Base station site selection method, device, computer equipment and storage medium

Abstract

The present application relates to the field of communication technologies, and particularly to a method, apparatus, computer device, and storage medium for base station site selection. The method includes: obtaining historical weak coverage grid data corresponding to a target area in a plurality of historical time periods; obtaining a current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to a target historical time period among the plurality of historical time periods; performing prediction processing on the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each historical time period to obtain a future second weak coverage area of the target area; and determining a target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area. The present application can improve the effectiveness and accuracy of base station site selection.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a base station site selection method, apparatus, computer device, and storage medium. Background Art

[0002] Network quality is the lifeline of communication enterprises, and good coverage is the basic guarantee for providing good network quality. To achieve the balance between resource investment and network coverage, accurately discovering the black holes in network coverage and precisely locating base stations have always been difficult problems in planning and construction.

[0003] In traditional technologies, weak coverage grid data is used for base station site selection, that is, correlation analysis is performed on the current problem grids with weak coverage, and the efficiency of pre-planned site selection can be improved through contiguous processing.

[0004] However, each base station has a capacity limit, the number of connected terminals will affect the network quality of the base station, the network speed perception will be poor in crowded places, and due to the influence of industrial transfer, road traffic planning, etc., the aggregation distribution of people will gradually change. Therefore, it may lead to the situation that the previously selected base station locations cannot adapt to the changes in network access traffic in the future. Summary of the Invention

[0005] Based on this, it is necessary to provide a base station site selection method, apparatus, computer device, and storage medium that can improve the effectiveness and accuracy of base station site selection for the above technical problems.

[0006] In a first aspect, this application provides a base station site selection method, and the method includes:

[0007] Obtain historical weak coverage grid data corresponding to a target area in multiple historical periods respectively;

[0008] According to the historical weak coverage grid data corresponding to a target historical period among the multiple historical periods, obtain the current first weak coverage area of the target area;

[0009] Perform prediction processing on the weak coverage areas of the target area according to the historical weak coverage grid data corresponding to each of the historical periods, to obtain the future second weak coverage area of the target area;

[0010] Determine a target site selection area of a base station in the target area according to the first weak coverage area and the second weak coverage area.

[0011] In one embodiment, obtaining the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to a target historical period among the multiple historical periods includes:

[0012] Perform clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtain the first weak coverage area according to the static clustering result.

[0013] In one embodiment, the static clustering result includes the clustering center and clustering range of each static clustering cluster; the obtaining of the first weak coverage area according to the static clustering result includes:

[0014] Determine the first weak coverage grid corresponding to each static clustering cluster according to the clustering center and clustering range of each static clustering cluster;

[0015] Determine the first weak coverage area according to the first weak coverage grid corresponding to each static clustering cluster.

[0016] In one embodiment, the predicting the weak coverage area of the target area based on the historical weak coverage grid data corresponding to each of the historical periods to obtain the second future weak coverage area of the target area includes:

[0017] Perform clustering processing on the historical weak coverage grid data corresponding to each of the historical periods respectively to obtain the dynamic clustering results corresponding to each of the historical periods, and obtain the historical weak coverage areas corresponding to each of the historical periods according to the dynamic clustering results corresponding to each of the historical periods;

[0018] Predict the weak coverage area of the target area based on the historical weak coverage areas corresponding to each of the historical periods to obtain the second weak coverage area.

[0019] In one embodiment, the dynamic clustering result includes the clustering center and clustering range of each dynamic clustering cluster; the obtaining of the historical weak coverage areas corresponding to each of the historical periods according to the dynamic clustering results corresponding to each of the historical periods includes:

[0020] Determine the historical weak coverage grid corresponding to each of the historical periods according to the clustering center and clustering range of the dynamic clustering clusters corresponding to each of the historical periods;

[0021] Determine the historical weak coverage areas corresponding to each of the historical periods according to the historical weak coverage grid corresponding to each of the historical periods.

[0022] In one embodiment, the predicting the weak coverage area of the target area based on the historical weak coverage areas corresponding to each of the historical periods to obtain the second weak coverage area includes:

[0023] According to the future prediction period, select, from the historical weak coverage areas corresponding to each of the historical periods, the historical weak coverage area corresponding to the future prediction period as the second weak coverage area obtained by predicting the weak coverage area of the target area.

[0024] In one embodiment, the determining the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area includes:

[0025] Determine the overlapping area between the first weak coverage area and the second weak coverage area;

[0026] Determine the target site selection area of the base station within the target area according to the overlapping area.

[0027] In one embodiment, the historical weak coverage grid data corresponding to the target historical period is that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

[0028] In a second aspect, the present application further provides a base station site selection device, and the device includes:

[0029] An acquisition module, configured to acquire historical weak coverage grid data corresponding to a target area in multiple historical periods;

[0030] A static analysis module, configured to obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in the multiple historical periods;

[0031] A dynamic prediction module, configured to perform prediction processing on the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each of the historical periods, to obtain the future second weak coverage area of the target area;

[0032] A site selection module, configured to determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area.

[0033] In a third aspect, the present application further provides a computer device, and the computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Acquire historical weak coverage grid data corresponding to a target area in multiple historical periods;

[0035] Obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in the multiple historical periods;

[0036] Predictively process the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each of the historical time periods, to obtain the future second weak coverage area of the target area;

[0037] Determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area.

[0038] Fourthly, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0039] Obtain the historical weak coverage grid data corresponding to the target area in multiple historical time periods respectively;

[0040] Obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical time period among the multiple historical time periods;

[0041] Predictively process the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each of the historical time periods, to obtain the future second weak coverage area of the target area;

[0042] Determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area.

[0043] Fifthly, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] Obtain the historical weak coverage grid data corresponding to the target area in multiple historical time periods respectively;

[0045] Obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical time period among the multiple historical time periods;

[0046] Predictively process the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each of the historical time periods, to obtain the future second weak coverage area of the target area;

[0047] Determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area.

[0048] The above base station site selection method, device, computer equipment and storage medium. The first weak coverage area is the weak coverage area currently existing in the target area obtained by analyzing the historical weak coverage grid data corresponding to the target historical period; the second weak coverage area is the weak coverage area that may exist in the future in the target area predicted according to the historical weak coverage grid data corresponding to each historical period. Therefore, according to the first weak coverage area and the second weak coverage area, determining the target site selection area of the base station in the target area can make the target site selection area take into account the current weak coverage grid distribution and the possible weak coverage grid distribution in the future. While improving the current weak coverage problem in the target area, it reduces the possibility of the increase or spread of future weak coverage grids, ensuring network quality. Therefore, the effectiveness and accuracy of base station site selection are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 FIG. is an application environment diagram of the base station site selection method in an embodiment;

[0050] Figure 2 FIG. is a flowchart of the base station site selection method in an embodiment;

[0051] Figure 3 FIG. is a flowchart of determining the second weak coverage area in an embodiment;

[0052] Figure 4 FIG. is a flowchart of determining the target site selection area in an embodiment;

[0053] Figure 5 FIG. is a flowchart of the base station site selection method in another embodiment;

[0054] Figure 6 FIG. is a structural block diagram of the base station site selection device in an embodiment;

[0055] Figure 7 FIG. is an internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The base station site selection method provided by the embodiments of the present application can be applied to such as Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 obtains the historical weak coverage grid data corresponding to the target area in multiple historical periods from the terminal 102, and obtains the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in the multiple historical periods; according to the historical weak coverage grid data corresponding to each historical period, performs prediction processing on the weak coverage area of the target area to obtain the future second weak coverage area of the target area; determines the target site selection area of the base station in the target area according to the first weak coverage area and the second weak coverage area. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0058] In one embodiment, as Figure 2 shown, a base station site selection method is provided. Taking the server 104 in Figure 1 as an example, the method includes the following steps:

[0059] S201, obtain the historical weak coverage grid data corresponding to the target area in multiple historical periods.

[0060] Among them, the target area can be an area selected from a map or an area selected according to the administrative division method. In this embodiment, in order to improve the recognition accuracy of the weak coverage area, the target area can be determined in a high-precision map, and the target area is divided into grids. The grid size of the target area can be set according to actual needs.

[0061] It can be understood that weak coverage means that the area that the base station needs to cover is large, the distance between base stations is too large, or the signal in the boundary area is weak due to building occlusion. In the weak coverage area, the overall quality of the network is not high. When the user is in the weak coverage area, it will directly affect the user experience. When determining the historical weak coverage grid, in one implementable manner, the historical weak coverage grid can be determined manually by statistically analyzing the signal evaluation information (measurement report, MR) or signaling data of the base station or cell; in another implementable manner, the historical weak coverage grid can be determined by methods such as drive test. Optionally, the historical weak coverage grid data in this embodiment may include: the position, number, (network) signal strength, etc. of the historical weak coverage grid in the target area.

[0062] Among them, the multiple historical periods corresponding to the target area can be multiple discontinuous time periods or multiple continuous time periods. Optionally, the multiple historical periods in this embodiment are multiple discontinuous time periods. For example, each historical period can be: January 2021, July 2021, January 2022, July 2022, etc. Further, the time interval between each selected historical period in this embodiment is 6 months. The reason is that for the target area, the historical weak coverage grid data within half a year may not change significantly. Therefore, in order to reduce the amount of data processing and data analysis, for example, the data in January 2021 can be used to measure the data for the 6 months from January 2021 to June 2021.

[0063] S202. Obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in multiple historical periods.

[0064] Among them, assuming that the base station site selection moment is the current moment, the target historical period in the multiple historical periods is the time period closest to the current moment. For example, if the current moment is August 2022, the target historical period is July 2022, which is the closest to August 2022. It can be understood that the historical weak coverage grid data corresponding to the target historical period is that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

[0065] In this embodiment, by analyzing the historical weak coverage grid data in July 2022, the weak coverage distribution situation (i.e., the first weak coverage area) within the current target area can be obtained. When selecting a base station site, a base station can be established based on the position of the first weak coverage area within the target area to solve the current weak coverage distribution problem within the target area.

[0066] Specifically, when analyzing the historical weak coverage grid data corresponding to the target historical period to obtain the current first weak coverage area of the target area, statistical methods or artificial intelligence models can be used. The purpose is to perform statistical analysis on the historical weak coverage grid data to obtain the first weak coverage area.

[0067] S203. Perform prediction processing on the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each historical period to obtain the future second weak coverage area of the target area.

[0068] It can be understood that for the target area, the historical weak coverage grid data corresponding to different historical periods may be different. The reasons for the differences in the historical weak coverage grid data include factors such as industrial transfer, road traffic planning, and population aggregation distribution. Therefore, the historical weak coverage grid data of the same target area changes over time. That is, the historical weak coverage grid data of the same target area is a set of data arranged in chronological order. Mining this set of data can obtain the law of change of the historical weak coverage grid data over time.

[0069] Furthermore, by analyzing this change law, that is, analyzing the historical weak coverage grid data corresponding to each historical period, it is possible to predict the law of change of the possible future weak coverage grid data in the target area within the future time period starting from the current moment. That is, the analysis step of predicting the weak coverage area in the target area is realized, and the second weak coverage area in the future of the target area is obtained through the prediction process.

[0070] Specifically, this prediction process can adopt a dynamic analysis algorithm for analyzing time series data. By using the dynamic analysis algorithm to analyze the historical weak coverage grid data arranged in chronological order corresponding to the same target area, the second weak coverage area that may exist in the target area within the future time period can be obtained. For example, if the future time period is August 2023, the second weak coverage area that may appear within the time span of 12 months starting from the current moment (August 2022) can be analyzed at this time.

[0071] S204. Determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area.

[0072] It can be understood that the above-mentioned first weak coverage area is the area with weak coverage grids currently existing analyzed based on the current weak coverage grid distribution, and the above-mentioned second weak coverage area is the area where weak coverage grids may exist in the future predicted based on the historical weak coverage grid distribution.

[0073] Specifically, when determining the target site selection area, the target site selection area of the base station within the target area can be determined according to the weight ratio (influence degree) between the first weak coverage area and the second weak coverage area, or by selecting the intersection or union of the first weak coverage area and the second weak coverage area, etc., so that the target site selection area can take into account the current weak coverage grid distribution and the possible future weak coverage grid distribution.

[0074] In the above base station site selection method, the first weak coverage area is the weak coverage area currently existing in the target area analyzed based on the historical weak coverage grid data corresponding to the target historical period; the second weak coverage area is the weak coverage area that may exist in the future in the target area predicted based on the historical weak coverage grid data corresponding to each historical period; therefore, according to the first weak coverage area and the second weak coverage area, determining the target site selection area of the base station in the target area can make the target site selection area take into account the current weak coverage grid distribution and the possible weak coverage grid distribution in the future, while improving the current weak coverage problem in the target area, reducing the possibility of the increase or spread of future weak coverage grids, ensuring the network quality, and therefore improving the effectiveness and accuracy of base station site selection.

[0075] In one embodiment, this embodiment provides an optional way to obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in multiple historical periods, that is, provides a way to refine S202. The specific implementation process may include: performing clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtaining the first weak coverage area according to the static clustering result.

[0076] It can be understood that clustering is a data mining technique that groups similar data into related or homogeneous groups without prior knowledge of the group definition. Specifically, a clustering cluster is formed by grouping objects that have the greatest similarity to other objects within the group and the least similarity to objects in other groups. In this embodiment, mainly the information of the signal strength dimension in each historical weak coverage grid data is mined; specifically, this embodiment uses a static clustering algorithm to perform clustering processing on the historical weak coverage grid data corresponding to the target historical period.

[0077] Exemplarily, the static clustering algorithms include: K-Nearest Neighbor (KNN) classification algorithm, weighted K-Nearest Neighbor (WKNN) algorithm, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, and hierarchical clustering algorithm, etc.

[0078] It can be understood that density-based clustering algorithms perform clustering based on the density of data sets in spatial distribution, without the need to preset the number of clustering clusters in advance. Therefore, it is particularly suitable for clustering data sets with unknown content. Different from hierarchical clustering methods, it defines clusters as the largest set of density-connected points, can divide regions with sufficient high density into clusters, and can discover clusters of any shape in a spatial database with "noise". Therefore, in the embodiments of the present invention, the DBSACN algorithm can be used to determine clustering clusters including multiple consecutive historical weak coverage grids. Among them, the DBSACN algorithm involves three parameters, namely the data set, MinPts, and Eps. In this embodiment, the data set is the historical weak coverage grid data within the target historical period, MinPts is a preset condition. For example, the preset condition is that the number of weak coverage grids included within the scanning range is a preset number, and Eps is a preset radius. For example, the preset radius is 2 weak coverage grids.

[0079] Specifically, the specific implementation process of the above DBSACN algorithm is as follows:

[0080] Step1: Take the sample historical weak coverage grid as the central grid and determine the scanning range with the preset radius as the scanning radius;

[0081] Among them, the sample historical weak coverage grid is any one of all the historical weak coverage grids corresponding to the target historical period;

[0082] Step2: Determine whether the number of historical weak coverage grids included within the scanning range meets the preset condition;

[0083] Step3: If the number of historical weak coverage grids included within the scanning range meets the preset condition, the computer generates a clustering cluster of historical weak coverage grids (i.e., a static clustering cluster) according to the historical weak coverage grids included within the scanning range;

[0084] Step4: Determine whether there is a historical weak coverage grid that has not been used as the central grid in the clustering cluster. If so, use this historical weak coverage grid as the sample historical weak coverage grid and continue to execute Step1. Otherwise, stop.

[0085] Therefore, the static clustering result obtained through the above static clustering algorithm can include the clustering centers and clustering ranges of each static clustering cluster.

[0086] Optionally, the first weak coverage area obtained according to the static clustering result in this embodiment may include multiple consecutive historical weak coverage grids, and the discrete historical weak coverage grids are removed. Optionally, obtaining the first weak coverage area according to the static clustering result includes: determining the first weak coverage grids corresponding to each static clustering cluster according to the clustering center and clustering range of each static clustering cluster; and determining the first weak coverage area according to the first weak coverage grids corresponding to each static clustering cluster.

[0087] Specifically, for any static clustering cluster, the union of the first weak coverage grids corresponding to the static clustering cluster is determined as the first weak coverage sub-area corresponding to the static clustering cluster, and then, according to each first weak coverage sub-area, the first weak coverage area is determined, where the first weak coverage sub-areas may not be continuous.

[0088] As Figure 3 shown, this embodiment provides an optional method for predicting the weak coverage area of the target area based on the historical weak coverage grid data corresponding to each historical period, so as to obtain the second weak coverage area in the future of the target area, that is, a method for refining S203 is provided.

[0089] S301, perform clustering processing on the historical weak coverage grid data corresponding to each historical period respectively to obtain the dynamic clustering results corresponding to each historical period, and obtain the historical weak coverage areas corresponding to each historical period according to the dynamic clustering results corresponding to each historical period.

[0090] It can be understood that the above static clustering algorithm performs independent clustering analysis on a certain data sample (such as the historical weak coverage grid data within the target historical period), and does not contain any time information. The historical weak coverage grid data corresponding to each historical period is a set of dynamic data that changes over time. The characteristic of dynamic data compared to static data is that it adds an extra time dimension. If the entire historical weak coverage grid data corresponding to each historical period is clustered as a whole, the characteristics of the historical weak coverage grid data changing over time cannot be reflected; therefore, in order to further explore the dynamic evolution properties of the historical weak coverage grid data and predict the distribution of weak coverage grids that may exist in the target area in the future, this embodiment uses a dynamic clustering algorithm to perform clustering processing on the historical weak coverage grid data corresponding to each historical period respectively.

[0091] Optionally, the dynamic clustering algorithm adopted in this embodiment may include: the improved k-means algorithm (Dynamic clustering of data with modified k-means algorithm[C]Proceedings of the 2012 conference on information and computer networks), DCC (a framework for dynamic granular clustering), ant colony stream clustering (Ant colony stream clustering: A fast density clustering algorithm for dynamic data streams), and dynamic clustering based on region-based collaborative clustering (A region-based collaborative management scheme for dynamic clustering in green vanet).

[0092] Exemplarily, the clustering process of the dynamic clustering algorithm is described as follows:

[0093] Sep10. Load predefined parameters, obtain target data, and initialize clusters.

[0094] It can be understood that when the first batch of data arrives, initial clusters need to be generated.

[0095] Among them, the target data is the historical weak coverage grid data corresponding to each historical period in this embodiment; the first batch of data can be the historical weak coverage grid data corresponding to January 2021 above. Specifically, when initializing the clusters, the above-mentioned static clustering algorithm or other methods can be used to generate initial clusters (also called the dynamic clustering clusters of the target data).

[0096] Sep20. Cluster the new target data to generate new clusters.

[0097] As shown in the above example, the new target data can be the historical weak coverage grid data corresponding to July 2021 above, and the clustering clusters obtained by clustering the historical weak coverage grid data corresponding to July 2021 are defined as new clusters.

[0098] Sep30. Merge the new clusters and the old clusters to obtain the dynamic clustering clusters corresponding to the new target data;

[0099] Among them, the old clusters refer to the clusters that existed before the new clusters were generated.

[0100] Therefore, the dynamic clustering clusters corresponding to July 2021 are obtained based on the dynamic clustering clusters in January 2021 and the new clusters in July 2021. And so on. (1) The dynamic clustering clusters corresponding to January 2022 are obtained based on the dynamic clustering clusters in January 2021, the dynamic clustering clusters in July 2021, and the new clusters in January 2022; (2) The dynamic clustering clusters corresponding to July 2022 are obtained based on the dynamic clustering clusters in January 2021, the dynamic clustering clusters in July 2021, the dynamic clustering clusters in January 2022, and the new clusters in July 2021.

[0101] As can be seen from the above, the dynamic clustering clusters corresponding to each historical period are all obtained based on the clustering results of each historical period before this historical period and the historical weak coverage grid data corresponding to this historical period itself. Therefore, the dynamic clustering clusters corresponding to each historical period can represent the distribution law of the historical weak coverage grid data in this historical period and all the periods before this historical period.

[0102] It can be understood that each dynamic clustering cluster obtained in this embodiment corresponds to a clustering center and a clustering range. Correspondingly, when determining the historical weak coverage areas corresponding to each historical period, the following process can be included: determining the historical weak coverage grids corresponding to each historical period according to the clustering centers and clustering ranges of the dynamic clustering clusters corresponding to each historical period; determining the historical weak coverage areas corresponding to each historical period according to the historical weak coverage grids corresponding to each historical period.

[0103] Specifically, for any dynamic clustering cluster, the union of the historical weak coverage grids corresponding to this dynamic clustering cluster is determined as the historical weak coverage sub-area corresponding to this dynamic clustering cluster, and the historical weak coverage area is determined according to each historical weak coverage sub-area, where the historical weak coverage sub-areas may not be continuous.

[0104] S302. Perform prediction processing on the weak coverage area of the target area according to the historical weak coverage areas corresponding to each historical period to obtain a second weak coverage area.

[0105] Specifically, according to the future prediction period, select the historical weak coverage area corresponding to the future prediction period from the historical weak coverage areas corresponding to each historical period as the second weak coverage area obtained by performing prediction processing on the weak coverage area of the target area.

[0106] Exemplarily, the future prediction period is a time period with a preset time length starting from the current moment; for example, if the future prediction period is 1 year after the current moment, then the historical weak coverage area corresponding to 1 year before the current moment can be selected from the historical weak coverage areas corresponding to each historical period as the second weak coverage area obtained by predicting the weak coverage area of the target area.

[0107] In this embodiment, by performing dynamic clustering analysis on the historical weak coverage grid data corresponding to each historical period, the second weak coverage area can accurately represent the area where weak coverage grids may exist in the target area during the future prediction period.

[0108] As Figure 4 shown, this embodiment provides an optional way to determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area, that is, a way to refine S204.

[0109] S401, determine the overlapping area between the first weak coverage area and the second weak coverage area.

[0110] Exemplarily, the first weak coverage area of the target area: Area A, Area B, Area C, and the second weak coverage area of the target area: Area B, Area C, Area D, then Area C is the overlapping area between the first weak coverage area and the second weak coverage area.

[0111] S402, determine the target site selection area of the base station within the target area according to the overlapping area.

[0112] Specifically, the overlapping area is determined as the target site selection area of the base station.

[0113] In this embodiment, by integrating the first weak coverage area and the second weak coverage area and focusing on the overlapping area of the two clustering clusters, when selecting the base station site, tilting the planning for the overlapping area can not only alleviate the current weak coverage problem in the target area, but also prepare in advance for possible future network quality hidden dangers.

[0114] Exemplarily, on the basis of the above embodiment, this embodiment provides an optional example of a base station site selection method. As Figure 5 shown, the specific implementation process includes:

[0115] S501, obtain the historical weak coverage grid data corresponding to the target area in multiple historical periods.

[0116] S502, perform clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result.

[0117] Among them, the static clustering result includes the clustering center and clustering range of each static clustering cluster.

[0118] S503. Determine the first weakly covered grid corresponding to each static clustering cluster according to the clustering center and clustering range of each static clustering cluster.

[0119] S504. Determine the first weakly covered area according to the first weakly covered grid corresponding to each static clustering cluster.

[0120] S505. Perform clustering processing on the historical weakly covered grid data corresponding to each historical time period respectively to obtain the dynamic clustering results corresponding to each historical time period.

[0121] Among them, the dynamic clustering result includes the clustering center and clustering range of each dynamic clustering cluster.

[0122] S506. Determine the historical weakly covered grid corresponding to each historical time period according to the clustering center and clustering range of the dynamic clustering cluster corresponding to each historical time period.

[0123] S507. Determine the historical weakly covered area corresponding to each historical time period according to the historical weakly covered grid corresponding to each historical time period.

[0124] S508. According to the future prediction time period, select the historical weakly covered area corresponding to the future prediction time period from the historical weakly covered areas corresponding to each historical time period as the second weakly covered area obtained by predicting the weakly covered area of the target area.

[0125] S509. Determine the overlapping area between the first weakly covered area and the second weakly covered area.

[0126] S5010. Determine the target site selection area of the base station in the target area according to the overlapping area.

[0127] The specific processes of the above S501 - S5010 can refer to the description of the above method embodiments, and their implementation principles and technical effects are similar, so they will not be elaborated here.

[0128] In this embodiment, the static clustering algorithm and the dynamic clustering algorithm are used to analyze the weak coverage grid data of the current (target historical period) and the weak coverage grid data of each historical period. The former locates the area where the weak coverage situation needs to be improved urgently, and the latter captures the distribution change trend of weak coverage and finds out the area where the weak coverage situation is serious in the future; the site selection planning is carried out in combination with the current status and development trend of base station signal coverage, while improving the current weak coverage problem, reducing the possibility of increasing or spreading weak coverage grids in the future, and ensuring network quality. In addition, the land resources for base stations are becoming increasingly tight, and planning the site selection in advance is conducive to operators taking the lead, so as to avoid the lack of suitable sites in the future to erect large equipment such as steel pipe towers and single-pole towers, and the weak coverage grid data of historical base stations can avoid data waste and improve the utilization rate of data.

[0129] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0130] Based on the same inventive concept, the embodiment of the present application also provides a base station site selection device for implementing the base station site selection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more base station site selection device embodiments provided below can refer to the limitations on the base station site selection method above, and will not be repeated here.

[0131] In one embodiment, Figure 6 As shown, a base station site selection device 1 is provided, comprising: an acquisition module 11, a static analysis module 12, a dynamic prediction module 13 and a site selection module 14, wherein:

[0132] An acquisition module 11 is used to acquire historical weak coverage grid data corresponding to a target area in multiple historical time periods;

[0133] A static analysis module 12, configured to obtain a current first weak coverage area of a target area according to historical weak coverage grid data corresponding to a target historical period in a plurality of historical periods;

[0134] The dynamic prediction module 13 is configured to perform prediction processing on the weak coverage area of the target area based on the historical weak coverage grid data corresponding to each historical period, so as to obtain the second weak coverage area of the target area in the future;

[0135] The site selection module 14 is configured to determine the target site selection area of the base station in the target area according to the first weak coverage area and the second weak coverage area.

[0136] In one embodiment, the static analysis module 12 is further configured to: perform clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtain the first weak coverage area according to the static clustering result.

[0137] In one embodiment, the static clustering result includes the clustering center and clustering range of each static clustering cluster; the static analysis module 12 is further configured to: determine the first weak coverage grid corresponding to each static clustering cluster according to the clustering center and clustering range of each static clustering cluster;

[0138] Determine the first weak coverage area according to the first weak coverage grid corresponding to each static clustering cluster.

[0139] In one embodiment, the dynamic prediction module 13 includes:

[0140] The dynamic clustering sub-module is configured to perform clustering processing on the historical weak coverage grid data corresponding to each historical period respectively to obtain the dynamic clustering results corresponding to each historical period respectively, and obtain the historical weak coverage areas corresponding to each historical period respectively according to the dynamic clustering results corresponding to each historical period respectively;

[0141] The prediction sub-module is configured to perform prediction processing on the weak coverage area of the target area according to the historical weak coverage areas corresponding to each historical period respectively, so as to obtain the second weak coverage area.

[0142] In one embodiment, the dynamic clustering sub-module is further configured to: determine the historical weak coverage grid corresponding to each historical period respectively according to the clustering center and clustering range of the dynamic clustering cluster corresponding to each historical period respectively;

[0143] Determine the historical weak coverage area corresponding to each historical period respectively according to the historical weak coverage grid corresponding to each historical period respectively.

[0144] In one embodiment, the prediction sub-module is further configured to: select the historical weak coverage area corresponding to the future prediction period from the historical weak coverage areas corresponding to each historical period respectively as the second weak coverage area obtained by performing prediction processing on the weak coverage area of the target area.

[0145] In one embodiment, the site selection module 14 is further configured to: determine an overlapping area between a first weak coverage area and a second weak coverage area;

[0146] Determine a target site selection area of the base station within the target area according to the overlapping area.

[0147] In one embodiment, the historical weak coverage grid data corresponding to the target historical period is such that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

[0148] Each module in the above base station site selection device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0149] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data of the base station site selection method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a base station site selection method is implemented.

[0150] Those skilled in the art can understand that Figure 7 the structure shown in

[0151] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0152] Obtain the historical weak coverage grid data respectively corresponding to the target area in multiple historical periods;

[0153] Obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in the multiple historical periods;

[0154] Based on the historical weak coverage grid data corresponding to each historical period, perform prediction processing on the weak coverage area of the target area to obtain the second weak coverage area of the target area in the future;

[0155] Based on the first weak coverage area and the second weak coverage area, determine the target site selection area of the base station within the target area.

[0156] In one embodiment, when the processor executes the computer program to obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in multiple historical periods, the following steps are specifically implemented: perform clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtain the first weak coverage area according to the static clustering result.

[0157] In one embodiment, the static clustering result includes the clustering center and clustering range of each static clustering cluster; when the processor executes the computer program to obtain the first weak coverage area according to the static clustering result, the following steps are specifically implemented: determine the first weak coverage grid corresponding to each static clustering cluster according to the clustering center and clustering range of each static clustering cluster; determine the first weak coverage area according to the first weak coverage grid corresponding to each static clustering cluster.

[0158] In one embodiment, when the processor executes the computer program to perform prediction processing on the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each historical period to obtain the second weak coverage area of the target area in the future, the following steps are specifically implemented: perform clustering processing on the historical weak coverage grid data corresponding to each historical period respectively to obtain the dynamic clustering results corresponding to each historical period, and obtain the historical weak coverage areas corresponding to each historical period according to the dynamic clustering results corresponding to each historical period; perform prediction processing on the weak coverage area of the target area according to the historical weak coverage areas corresponding to each historical period to obtain the second weak coverage area.

[0159] In one embodiment, the dynamic clustering result includes the clustering center and clustering range of each dynamic clustering cluster; when the processor executes the computer program to obtain the historical weak coverage areas corresponding to each historical period according to the dynamic clustering results corresponding to each historical period, the following steps are specifically implemented: determine the historical weak coverage grid corresponding to each historical period according to the clustering center and clustering range of the dynamic clustering cluster corresponding to each historical period; determine the historical weak coverage area corresponding to each historical period according to the historical weak coverage grid corresponding to each historical period.

[0160] In one embodiment, when the processor executes a computer program to predict the weak coverage area of the target area according to the historical weak coverage areas corresponding to each historical period and obtain the logic of the second weak coverage area, the following steps are specifically implemented: According to the future prediction period, select the historical weak coverage area corresponding to the future prediction period from the historical weak coverage areas corresponding to each historical period as the second weak coverage area obtained by predicting the weak coverage area of the target area.

[0161] In one embodiment, when the processor executes a computer program to determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area, the following steps are specifically implemented: Determine the overlapping area between the first weak coverage area and the second weak coverage area; Determine the target site selection area of the base station within the target area according to the overlapping area.

[0162] In one embodiment, the historical weak coverage grid data corresponding to the target historical period is that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

[0163] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0164] Obtain the historical weak coverage grid data corresponding to the target area in multiple historical periods;

[0165] According to the historical weak coverage grid data corresponding to the target historical period in multiple historical periods, obtain the current first weak coverage area of the target area;

[0166] According to the historical weak coverage grid data corresponding to each historical period, perform prediction processing on the weak coverage area of the target area to obtain the future second weak coverage area of the target area;

[0167] According to the first weak coverage area and the second weak coverage area, determine the target site selection area of the base station within the target area.

[0168] In one embodiment, when the logic that the computer program obtains the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period in multiple historical periods is executed by the processor, the following steps are specifically implemented: Perform clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtain the first weak coverage area according to the static clustering result.

[0169] In one embodiment, the static clustering result includes the clustering centers and clustering ranges of the static clustering clusters; when the logic that the computer program obtains the first weak coverage area according to the static clustering result is executed by the processor, the following steps are specifically implemented: according to the clustering centers and clustering ranges of the static clustering clusters, determine the first weak coverage grids corresponding to the static clustering clusters; according to the first weak coverage grids corresponding to the static clustering clusters, determine the first weak coverage area.

[0170] In one embodiment, when the logic that the computer program performs prediction processing on the weak coverage area of the target area according to the historical weak coverage grid data corresponding to each historical period to obtain the second weak coverage area in the future of the target area is executed by the processor, the following steps are specifically implemented: perform clustering processing on the historical weak coverage grid data corresponding to each historical period respectively to obtain the dynamic clustering results corresponding to each historical period, and obtain the historical weak coverage areas corresponding to each historical period according to the dynamic clustering results corresponding to each historical period; according to the historical weak coverage areas corresponding to each historical period, perform prediction processing on the weak coverage area of the target area to obtain the second weak coverage area.

[0171] In one embodiment, the dynamic clustering result includes the clustering centers and clustering ranges of the dynamic clustering clusters; when the logic that the computer program obtains the historical weak coverage areas corresponding to each historical period according to the dynamic clustering results corresponding to each historical period is executed by the processor, the following steps are specifically implemented: according to the clustering centers and clustering ranges of the dynamic clustering clusters corresponding to each historical period, determine the historical weak coverage grids corresponding to each historical period; according to the historical weak coverage grids corresponding to each historical period, determine the historical weak coverage areas corresponding to each historical period.

[0172] In one embodiment, when the logic that the computer program performs prediction processing on the weak coverage area of the target area according to the historical weak coverage areas corresponding to each historical period to obtain the second weak coverage area is executed by the processor, the following steps are specifically implemented: according to the future prediction period, select the historical weak coverage area corresponding to the future prediction period from the historical weak coverage areas corresponding to each historical period as the second weak coverage area obtained by performing prediction processing on the weak coverage area of the target area.

[0173] In one embodiment, when the logic that the computer program determines the target site selection area of the base station in the target area according to the first weak coverage area and the second weak coverage area is executed by the processor, the following steps are specifically implemented: determine the overlapping area between the first weak coverage area and the second weak coverage area; according to the overlapping area, determine the target site selection area of the base station in the target area.

[0174] In one embodiment, the historical weak coverage grid data corresponding to the target historical period is such that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

[0175] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the following steps:

[0176] Obtain the historical weak coverage grid data respectively corresponding to a target area in multiple historical periods;

[0177] Obtain the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period among the multiple historical periods;

[0178] Perform prediction processing on the weak coverage areas of the target area according to the historical weak coverage grid data respectively corresponding to each historical period, to obtain the future second weak coverage area of the target area;

[0179] Determine the target site selection area of the base station within the target area according to the first weak coverage area and the second weak coverage area.

[0180] In one embodiment, when the logic that the computer program obtains the current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to the target historical period among the multiple historical periods is executed by the processor, the following steps are specifically implemented: perform clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtain the first weak coverage area according to the static clustering result.

[0181] In one embodiment, the static clustering result includes the clustering centers and clustering ranges of each static clustering cluster; when the logic that the computer program obtains the first weak coverage area according to the static clustering result is executed by the processor, the following steps are specifically implemented: determine the first weak coverage grids corresponding to each static clustering cluster according to the clustering centers and clustering ranges of each static clustering cluster; determine the first weak coverage area according to the first weak coverage grids corresponding to each static clustering cluster.

[0182] In one embodiment, when the logic that the computer program performs prediction processing on the weak coverage areas of the target area according to the historical weak coverage grid data respectively corresponding to each historical period to obtain the future second weak coverage area of the target area is executed by the processor, the following steps are specifically implemented: perform clustering processing on the historical weak coverage grid data respectively corresponding to each historical period to obtain the dynamic clustering results respectively corresponding to each historical period, and obtain the historical weak coverage areas respectively corresponding to each historical period according to the dynamic clustering results respectively corresponding to each historical period; perform prediction processing on the weak coverage areas of the target area according to the historical weak coverage areas respectively corresponding to each historical period, to obtain the second weak coverage area.

[0183] In one embodiment, the dynamic clustering result includes the clustering center and the clustering range of each dynamic clustering cluster; when the logic of obtaining the historical weak coverage area corresponding to each historical period according to the dynamic clustering result corresponding to each historical period is executed by a processor, the following steps are specifically implemented: determining the historical weak coverage grid corresponding to each historical period according to the clustering center and the clustering range of the dynamic clustering cluster corresponding to each historical period; determining the historical weak coverage area corresponding to each historical period according to the historical weak coverage grid corresponding to each historical period.

[0184] In one embodiment, when the logic of the computer program for predicting the weak coverage area of the target area according to the historical weak coverage area corresponding to each historical period to obtain the second weak coverage area is executed by a processor, the following steps are specifically implemented: selecting, according to the future prediction period, the historical weak coverage area corresponding to the future prediction period from the historical weak coverage areas corresponding to each historical period as the second weak coverage area obtained by predicting the weak coverage area of the target area.

[0185] In one embodiment, when the logic of the computer program for determining the target site selection area of the base station in the target area according to the first weak coverage area and the second weak coverage area is executed by a processor, the following steps are specifically implemented: determining the overlapping area between the first weak coverage area and the second weak coverage area; determining the target site selection area of the base station in the target area according to the overlapping area.

[0186] In one embodiment, the historical weak coverage grid data corresponding to the target historical period is that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

[0187] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0188] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0189] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for base station site selection, characterized in that, The method includes: Obtaining historical weak coverage grid data corresponding to a target area in multiple historical periods respectively; Obtaining a current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to a target historical period among the multiple historical periods; Performing clustering processing on the historical weak coverage grid data corresponding to each of the historical periods respectively to obtain dynamic clustering results corresponding to each of the historical periods, obtaining historical weak coverage areas corresponding to each of the historical periods according to the dynamic clustering results corresponding to each of the historical periods; predicting the weak coverage area of the target area according to the historical weak coverage areas corresponding to each of the historical periods to obtain a second weak coverage area; Determining a target site selection area of a base station within the target area according to the first weak coverage area and the second weak coverage area.

2. The method according to claim 1, wherein The obtaining a current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to a target historical period among the multiple historical periods includes: Performing clustering processing on the historical weak coverage grid data corresponding to the target historical period to obtain a static clustering result, and obtaining the first weak coverage area according to the static clustering result.

3. The method according to claim 2, wherein The static clustering result includes the clustering center and clustering range of each static clustering cluster; the obtaining the first weak coverage area according to the static clustering result includes: Determining first weak coverage grids corresponding to each static clustering cluster according to the clustering center and clustering range of each static clustering cluster; Determining the first weak coverage area according to the first weak coverage grids corresponding to each static clustering cluster.

4. The method according to claim 1, wherein The dynamic clustering result includes the clustering center and clustering range of each dynamic clustering cluster; the obtaining historical weak coverage areas corresponding to each of the historical periods according to the dynamic clustering results corresponding to each of the historical periods includes: Determining historical weak coverage grids corresponding to each of the historical periods according to the clustering center and clustering range of the dynamic clustering clusters corresponding to each of the historical periods; Determining historical weak coverage areas corresponding to each of the historical periods according to the historical weak coverage grids corresponding to each of the historical periods.

5. The method according to claim 1, characterized in that The predicting the weak coverage area of the target area according to the historical weak coverage areas corresponding to each of the historical periods to obtain the second weak coverage area includes: Selecting, according to a future prediction period, a weak coverage area corresponding to the future prediction period from the historical weak coverage areas corresponding to each of the historical periods as the second weak coverage area obtained by predicting the weak coverage area of the target area.

6. The method according to any one of claims 1 to 5, characterized in that, The determining a target site selection area of a base station within the target area according to the first weak coverage area and the second weak coverage area includes: Determining an overlapping area between the first weak coverage area and the second weak coverage area; Determining the target site selection area of the base station within the target area according to the overlapping area.

7. The method according to claim 1, characterized in that, The historical weak coverage grid data corresponding to the target historical period is that the historical moment corresponding to the historical weak coverage grid data falls within the target historical period.

8. A base station site selection device, characterized in that The device includes: An acquisition module, configured to acquire historical weak coverage grid data corresponding to a target area in multiple historical periods; A static analysis module, configured to obtain a current first weak coverage area of the target area according to the historical weak coverage grid data corresponding to a target historical period among the multiple historical periods; A dynamic prediction module, including a dynamic clustering sub-module and a prediction sub-module; wherein, the dynamic clustering sub-module is configured to perform clustering processing on the historical weak coverage grid data corresponding to each historical period respectively, to obtain dynamic clustering results corresponding to each historical period respectively, and obtain historical weak coverage areas corresponding to each historical period respectively according to the dynamic clustering results corresponding to each historical period respectively; the prediction sub-module is configured to perform prediction processing on the weak coverage area of the target area according to the historical weak coverage areas corresponding to each historical period respectively, to obtain a second weak coverage area; A site selection module, configured to determine a target site selection area of a base station within the target area according to the first weak coverage area and the second weak coverage area; 9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images