A base station co-siting determination method and apparatus

Abstract

The present disclosure provides a base station co-site determination method and device, wherein the method comprises: obtaining first data and second data; preprocessing the first data and the second data to obtain a first sample set and a second sample set; generating a first cluster and a second cluster using a clustering algorithm based on the first sample set and the second sample set; and determining that a 4G base station and a 5G base station are co-sited using an overlap algorithm based on the first cluster and the second cluster. The method can determine whether the 4G base station and the 5G base station are co-sited without measuring the longitude and latitude of the base station by obtaining the first data and the second data, and is suitable for a wide range of applications. The use of the first data and the second data is reduced by preprocessing the first data and the second data, thereby reducing the error caused by abnormal data. The accuracy of the base station co-site determination result is improved by using the overlap algorithm to determine that the 4G base station and the 5G base station are co-sited.

Description

Technical Field

[0001] This disclosure relates to the field of wireless communication, and in particular to a method and apparatus for determining co-location of base stations. Background Technology

[0002] In the field of wireless communication technology, determining whether 4G and 5G base stations co-locate is of great help in communication engineering, such as network planning, signal coverage, enhancing signal stability, and promoting the development of 5G networks. Related technologies typically determine co-location by obtaining the coverage area of ​​MR or MDT sampling points, but this has limited applicability and cannot confirm whether base stations in a cell pair with shared coverage are co-located. Alternatively, methods involve obtaining measurement information from primary and neighboring cells in the MR, extracting feature data from the base station dimension, and using a classification algorithm to train a model. Based on the trained model, base stations are classified to obtain the co-location identification results for all base stations. However, these methods require the participation of known information about different co-located sites when training the model based on base station-level feature data to confirm the co-located site model in the training model, thus determining whether the locations are co-located. This approach is inefficient and has limited applicability. Summary of the Invention

[0003] This disclosure provides a method and apparatus for determining co-location of base stations, in order to solve problems in related technologies, expand the applicability of the method for determining co-location of base stations, and improve the accuracy of the determination results.

[0004] A first aspect of this disclosure provides a method for determining base station co-location, the method comprising: acquiring first data and second data, wherein the first data is 4G measurement statistics (MR) data and / or minimized drive test (MDT) data, and the second data is 5G MR data and / or 5G MDT data, both the first data and the second data including reference received signal strength (RSRP); preprocessing the first data and the second data to obtain a first sample set and a second sample set; generating a first cluster and a second cluster using a clustering algorithm based on the first sample set and the second sample set, wherein the first cluster is a 4G base station cluster and the second cluster is a 5G base station cluster; and determining the co-location of 4G base stations and 5G base stations using an overlap degree algorithm based on the first cluster and the second cluster.

[0005] In some embodiments of this disclosure, preprocessing the first data and the second data to obtain the first sample set and the second sample set includes: using an anomaly filtering algorithm to remove abnormal data from the first data and the second data; and determining the first sample set and the second sample set based on the first data and the second data after removing the abnormal data.

[0006] In some embodiments of this disclosure, the first data and the second data further include at least one of the following: Physical Cell Identifier (PCI), Cell Antenna Frequency (arfcn), Sub-cell User Longitude, and Sub-cell User Latitude.

[0007] In some embodiments of this disclosure, generating a first cluster and a second cluster using a clustering algorithm based on a first sample set and a second sample set includes: determining the number of clusters to be divided in the first sample set (k1) and the number of clusters to be divided in the second sample set (k2); determining k1 center data points for the first cluster based on the first sample set; determining k2 center data points for the second cluster based on the second sample set; calculating the distance between a sample in the first sample set and the k1 center data points; calculating the distance between a sample in the second sample set and the k2 center data points; and determining the cluster of a sample, wherein the center data point of the cluster is closest to the sample.

[0008] In some embodiments of this disclosure, the method further includes: calculating the centroids of clusters in the first and second clusters; determining the centroids as the center data of clusters in the first and second clusters to achieve iteration; and stopping the iteration when the algorithm reaches the maximum number of iterations or when the samples meet preset conditions.

[0009] In some embodiments of this disclosure, the method further includes: establishing an objective function based on the centroids of the first and second clusters, wherein the objective function is used to determine whether a sample satisfies a preset condition.

[0010] In some embodiments of this disclosure, according to the method of claim 1, the method is characterized in that, based on the first type of cluster and the second type of cluster, the method of using an overlap algorithm to determine the co-location of 4G base stations and 5G base stations includes: taking the centroid of the second type of cluster or the cluster in the first type of cluster as the center, calculating the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius; if the Gaussian distribution overlap between the first type of cluster and the second type of cluster is greater than a preset value, the co-location of 4G base stations and 5G base stations is determined.

[0011] A second aspect of this disclosure provides a base station co-location determination apparatus, comprising: an acquisition unit for acquiring first data and second data, wherein the first data is 4G Measurement Statistics (MR) data or 4G Minimum Drive Test (MDT) data, and the second data is 5G MR data or 5G Minimum Drive Test (GMDT) data, both the first and second data including Reference Received Signal Strength (RSRP); a first processing unit for preprocessing the first and second data to obtain a first sample set and a second sample set; a second processing unit for generating a first cluster and a second cluster based on the first and second sample sets using a clustering algorithm, wherein the first cluster is a 4G base station cluster and the second cluster is a 5G base station cluster; and a third processing unit for determining the co-location of 4G base stations and 5G base stations based on the first and second clusters using an overlap algorithm.

[0012] A third aspect of this disclosure provides a communication device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods described in the first aspect of this disclosure.

[0013] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first aspect of this disclosure.

[0014] In summary, the base station co-location determination method proposed in this disclosure includes: acquiring first data and second data; preprocessing the first data and second data to obtain a first sample set and a second sample set; generating a first cluster and a second cluster using a clustering algorithm based on the first sample set and the second sample set; and determining the co-location of a 4G base station and a 5G base station using an overlap degree algorithm based on the first cluster and the second cluster. This method, by acquiring the first data and second data, can determine whether a 4G base station and a 5G base station are co-located without measuring the latitude and longitude of the base stations, thus having a wide range of applications. Preprocessing the first data and second data reduces the amount of data used for solving the problem and reduces errors caused by abnormal data. Using the overlap degree algorithm to determine the co-location of a 4G base station and a 5G base station improves the applicability of the solution and the accuracy of the base station co-location determination results.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0017] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0018] Figure 2 A flowchart illustrating a method for determining a base station co-location according to an embodiment of this disclosure;

[0019] Figure 3 A flowchart illustrating another method for determining a base station co-location as provided in this disclosure embodiment;

[0020] Figure 4 A flowchart illustrating yet another method for determining a base station co-location, as provided in this disclosure embodiment;

[0021] Figure 5 A flowchart illustrating another method for determining a base station co-location as provided in this disclosure;

[0022] Figure 6 A flowchart illustrating another method for determining a base station co-location as provided in this disclosure embodiment;

[0023] Figure 7 This is a schematic diagram of a cluster distribution provided in an embodiment of the present disclosure;

[0024] Figure 8 A flowchart illustrating yet another method for determining a base station co-location, as provided in this disclosure embodiment;

[0025] Figure 9 A schematic diagram of Gaussian distribution overlap provided in an embodiment of this disclosure;

[0026] Figure 10 Another Gaussian distribution overlap diagram provided in this embodiment of the disclosure;

[0027] Figure 11 This is a schematic diagram of the structure of a base station co-site determination device provided in an embodiment of this disclosure;

[0028] Figure 12 This is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure. Detailed Implementation

[0029] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0030] In the field of wireless communication technology, determining whether 4G and 5G base stations share a site is of great help for communication engineering such as network planning, signal coverage, enhancing signal stability, and promoting the development of 5G networks. However, how to quickly and accurately determine whether base stations share a site is a major technical challenge.

[0031] The relevant technical solutions are briefly introduced below:

[0032] By measuring and statistically analyzing the Reference Received Signal Strength (RSRP), Timing Advance (TA), and local cell location information of the primary neighboring cells obtained from MR (Mean Detection and Ranging) data, feature data is extracted based on the base station dimension, and a classification algorithm is used for model training. The model classifies the base stations and outputs the co-location identification results for all base stations.

[0033] The above solution has the following drawbacks:

[0034] (1) In the above measurement report, the neighbor cell data measured by the main cell is limited by the terminal measurement results and the number of reports, and the data obtained is limited. At the same time, it cannot reflect the field strength of neighbor cells of multiple frequency bands and standards at each sampling point location, which may lead to a large error in the results.

[0035] (2) When using feature data at the base station dimension for model training, it is necessary to obtain information on different sites with co-location in order to confirm the co-location site model in the training model and then determine whether unknown sites are co-located, resulting in a limited scope of application.

[0036] To address the problems existing in related technologies, this disclosure proposes a method for determining co-location of base stations. By acquiring first and second data, it eliminates the need for known information about co-location sites or the latitude and longitude of existing sites to participate in the judgment, thus broadening its applicability. Through an overlap degree algorithm, it determines the co-location of 4G and 5G base stations, improving the applicability of the solution and the accuracy of the base station co-location determination results.

[0037] Before introducing the detailed solution of this disclosure, the application scenario of this disclosure solution will be described first. Figure 1 This is an application scenario diagram of a base station co-location determination method in one embodiment.

[0038] like Figure 1 As shown, this application scenario includes a 4G base station 101, one or more users 102, and a 5G base station 103, wherein user 102 is a user covered by the cell of 4G base station 101 and / or 5G base station 103. By obtaining the first data and the second data of user 102, the method described in this disclosure can be used to determine whether 4G base station 101 and 5G base station 103 share the same site.

[0039] It is understood that the scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions proposed in the embodiments of this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in the embodiments of this disclosure are also applicable to similar technical problems.

[0040] The following embodiments of this disclosure can be applied to Figure 1 The application scenarios shown include, but are not limited to, the communication systems or parts thereof. Figure 1 The entities shown are illustrative; a communication system may include... Figure 1 All or part of the main body, or may include Figure 1Other entities besides the main body, the number and form of each entity are arbitrary, the connection relationship between the entities is illustrative, the entities may not be connected or may be connected, and the connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0041] The present disclosure will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0042] Figure 2 This is a flowchart illustrating a method for determining a base station co-location according to an embodiment of this disclosure. Figure 2 As shown, steps 201-204 are included.

[0043] Step 201: Obtain the first data and the second data.

[0044] In some embodiments, the method of acquiring the first data and the second data is not limited, such as acquiring them through periodic measurement or from a big data center.

[0045] In some embodiments, the first data is 4G measurement statistics (MR) data and / or 4G minimized drive test (MDT) data, and the second data is 5G MR data and / or 4G minimized drive test (GMDT) data.

[0046] In some embodiments, both the first data and the second data include the reference signal received strength (RSRP).

[0047] In some embodiments, the first data and the second data further include at least one of the following: Physical Cell Identifier (PCI), Cell Antenna Frequency (arfcn), Sub-cell User Longitude, and Sub-cell User Latitude.

[0048] For example, by acquiring the original measurement report (MRO) data of 4G base stations and 5G base stations in the target area and parsing the MRO, MR data such as PCI, arfcn, longitude, latitude, RSRP, and arfcn of multiple cells covered by 4G base stations and 5G base stations in the target area can be obtained.

[0049] Step 202: Preprocess the first data and the second data to obtain the first sample set and the second sample set.

[0050] In some embodiments, the first data and the second data are preprocessed to remove abnormal data, resulting in a first sample set and a second sample set. This improves the reliability of the first data and the second data, while reducing the pressure of data reading and clustering operations.

[0051] In some embodiments, the first sample set is a dataset formed by removing outlier data from the first dataset, and the second sample set is a dataset formed by removing outlier data from the second dataset.

[0052] In some embodiments, the first and second data can be preprocessed using the Box-plot function, but this is not limited to that. The first and second data can also be preprocessed using the 3-sigma principle, the Z-score function, etc. This disclosure does not limit the preprocessing methods.

[0053] In some embodiments, each sample in the sample set may include multiple parameters. For example, the latitude of the user under each cell and the longitude of the user under that latitude can form a sample in a sample.

[0054] Step 203: Based on the first sample set and the second sample set, use a clustering algorithm to generate the first cluster and the second cluster.

[0055] In some embodiments, based on a first sample set and a second sample set, a clustering algorithm is used to generate a first cluster and a second cluster, laying the foundation for determining the co-location of 4G base stations and 5G base stations.

[0056] In some embodiments, the first cluster is a 4G base station cluster and the second cluster is a 5G base station cluster, wherein the first cluster may contain one or more clusters and the second cluster may contain one or more clusters.

[0057] In some embodiments, the clustering algorithm may be the K-means algorithm, but is not limited thereto. It may also be the DBSCAN algorithm, Mean shift algorithm, or other algorithms that can divide the data into different clusters. This disclosure does not limit the specific algorithms used.

[0058] Step 204: Based on the first and second cluster types, use the overlap algorithm to determine the co-location of 4G and 5G base stations.

[0059] In some embodiments, an overlap algorithm can be used to calculate the Gaussian distribution overlap between the first type of cluster and the single second type of cluster within a preset radius of the centroid of a single second type of cluster. Based on the Gaussian distribution overlap calculation results, the co-location of 4G base stations and 5G base stations can be determined.

[0060] In other words, an overlap algorithm can also be used to calculate the Gaussian distribution overlap between the second type of cluster and the aforementioned single first type of cluster within a preset radius of the centroid of a single first type of cluster. Based on the Gaussian distribution overlap calculation results, the co-location of 4G base stations and 5G base stations can be determined.

[0061] In summary, the base station co-location determination method proposed in this disclosure includes: acquiring first data and second data; preprocessing the first data and second data to obtain a first sample set and a second sample set; generating a first cluster and a second cluster using a clustering algorithm based on the first sample set and the second sample set; and determining the co-location of 4G and 5G base stations using an overlap degree algorithm based on the first cluster and the second cluster. This method, by acquiring the first data and second data, can determine whether 4G and 5G base stations are co-located without measuring the latitude and longitude of the base stations, thus having a wide range of applications. Preprocessing the first data and second data reduces the amount of data used for solving the problem and reduces errors caused by abnormal data. Using the overlap degree algorithm to determine the co-location of 4G and 5G base stations improves the applicability of the scheme and the accuracy of the base station co-location determination results.

[0062] Figure 3 A flowchart of a base station co-site determination method proposed in this disclosure is further shown. Based on Figure 2 The illustrated embodiment further explains step 202. Figure 3 It includes the following steps.

[0063] Step 301: Use an anomaly filtering algorithm to remove abnormal data from the first and second data sets.

[0064] In some embodiments, by using an anomaly filtering algorithm to remove abnormal data from the first data and the second data, the reliability of the first data and the second data is improved, thereby improving the accuracy of the method and reducing computational pressure.

[0065] In some embodiments, the type of abnormal data in the first data and the second data is not limited, such as abnormal data location of longitude or latitude data, abnormal data value of RSRP data, etc.

[0066] In some embodiments, the first and second data can be preprocessed using the Box-plot function, but this is not limited to that. The first and second data can also be preprocessed using the 3-sigma principle, the Z-score function, etc. This disclosure does not limit the preprocessing methods.

[0067] In some embodiments, a box plot can be generated using the Box-plot function to identify outliers in the first and second datasets.

[0068] Figure 4 Here is an example diagram of a box plot, such as Figure 4As shown, the lower quartile (Q1) is the value of the sample located at approximately one-quarter of the total values ​​in the first or second sample, arranged from smallest to largest; the median (Q2) is the value of the sample located at approximately one-half of the total values ​​in the first or second sample, arranged from smallest to largest; the upper quartile (Q3) is the value of the sample located at approximately three-quarters of the total values ​​in the first or second sample, arranged from smallest to largest; the interquartile range (IQR) is the difference between Q3 and Q2; the upper limit of the box plot is the sum of Q3 and 1.5 times the IQR, and the lower limit of the box plot is the difference between Q1 and 1.5 times the IQR; sample values ​​outside the upper or lower limits of the box plot are considered outliers.

[0069] Step 302: Based on the first data and the second data after removing outlier data, determine the first sample set and the second sample set.

[0070] In some embodiments, all or part of the first data after removing abnormal data can be determined as the first sample set. For example, the sample data located between Q1 and Q3 in the box plot generated by the first data using the Box-plot function can be determined as the first sample set; or, for example, the sample data located between the upper limit and the lower limit in the box plot generated by the first data using the Box-plot function can be determined as the first sample set. This disclosure does not limit this.

[0071] In some embodiments, all or part of the second data after removing outlier data can be determined as the second sample set. For example, the sample data located between Q1 and Q3 in the box plot generated by the second data using the Box-plot function can be determined as the second sample set; or, for example, the sample data located between the upper limit and the lower limit in the box plot generated by the second data using the Box-plot function can be determined as the second sample set. This disclosure does not limit this.

[0072] In summary, according to the base station co-location determination method proposed in this disclosure, an anomaly filtering algorithm is used to remove abnormal data from the first and second data sets; based on the first and second data sets after removing abnormal data, the first and second sample sets are determined, thereby improving the reliability of the data in the first and second datasets, improving the accuracy of this method, and reducing the subsequent computational burden.

[0073] Figure 5 A flowchart of a base station co-site determination method proposed in this disclosure is further shown. Based on Figure 2 The illustrated embodiment further explains step 203. Figure 5 It includes the following steps.

[0074] Step 501: Determine the number of clusters to be divided in the first sample set k1 and the number of clusters to be divided in the second sample set k2.

[0075] In some embodiments, the number of clusters to be divided in the first sample set k1 and the number of clusters to be divided in the second sample set k2 can be randomly determined.

[0076] Optionally, in some embodiments, the number of 4G base stations and 5G base stations can be estimated based on the cell antenna frequency point arfcn in the first data and the second data, and then the estimated number of 4G base stations can be determined as the number of clusters to be divided in the first sample set k1, and the estimated number of 5G base stations can be determined as the number of clusters to be divided in the second sample set k2.

[0077] Step 502: Based on the first sample set, determine k1 central data points of the first cluster.

[0078] In some embodiments, k1 4GMR samples in the first sample set may be randomly selected as k1 central data points of the first cluster, or k1 4GMDT samples in the first sample set may be randomly selected as k1 central data points of the first cluster, or k1 central data points of the first cluster may be determined based on preset rules. For example, the 4GMDT samples in the first sample set may be divided into k1 segments on average, and the median sample in each segment may be determined as the central data point of the first cluster. This disclosure does not limit the method of determining the k1 central data points of the first cluster.

[0079] Step 503: Based on the second sample set, determine the k2 central data points of the second cluster.

[0080] In some embodiments, k2 5GMR samples from the second sample set may be randomly selected as k1 central data points of the second cluster, or k2 5GMDT samples from the second sample set may be randomly selected as k2 central data points of the second cluster, or the k2 central data points of the second cluster may be determined based on preset rules. For example, the 5GMR samples in the second sample set may be divided into k2 segments on average, and the median sample in each segment may be determined as the central data point of the second cluster. This disclosure does not limit the method of determining the k2 central data points of the second cluster.

[0081] Step 504: Calculate the distance between the samples in the first sample set and the k1 central data points.

[0082] In some embodiments, the distance between each sample in the first sample set and the k1 central data can be calculated based on the coordinates of the samples in the first sample set and the coordinates of the k1 central data. The distance can be calculated using formulas such as the Euclidean distance formula and the semi-sine formula. This disclosure does not limit the calculation method for the distance between the samples in the first sample set and the k1 central data.

[0083] Step 505: Calculate the distance between the samples in the second sample set and the k2 central data points.

[0084] In some embodiments, the distance between each sample in the second sample set and the k2 center data can be calculated based on the coordinates of the samples in the second sample set and the coordinates of the k2 center data. The distance can be calculated using formulas such as the Euclidean distance formula and the semi-sine formula. This disclosure does not limit the calculation method for the distance between the samples in the second sample set and the k2 center data.

[0085] Step 506: Determine the cluster of the sample.

[0086] In some embodiments, the clusters of samples can be determined based on the distance between the samples in the sample set and the center data, wherein the center data of the cluster is closest to the sample.

[0087] In other words, the cluster corresponding to the nearest central data point to a sample in the first sample set among the k1 central data points can be determined as the cluster of that sample, and the cluster corresponding to the nearest central data point to a sample in the second sample set among the k2 central data points can be determined as the cluster of that sample.

[0088] In summary, according to the base station co-location determination method proposed in this disclosure, the generation of a first cluster and a second cluster based on a first sample set and a second sample set using a clustering algorithm includes: determining the number of clusters to be divided in the first sample set (k1) and the number of clusters to be divided in the second sample set (k2); determining k1 center data points for the first cluster based on the first sample set; determining k2 center data points for the second cluster based on the second sample set; calculating the distance between a sample in the first sample set and the k1 center data points; calculating the distance between a sample in the second sample set and the k2 center data points; and determining the cluster of a sample, wherein the center data point of the cluster is closest to the sample. This method, by calculating the distance between samples and center data points in the first and second sample sets, determines the clusters of samples in the first and second sample sets, laying the foundation for determining the co-location of 4G and 5G base stations.

[0089] Figure 6 A flowchart of a base station co-site determination method proposed in this disclosure is further shown. Based on Figure 5 In the illustrated embodiment, the method further includes the following steps.

[0090] Step 601: Calculate the centroids of the first and second type clusters.

[0091] In some embodiments, the centroids of clusters in the first and second types of clusters can be calculated using the following formula:

[0092]

[0093] Among them, u i C represents the centroid of a cluster within a cluster class. i Represents a cluster, |C i | represents the number of samples in the cluster, and x represents the coordinates of the samples in the cluster. It should be understood that the cluster in the above parameter explanation can be either the first cluster or the second cluster. In other words, the centroid of both the first and second clusters can be calculated using Equation 1.

[0094] Step 602: Determine the centroid as the center data of the middle cluster of the first or second type of cluster to achieve iteration.

[0095] In some embodiments, the centroid is determined as the center data of the middle cluster of the first or second type of cluster to achieve iteration.

[0096] For example, when the centroid of a cluster is determined for the first time, the centroid obtained in step 601 can replace the center data of the first cluster determined in step 502 and be determined as the new center data of the first cluster, or replace the center data of the second cluster determined in step 503 and be determined as the new center data of the second cluster, so as to achieve iteration.

[0097] In some embodiments, iterative calculations of cluster centroids can be performed by repeating steps 504-602 described above.

[0098] For example, when the centroid of a cluster is determined through iteration for the Nth time, the centroid determined for the Nth time can be used to replace the center data of the cluster (i.e., the centroid of the cluster is determined for the N-1th time) in order to determine the new center data of the cluster.

[0099] Step 603: Stop iterating when the algorithm reaches the maximum number of iterations or when the sample meets the preset conditions.

[0100] In some embodiments, a maximum number of iterations can be preset so that the algorithm stops iterating when it reaches the maximum number of iterations.

[0101] In some embodiments, iteration may be stopped when a sample meets a preset condition, such as when the position change of the centroid in two adjacent iterations meets a preset condition.

[0102] In some alternative embodiments, an objective function can be established based on the centroids of the first and second clusters to determine whether a sample meets a preset condition through the calculated value of the objective function. In other words, the objective function is used to determine whether a sample meets a preset condition.

[0103] For example, let's take the objective function as the formula for the squared difference between the samples and the center data in a cluster. The objective function is as follows:

[0104]

[0105] Among them, C i Let x represent a cluster, and let C represent a cluster. i The sample in, u i Representing cluster C i The central data (i.e., cluster C) i (centroid), E represents the squared difference between the sample and the center of the cluster, and it should be understood that C i It can be either the first type of cluster or the second type of cluster. When the E value calculated by Equation 2 meets the range of the preset conditions, it is determined that the sample meets the preset conditions, and the iteration stops.

[0106] In summary, the base station co-location determination method proposed in this disclosure includes: calculating the centroids of clusters in the first and second types of clusters; determining the centroids as the center data of clusters in the first or second type of clusters to achieve iteration; stopping the iteration when the algorithm reaches the maximum number of iterations or when the samples meet the preset conditions, thereby improving the accuracy of clustering the samples in the sample set through cluster iteration, and thus improving the accuracy of base station co-location determination.

[0107] Figure 8 A flowchart of a base station co-site determination method proposed in this disclosure is further shown. Based on Figure 2 The illustrated embodiment further explains step 204. Figure 8 It includes the following steps.

[0108] Step 701: Using the centroid of the second type of cluster or the cluster in the first type of cluster as the center, calculate the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius.

[0109] In some embodiments, the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius can be calculated with the centroid of the cluster in the second type of cluster as the center, or the Gaussian distribution overlap between the second type of cluster and the first type of cluster within a preset radius can be calculated with the centroid of the cluster in the first type of cluster as the center, thereby determining whether the 4G base station and the 5G base station are co-located.

[0110] In some embodiments, the present disclosure does not limit the length of the preset radius, which may be, for example, 200 meters, 400 meters, etc.

[0111] In some embodiments, the probability density function of the Gaussian mixture model is as follows:

[0112]

[0113] Where, α i G(X, μ) represents the Gaussian mixing coefficient. i , Σ i ) represents the Gaussian distribution of the i-th cluster, where αi >0 and

[0114] Specifically, G(X, μ) i , Σ i It can be calculated using the following formula:

[0115]

[0116] Where d represents the number of dimensions of the sample (for example, when each sample includes the longitude of the user under the cell and the longitude of the user under the cell, d takes the value of 2; when each sample includes RSRP, the longitude of the user under the cell and the longitude of the user under the cell, d takes the value of 3), Σ is the covariance matrix of the samples in the i-th cluster, μ is the mean of the samples in the i-th cluster, and X is the sample in the i-th cluster.

[0117] In some embodiments, a two-dimensional Gaussian distribution is used as an example (i.e., when d = 2 in Equation 4). When two Gaussian distributions are mixed, two peaks and a saddle will appear, such as... Figure 9 As shown; when the two Gaussian distributions are almost completely mixed, the saddle may disappear, but the peak remains. In this case, there is only one distinct peak, as shown. Figure 10 As shown.

[0118] Furthermore, based on Equation 3, the Gaussian mixture overlap can be determined using the following formula:

[0119]

[0120] Among them, OLR(G1, G X ), representing Gaussian distributions G1 and G X Gaussian mixture overlap between G1 and G, if P(X) has onepeak, indicates that G1 and G X There is only one peak between them, in which case the Gaussian mixture overlap is 1; if P(X) has two peaks, it means that G1 and G... X When both lower and higher peaks exist simultaneously, the Gaussian mixture overlap is determined by the saddle point and the lower peak in P(X). The saddle point is represented by P(X). saddle The lower peak is represented by P(X). sulbmax The diagram below shows an OLR representation. It should be understood that OLR does not represent the proportion of data falling within the overlapping area; therefore, it is unrelated to the amount of data, but only to the distribution of the data.

[0121] Step 702: The Gaussian distribution overlap between the first cluster and the second cluster is greater than a preset value, thus determining that the 4G base station and the 5G base station share the same site.

[0122] In some embodiments, the co-location of 4G and 5G base stations can be determined based on the Gaussian distribution overlap between the first and second clusters. Specifically, when the Gaussian distribution overlap between the first and second clusters is greater than a preset value, it is determined that there is significant overlap between the first and second clusters, thereby determining that 4G and 5G base stations are co-located. Conversely, when the Gaussian distribution overlap between the first and second clusters is less than or equal to a preset value, it is considered that there is no correlation between the clusters, i.e., there is no overlap between 4G and 5G base stations.

[0123] In summary, the base station co-location determination method proposed in this disclosure includes: using the centroid of a cluster in the second type of cluster or the first type of cluster as the center, calculating the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius; if the Gaussian distribution overlap between the first type of cluster and the second type of cluster is greater than a preset value, the co-location of the 4G base station and the 5G base station is determined. This enables the determination of the co-location of the 4G base station and the 5G base station using user parameters within the coverage area of ​​the base station when the base station site is unknown, thereby improving the efficiency of base station co-location determination.

[0124] Therefore, this solution has the following beneficial effects:

[0125] 1. By acquiring MR or MDT data of 4G and 5G, it is possible to determine whether 4G and 5G base stations are co-located without measuring the latitude and longitude of the base stations.

[0126] 2. By preprocessing 4G and 5G MR or MDT data, the amount of data used for solving the problem is reduced, and the error caused by abnormal data is reduced.

[0127] 3. By using an overlap algorithm to determine the co-location of 4G and 5G base stations, the applicability of the solution and the accuracy of the base station co-location determination results are improved.

[0128] Figure 11 This is a schematic diagram of the structure of a base station co-location determination device 1100 provided in an embodiment of this disclosure. Figure 11 As shown, the base station co-site determination device includes:

[0129] The acquisition unit 1110 is used to acquire first data and second data, wherein the first data is 4G measurement statistics (MR) data or 4G minimum drive test (MDT) data, and the second data is 5G MR data or 5G MDT data. Both the first data and the second data include the reference signal received strength (RSRP).

[0130] The first processing unit 1120 is used to preprocess the first data and the second data to obtain the first sample set and the second sample set.

[0131] The second processing unit 1130 is used to generate a first cluster and a second cluster based on the first sample set and the second sample set using a clustering algorithm, wherein the first cluster is a 4G base station cluster and the second cluster is a 5G base station cluster.

[0132] The third processing unit 1140 is used to determine the co-location of 4G base stations and 5G base stations based on the first and second clusters and using an overlap algorithm.

[0133] According to the base station co-location determination apparatus proposed in this disclosure, a first data and a second data are acquired by an acquisition unit. The first data is 4G measurement statistics (MR) data or 4G minimum drive test (MDT) data, and the second data is 5G MR data or 5G MDT data. Both the first data and the second data include the reference received signal strength (RSRP). A first processing unit 1120 preprocesses the first data and the second data to obtain a first sample set and a second sample set. A second processing unit generates a first cluster and a second cluster based on the first sample set and the second sample set using a clustering algorithm. The first cluster is a 4G base station cluster, and the second cluster is a 5G base station cluster. A third processing unit determines the co-location of 4G base stations and 5G base stations based on the first cluster and the second cluster using an overlap algorithm. Therefore, by acquiring the first and second data, it is possible to determine whether 4G and 5G base stations are co-located without measuring the latitude and longitude of the base stations, which has a wide range of applications. By preprocessing the first and second data, the amount of data used for solving the problem is reduced, and the error caused by abnormal data is reduced. By using the overlap algorithm, the accuracy of the co-location determination results of 4G and 5G base stations is improved.

[0134] In some embodiments of this disclosure, the first processing unit 1120 is used to use an anomaly filtering algorithm to remove abnormal data from the first data and the second data; and to determine a first sample set and a second sample set based on the first data and the second data after removing the abnormal data.

[0135] In some embodiments of this disclosure, the first data and the second data further include at least one of the following: Physical Cell Identifier (PCI), Cell Antenna Frequency (arfcn), Sub-cell User Longitude, and Sub-cell User Latitude.

[0136] In some embodiments of this disclosure, the second processing unit 1130 is configured to determine the number of clusters to be divided in the first sample set (k1) and the number of clusters to be divided in the second sample set (k2); determine k1 center data points of the first cluster based on the first sample set; determine k2 center data points of the second cluster based on the second sample set; calculate the distance between the sample in the first sample set and the k1 center data points; calculate the distance between the sample in the second sample set and the k2 center data points; and determine the cluster of the sample, wherein the center data point of the cluster is closest to the sample.

[0137] In some embodiments of this disclosure, the third processing unit 1140 is used to calculate the centroids of the clusters in the first type of cluster and the second type of cluster; determine the centroid as the center data of the cluster in the first type of cluster or the second type of cluster to achieve iteration; and stop the iteration when the algorithm reaches the maximum number of iterations or the sample meets the preset conditions.

[0138] In some embodiments of this disclosure, the third processing unit 1140 is used to establish an objective function based on the centroids of the first and second clusters, wherein the objective function is used to determine whether a sample satisfies a preset condition.

[0139] In some embodiments of this disclosure, the third processing unit 1140 is used to calculate the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius, with the centroid of the second type of cluster or the cluster in the first type of cluster as the center; if the Gaussian distribution overlap between the first type of cluster and the second type of cluster is greater than a preset value, it is determined that the 4G base station and the 5G base station are co-located.

[0140] It should be noted that the base station co-location determination device provided in the above embodiments is only illustrated by the division of the above program modules when determining the base station co-location. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the base station co-location determination device can be divided into different program modules to complete all or part of the processing described above.

[0141] Since the apparatus provided in this embodiment corresponds to the methods provided in the above embodiments, the implementation of the methods is also applicable to the apparatus provided in this embodiment, and will not be described in detail in this embodiment.

[0142] The methods and apparatus provided in the embodiments of this application have been described above. To implement the functions of the methods provided in the embodiments of this application, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0143] Figure 12 This is a schematic diagram of the hardware composition structure of the communication device provided in the embodiments of this disclosure, such as... Figure 12As shown, the communication device 1200 includes at least one processor 1202; and a memory 1201 communicatively connected to the at least one processor 1202; wherein the memory 1201 stores instructions executable by the at least one processor 1202, the instructions being executed by the at least one processor 1202 to implement the steps of the base station co-location determination method according to the embodiments of this disclosure; or, the instructions being executed by the at least one processor 1202 to implement the steps of the base station co-location determination method according to the embodiments of this disclosure.

[0144] It is understood that the communication device also includes a communication interface 1203. The various components in the communication device are coupled together via a bus system 1204. It is understood that the bus system 1204 is used to implement communication between these components. In addition to a data bus, the bus system 1204 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 12 The general designated all buses as Bus System 1204.

[0145] It is understood that memory 1201 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 1201 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0146] The methods disclosed in the above embodiments can be applied to, or implemented by, processor 1202. Processor 1202 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware of processor 1202 or by instructions in software form.

[0147] The processor 1202 described above can be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 1202 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules can be located in a storage medium, which is located in the memory 1201. The processor 1202 reads information from the memory 1201 and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0148] In an exemplary embodiment, the communication device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0149] This disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, which, when executed, implement the steps of the base station co-location determination method described in this embodiment of the invention.

[0150] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0151] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0152] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0153] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). In addition, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning paper or other media, followed by editing, interpreting or otherwise processing as necessary, and then stored in computer memory.

[0154] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0155] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0156] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0157] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method of determining co-siting of base stations, characterized by, The methods include: Acquire first data and second data, wherein the first data is 4G measurement statistics (MR) data and / or 4G minimum drive test (MDT) data, and the second data is 5G MR data and / or 5G MDT data, and both the first data and the second data include reference signal received strength (RSRP). The first data and the second data are preprocessed to obtain a first sample set and a second sample set; Based on the first sample set and the second sample set, a clustering algorithm is used to generate a first cluster and a second cluster, wherein the first cluster is a 4G base station cluster and the second cluster is a 5G base station cluster; Based on the first cluster and the second cluster, the overlap algorithm is used to determine the co-location of 4G base stations and 5G base stations. The step of determining the co-location of 4G and 5G base stations using an overlap algorithm based on the first and second cluster types includes: Using the centroid of a cluster in the second type of cluster or the first type of cluster as the center, calculate the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius; If the Gaussian distribution overlap between the first cluster and the second cluster is greater than a preset value, it is determined that the 4G base station and the 5G base station share the same site. The method further includes: When the Gaussian distribution overlap between the first cluster and the second cluster is less than or equal to a preset value, it is determined that the 4G base station and the 5G base station do not overlap.

2. The method of claim 1, wherein, The preprocessing of the first data and the second data to obtain the first sample set and the second sample set includes: An anomaly filtering algorithm is used to remove abnormal data from the first data and the second data. Based on the first data and the second data after removing the abnormal data, the first sample set and the second sample set are determined.

3. The method of claim 1, wherein, The first and second data also include at least one of the following: Physical Cell Identifier (PCI), Cell Antenna Frequency (arfcn), User Longitude under the Cell, and User Latitude under the Cell.

4. The method of claim 1, wherein, The step of generating a first cluster and a second cluster using a clustering algorithm based on the first sample set and the second sample set includes: Determine the number of clusters to be divided in the first sample set, k1, and the number of clusters to be divided in the second sample set, k2; Based on the first sample set, determine k1 central data points of the first cluster; Based on the second sample set, determine k2 central data points for the second cluster; Calculate the distance between the samples in the first sample set and the k1 central data points; Calculate the distance between the samples in the second sample set and the k2 center data points; Determine the clusters of the samples, wherein the center data of the cluster is closest to the sample.

5. The method of claim 4, wherein, The method further includes: Calculate the centroids of the clusters in the first and second types of clusters; The centroid is determined to be the center data of a cluster in the first type of cluster or the second type of cluster, in order to achieve iteration; The iteration stops when the algorithm reaches the maximum number of iterations or when the sample meets the preset conditions.

6. The method of claim 5, wherein, The method further includes: Based on the centroids of the clusters in the first and second types of clusters, an objective function is established. The objective function is used to determine whether the sample satisfies the preset condition.

7. A base station co-site determination device, characterized in that, The device includes: The acquisition unit is used to acquire first data and second data, wherein the first data is 4G measurement statistics (MR) data or 4G minimum drive test (MDT) data, and the second data is 5G MR data or 5G MDT data. Both the first data and the second data include reference signal received strength (RSRP). The first processing unit is used to preprocess the first data and the second data to obtain a first sample set and a second sample set. The second processing unit is used to generate a first cluster and a second cluster based on the first sample set and the second sample set using a clustering algorithm, wherein the first cluster is a 4G base station cluster and the second cluster is a 5G base station cluster; The third processing unit is used to determine the co-location of 4G base stations and 5G base stations based on the first cluster and the second cluster using an overlap algorithm. The step of determining the co-location of 4G and 5G base stations using an overlap algorithm based on the first and second cluster types includes: Using the centroid of a cluster in the second type of cluster or the first type of cluster as the center, calculate the Gaussian distribution overlap between the first type of cluster and the second type of cluster within a preset radius; If the Gaussian distribution overlap between the first cluster and the second cluster is greater than a preset value, it is determined that the 4G base station and the 5G base station share the same site. The third processing unit is further configured to: When the Gaussian distribution overlap between the first cluster and the second cluster is less than or equal to a preset value, it is determined that the 4G base station and the 5G base station do not overlap.

8. A communication device, characterized by include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

Images