Base station positioning method, device, electronic device and storage medium

Abstract

The present application provides a base station positioning method, apparatus, device and computer program product, including: mapping multiple UE reporting data of the target base station as sampling points to a grid map. Iterative execution: for each frequency band and / or each cell, calculate the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point; based on the variance corresponding to all frequency bands and / or all cells under each grid, determine the average individual variance of each grid and the average overall variance of all grids; remove the sampling points in the grid where the difference between the average individual variance and the average overall variance reaches a preset difference standard. For each cell, cluster calculation is performed on all the sampling points contained in it according to the signal indicator dimension, and the cluster centers of all the cluster clusters contained in it are weighted according to the number of sampling points of the cluster clusters to which they belong, to obtain the zone center of each cell. The zone center of each cell is weighted according to the sampling point density of the cell to which it belongs, to obtain the location of the target base station.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a base station positioning method, apparatus, device and computer program product. Background Art

[0002] The location information of base stations is crucial for the planning and diagnosis of communication networks. Traditional base station positioning methods usually rely on signal strength analysis and require manual measurement of signals near base stations. With the continuous development of communication networks, the density of base stations is getting higher and higher. Due to the influence of various environmental factors, such as terrain and building obstructions, traditional positioning methods based on manual measurement can no longer meet the requirements of high efficiency and high accuracy. Summary of the invention

[0003] The purpose of this application is to provide a base station positioning method, device, equipment and computer program product, which can solve the problems of low accuracy and efficiency of traditional base station positioning methods.

[0004] In order to achieve the above purpose, the embodiment of the present application is implemented as follows:

[0005] In a first aspect, a base station positioning method is provided, comprising:

[0006] Acquire multiple user equipment UE reporting data received by the target base station, and use each of the UE reporting data as a sampling point to map to a grid map, wherein the UE reporting data carries signal information measured by the corresponding UE;

[0007] Multiple rounds of iterative execution: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map;

[0008] For each cell of the target base station, clustering calculation is performed on all sampling points included according to the signal indicator dimension matched by the UE reported data to obtain a clustering cluster of the sampling points of each cell;

[0009] For each of the cells, weighted calculation is performed on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, so as to obtain the center of each of the cells;

[0010] The center of each cell is weightedly calculated according to the sampling point density of the cell to which it belongs, so as to obtain the position of the target base station.

[0011] In a second aspect, a base station positioning device is provided, comprising:

[0012] A data processing module, which obtains a plurality of UE reported data received by the target base station, and uses each of the UE reported data as a sampling point to map it into a grid map;

[0013] The iterative processing module performs multiple rounds of iterations: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map;

[0014] A clustering calculation module, for each cell of the target base station, performs clustering calculation on all sampling points included according to the signal indicator dimension matched by the UE reported data, to obtain a clustering cluster of the sampling points of each cell;

[0015] A first calculation module, for each cell, performs weighted calculation on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, to obtain the center of each cell;

[0016] The second calculation module performs weighted calculation on the center of each cell according to the sampling point density of the cell to which it belongs, so as to obtain the position of the target base station.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor; and a memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed, cause the processor to execute the method described in the first aspect.

[0018] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store computer-executable instructions, and the computer-executable instructions implement the method described in the first aspect when executed by a processor.

[0019] The embodiment of the present application uses the multiple user equipment UE report data received by the target base station as sampling points to map to the grid map. Next, an iterative method is used to determine the discrete point grid based on the distance variance, and the sampling points in the discrete point grid are characterized as abnormal sampling points for filtering, which is equivalent to removing the sampling points with uneven data distribution or multiple signal sources. After that, a nonlinear weighted method is used to weight the cluster centers of all clusters contained in each cell according to the number of sampling points of the cluster cluster to which it belongs, to obtain the area center of each cell, and the area center of each cell is weighted according to the sampling point density of the cell to which it belongs, so as to determine the location of the target base station. The advantage of the linear weighted method is that it can reduce the impact of outliers, better adapt to complex network environments, and capture the nonlinear characteristics of signal propagation. Therefore, the location of the target base station is more accurate, and compared with the traditional positioning method of manual measurement, it has a significant improvement in efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A flowchart of a base station positioning method according to an embodiment of the present application is shown.

[0022] Figure 2 A schematic diagram of determining a starting point for clustering calculation in a base station positioning method according to an embodiment of the present application.

[0023] Figure 3 A schematic diagram of the structure of a base station positioning device according to an embodiment of the present application.

[0024] Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0026] An embodiment of the present application provides a base station positioning method. Figure 1 It is a flow chart of the base station positioning method, which includes the following steps:

[0027] S102, obtaining multiple UE report data received by the target base station, and using each UE report data as a sampling point to map to a grid map, wherein the UE report data carries signal information measured by the corresponding UE.

[0028] In this embodiment, the UE reported data may include, but is not limited to, Minimization Drive Test (MDT) data. MDT data includes information such as longitude and latitude, Reference Signal Receiving Power (RSRP), etc. Among them, RSRP can represent signal strength, which belongs to the signal information measured by the UE. As the name implies, the UE reported data is the message data reported by the UE to the base station, so each UE reported data can be used as a sampling point to be mapped to the grid map. That is, the sampling points in the grid map can be associated with the corresponding MDT data, including the sampling point location information reflected by the longitude and latitude and the sampling point signal strength reflected by RSRP.

[0029] Based on the above, this embodiment can classify the UE reported data collected by the target base station based on at least one dimension of source, coverage object, and usage scenario to obtain multiple UE reported data under each category; then, each UE reported data under the specified category will be used as a sampling point to map it to the grid map.

[0030] Among them, the dimension of source includes at least one classification of operator, network standard, and frequency band; the dimension of coverage object includes at least one classification of urban and rural areas; and the dimension of usage scenario includes at least one classification of macro station and indoor station.

[0031] It should be understood that classification based on the source dimension can make UE reported data from the same source more suitable for fusion; classification based on the coverage object and / or usage scenario dimension can enable subsequent more targeted allocation of network resources to base stations in combination with the needs of coverage objects and / or usage scenarios.

[0032] S104, multiple rounds of iterative execution: for each frequency band and / or each cell of the target base station, calculate the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point; based on the variances corresponding to all frequency bands and / or all cells under each grid, determine the average individual variance of each grid and the average overall variance of all grids; determine the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard as a discrete point grid, and remove the sampling points belonging to the discrete point grid from the grid map.

[0033] In this embodiment, the longitude and latitude of the center point of each grid is known information of the grid map, and the longitude and latitude of the sampling point is the longitude and latitude contained in the corresponding UE reported data. The preset gap standard can be the degree to which the average individual variance exceeds the average overall variance. For example, the preset gap standard can be that the average individual variance exceeds the average overall variance by 2 times, and in this step, the grid where the average individual variance exceeds the average overall variance by 2 times can be determined as a discrete point grid.

[0034] It should be noted that the iterative method of this embodiment is to determine the discrete point grid based on the distance variance, and characterize the sampling points in the discrete point grid as abnormal sampling points for filtering, which is equivalent to removing the sampling points with uneven data distribution or multiple signal sources. If the abnormal sampling points are determined only based on the signal strength reflected by RSRP, such as filtering out the sampling points where the RSRP signal strength is lower than the normal range, the impact of environmental factors (terrain, building shielding) on ​​signal propagation is ignored, resulting in non-noise information being mistakenly filtered.

[0035] In addition, the present embodiment can also directly determine the discrete point grid according to the number of sampling points. For example, the grid whose number of sampling points in the grid map does not reach a preset number standard (such as 5) is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map.

[0036] S106: For each cell of the target base station, cluster calculation is performed on all sampling points included according to the signal indicator dimension matched by the UE reported data to obtain a cluster of sampling points of each cell.

[0037] In this embodiment, the signal indicator dimension used for clustering calculation depends on the UE reported data. If the UE reported data is MDT data, the signal indicator dimension may be the RSRP indicator dimension.

[0038] It should be noted that the algorithm sampled for clustering calculation is not unique, and may be a K-means clustering algorithm, a C-means clustering algorithm, a Stromberg mixture model clustering algorithm, etc., which is not specifically limited here.

[0039] In the clustering calculation process, the starting mass points are the starting points of the clustering algorithm, and they determine the initial cluster centers. The selection of the starting mass points will directly affect the results of the clustering algorithm. Different starting mass points may lead to different clustering results, because clustering algorithms usually iteratively adjust the positions of the mass points to minimize the sum of squared deviations within the class. If the starting mass points are selected properly, the algorithm may be able to converge to the global optimal solution faster; conversely, if the starting mass points are not selected properly, the algorithm may fall into the local optimal solution, resulting in inaccurate clustering results.

[0040] Here, this embodiment provides a method for selecting a starting point for clustering calculation for a grid map sampling point. Specifically, refer to Figure 2 As shown in (a), the centroid of all sampling points can be first determined based on the latitude and longitude information in the data reported by each UE; and Figure 2 As shown in (b), the centroid of each cell is determined based on the latitude and longitude information in the data reported by all UEs in each cell of the target base station; next, refer to Figure 2 As shown in (c), for each cell, all the sampling points contained in it are divided based on the distance between them and the centroid of all the sampling points, and reference is made to Figure 2 As shown in (d), at least one target sampling point is randomly selected from the segmentation result; then, for each cell, the target sampling point is taken as the starting point, and clustering calculation is performed on all the sampling points included according to the signal indicator dimension matching the UE reported data (the clustering algorithm is not specifically limited), to obtain the clustering clusters of the sampling points of each cell.

[0041] S108 , for each cell, performing weighted calculation on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, to obtain the center of each cell.

[0042] For example, cell A contains cluster 1 and cluster 2, where the number of sampling points of cluster 1 is 60 and the number of sampling points of cluster 2 is 40. The center coordinates of the rooftop cell A can be obtained according to the formula: 0.6×the cluster center coordinates of cluster 1+0.6×0.4the cluster center coordinates of cluster 2.

[0043] S110, performing weighted calculation on the center of each cell according to the sampling point density of the cell to which it belongs, to obtain the position of the target base station.

[0044] In summary, the method of this embodiment uses the reported data of multiple user equipment UEs received by the target base station as sampling points to map to the grid map. Next, an iterative method is used to determine the discrete point grid based on the distance variance, and the sampling points in the discrete point grid are characterized as abnormal sampling points for filtering, which is equivalent to removing the sampling points with uneven data distribution or multiple signal sources. Afterwards, a nonlinear weighting method is used to weight the cluster centers of all clusters contained in each cell according to the number of sampling points of the cluster cluster to which they belong, to obtain the area center of each cell, and the area center of each cell is weighted according to the sampling point density of the cell to which it belongs, so as to determine the location of the target base station. The advantage of the linear weighting method is that it can reduce the impact of outliers, better adapt to complex network environments, and capture the nonlinear characteristics of signal propagation. Therefore, the determined location of the target base station is more accurate, and compared with the traditional positioning method of manual measurement, it has a significant improvement in efficiency and accuracy.

[0045] The following is a detailed description of the method flow of this embodiment.

[0046] The method of this embodiment involves multiple links such as data preprocessing, geographic gridding, data cleaning, cluster analysis and weighted position calculation. By collecting and cleaning the MDT data of all cells under the target base station, the effective RSRP sampling points are screened out and sorted and classified; then, these data are mapped to a two-dimensional geographic grid map, and the data in the grid is analyzed and cleaned, and the sampling points of the discrete point grid are removed; then, the geometric center and cell centroid of the sampling point are calculated, and the sampling points are clustered and weighted; finally, according to the density and center weight of the sampling points in the cell, the fitting position of the target base station is calculated. The corresponding process includes:

[0047] Step 1: Obtain MDT data of all cells under the target base station. The MDT data is reported by a user equipment UE. The MDT data includes longitude and latitude and RSRP, where RSRP represents the signal strength measured by the reference UE.

[0048] Step 2: Remove abnormal MDT data.

[0049] In this step, the RSRP valid interval may be set to [-120, 160], and the MDT data whose RSRP does not belong to the valid interval may be filtered out.

[0050] Step 3: sort the MDT data in order of RSRP from strong to weak, and then retain the first 80% of the MDT data under each network cell identifier according to the sorting.

[0051] Step 4: Logically classify the cleaned MDT data according to data source (operator, network standard, frequency band), coverage object (urban and rural), and usage scenario (macro station and indoor station).

[0052] Based on the above process of step 1 to step 4, it can be known that the method of this embodiment first processes invalid data of the initial MDT data, such as removing outliers, filling missing values ​​and eliminating duplicate data, so as to reduce the impact of noise and erroneous information on the classification results. This step lays the foundation for subsequent data analysis and improves the reliability and accuracy of overall data processing. Secondly, targeted MDT data processing according to different classifications (such as service providers, frequency bands, usage areas and scenarios) can more accurately meet the needs of subsequent positioning algorithms. This fine-grained data processing can reveal the specific characteristics of each category of data, which helps the algorithm to better capture and utilize these characteristics, thereby improving the accuracy and efficiency of base station positioning.

[0053] Step 5: Map the MDT data of a specified category into a two-dimensional grid map.

[0054] Each MDT data may be used as a sample. Each grid may represent a specific geographical area, and after mapping, may contain at least one sampling point or may not contain any sampling point.

[0055] Step 6: Count the number of sampling points in each grid. Grids with less than 5 sampling points are considered as discrete grids, and the sampling points in the discrete grids are proposed.

[0056] Step 7: For each frequency band and / or each cell of the target base station, calculate the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point.

[0057] Step 8: Based on the variances corresponding to all frequency bands and / or all cells under each grid, determine the average individual variance of each grid and the average overall variance of all grids.

[0058] Step 9: determine the grids whose average individual variance exceeds 2 times of the average overall variance as discrete point grids, and remove the sampling points belonging to the discrete point grids from the grid map.

[0059] Afterwards, the process from step 7 to step 9 may be repeated to iterate the sampling points until no sampling points are deleted.

[0060] Step 10: determining the centroid of all sampling points based on the longitude and latitude information in each MDT data; and determining the centroid of each cell based on the longitude and latitude information in all MDT data under each cell of the target base station.

[0061] Step 11: for each cell, all the included sampling points are segmented based on the distances between the sampling points and the centroids of all the sampling points, and at least one target sampling point is randomly selected from the segmentation results.

[0062] Step 12: for each cell, taking the target sampling point as the starting point, based on the cluster analysis method in multivariate statistical analysis, clustering calculation is performed on all the sampling points included in the signal index dimension to obtain the cluster clusters of the sampling points of each cell.

[0063] Step 13: For each cell, weighted calculation is performed on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, so as to obtain the center of each cell.

[0064] Step 14: Perform weighted calculation on the center of each cell according to the sampling point density of the cell to which it belongs, to obtain the fitting position of the target base station.

[0065] In addition, corresponding to Figure 1 In addition to the method shown, another embodiment of this embodiment further provides a base station positioning device. Figure 33 is a schematic diagram of the structure of the base station positioning device 300, including:

[0066] The data processing module 310 obtains a plurality of UE reported data received by the target base station, and uses each of the UE reported data as a sampling point to map into a grid map;

[0067] The iterative processing module 320 performs multiple rounds of iterations: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map;

[0068] The clustering calculation module 330 performs clustering calculation on all sampling points contained in each cell of the target base station according to the signal indicator dimension matched by the UE reported data to obtain a clustering cluster of the sampling points of each cell;

[0069] The first calculation module 340 performs weighted calculation on the cluster centers of all the clusters contained in each cell according to the number of sampling points of the clusters to which they belong, so as to obtain the center of each cell;

[0070] The second calculation module 350 performs weighted calculation on the center of each cell according to the sampling point density of the cell to which it belongs, to obtain the position of the target base station.

[0071] The device of this embodiment uses the multiple user equipment UE report data received by the target base station as sampling points to map to the grid map. Next, an iterative method is used to determine the discrete point grid based on the distance variance, and the sampling points in the discrete point grid are characterized as abnormal sampling points for filtering, which is equivalent to removing the sampling points with uneven data distribution or multiple signal sources. After that, a nonlinear weighted method is used to weight the cluster centers of all clusters contained in each cell according to the number of sampling points of the cluster cluster to which they belong, to obtain the area center of each cell, and the area center of each cell is weighted according to the sampling point density of the cell to which it belongs, so as to determine the location of the target base station. The advantage of the linear weighted method is that it can reduce the impact of outliers, better adapt to complex network environments, and capture the nonlinear characteristics of signal propagation. Therefore, the location of the target base station is more accurate, and compared with the traditional positioning method of manual measurement, it has a significant improvement in efficiency and accuracy.

[0072] Optionally, the data processing module 310 obtains multiple UE reporting data received by the target base station, and uses each of the UE reporting data as a sampling point to map to the grid map, including: classifying the UE reporting data collected by the target base station based on at least one dimension of source, coverage object, and usage scenario to obtain multiple UE reporting data under each category; and using each of the UE reporting data under the specified category as a sampling point to map to the grid map.

[0073] Optionally, the dimension of the source includes at least one of the classifications of operator, network standard, and frequency band; the dimension of the coverage object includes at least one of the classifications of urban and rural areas; and the dimension of the usage scenario includes at least one of the classifications of macro stations and indoor stations.

[0074] Optionally, before clustering the sampling points in the grid map according to the indicator dimension of the UE reported data for each cell of the target base station, the data processing module 310 is also used to: determine the grid whose number of sampling points in the grid map does not reach a preset number standard as a discrete point grid, and remove the sampling points belonging to the discrete point grid in the grid map.

[0075] Optionally, the clustering calculation module 330 performs clustering calculation on all sampling points contained in each cell of the target base station according to the signal indicator dimension matched by the UE reported data to obtain a cluster of sampling points of each cell, including: determining the centroid of all sampling points based on the longitude and latitude information in each UE reported data; and determining the centroid of each cell based on the longitude and latitude information in all UE reported data under each cell of the target base station; for each cell, dividing all sampling points contained in the cell based on the distance between the centroids of all sampling points, and randomly selecting at least one target sampling point from the division results; for each cell, taking the target sampling point contained in the cell as the starting point, performing clustering calculation on all sampling points contained in the cell according to the signal indicator dimension matched by the UE reported data to obtain a cluster of sampling points of each cell.

[0076] Optionally, the UE reported data includes Minimization of Drive Tests (MDT) data, and the indicator dimension of the UE reported data includes a Reference Signal Received Power (RSRP) indicator dimension.

[0077] It should be noted that the base station positioning device of this embodiment can be used as Figure 1 The execution subject of the method shown can thus realize Figure 1 The steps and functions in the method shown.

[0078] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0079] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0080] The memory is used to store the computer program. Specifically, the computer program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides the computer program to the processor.

[0081] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming the above-mentioned Figure 3 The base station positioning device shown. Correspondingly, the processor executes the program stored in the memory and is specifically used to perform the following operations:

[0082] Acquire multiple user equipment UE reporting data received by the target base station, and use each of the UE reporting data as a sampling point to map to a grid map, wherein the UE reporting data carries signal information measured by the corresponding UE.

[0083] Multiple rounds of iterative execution: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map.

[0084] For each cell of the target base station, cluster calculation is performed on all sampling points included according to the signal indicator dimension matched by the UE reported data to obtain a cluster of sampling points of each cell.

[0085] For each cell, weighted calculation is performed on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, so as to obtain the area center of each cell.

[0086] The center of each cell is weightedly calculated according to the sampling point density of the cell to which it belongs, so as to obtain the position of the target base station.

[0087] The above is as in this manual Figure 1 The method shown can be applied to a processor and implemented by the processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0088] Of course, in addition to software implementation, the electronic device of this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0089] In addition, the present application also provides a computer-readable storage medium, which stores one or more computer programs, wherein the one or more computer programs include instructions. When the instructions are executed by a portable electronic device including multiple application programs, the portable electronic device can execute Figure 1 The steps in the method shown include:

[0090] Acquire multiple user equipment UE reporting data received by the target base station, and use each of the UE reporting data as a sampling point to map to a grid map, wherein the UE reporting data carries signal information measured by the corresponding UE.

[0091] Multiple rounds of iterative execution: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map.

[0092] For each cell of the target base station, cluster calculation is performed on all sampling points included according to the signal indicator dimension matched by the UE reported data to obtain a cluster of sampling points of each cell.

[0093] For each cell, weighted calculation is performed on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, so as to obtain the area center of each cell.

[0094] The center of each cell is weightedly calculated according to the sampling point density of the cell to which it belongs, so as to obtain the position of the target base station.

[0095] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] The above are only embodiments of this specification and are not intended to limit this specification. For those skilled in the art, this specification may be subject to various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included in the scope of the claims of this specification. In addition, all other embodiments obtained by ordinary technicians in this field without creative work shall fall within the scope of protection of this document.

Claims

1. A base station positioning method, characterized in that: include: Acquire multiple user equipment UE reporting data received by the target base station, and use each UE reporting data as a sampling point to map to a grid map, wherein the UE reporting data carries signal information measured by the corresponding UE; Multiple rounds of iterative execution: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map; For each cell of the target base station, clustering calculation is performed on all sampling points included according to the signal indicator dimension matched by the UE reported data to obtain a clustering cluster of the sampling points of each cell; For each of the cells, weighted calculation is performed on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, so as to obtain the center of each of the cells; The center of each cell is weightedly calculated according to the sampling point density of the cell to which it belongs, so as to obtain the position of the target base station.

2. The method according to claim 1, characterized in that: Acquiring multiple user equipment UE report data received by the target base station, and using each UE report data as a sampling point to map to a grid map, including: Based on at least one dimension of source, coverage object, and usage scenario, classify the UE reporting data collected by the target base station to obtain multiple UE reporting data under each classification; Each UE report data under the specified category is used as a sampling point to be mapped into the grid map.

3. The method according to claim 2, characterized in that The dimension of the source includes at least one of the classifications of operator, network standard, and frequency band; the dimension of the coverage object includes at least one of the classifications of urban and rural areas; and the dimension of the usage scenario includes at least one of the classifications of macro stations and indoor stations.

4. The method according to claim 1, characterized in that: Before clustering the sampling points in the grid map according to the indicator dimension of the data reported by the UE for each cell of the target base station, the method further includes: A grid whose number of sampling points in the grid map does not meet a preset number standard is determined as a discrete point grid, and sampling points belonging to the discrete point grid are removed from the grid map.

5. The method according to claim 1, characterized in that For each cell of the target base station, clustering calculation is performed on all sampling points included according to the signal indicator dimension matched by the UE reported data to obtain a clustering cluster of the sampling points of each cell, including: Determine the centroid of all sampling points based on the longitude and latitude information in the data reported by each UE; and determine the centroid of each cell based on the longitude and latitude information in the data reported by all UEs in each cell of the target base station; For each of the cells, all the sampling points contained therein are segmented based on the distances between the cells and the centroids of all the sampling points, and at least one target sampling point is randomly selected from the segmentation results; For each cell, taking the target sampling point as a starting point, clustering calculation is performed on all the sampling points included according to the signal indicator dimension matching the UE reported data to obtain a cluster of sampling points of each cell.

6. The method according to claim 5, characterized in that The clustering calculation adopts the K-means clustering algorithm.

7. The method according to claim 1, characterized in that The UE reported data includes Minimization of Drive Tests (MDT) data, and the indicator dimension of the UE reported data includes a Reference Signal Received Power (RSRP) indicator dimension.

8. A base station positioning device, characterized in that: include: The data processing module obtains multiple UE reported data received by the target base station, and uses each UE reported data as a sampling point to map it into a grid map; The iterative processing module performs multiple rounds of iterations: for each frequency band and / or each cell of the target base station, the variance between the longitude and latitude of the center point of each grid and the longitude and latitude of the sampling point is calculated; based on the variances corresponding to all frequency bands and / or all cells under each grid, the average individual variance of each grid and the average overall variance of all grids are determined; the grid whose difference between the average individual variance and the average overall variance reaches a preset difference standard is determined as a discrete point grid, and the sampling points belonging to the discrete point grid are removed from the grid map; A clustering calculation module, for each cell of the target base station, performs clustering calculation on all sampling points included according to the signal indicator dimension matched by the UE reported data, to obtain a clustering cluster of the sampling points of each cell; A first calculation module, for each cell, performs weighted calculation on the cluster centers of all the contained clusters according to the number of sampling points of the clusters to which they belong, to obtain the center of each cell; The second calculation module performs weighted calculation on the center of each cell according to the sampling point density of the cell to which it belongs, so as to obtain the position of the target base station.

9. An electronic device, comprising: processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer-readable storage medium storing a computer program, characterized in that: The computer program is operable to cause a computer to perform the method according to any one of claims 1 to 7.

Images