Base station positioning method and device, equipment, storage medium and product

Abstract

The embodiment of the invention provides a base station positioning method and device, equipment, a storage medium and a product. The method comprises the following steps: determining a core coverage area of each service cell according to a terminal side measurement data set of each service cell; combining the core coverage areas of the service cells under the same base station, and determining a base station coverage area of the base station; and determining at least one physical base station corresponding to the base station and position information of the physical base station according to the base station coverage area. According to the embodiment of the invention, the method effectively improves the positioning precision and anti-interference capability in a complex environment, reduces the consumption of computing resources, achieves the efficient and real-time positioning of a base station, improves the consistency processing capability of multi-band and multi-cell signals, and improves the positioning applicability of a specific scene.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of wireless communication, and particularly relates to a base station positioning method, device, equipment, storage medium and product. BACKGROUND

[0002] In the base station positioning technology in the field of wireless communication, the existing method usually relies on grid processing of base station data and uses a clustering algorithm to realize positioning. However, the above method has weak anti-interference ability, poor positioning accuracy, and limited application scenarios, and cannot meet the real-time positioning demand in a complex environment such as signal shielding or signal fluctuation. SUMMARY

[0003] The embodiments of the present application provide a base station positioning method, device, equipment, storage medium and product, which can solve the technical problem of poor positioning accuracy and positioning efficiency of the existing base station positioning technology.

[0004] In a first aspect, the embodiments of the present application provide a base station positioning method, which comprises the following steps: determining a core coverage area of each service cell according to a terminal-side measurement data set of the service cell; merging the core coverage areas of the service cells under the same base station to determine a base station coverage area of the base station; determining at least one physical base station corresponding to the base station and position information of the physical base station according to the base station coverage area.

[0005] In an implementable embodiment, the step of determining the core coverage area of each service cell according to the terminal-side measurement data set of the service cell comprises the following steps: performing grid processing on the terminal-side measurement data set of each service cell respectively to obtain a plurality of first grids of the service cell; dividing the plurality of first grids of each service cell according to the grid signal of each first grid respectively to obtain a plurality of strong signal grids of the service cell and a weak signal grid of the service cell; performing clustering on the plurality of strong signal grids of each service cell to determine a clustering core area of the service cell; performing data backfilling on the clustering core area of each service cell according to the grid feature data of the weak signal grid to obtain the core coverage area of the service cell.

[0006] In an implementable embodiment, the step of performing clustering on the plurality of strong signal grids of each service cell to determine the clustering core area of the service cell comprises the following steps: calculating a mean shift vector of each of the strong signal grids according to grid feature data of the strong signal grids, a target bandwidth parameter, and a preset Gaussian kernel function; performing iterative updating of a cluster center according to the mean shift vector of each of the strong signal grids, to obtain a plurality of cluster clusters of each of the service cells; determining a cluster core area of each of the service cells according to a grid density of each of the cluster clusters.

[0007] In an implementable embodiment, the step of determining at least one physical base station corresponding to the base station and position information of the physical base station according to the base station coverage area comprises: performing grid processing on a plurality of grids existing in the base station coverage area, to obtain a plurality of second grids of the base station; performing clustering on grid feature data of the plurality of second grids, to obtain at least one cluster cluster corresponding to the base station; determining a physical base station and position information of the physical base station according to the cluster cluster.

[0008] In an implementable embodiment, the step of determining a physical base station and position information of the physical base station according to the cluster cluster comprises: extracting position features of each second grid in the cluster cluster, to determine a plurality of central latitudes corresponding to the cluster cluster and a plurality of central longitudes corresponding to the cluster cluster respectively performing mean calculation on the plurality of central longitudes corresponding to the cluster cluster and the plurality of central latitudes corresponding to the cluster cluster, to obtain an average longitude and an average latitude; determining position information of the physical base station according to the average longitude and the average latitude, and taking a service cell existing under the cluster cluster as a service cell corresponding to the physical base station.

[0009] In an implementable embodiment, before the step of determining a core coverage area of each of the service cells according to a terminal-side measurement data set of each of the service cells, the method further comprises: performing field optimization on a plurality of original measurement data points of each of the service cells according to a target field, to obtain a plurality of first measurement data points of each of the service cells; performing default item deletion on the plurality of first measurement data points, to obtain a plurality of second measurement data points of each of the service cells; performing abnormal item deletion on the plurality of second measurement data points, to obtain a terminal-side measurement data set of each of the service cells.

[0010] In a second aspect, an embodiment of the present application provides a base station positioning device, the device comprising: a processing module configured to determine a core coverage area of each of the serving cells according to a terminal-side measurement data set of the serving cell; a merging module configured to merge the core coverage areas of the serving cells under a same base station to determine a base station coverage area of the base station; The processing module is further configured to determine at least one physical base station corresponding to the base station and location information of the physical base station according to the base station coverage area.

[0011] In a third aspect, an embodiment of the present application provides a base station positioning device, which comprises a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the base station positioning method according to the first aspect.

[0012] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores computer program instructions; the computer program instructions are executed by a processor to implement the base station positioning method according to the first aspect.

[0013] In a fifth aspect, an embodiment of the present application provides a computer program product, instructions in the computer program product are executed by a processor of an electronic device to enable the electronic device to implement the base station positioning method according to the first aspect.

[0014] The base station positioning method, device, equipment, storage medium and product provided by the embodiments of the present application can determine the core coverage areas of the serving cells first, then merge the core coverage areas of the serving cells under a same base station to determine a base station coverage area, and finally accurately identify a physical base station and its location based on the data set of the base station coverage area, thereby effectively improving the positioning precision and anti-interference capability in a complex environment, reducing the consumption of computing resources, realizing efficient and real-time base station positioning, enhancing the consistency processing capability of multi-frequency and multi-cell signals, and improving the positioning applicability in specific scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. Those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0016] Figure 1 is an embodiment one flowchart of a base station positioning method provided by the embodiments of the present application; Figure 2 is an embodiment two flowchart of a base station positioning method provided by the embodiments of the present application; Figure 3 is a data backfilling diagram of the base station positioning method provided by the embodiment two. Figure 4 is a cell clustering schematic diagram of a base station positioning method provided by an embodiment of the present application; Figure 5 is an embodiment three flow schematic diagram of a base station positioning method provided by an embodiment of the present application; Figure 6 is a secondary gridding processing schematic diagram of a base station positioning method provided by the embodiment three; Figure 7 is a base station clustering schematic diagram of a base station positioning method provided by the embodiment three; Figure 8 is a structure schematic diagram of a base station positioning device provided by an embodiment of the present application; Figure 9 is a structure schematic diagram of a base station positioning device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0017] The features and exemplary embodiments of various aspects of the present application will be described below in detail, in order to make the purposes, technical solutions and advantages of the present application more clear and apparent, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0018] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitations, the elements defined by the statement "include" do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0019] The existing base station positioning technology mainly has the following three fundamental defects: 1. Inaccurate positioning: poor precision in complex scenarios and poor anti-interference ability: The positioning result of the existing scheme is unreliable in a complex actual environment. Firstly, the single RSRP (Reference Singnal Received Power) data relied on is magnified in defects when the signal is blocked and overlapped, resulting in positioning deviation. Secondly, in a high-density hotspot area, the signal strength of multiple base stations is high, forming a "high-value continuous" phenomenon, which makes it impossible to accurately distinguish the signal center of a single base station, resulting in "station address drift". Thirdly, the clustering algorithm (such as K-means) result is seriously dependent on the initial random value, and the stability is insufficient, which is easy to deviate from the true position in a complex scene.

[0020] 2. Incomplete coverage: inherent defects in the technical route, leading to failure in specific scenarios: the existing technology has obvious application blind area and cannot meet the positioning needs of all base stations. Firstly, it cannot effectively support 5G base station positioning because it relies on 4G network MDT (Minimization of Drive Tests) data, and there is currently no 5G MDT data, resulting in direct failure of the scheme. Secondly, it cannot distinguish multiple physical sites under the CRAN (Centralized Radio Access Network) architecture, and can only regard them as a logical station to output a single coordinate, which cannot realize RRU (Remote Radio Unit) level fine positioning and is difficult to meet the network precise optimization needs.

[0021] 3. Slow computing power: low efficiency and lack of real-time performance: the existing scheme consumes a lot of resources and cannot be efficiently deployed. The Res-UNet deep learning model used by the thermal imaging method requires large-scale labeled data, huge GPU (Graphics Processing Unit) computing power and long training period, and the economic and time cost is uncontrollable. The grid clustering method has a complex calculation process due to multiple rounds of iteration variance calculation, independent clustering of each cell, and multi-layer weighted fusion processing, and has high computational complexity, making it difficult to realize fast calculation of ten thousand base stations. At the same time, the deep learning model has poor generalization ability and needs to be retrained when the environment changes, which is high in operation and maintenance cost.

[0022] In order to solve the problems of the existing technology, the embodiments of the present application provide a base station positioning method, device, equipment, storage medium and product. First, the base station positioning method provided by the embodiments of the present application is introduced.

[0023] Figure 1 The flowchart of the base station positioning method provided by one embodiment of the present application is shown. As shown in Figure 1 The method can include steps 210-230: Step 210, determining the core coverage area of each serving cell according to the terminal-side measurement data set of each serving cell.

[0024] The execution subject of the embodiment is a base station positioning device, which is a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc. The base station positioning device can determine the core coverage area of each serving cell based on the terminal-side measurement data of each serving cell; further, the terminal-side measurement data set of the core coverage area of all serving cells under the same base station determines at least one physical base station corresponding to the base station and the location information of the physical base station.

[0025] It can be understood that the serving cell is a wireless coverage area configured by a base station and has a unique cell identifier, which is the basic unit for terminal devices to access a wireless network; the terminal-side measurement data set is composed of multiple OTTMR (Over The Top Measurement Report) data, which is a real-time measurement record about the wireless communication network environment where the terminal is located, actively collected and reported by the Internet application service program on the user terminal when providing network services. The OTTMR data includes but is not limited to the data collection timestamp, the terminal location information, the mobile communication network operator information, the mobile communication network network basic information, the mobile communication network serving cell measurement value, etc.

[0026] The core coverage area of the serving cell refers to the continuous geographic area within the wireless signal coverage range of the serving cell, where the signal quality is the best, the distribution is the most concentrated, and the stability is the most stable.

[0027] For the terminal-side measurement data set of a single serving cell: to reduce the data volume and computational complexity, the multiple OTTMR data in the terminal-side measurement data set of the serving cell are subjected to rasterization processing to obtain multiple grids, and the signal strength of all grids is classified according to the RSRP mean value of each grid. The grid feature data of the strong signal grid of a single serving cell is subjected to multiple rounds of clustering calculation, the cluster with the highest density is taken as the core coverage area of the serving cell, and the weak signal grid data belonging to the area is backfilled to ensure the integrity of the data.

[0028] Step 220, merging the core coverage areas of the serving cells under the same base station to determine the base station coverage area of the base station.

[0029] The base station refers to a logical network node that provides wireless communication services, which can contain one or more serving cells and has a unique base station identifier. The base station coverage area is a geographic area representing the overall signal coverage range of the base station, which is composed of the core coverage areas of all serving cells under the same logical base station.

[0030] All the serving cells belonging to the same base station are screened out, and the core coverage areas of the serving cells are obtained. The grids of the core coverage areas of the serving cells under the same base station are merged by using a spatial union operation: if the grids of the core coverage areas of different serving cells overlap, only one overlapping grid is retained; if the core coverage areas of different serving cells do not overlap and the spatial distance is less than a preset distance threshold (for example, 100 meters), the area connection is achieved by filling in the intermediate blank grids, and the average RSRP of the blank grids is calculated by interpolation according to the average values of the surrounding grids. After the grids of the core coverage areas of the serving cells under the same base station are merged, the obtained grid set is the base station coverage area of the base station. In addition to the above manner, other manners can also be used for area merging, which is not limited in the embodiment.

[0031] In step 230, at least one physical base station corresponding to the base station and the location information of the physical base station are determined according to the base station coverage area.

[0032] The physical base station refers to a wireless network hardware facility actually deployed in a physical space, and is an entity device providing wireless signal transmission and reception functions. Each physical base station corresponds to a unique geographical location, and one logical base station can correspond to one or more physical base stations. The location information includes the geographical location of the physical base station, including the longitude of the physical base station and the latitude of the physical base station.

[0033] The base station coverage area is uniformly rasterized to obtain a plurality of grids, and clustering calculation is performed on the grid feature data of the plurality of grids, so as to obtain a plurality of clustering clusters. One clustering cluster corresponds to one physical base station, and the centroid position of each clustering cluster is the geographical location of each physical base station.

[0034] In a feasible implementation, before step 210, steps A11-A13 can be included: In step A11, a plurality of first measurement data points of the serving cells are obtained by performing field optimization on a plurality of original measurement data points of the serving cells according to a target field.

[0035] The original measurement data point refers to a real-time measurement record about the wireless communication network environment in which the terminal is located, which is actively collected and reported on the terminal side without any processing. The data format and content of each original measurement data point can be different.

[0036] The target field is a set of key data fields that are pre-set and required for training. In the embodiment, the target field includes the collection timestamp of the data, the location information of the terminal, the mobile communication network operator information, the network basic information of the mobile communication network, and the mobile communication network serving cell measurement value.

[0037] In the data processing stage, the data filtering mode, how to extract and select the features will indirectly affect the positioning effect and operation time efficiency. Moreover, due to the limited coverage of the base station, default values and measurement errors will occur in the signal collection process. In order to ensure the data quality and prevent the occurrence of data imbalance in the subsequent training process, the multiple original measurement data points of each service cell need to be preprocessed.

[0038] In some embodiments, the fields present in the original measurement data points include but are not limited to the timestamp of data collection, the location information of the terminal, the terminal information, the mobile communication network operator information, the network basic information of the mobile communication network, the mobile communication network service cell measurement value, and the mobile network neighbor cell measurement value. Table 1 is used to illustrate the specific content of each field. The mobile network in the table refers to the mobile communication network.

[0039] Table 1 In order to avoid the database structure composed of multiple OTTMR data being complex, the content being too large, and occupying too many system resources, thereby causing the server to run slowly, the database structure needs to be optimized according to the target field. Specifically, for each original measurement data point of each service cell, the fields in the original measurement data point that completely match the target field are extracted, and the redundant information in the original measurement data point that is not included in the target field is deleted, thereby forming the first measurement data point corresponding to the original measurement data point.

[0040] Step A12, deleting the default items from the first measurement data points to obtain multiple second measurement data points of the service cells.

[0041] For all first measurement data points of each service cell, it is detected whether the target field of the first measurement data point is missing. For the first measurement data point with a default item, it is directly excluded. The remaining first measurement data points in the same service cell after the default item deletion are summarized, thereby obtaining multiple second measurement data points of the service cell.

[0042] Step A13, deleting the abnormal items from the second measurement data points to obtain the terminal-side measurement data set of the service cells.

[0043] In order to eliminate data points with unreasonable values or conflicting with the characteristics of the serving cell, ensure the validity of the data, and delete outliers for each second measurement data point, specifically, the following method can be used: based on all second measurement data points of the same serving cell, the average value μ and the standard deviation σ of the field to be detected for outliers are calculated according to the 3σ principle, if the specific value of the field is outside the range of average value ± 3σ, the corresponding second measurement data point is determined as an outlier and is deleted, so as to reduce the influence of noise points on the subsequent analysis results. In addition, other outlier detection methods can also be used, which are not limited in the embodiment.

[0044] In the embodiment, the fields to be detected for outliers include the longitude of the terminal, the latitude of the terminal, the CI (Cell Identity, cell identifier) in the mobile communication network basic information, the currently occupied base station ID (identifier) in the mobile communication network basic information, and the mobile communication network serving cell measurement value.

[0045] The second measurement point data remaining in the same serving cell after the deletion of outliers is summarized to form a terminal-side measurement data set of the serving cell.

[0046] After obtaining the terminal-side measurement data set of each serving cell, the serving cells with the number of sampling points corresponding to the OTTMR data in the terminal-side measurement data set greater than a preset number (for example, 1000) are taken as a training data set, which participates in subsequent base station positioning and executes step 210 and subsequent steps.

[0047] In the embodiment, the original measurement data points are optimized by field optimization, default item and outlier deletion, so as to screen out complete, effective and structured terminal-side measurement data from the original measurement data points, provide a reliable data basis for subsequent analysis, and significantly improve the accuracy, robustness and stability of the positioning result.

[0048] The embodiment determines the core coverage area of each serving cell first, then merges the core coverage areas of each serving cell under the same base station to determine the base station coverage area, and finally accurately identifies the physical base station and its position based on the data set of the base station coverage area, which effectively improves the positioning accuracy and anti-interference ability in complex environment, reduces the consumption of computing resources, realizes efficient and real-time base station positioning, enhances the consistency processing ability of multi-frequency and multi-cell signals, and improves the positioning applicability in specific scenarios.

[0049] Based on the first embodiment of the application, in the second embodiment of the application, the same or similar contents as the above embodiment one can refer to the above introduction, and the following will not be described in detail. On this basis, please refer to Figure 2 , the step 210 of the base station positioning method can include steps 310-330: Step 310, respectively, the terminal side measurement data set of each service cell is gridded to obtain a plurality of first grids of each service cell.

[0050] For each service cell terminal side measurement data set: due to the OTTMR data in the terminal side measurement data set, the data volume is large and the distribution is dense, direct processing will bring high computational overhead, therefore, the terminal side measurement data set of the service cell is gridded to obtain a plurality of first grids of the service cell and the grid feature data of each first grid. Wherein, the first grid refers to the spatial grid unit obtained by spatial gridding processing the terminal side measurement data set of a single service cell. In this embodiment, the grid size is a preset fixed value, each first grid contains the statistical characteristics of all terminal side measurement data in the space range, which is the basic analysis unit of the service cell signal space distribution. The grid feature data of the first grid includes but is not limited to the central longitude of the first grid, the central latitude of the first grid and the grid signal of the first grid.

[0051] The specific process of gridding each service cell terminal side measurement data set is: based on the theoretical coverage range of the service cell, a two-dimensional grid map is constructed, and the grid coordinates are converted from longitude and latitude to plane coordinates; each OTTMR data in the terminal side measurement data set of the service cell is mapped to the corresponding first grid according to its longitude and latitude information.

[0052] For all OTTMR data falling into the first grid, the following statistical characteristics are calculated: the RSRP values of all OTTMR data in the first grid are calculated, and the calculated RSRP mean value is taken as the grid signal of the first grid; the longitude and latitude of all OTTMR data in the first grid are calculated respectively, and the calculated longitude mean value is taken as the central longitude of the first grid, and the calculated latitude mean value is taken as the central latitude of the first grid.

[0053] In some embodiments, because the size of OTTMR sampling point is about 0.001m×0.008m, the data volume is large, under the premise of not affecting the training result, based on the characteristics of 5G signal wavelength λ≈0.05m, it is proved by experiment that the positioning error is ≤3m under 2m×2m grid size, and the error is only 0.3m under 1m×1m grid, but the calculation efficiency is improved by 1 times, therefore, for each service cell terminal side measurement data set, 2m×2m grid is selected for gridding in this embodiment.

[0054] Step 320, according to the grid signal of each first grid, the plurality of first grids of each service cell are divided respectively to obtain a plurality of strong signal grids of each service cell and a weak signal grid of each service cell.

[0055] For all the first grids of each serving cell: sort the grid signals of all the first grids in descending order or in ascending order, which is not limited in the embodiment. After the sorting, the first grids with a preset proportion (e.g. 50%) of relatively strong grid signals are taken as the strong signal grids of the serving cell, and the remaining proportion of the first grids with relatively weak grid signals are taken as the weak signal grids of the serving cell.

[0056] Step 330: cluster the multiple strong signal grids of each serving cell to determine the cluster core area of each serving cell.

[0057] For all the strong signal grids of each serving cell: perform multiple rounds of cluster calculation on the grid feature data of all the strong signal grids to obtain multiple cluster clusters corresponding to the serving cell, and take the cluster cluster with the highest density as the cluster core area of the serving cell. In the embodiment, the K-Means algorithm, DBSCAN algorithm, MeanShift algorithm and other clustering algorithms can be used for cluster calculation, which is not limited in the embodiment.

[0058] Step 340: data backfill the cluster core area of each serving cell according to the grid feature data of each weak signal grid to obtain the core coverage area of each serving cell.

[0059] For the cluster core area of each serving cell: query and filter the weak signal grids with spatial positions satisfying the preset condition from the weak signal grid set of the serving cell. The preset condition is that the central longitude and central latitude of the weak signal grid completely fall within the boundary range of the cluster core area, and the preset condition can be adjusted, which is not limited in the embodiment.

[0060] The filtered weak signal grids are re-included in the cluster core area of the serving cell, and the grid feature data of each weak signal grid is backfilled to the cluster core area. The spatial area merging of the strong signal grids and the weak signal grids satisfying the preset condition is completed, and the overall spatial area after merging is the core coverage area of the serving cell. The area integrates the strong signal aggregation area and the surrounding effective weak signal coverage area of the serving cell, and ensures the integrity of the data. In addition to the above backfilling method, spatial interpolation or other methods can be used for data backfilling to obtain the core coverage area of the serving cell, which is not limited in the embodiment.

[0061] Take Figure 3 as an example for data backfilling, Figure 3The green squares in the diagram represent the strong signal grids of the serving cell, while the yellow squares represent the weak signal grids. After clustering the grid feature data of all strong signal grids, the core clustering region is obtained. Then, data backfilling is performed based on the data of the weak signal grids to obtain the core coverage area of ​​the serving cell.

[0062] In one possible implementation, step 330 may include steps B11-B13: Step B11: Calculate the mean drift vector of each strong signal grid based on the grid feature data, target bandwidth parameters, and preset Gaussian kernel function of each serving cell's multiple strong signal grids.

[0063] Step B12: Iteratively update the cluster centers based on the mean drift vector of each strong signal grid to obtain multiple clusters of each serving cell.

[0064] Step B13: Determine the cluster core region of each serving cell based on the grid density of each cluster.

[0065] In some embodiments, the MeanShift clustering algorithm is used to cluster the terminal-side measurement datasets of all strong signal grids in each serving cell. MeanShift is a kernel density estimation-based clustering algorithm that does not require pre-specifying the number of clusters; instead, it automatically determines cluster centers by finding local maxima of density at data points. This clustering algorithm can effectively handle clusters of arbitrary shapes. The core idea is to find the kernel density extrema and use them as the centroids of the clusters, then assign centroids to sample points according to the nearest neighbor principle. The algorithm mainly estimates the density at each point in the sample space based on the sample distribution. When estimating the density at a point, the kernel density estimation method considers the influence of sample points in the neighboring region. The size of the neighboring region is determined by the bandwidth parameter. Determine the bandwidth parameters It has a significant impact on the final density estimate and needs to be configured according to the actual situation.

[0066] The existing MeanShift clustering algorithm has a problem: Within the region, each point is related to the cluster center of interest in the current iteration step. Their contributions are all the same, but this contribution is different from... The distance to each point is relevant, and the importance of each sample is different. To ensure that each sample point... For the sample The contribution is different; a kernel function is added to the existing MeanShift vector form, resulting in an improved MeanShift vector.

[0067] The specific formula of the improved mean shift vector is: wherein n represents the number of sample points located in the region. is a preset Gaussian kernel function, and the function form is as follows: . . refers to a high-dimensional spherical region with a radius of , and is defined as: .

[0068] For all strong signal grids of each service cell: extract the grid feature data of the strong signal grid, construct the corresponding grid feature vector, and for the grid feature vector x of the strong signal grid, traverse all other strong signal grids in the service cell, calculate the spatial distance between x and the grid feature vector of other strong signal grids, and include the grid feature vector with a spatial distance less than or equal to the target bandwidth parameter h in the region. Use a preset Gaussian kernel function to calculate the weight of the grid feature vector of all strong grid signals in the region with respect to the grid feature vector x. Substitute the weight of the grid feature vector of all strong grid signals in the region with respect to the grid feature vector x into the specific formula of the improved mean shift vector, thereby obtaining the mean shift vector of the strong signal grid. . For the grid feature vector x of each strong signal grid, set it as a clustering center to obtain a clustering center estimate , and use the calculated clustering center estimate as a new iteration initial value to repeatedly execute the calculation process of the mean shift vector. In each iteration process, calculate a new clustering center estimate

[0069] , and judge whether the difference between the new clustering center estimate and the previous iteration result is less than a preset threshold ε. When ∣ X∣<ε is satisfied, the iteration is terminated, and the obtained clustering center estimate X value is the final clustering center.

[0070] ​After calculating the estimated values ​​of all cluster centers, strong signal gratings corresponding to spatially close distance centers are merged to obtain multiple clusters of the serving cell. For each cluster, the number of strong signal gratings within the cluster is counted, and the spatial area of ​​the cluster is calculated based on the latitude and longitude range of the gratings within the cluster, thus obtaining the grating density: grating density = number of strong signal gratings in the cluster / cluster spatial area. The grating densities of all clusters are compared, and the cluster with the highest density is selected and defined as the cluster core region of the serving cell. Besides the above method, other methods can also be used to calculate the grating density; this embodiment does not limit this method.

[0071] After clustering the raster feature data of multiple strong signal gratings in all serving cells, the clustering results are as follows: Figure 4 As shown, the centroid of the cell is the cluster center of the cluster.

[0072] In some embodiments, to improve the accuracy of clustering, the target bandwidth parameter of the MeanShift algorithm is adjusted. Optimization was performed. Using feature extraction from a machine learning model, the clustering effect was tested on 100 sets of sample base station data (including single-sector and CRAN types) under different target bandwidth parameters. Experimental results show that when the target bandwidth parameter... When h=0.0009, the contour coefficient is the highest (0.72±0.05) and the positioning error is the smallest (3.2m±1.1m). Therefore, h=0.0009 is selected in this embodiment.

[0073] In this embodiment, the mean shift algorithm based on the Gaussian kernel function is used to cluster all strong grid signal data. This can efficiently and accurately identify the core area from the strong signal grid data of the serving cell, effectively overcoming the influence of data noise and uneven distribution. At the same time, it can adaptively discover the density distribution in the data and has strong robustness.

[0074] The embodiment obtains a plurality of first grids of each service cell by respectively performing grid processing on a terminal-side measurement data set of each service cell; divides the plurality of first grids of each service cell according to the grid signal of each first grid to obtain a plurality of strong signal grids of each service cell and a weak signal grid of each service cell; performs clustering on the plurality of strong signal grids of each service cell to determine a clustering core area of each service cell; and performs data backfilling on the clustering core area of each service cell according to grid feature data of the weak signal grid to obtain a core coverage area of each service cell. In this way, the core coverage area of the service cell can be efficiently and accurately extracted from massive data, effectively eliminating the interference of edge and invalid data, and significantly improving the quality of training data of the base station positioning model, thereby laying a foundation for subsequent accurate positioning of the base station.

[0075] Based on any one or more embodiments of the present application, in a third embodiment of the present application, the same or similar content as the above embodiments can be referred to the above introduction, and will not be described in detail hereinafter. On this basis, please refer to Figure 5 , the base station positioning method can include steps 410-430 in step 230: Step 410, performing grid processing on a plurality of grids existing in the base station coverage area to obtain a plurality of second grids of the base station.

[0076] The base station coverage area of the base station is obtained by merging the core coverage areas of all service cells under the base station, and the core coverage area of each service cell is a first grid with a smaller size. Therefore, there are a plurality of small-size grids in the base station coverage area. Although the small grid size improves the representation accuracy, it significantly increases the calculation load. Therefore, under the premise of acceptable accuracy, the first grids of the core coverage areas of all service cells under the base station can be subjected to secondary grid processing to obtain a plurality of second grids of the base station. The central longitude of the second grid is the average value of the longitudes of all first grids in the second grid; the central latitude of the second grid is the average value of the latitudes of all first grids in the second grid; and the grid signal of the second grid is the average value of the RSRP of all first grids in the second grid.

[0077] In some embodiments, without affecting the training results, the grid size of the first grid is 2m×2m, and when performing secondary grid processing on the plurality of grids existing in the base station coverage area, the grid size can be processed according to 5 to 20 times (10m×10m to 20m×20m). For example, the first grid with a grid size of 2m×2m is subjected to secondary grid processing according to a grid size of 10m×10m, and the plurality of second grids obtained are as shown in Figure 6As shown. In the present embodiment, the above-mentioned grid size can be adjusted according to actual conditions, and the present embodiment does not limit this.

[0078] Step 420, clustering the grid feature data of the plurality of second grids to obtain at least one cluster corresponding to the base station.

[0079] For the grid feature data of all second grids under the same base station, a plurality of rounds of clustering calculation are carried out to obtain a plurality of clusters corresponding to the base station, and each cluster corresponds to a unique cluster label. In the clustering calculation, K-Means algorithm, DBSCAN algorithm, MeanShift algorithm and other clustering algorithms can be used, and the present embodiment does not limit this. However, in the present embodiment, MeanShift clustering algorithm with Gaussian kernel function is selected for clustering calculation.

[0080] Step 430, determining the physical base station and the location information of the physical base station according to the cluster.

[0081] In the existing wireless communication network, due to the deployment scene of CRAN (centralized radio access network) site, there are multiple physical sites under a logical base station; therefore, in the present embodiment, the number of clusters obtained by clustering is determined as the number of physical base stations under the logical base station, and the centroid position of each cluster is determined as the geographical position of the corresponding physical base station, so as to obtain the location information of each physical base station.

[0082] After clustering the grid feature data of all second grids, the clustering result obtained is as shown in Figure 7 , wherein the centroid of the physical base station is the cluster center (i.e. centroid) of the cluster.

[0083] In a feasible embodiment, step 430 can include steps C11-C13: Step C11, extracting the location features of each second grid in the cluster to determine a plurality of central latitudes corresponding to the cluster and a plurality of central longitudes corresponding to the cluster.

[0084] Step C12, respectively performing mean value calculation on the plurality of central longitudes corresponding to the cluster and the central latitudes corresponding to the cluster to obtain an average longitude and an average latitude.

[0085] Step C13, determining the location information of the physical base station according to the average longitude and the average latitude, and taking the service cell existing under the cluster as the service cell corresponding to the physical base station.

[0086] The position feature of the second grid includes a central longitude of the second grid and a central latitude of the second grid. For each cluster: traversing each second grid in the cluster, extracting the position feature thereof, obtaining the central longitude of each second grid and the central latitude of each second grid, and outputting a plurality of central longitudes and a plurality of central latitudes corresponding to the cluster.

[0087] For each cluster: performing mean value calculation on all central longitudes and all central latitudes corresponding to the cluster respectively, obtaining an average longitude and an average latitude corresponding to the cluster, taking the average longitude and the average latitude as the geographic position of the physical base station corresponding to the cluster, and obtaining the position information of the physical base station.

[0088] For each cluster: analyzing the data sources of all second grids in the cluster to determine the home serving cell representation corresponding to each second grid, performing deduplication processing on the extracted home serving cell identifiers to obtain all serving cells existing under the cluster, and associating all serving cells existing under the cluster with the physical base station corresponding to the cluster to determine the serving cells corresponding to the physical base station, and finally outputting the position information of the physical base station and the corresponding serving cell list.

[0089] The embodiment obtains a plurality of second grids of the base station by performing grid processing on a plurality of grids existing in the base station coverage area, performs clustering on the grid feature data of the plurality of second grids to obtain at least one cluster corresponding to the base station, and determines a physical base station and the position information of the physical base station according to the cluster. By multi-level grid processing, the data complexity is effectively reduced, and the processing effect is improved. The clustering algorithm can effectively identify the coverage characteristics of the physical base station, thereby providing a reliable base station positioning result. The embodiment also realizes prediction of the positions of full-quantity physical base stations such as remote sites, single / dual-sector sites, CRAN sites, and standard base stations in the existing network.

[0090] As shown in Figure 8 The embodiment of the present application provides a base station positioning device 200, which can include a processing module 201 and a merging module 202. The processing module 201 is configured to determine the core coverage area of each serving cell according to the terminal-side measurement data set of the serving cell.

[0091] The merging module 202 is configured to merge the core coverage areas of the serving cells under the same base station to determine the base station coverage area of the base station.

[0092] The processing module 201 is further configured to determine at least one physical base station corresponding to the base station and the position information of the physical base station according to the base station coverage area.

[0093] Optionally, the processing module 201 is further configured to: perform rasterization processing on the terminal-side measurement data set of each serving cell respectively to obtain a plurality of first grids of the serving cells; divide the plurality of first grids of each serving cell according to the grid signals of the first grids respectively to obtain a plurality of strong signal grids of the serving cells and weak signal grids of the serving cells; perform clustering on the plurality of strong signal grids of each serving cell to determine a clustering core area of the serving cell; perform data backfilling on the clustering core area of each serving cell according to the grid feature data of the weak signal grids to obtain a core coverage area of the serving cell.

[0094] Optionally, the processing module 201 is further configured to: calculate a mean shift vector of each strong signal grid according to the grid feature data of the strong signal grids of each serving cell, a target bandwidth parameter, and a preset Gaussian kernel function; perform iterative updating of a clustering center according to the mean shift vector of each strong signal grid to obtain a plurality of clustering clusters of each serving cell; determine a clustering core area of each serving cell according to the grid density of each clustering cluster.

[0095] Optionally, the processing module 201 is further configured to: perform rasterization processing on a plurality of grids existing in the base station coverage area to obtain a plurality of second grids of the base station; perform clustering on the grid feature data of the plurality of second grids to obtain at least one clustering cluster corresponding to the base station; determine a physical base station and location information of the physical base station according to the clustering cluster.

[0096] Optionally, the processing module 201 is further configured to: extract location features of each second grid in the clustering cluster to determine a plurality of central latitudes corresponding to the clustering cluster and a plurality of central longitudes corresponding to the clustering cluster perform mean value calculation on the plurality of central longitudes corresponding to the clustering cluster and the plurality of central latitudes corresponding to the clustering cluster respectively to obtain an average longitude and an average latitude; determine the location information of the physical base station according to the average longitude and the average latitude, and take a serving cell existing under the clustering cluster as a serving cell corresponding to the physical base station.

[0097] Optionally, the control module 202 is further configured to: Field optimization is performed on the multiple original measurement data points of each serving cell according to the target field, to obtain multiple first measurement data points of the each serving cell; Default item deletion is performed on the each first measurement data point, to obtain multiple second measurement data points of the each serving cell; Abnormal item deletion is performed on the each second measurement data point, to obtain a terminal-side measurement data set of the each serving cell.

[0098] Figure 9 A hardware structure schematic diagram of a base station positioning device provided by an embodiment of the present application is shown.

[0099] The base station positioning device can include a processor 301 and a memory 302 storing computer program instructions.

[0100] Specifically, the processor 301 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0101] The memory 302 can include a mass storage for data or instructions. By way of example and not limitation, the memory 302 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 302 can include a removable or non-removable (or fixed) medium, or the memory 302 is a non-volatile solid-state memory. The memory 302 can be internal or external to the integrated gateway disaster recovery device.

[0102] In one example, the memory 302 can be a read only memory (ROM). In one example, the ROM can be a mask programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0103] The memory 302 can include read-only memory (ROM), random-access memory (RAM), magnetic disk storage mediums, optical storage mediums, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Accordingly, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to perform the operations described with reference to the methods according to an aspect of the present disclosure.

[0104] The processor 301 implements functions by reading and executing computer program instructions stored in the memory 302. Figure 1 The base station positioning method in the illustrated embodiment.

[0105] In one example, the base station positioning device can further include a communication interface 303 and a bus 304. Wherein, as shown, the processor 301, the memory 302, the communication interface 303 are connected through the bus 304 and complete the communication between each other. Figure 9

[0106] The communication interface 303 is mainly used to realize the communication between each module, device, unit and / or equipment in the embodiments of the present application.

[0107] The bus 304 includes hardware, software, or both, that couples components of the base station positioning device to each other. By way of example, and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or a combination of two or more of these. Where suitable, the bus 304 can include one or more buses. Although specific buses are described and illustrated, the present application contemplates any suitable bus or interconnect.

[0108] The base station positioning device can be based on the base station positioning method, thereby realizing the functions described in combination with Figure 1 Figure 7 ​​The method for positioning a base station is described.

[0109] In addition, in combination with the method for positioning a base station in the above-described embodiments, the embodiments of the present application can provide a computer storage medium for implementation. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to implement any of the above-described embodiments of the method for positioning a base station.

[0110] The embodiments of the present application also provide a computer program product, which includes a computer program, and the computer program is executed by a processor to implement any of the above-described embodiments of the method for positioning a base station.

[0111] It needs to be clear that the present application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are omitted herein. In the above-described embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order of the steps, after understanding the spirit of the present application.

[0112] The functional blocks shown in the structural block diagrams described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc. When implemented in software, the elements of the present application are program or code segments used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. The "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of the machine-readable medium include electronic circuits, semiconductor memory devices, Read-Only Memory (ROM), flash memory, Erasable Read-Only Memory (EROM), floppy disks, Compact Disc Read-Only Memory (CD-ROM), optical disks, hard disks, optical fiber media, Radio Frequency (RF) links, etc. The code segments can be downloaded via a computer network such as the Internet, an intranet, etc.

[0113] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0114] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0115] The above merely illustrates the present application by way of specific implementation, and those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, module and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements shall be included in the protection scope of the present application.

Claims

1. A base station positioning method, characterized in that, The method includes: The core coverage area of ​​each serving cell is determined based on the terminal-side measurement dataset of each serving cell; The core coverage areas of each serving cell under the same base station are merged to determine the base station coverage area of ​​the base station; Based on the coverage area of ​​the base station, determine at least one physical base station corresponding to the base station and the location information of the physical base station.

2. The method according to claim 1, characterized in that, The step of determining the core coverage area of ​​each serving cell based on the terminal-side measurement dataset of each serving cell includes: The terminal-side measurement datasets of each serving cell are rasterized to obtain multiple first grids for each serving cell; The multiple first grids of each serving cell are divided according to the grid signal of each first grid to obtain multiple strong signal grids and weak signal grids of each serving cell. Clustering is performed on multiple strong signal grids of each serving cell to determine the cluster core region of each serving cell; Based on the grid feature data of each weak signal grid, the cluster core region of each serving cell is backfilled to obtain the core coverage area of ​​each serving cell.

3. The method according to claim 2, characterized in that, The step of clustering multiple strong signal grids of each serving cell to determine the cluster core region of each serving cell includes: Based on the grid feature data, target bandwidth parameters, and preset Gaussian kernel function of multiple strong signal grids of each serving cell, the mean drift vector of each strong signal grid is calculated. The cluster centers are iteratively updated based on the mean drift vector of each strong signal grid to obtain multiple clusters of each serving cell; The cluster core region of each serving cell is determined based on the grid density of each cluster.

4. The method according to claim 1, characterized in that, The step of determining at least one physical base station corresponding to the base station and the location information of the physical base station based on the base station coverage area includes: Multiple grids existing in the coverage area of ​​the base station are rasterized to obtain multiple second grids of the base station; Clustering is performed on the raster feature data of the plurality of second grids to obtain at least one cluster corresponding to the base station; The physical base station and its location information are determined based on the cluster.

5. The method according to claim 4, characterized in that, The step of determining the physical base station and its location information based on the cluster includes: Extract the positional features of each second grid cell in the cluster to determine multiple center latitudes and multiple center longitudes corresponding to the cluster; The average longitude and average latitude are calculated by taking the average longitude and average latitude of the clusters respectively. The location information of the physical base station is determined based on the average longitude and the average latitude, and the serving cells existing under the cluster are taken as the serving cells corresponding to the physical base station.

6. The method according to any one of claims 1 to 5, characterized in that, Before the step of determining the core coverage area of ​​each serving cell based on the terminal-side measurement dataset of each serving cell, the method further includes: The fields of multiple original measurement data points of each serving cell are optimized according to the target field to obtain multiple first measurement data points of each serving cell; Default items are deleted from each of the first measurement data points to obtain multiple second measurement data points for each serving cell; Anomalies are removed from each of the second measurement data points to obtain the terminal-side measurement dataset for each serving cell.

7. A base station positioning device, characterized in that, The device includes: The processing module is used to determine the core coverage area of ​​each serving cell based on the terminal-side measurement dataset of each serving cell; The merging module is used to merge the core coverage areas of each serving cell under the same base station to determine the base station coverage area of ​​the base station; The processing module is further configured to determine at least one physical base station corresponding to the base station and the location information of the physical base station based on the coverage area of ​​the base station.

8. A base station positioning device, characterized in that, The base station positioning device includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the base station positioning method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the base station positioning method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the base station positioning method as described in any one of claims 1-6.

Images