. 12 shows a merging result of the clustering regions, fig. 12 is a schematic diagram of another clustering region provided in the embodiment of the present application, fig. 12 (a) is a schematic diagram of a result of clustering a grid, a dotted line is used for determining the clustering regions, and a five-pointed star in fig. 12 (b) is used for determining a clustering center of each sub-clustering region.

v, outputting a target site planning result: and g, finishing the output result process, finishing clustering analysis according to the set conditions, and outputting a grid clustering result and a clustering area boundary.

The output of the clustering analysis result mainly comprises 2 parts: clustering the regional boundary map and automatically generating the planning site. The boundaries of the clustering areas can be irregular polygons, and the line width, color and transparency of the polygons support modification; the planning site information contains key information such as site names, longitude and latitude, clustering grid number and the like, and meanwhile, the planning site is edited, for example: site name modification, longitude and latitude change and the like. As shown in fig. 13, fig. 13 is a schematic diagram of a clustering result of a site planning provided in the embodiment of the present application, which is divided into 3 clustering regions, and each clustering region includes a target planning site.

Compared with the traditional site planning, the site planning method provided by the embodiment of the application can reduce the labor, greatly improve the work efficiency of network analysis and site planning, save the expenses of a notebook computer, data analysis software and the like, and reduce the limit on the capability of personnel. The specific analysis is as follows:

1. the investment of personnel is less: taking site planning workers in a two-line city as an example, 3 planning personnel are needed for completing site planning work of 1 operator, and only 1 planning personnel is needed for completing relevant work in site automatic planning of the site planning method provided by the embodiment of the application in the internet OTT big data analysis platform of our company. The human input is reduced by 66.67 percent.

2. The cost advantage is obvious: under the condition of pure manual operation, not only a large amount of personnel is required to be invested, but also a notebook computer and professional data analysis software are required to be equipped for planning personnel, and under individual conditions, professional operator network test equipment is required to be equipped. Labor cost: 1.2 ten thousand yuan/person/month; cost of notebook computer: 5000 yuan/station; data testing analysis software cost: 4 ten thousand yuan/year. In summary, the site planning work of one operator in a two-line city is completed, and the total investment cost of 1 year is as follows: 1.2 ten thousand yuan by 3 people by 12 months +5000 yuan by 3+4 ten thousand yuan ═ 48.7 ten thousand yuan.

The site planning method provided by the embodiment of the application has the advantages that the site planning can be automatically planned only by configuring 1 planner and 1 notebook computer, the site planning work of one operator in a two-line city is completed, and the total investment cost required in 1 year is as follows: 1.2 ten thousand yuan 1 person 12 month +5000 yuan 14.9 ten thousand yuan.

On the aspect of personnel cost and tool cost, the planning work of one operator in one second-line city can be saved by 33.8 ten thousand yuan for 1 year, and the cost is saved by 69.40%.

3. The efficiency is high: taking site planning workers in a two-line city as an example, site planning work of 1 operator is completed under the condition of pure manual operation, and 3 planners need 6-7 working days to complete. The automatic site planning of the site planning method provided by the embodiment of the application can be completed by only 1 planner in 3 working days. The working efficiency is improved by 6-7 times.

4. The accuracy is high: under the condition of pure manual operation, when a problem area is searched, omission often exists, and an area with poor coverage is ignored and is not included in a site planning scheme. According to the automatic site planning method provided by the embodiment of the application, all grids in the whole planning area can be analyzed according to the conditions set by the planning staff, so that omission does not exist, and the accuracy of searching and site planning of the problem area is higher than that of simple manual operation.

The site planning method provided by the embodiment of the application has various alternatives, and some possible alternatives are given as follows:

1. filtering discrete grid alternatives: in the process of filtering the discrete grids, the site planning method provided in the embodiment of the present application adopts a "grid proportion" form for filtering, as shown in fig. 14, fig. 14 is a schematic diagram of another clustering region provided in the embodiment of the present application: in fig. 14 (a), 64 grid data are counted in the sliding window, and 33 grids satisfying the clustering condition are used, which accounts for 51.56%. If the grid proportion condition is set to 50%, the region (a) of fig. 14 satisfies the clustering condition.

The "grid occupancy ratio" condition in the above-described conditions is that "the number of grids" can be used instead, for example, the condition setting of "the grid occupancy ratio > 50%" is that "the number of grids > 32" can be used instead. Therefore, the site planning method provided by the embodiment of the present application needs to protect the substitution scheme of replacing the grid proportion by the number of grids at the same time:

2. grid size alternatives: the site planning method provided by the embodiment of the present application is mainly used in combination with an "internet OTT big data analysis platform", and is currently restricted by a platform function, the clustering objects in the site planning method provided by the embodiment of the present application are two types of grids, namely, a geo hash code grid 38m 19m and a common grid 25m, and other grid forms, such as 5m, 10m, 20m … …, may be used in other platforms. The site planning method provided by the embodiment of the application needs to protect alternatives with different grid sizes at the same time.

3. Sliding window alternative: considering that the generated raster data is in a square or rectangular format after the OTT data is rasterized by the platform, in order to align the raster boundary and improve the accuracy of the algorithm, the sliding window applied by the site planning method provided by the embodiment of the present application is a "square" sliding window.

As can be seen from fig. 14 (b), if the "square" sliding window is changed to the "circular" sliding window, only the samples of the four corner (gray grid) regions of the square are slightly different, and the final cluster analysis effect is closer. Therefore, the scheme needs to protect the alternative scheme of the square sliding window and the round sliding window at the same time.

In order to implement the site planning method in the foregoing embodiment, an embodiment of the present application provides a site planning apparatus based on clustering, please refer to fig. 15, where fig. 15 is a schematic block diagram of the site planning apparatus provided in the embodiment of the present application, and the site planning apparatus 40 includes: an acquisition module 41 and a processing module 42.

The obtaining module 41 is configured to obtain raster data obtained by rasterizing data to be planned. The data to be planned is sampling points of the arrangement station, and the grid data is a grid comprising a plurality of sampling points. The processing module 42 is configured to cluster the grid data according to a preset clustering parameter to obtain a planned site to be determined. And the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid. The processing module 42 is further configured to use the planning site to be determined, which matches the planning requirement of the user, as the target site.

In an optional embodiment, the preset clustering parameters include grid topic information, a first clustering window, and a preset grid threshold. The processing module 42 is further configured to obtain a plurality of first clustering grids matched with the grid topic information in the grid data. The processing module 42 is further configured to slide the first clustering window, and determine whether a first number of the first clustering grids in the first clustering window is greater than or equal to a preset grid threshold. The processing module 42 is further configured to mark the first clustering grid in the first clustering window as a discrete clustering grid if the first number is smaller than the preset grid threshold. The processing module 42 is further configured to mark the first clustering grid in the first clustering window as a dense clustering grid if the first number is greater than or equal to the preset grid threshold, and obtain a to-be-determined planning site according to all the dense clustering grids.

It should be understood that the obtaining module 41 and the processing module 42 may cooperatively implement the steps corresponding to the site planning method provided in any one of the above embodiments.

An electronic device is provided in an embodiment of the present application, and as shown in fig. 16, fig. 16 is a block schematic diagram of an electronic device provided in an embodiment of the present application. The electronic device 60 comprises a memory 61, a processor 62 and a communication interface 63. The memory 61, processor 62 and communication interface 63 are electrically connected to each other, directly or indirectly, to enable transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 61 may be used to store software programs and modules, such as program instructions/modules corresponding to the site planning method provided in the embodiment of the present application, and the processor 62 executes the software programs and modules stored in the memory 61, so as to execute various functional applications and data processing. The communication interface 63 may be used for communicating signaling or data with other node devices. The electronic device 60 may have a plurality of communication interfaces 63 in this application.

The Memory 61 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.

The processor 62 may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), etc.; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc.

The electronic device 60 may implement any of the site planning methods provided herein. The electronic device 60 may be, but is not limited to, a cell phone, a tablet computer, a notebook computer, a server, or other electronic device with processing capabilities.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In summary, the embodiments of the present application provide a method and an apparatus for site planning based on clustering, an electronic device, and a storage medium, which relate to the field of device management for mobile communications. The site planning method comprises the following steps: acquiring raster data obtained after rasterization processing is carried out on data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of sampling points; clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid; and taking the planning site to be determined matched with the planning requirement of the user as a target site. Compared with the traditional manual site planning, the site planning method provided by the application can reduce manpower, greatly improve the work efficiency of network analysis and site planning, simultaneously save the expenses of cost of a notebook computer, data analysis software and the like, and reduce the limit on personnel capacity.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for cluster-based site planning, the method comprising:

acquiring raster data obtained after rasterization processing is carried out on data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of the sampling points;

clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid;

and taking the planning site to be determined matched with the planning requirement of the user as a target site.

2. The method of claim 1, wherein the preset clustering parameters include grid topic information, a first clustering window, and a preset grid threshold;

clustering the grid data according to preset clustering parameters to obtain a planned site to be determined, wherein the method comprises the following steps:

acquiring a plurality of first clustering grids matched with the grid thematic information in the grid data;

sliding the first clustering window, and judging whether the first number of the first clustering grids in the first clustering window is greater than or equal to the preset grid threshold;

if the first number is smaller than the preset grid threshold, marking a first clustering grid in the first clustering window as a discrete clustering grid;

if the first number is larger than or equal to the preset grid threshold, marking the first clustering grid in the first clustering window as a dense clustering grid, and acquiring the planning site to be determined according to all the dense clustering grids.

3. The method of claim 2, wherein the preset clustering parameters further comprise a second clustering window and a preset clustering percentage threshold, the second clustering window being larger than the first clustering window;

acquiring the planning site to be determined according to all the dense clustering grids, wherein the acquiring comprises the following steps:

sliding the second clustering window, and judging whether the dense grid ratio of the second clustering window is greater than or equal to the preset clustering ratio threshold;

wherein the dense grid ratio is a ratio of the number of dense clustering grids to a total number of grids in the second clustering window, the total number of grids being a sum of the number of discrete clustering grids and the number of dense clustering grids;

and if the dense grid ratio is greater than or equal to the preset clustering occupation ratio threshold, taking the clustering center of the second clustering window as the planning site to be determined.

4. The method of claim 3, wherein targeting the planned site to be determined that matches the user's planning needs comprises:

determining the grid attribute of a target clustering window according to the planning requirement;

fusing second clustering windows corresponding to the plurality of planning sites to be determined according to the grid attributes to obtain target clustering windows and clustering area boundaries;

and taking the clustering center of the target clustering window as a target site in the boundary of the clustering area.

5. The method of claim 1, wherein obtaining raster data that rasterizes data to be planned comprises:

deleting invalid data in the data to be planned to obtain first data; the invalid data is data reported by mistake when the data to be planned is decoded;

and rasterizing the first data to acquire the raster data.

6. The method according to any one of claims 1-5, further comprising:

adding key information to the target site; the key information includes site names, location information, and the number of clustering grids.

7. An apparatus for cluster-based site planning, the apparatus comprising:

the acquiring module is used for acquiring raster data obtained by rasterizing the data to be planned; the data to be planned is sampling points of a layout station, and the grid data is a grid comprising a plurality of the sampling points;

the processing module is used for clustering the grid data according to preset clustering parameters to obtain a planning site to be determined; the planning site to be determined is a clustering center obtained by clustering a plurality of sampling points in the grid;

the processing module is further used for taking the planning site to be determined matched with the planning requirement of the user as a target site.

8. The apparatus of claim 7, wherein the preset clustering parameters comprise grid topic information, a first clustering window, and a preset grid threshold;

the processing module is further used for acquiring a plurality of first clustering grids matched with the grid thematic information in the grid data;

the processing module is further configured to slide the first clustering window, and determine whether a first number of first clustering grids in the first clustering window is greater than or equal to the preset grid threshold;

the processing module is further configured to mark a first clustering grid in the first clustering window as a discrete clustering grid if the first number is smaller than the preset grid threshold;

the processing module is further configured to mark the first clustering grid in the first clustering window as a dense clustering grid if the first number is greater than or equal to the preset grid threshold, and obtain the planned site to be determined according to all the dense clustering grids.

9. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor to perform the method of any one of claims 1 to 6.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 6.