A method, device, equipment and storage medium for identifying abnormal data of a base station

Abstract

The present application discloses a method, apparatus, device and storage medium for identifying abnormal data of a base station. The method includes: determining a base station location map corresponding to each base station among a plurality of base stations associated with a base station location data set, where the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station; determining a base station handover map corresponding to each base station among a plurality of base stations associated with a base station handover data set, where the base station handover map indicates the actual handover relationship between each target base station and the base station after a plurality of terminal devices perform a base station handover with the base station as the source base station; respectively comparing the base station location map of the base station with the base station handover map of the base station to determine an abnormal base station; based on the abnormal base station, determining base station location abnormal data from the base station location data set and determining base station handover abnormal data from the base station handover data set. The method of the present application improves the accuracy of base station location data and base station handover data.

Description

Technical Field

[0001] This application relates to the field of information processing technologies, and particularly to a method, apparatus, device, and storage medium for identifying abnormal base station data. Background Art

[0002] With the continuous progress of technologies, base station location data and base station handover data play an increasingly important role in modern society and have extensive applications in multiple fields such as navigation services, location sharing, disaster management, commercial applications, RFID systems, communication quality optimization, network planning, data analysis and mining, and intelligent transportation.

[0003] However, base station location data and base station handover data are data collected from different data sources. Due to reasons such as inaccurate positioning of base stations or network failures, the accuracy of the obtained base station location data and base station handover data is relatively low. Summary of the Invention

[0004] Based on the above problems, this application provides a method, apparatus, device, and storage medium for identifying abnormal base station data, aiming to improve the accuracy of base station location data and base station handover data.

[0005] The embodiments of this application disclose the following technical solutions:

[0006] In a first aspect, this application provides a method for identifying abnormal base station data, including:

[0007] Determine the base station location map corresponding to each base station among the multiple base stations associated with the base station location data set, where the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station;

[0008] Determine the base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set, where the base station handover map indicates the actual handover relationship between each target base station and the base station after multiple terminal devices perform a base station handover with the base station as the source base station;

[0009] Compare the base station location map of the base station with the base station handover map of the base station respectively to determine abnormal base stations;

[0010] Based on the abnormal base stations, determine base station location abnormal data from the base station location data set and determine base station handover abnormal data from the base station handover data set.

[0011] In this embodiment, the base station location map corresponding to each base station among multiple base stations is determined according to the base station location data set, which can clearly show the handover relationship between the base station and all adjacent base stations capable of establishing a handover relationship; then, the base station handover map corresponding to each base station among multiple base stations is determined according to the base station handover data set, which can clearly show the actual handover relationship between each target base station and the base station after multiple terminal devices perform base station handover with the base station as the source base station. By comparing the constructed base station location map and the base station handover map, abnormal base stations can be accurately identified, so that the abnormal base station location data and the base station handover data can be accurately corresponded, thereby improving the accuracy of the base station location data and the base station handover data.

[0012] Optionally, for the method described above, determining the base station location map corresponding to each base station among the multiple base stations associated with the base station location data set includes:

[0013] Based on the base station longitude and latitude information and network mode information in the base station location data set, adjacent base stations corresponding to the base station are determined from multiple base stations;

[0014] According to the distance between the adjacent base station and the base station, the weight corresponding to the adjacent base station is determined;

[0015] Taking the base station as the center and the weight corresponding to the adjacent base station as the edge weight, a base station location map between the base station and the adjacent base stations is constructed; the edge weight is used to represent the distance between the adjacent base station and the base station in the base station location map, which can more clearly show the possible handover relationship between the base stations, so as to improve the accuracy of abnormal base station positioning.

[0016] Optionally, for the method described above, the adjacent base stations include attached base stations and neighboring base stations. Based on the base station longitude and latitude information and network mode information in the base station location data set, determining the adjacent base stations corresponding to the base station from multiple base stations includes:

[0017] The attached base station of the base station is determined according to the base station longitude and latitude information; the distance between the attached base station and the base station is less than a preset threshold;

[0018] Based on the base station longitude and latitude information and network mode information, neighboring base stations are determined from multiple base stations to more accurately understand the relative positions and relationships between different base stations and improve the accuracy of constructing the base station location map.

[0019] Optionally, for the method described above, based on the base station longitude and latitude information and network mode information, determining the neighboring base stations from multiple base stations includes:

[0020] Calculate the proximity coefficient corresponding to each base station among multiple base stations based on the longitude and latitude information and network mode information of the base stations; the proximity coefficient is used to characterize the possibility of handover between each base station among the multiple base stations; the proximity coefficient is negatively correlated with the distance and is related to the network mode information;

[0021] Centering on the base station, divide multiple detection ranges according to a preset angle;

[0022] Determine the base station with the largest proximity coefficient and a distance less than or equal to the farthest communication distance of the base station in each of the multiple detection ranges as the neighboring base station, which can accurately determine the neighboring base stations that may have a handover relationship with the base station from all base stations, improve the accuracy of constructing the base station location map, and avoid missing base stations that may have a handover relationship.

[0023] Optionally, in the method described above, the proximity coefficient being related to the network mode information includes:

[0024] The network mode is inversely proportional to the farthest communication distance of the base station and is directly proportional to the weight factor;

[0025] The proximity coefficient is positively correlated with the farthest communication distance of the base station and is positively correlated with the weight factor.

[0026] Optionally, in the method described above, determining the base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set includes:

[0027] Classify the base station handover data according to the user identifier in the base station handover data to obtain the data sets corresponding to the respective user identifiers;

[0028] Sort the base station handover data in the data set in ascending order of time to obtain the data sequences corresponding to the respective user identifiers;

[0029] Perform statistical analysis on the data in the data sequence, and respectively determine the statistical results corresponding to the target base station and the base station in multiple feature dimensions; the feature dimensions include the maximum value, minimum value, average value, and variance of the handover frequency within a preset time;

[0030] Obtain the handover feature vector between the target base station and the base station according to the statistical results corresponding to the target base station and the base station in multiple feature dimensions;

[0031] Centering on the base station and using the handover feature vector as the edge weight, construct the base station handover map corresponding to the base station, which can clearly display the actual handover relationship between the base stations and improve the accuracy of abnormal base station identification.

[0032] Optionally, in the method described above, comparing the base station location map of the base station and the base station handover map of the base station respectively to determine the abnormal base station includes:

[0033] The pre-configured base station abnormal handover detection and recognition model is used to compare the base station handover relationships in the base station location map and the base station handover map, and the base stations with inconsistent comparisons are determined as abnormal base stations; the pre-configured base station abnormal handover detection and recognition model is obtained by comparing and training the historical base station location map and the historical base station handover map according to preset rules using a rule model, which improves the accuracy of abnormal base station detection.

[0034] In a second aspect, the present application provides a device for identifying abnormal base station data, including:

[0035] A base station location map construction module, configured to determine the base station location map corresponding to each base station among the multiple base stations associated with the base station location data set, where the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station;

[0036] A base station handover map construction module, configured to determine the base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set, where the base station handover map indicates the actual handover relationships between each target base station and the base station after multiple terminal devices perform base station handovers with the base station as the source base station;

[0037] An abnormal base station determination module, configured to compare the base station location map of the base station with the base station handover map of the base station respectively to determine the abnormal base station;

[0038] An abnormal data determination module, configured to determine base station location abnormal data from the base station location data set and determine base station handover abnormal data from the base station handover data set based on the abnormal base station.

[0039] In a third aspect, the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0040] The memory stores computer-executable instructions;

[0041] The processor executes the computer-executable instructions stored in the memory to implement the method for identifying abnormal base station data in any one of the above embodiments.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the method for identifying abnormal base station data in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0044] Figure 1A Schematic diagram of the application scenario provided by the embodiment of the present application;

[0045] Figure 1B Schematic flow chart of an embodiment of a method for identifying abnormal data of a base station provided by the embodiment of the present application;

[0046] Figure 2 Schematic flow chart of another embodiment of a method for identifying abnormal data of a base station provided by the embodiment of the present application;

[0047] Figure 3 Schematic flow chart of still another embodiment of a method for identifying abnormal data of a base station provided by the embodiment of the present application;

[0048] Figure 4 Schematic flow chart of yet another embodiment of a method for identifying abnormal data of a base station provided by the embodiment of the present application;

[0049] Figure 5 Schematic structural diagram of an embodiment of a device for identifying abnormal data of a base station provided by the embodiment of the present application;

[0050] Figure 6 Schematic structural diagram of an embodiment of an electronic device provided by the embodiment of the present application. Detailed implementation manners

[0051] As described above, due to inaccurate positioning of the base station or network failures and other reasons, the current base station location data and base station handover data have low accuracy.

[0052] After research, the inventors have proposed a method, device, equipment and storage medium for identifying abnormal data of a base station to improve the accuracy of base station location data and base station handover data.

[0053] To enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0054] See Figure 1A , which is a schematic diagram of the application scenario provided by the embodiment of the present application. As Figure 1A shown, taking base station A as an example, according to the base station location data, the adjacent base stations that can establish a handover relationship with base station A in the base station location map corresponding to base station A are base station B and base station C. When the terminal device uses base station A as the source base station for base station handover, according to the base station handover data of all terminal devices, it is determined that there is an actual handover relationship between base station A and base station B in the base station handover map, and there is also an actual handover relationship between base station A and base station D, while there is no actual handover relationship between base station A and base station C. By comparing the base station location map of base station A with the base station handover map, the base station location data of base station C is obtained as abnormal data, and the base station handover data corresponding to base station D is abnormal data.

[0055] Then, according to the base station handover map corresponding to each base station among the multiple base stations associated with the determined base station handover data set, the base station handover map indicates the actual handover relationship between each target base station and the base station after the multiple terminal devices use the base station as the source base station for base station handover

[0056] See Figure 1B , which is a schematic flowchart of an embodiment of a method for identifying abnormal base station data provided by the embodiment of the present application. As Figure 1B shown, the method includes:

[0057] S101: Determine the base station location map corresponding to each base station among the multiple base stations associated with the base station location data set, and the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station.

[0058] In this embodiment, taking base station A as an example, according to the base station longitude and latitude information in the obtained base station location data, the base stations whose distance from base station A is less than the preset threshold are determined as the attached base stations corresponding to base station A, and the edge weight of the attached base stations is set to 1. Then, according to the base station longitude and latitude information and network mode information in the base station location data, among the remaining base stations except the attached base stations, the neighboring base stations that may establish a handover relationship with base station A are determined, and the corresponding edge weight values of the neighboring base stations are calculated. Taking base station A as the in-vertex, the attached base stations and neighboring base stations as the out-vertices, a base station location map is constructed. Among them, the weight of the edge between the out-vertex and the in-vertex is the edge weight.

[0059] It can be understood that since the base stations of different operators do not communicate with each other, the corresponding base station location maps need to be constructed for different operators respectively. Among them, if there are shared base stations among multiple operators, the shared base stations exist in the base station location maps of multiple operators.

[0060] S102: Determine the base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set. The base station handover map indicates the actual handover relationship between each target base station and the base station after multiple terminal devices perform base station handover with the base station as the source base station.

[0061] In this embodiment, according to the user identifier in the obtained base station handover data, the base station handover data set is classified according to the user identifier, and then for each user identifier, the corresponding base station handover data is sorted in chronological order, so as to obtain the data sequence corresponding to each user identifier. Taking base station B as an example, the base stations having a handover relationship with base station B are determined from the data in the data sequence corresponding to each user identifier, and data statistics are performed on the data sequence corresponding to each user identifier based on the base stations having a handover relationship, so as to obtain the statistical results corresponding to different feature dimensions. Then, the handover feature vector containing the above statistical results is used as the edge weight. Taking base station B as the in-vertex and the base stations having a handover relationship as the out-vertices, a base station handover map is constructed. Among them, the weight of the edge between the out-vertex and the in-vertex is the handover feature vector.

[0062] S103: Compare the base station location map of the base station with the base station handover map of the base station respectively, and determine the abnormal base stations.

[0063] In this embodiment, a pre-configured base station abnormal handover detection and recognition model is used to compare the base station handover relationships in the base station location map and the base station handover map, and the base stations with inconsistent comparison results are determined as abnormal base stations.

[0064] S104: Based on the abnormal base stations, determine the base station location abnormal data from the base station location data set and determine the base station handover abnormal data from the base station handover data set.

[0065] In this embodiment, according to the identifier corresponding to the determined abnormal base station, the base station location abnormal data is determined from the base station location data set and the base station handover abnormal data is determined from the base station handover data set.

[0066] It can be understood that in order to reduce the storage space and improve the query performance of the graph, the base station location map and the base station handover map can adopt an inverse adjacency list as the storage structure of the graph.

[0067] In this embodiment, the base station location map corresponding to each base station among multiple base stations is determined according to the base station location data set, which can clearly show the handover relationship between the base station and all adjacent base stations that can establish a handover relationship; then, the base station handover map corresponding to each base station among multiple base stations is determined according to the base station handover data set, which can clearly show the actual handover relationship between each target base station and the base station after multiple terminal devices perform base station handover with the base station as the source base station. By comparing the constructed base station location map and the base station handover map, abnormal base stations can be accurately identified, so as to accurately correspond to the abnormal base station location data and the base station handover data, thereby improving the accuracy of the base station location data and the base station handover data.

[0068] See Figure 2 , which is a schematic flowchart of another embodiment of a method for identifying abnormal base station data provided by an embodiment of the present application. Different from Figure 1B , Figure 2 This shows a specific implementation manner of "determining the base station location map corresponding to each base station among the multiple base stations associated with the base station location data set" in S101, which is specifically introduced in combination with Figure 2 S1011 - S1013 in

[0069] S1011: Based on the base station longitude and latitude information and network mode information in the base station location data set, determine the adjacent base stations corresponding to the base station from multiple base stations.

[0070] In this embodiment, the obtained base station location data includes base station identification, network mode information, base station longitude and latitude information, and the province, city, and district to which it belongs. Determine the attached base station of the base station according to the base station longitude and latitude information; the distance between the attached base station and the base station is less than a preset threshold; based on the base station longitude and latitude information and network mode information, determine the adjacent base stations from multiple base stations.

[0071] It can be understood that the base station longitude and latitude information in the base station location data set can be matched according to the geographical location of the map and the location of the province, city, and district to which it belongs.

[0072] S1012: Determine the weight corresponding to the adjacent base station according to the distance between the adjacent base station and the base station.

[0073] In this embodiment, for example, if the adjacent base station is an attached base station, the weight corresponding to the adjacent base station is defaulted to 1. If the adjacent base station is a neighboring base station, the distance between the adjacent base station and the base station is normalized using the Sigmoid activation function to determine the weight corresponding to the adjacent base station.

[0074] S1013: With the base station as the center and the weight corresponding to the adjacent base station as the edge weight, construct a base station location map between the base station and the adjacent base stations.

[0075] In this embodiment, taking base station A as an example, with base station A as the in-vertex and the attached base station and neighboring base stations as the out-vertices, a base station location map is constructed. Among them, the weight of the edge between the out-vertex and the in-vertex is the edge weight; the edge weight is used to represent the distance between adjacent base stations and the base station in the base station location map.

[0076] In this embodiment, based on the longitude and latitude information and network mode information of the base stations in the base station location data set, the adjacent base stations corresponding to the base stations are determined from multiple base stations, improving the accuracy of positioning adjacent base stations, and thus more accurately obtaining adjacent base stations that may have a handover relationship; then, according to the distance between the adjacent base stations and the base station, the weights corresponding to the adjacent base stations are determined, which can more accurately reflect the spatial position relationship between the base stations. With the base station as the center and the weights corresponding to the adjacent base stations as the edge weights, a base station location map between the base station and the adjacent base stations is constructed, which can more clearly show the possible handover relationship between the base stations to improve the accuracy of abnormal base station positioning.

[0077] Combined with Figure 2 As shown, after executing S1011 - S1013, referring to the previous embodiment, execute S102 - S104 to realize the determination of base station location abnormal data and base station handover abnormal data.

[0078] Further, on the basis of the above embodiment, if the adjacent base stations include the attached base station and the neighboring base stations, a specific implementation manner of "determining the adjacent base stations corresponding to the base station from multiple base stations based on the longitude and latitude information and network mode information of the base stations in the base station location data set" in S1011 includes:

[0079] Determine the attached base station of the base station according to the longitude and latitude information of the base station; the distance between the attached base station and the base station is less than a preset threshold.

[0080] In this embodiment, taking base station A as an example, according to the longitude and latitude information corresponding to all base stations and the longitude and latitude information of base station A, the base stations with a distance less than the preset distance of 10m from base station A are calculated as the attached base stations.

[0081] Determine the neighboring base stations from multiple base stations based on the longitude and latitude information and network mode information of the base stations.

[0082] In this embodiment, based on the longitude and latitude information and network mode information of the base stations, the proximity coefficients between all base stations except the attached base stations and base station A are calculated. Then, with base station A as the center, multiple detection ranges are divided according to a preset angle, and the base stations with the largest proximity coefficient and a distance less than or equal to the farthest communication distance of the base station are determined as the neighboring base stations from each detection range.

[0083] In this embodiment, the attached base station of the base station is determined according to the longitude and latitude information of the base station; the distance between the attached base station and the base station is less than a preset threshold; then, based on the longitude and latitude information of the base station and the network mode information, the neighboring base stations are determined from multiple base stations, so as to more accurately understand the relative positions and relationships between different base stations and improve the accuracy of constructing the base station location map.

[0084] Further, on the basis of the above embodiment, a specific implementation manner of "determining the neighboring base stations from multiple base stations based on the longitude and latitude information of the base station and the network mode information" includes:

[0085] Calculate the proximity coefficient corresponding to each base station among multiple base stations based on the longitude and latitude information of the base station and the network mode information.

[0086] Among them, the proximity coefficient is used to characterize the possibility of handover between each base station among multiple base stations and the base station; the proximity coefficient is negatively correlated with the distance and is related to the network mode information.

[0087] In this embodiment, with base station A as the center, since the base station signal strength is inversely proportional to the base station distance; for different network modes, the communication priority of the base station with the network mode of 5G is higher than that of the base station with the network mode of 4G. The proximity coefficient can be expressed by the following expression:

[0088]

[0089] The proximity coefficient is positively correlated with the farthest communication distance of the base station and is positively correlated with the weight factor.

[0090] Among them, Zscore represents the proximity coefficient between the current base station and the central base station;

[0091] T is the farthest communication distance threshold of the current base station. Specifically, the network mode is inversely proportional to the farthest communication distance of the base station; for example, the farthest communication distance threshold of a 2G base station can be 10 km, the farthest communication distance threshold of a 3G base station can be 5 km, the farthest communication distance threshold of a 4G base station can be 3 km, and the farthest communication distance threshold of a 5G base station can be 500 m.

[0092] H is the distance between the current base station and the central base station;

[0093] K1 is the initialization factor, which can be set to the default value; for example, K1 = 10.

[0094] K2 is the weight factor. Specifically, the network mode is directly proportional to the weight factor. For example, the weight factor of a 2G base station can be set to 0.5; the weight factor of a 3G base station can be set to 0.5; the weight factor of a 4G base station can be set to 1; the weight factor of a 5G base station can be set to 2.

[0095] Centered around the base station, multiple detection ranges are divided according to a preset angle.

[0096] In this embodiment, for example, if the preset angle is 5°, taking base station A as the center, a polar coordinate system is constructed with 0° in the due east direction, and every 5° in the counterclockwise direction is used as a detection range.

[0097] From each of the multiple detection ranges, the base station with the largest proximity coefficient and a distance less than or equal to the farthest communication distance of the base station is determined as the neighboring base station.

[0098] In this embodiment, according to the calculated proximity coefficient of each base station, the base station with the largest proximity coefficient and a distance less than or equal to the farthest communication distance of the base station is determined as the neighboring base station from each detection range respectively. If the distance between the base station with the largest proximity coefficient and base station A exceeds the farthest communication distance threshold of this base station, it is determined that there is no neighboring base station in this detection range.

[0099] In this embodiment, the proximity coefficient corresponding to each base station among multiple base stations is calculated based on the base station longitude and latitude information and network mode information, which can more accurately identify neighboring base stations. Centered around the base station, multiple detection ranges are divided according to a preset angle for identifying neighboring base stations by region to reduce signal blind spots; then, from each of the multiple detection ranges, the base station with the largest proximity coefficient and a distance less than or equal to the farthest communication distance of the base station is determined as the neighboring base station, which can accurately determine the neighboring base stations that may have a handover relationship with the base station from all base stations, improve the accuracy of constructing the base station location map, and avoid missing base stations that may have a handover relationship.

[0100] See Figure 3 , which is a schematic flowchart of another embodiment of a method for identifying abnormal data of a base station provided by an embodiment of the present application. Different from Figure 1B Figure 3 shows a specific implementation manner of "determining the base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set" in S102, which is specifically introduced in combination with Figure 3 S1021 - S1025 in

[0101] S1021: Classify the base station handover data according to the user identifier in the base station handover data to obtain the data sets corresponding to the respective user identifiers.

[0102] In this embodiment, the obtained base station handover data is the relevant information extracted from the event data in the standardized signaling log data, including the start time, user identifier, base station longitude and latitude information, current base station identifier, and previous base station identifier. According to the user identifier corresponding to each user, the base station handover data is classified to obtain the data sets corresponding to the respective user identifiers.

[0103] S1022: Sort the base station handover data in the dataset in ascending order of time to obtain the data sequences corresponding to each user identifier.

[0104] In this embodiment, taking the dataset corresponding to user identifier A as an example, sort the dataset corresponding to user identifier A in ascending order of start time to obtain the data sequence corresponding to user identifier A.

[0105] It can be understood that after obtaining the data sequences corresponding to each user identifier, the data can be preprocessed. Specifically, the preprocessing operations include removing duplicate data in the data sequences corresponding to the user identifiers and filling or filtering abnormal data in the data sequences. Among them, filling or filtering abnormal data in the data sequences includes performing the following operations on each target data in the data sequences:

[0106] (1) If the latitude and longitude information of the previous base station corresponding to the target data in the data sequence is the same as the latitude and longitude information of the current base station corresponding to the previous data, the target data is normal data.

[0107] (2) If the latitude and longitude information of the previous base station corresponding to the target data in the data sequence is different from the latitude and longitude information of the current base station corresponding to the previous data, and the time interval between the start time corresponding to the target data and the start time corresponding to the previous data is less than or equal to 60s, it is considered that data is lost between the two data, and a new data is filled between the target data and the previous data. In the new data, the latitude and longitude information of the current base station is the latitude and longitude information of the previous base station corresponding to the target data, and the latitude and longitude information of the previous base station is the latitude and longitude information of the current base station corresponding to the previous data.

[0108] (3) If the latitude and longitude information of the previous base station corresponding to the target data in the data sequence is different from the latitude and longitude information of the current base station corresponding to the previous data, and the time interval between the start time corresponding to the target data and the start time corresponding to the previous data is greater than 60s, the target data is considered normal data.

[0109] (4) If the latitude and longitude information of the previous base station corresponding to the target data in the data sequence is missing, and the time interval between the target data and the previous data is less than or equal to 60s, fill the latitude and longitude information of the previous base station corresponding to the target data with the latitude and longitude information of the current base station corresponding to the previous data.

[0110] (5) If the latitude and longitude information of the previous base station corresponding to the target data in the data sequence is missing, and the time interval between the target data and the previous data is greater than 60s, the target data is abnormal data and is filtered.

[0111] S1023: Perform statistical analysis on the data in the data sequence, and respectively determine the statistical results corresponding to the target base station and the base stations in multiple characteristic dimensions.

[0112] Among them, the characteristic dimensions include the maximum value, minimum value, average value, and variance of the handover frequency within a preset time.

[0113] In this embodiment, for each user identifier, the number of handovers between the target base station and the base stations is determined according to the data sequence, and the handover relationship with a higher handover frequency between the target base station and the base stations is selected. For example, if there are 10 handover relationships between the target base station and other base stations, the handover frequencies corresponding to these 10 handover relationships are sorted, and 9 handover relationships corresponding to higher handover frequencies are retained.

[0114] It can be understood that during the statistical process, if the longitude and latitude information of the current base station corresponding to the current data is the same as that of the previous base station, it is not considered that there is a handover relationship.

[0115] Based on the determined handover relationships, the statistical results corresponding to each target base station and the base stations in multiple characteristic dimensions are respectively counted, such as the number of handover people between the target base station and the base stations, the handover frequency between the target base station and the base stations at different time periods, the number of handover people between the target base station and the base stations at different time periods, the maximum value, minimum value, average value, and variance of the number of handovers between the target base station and the base stations within 30 minutes, and so on.

[0116] S1024: Obtain the handover feature vector between the target base station and the base stations according to the statistical results corresponding to the target base station and the base stations in multiple characteristic dimensions.

[0117] In this embodiment, the statistical results corresponding to the target base station and the base stations in multiple characteristic dimensions are used as the handover feature vector between the target base station and the base stations.

[0118] S1025: With the base station as the center and the handover feature vector as the edge weight, construct the base station handover graph corresponding to the base station.

[0119] In this embodiment, taking the target base station as base station A as an example, with base station A as the in-vertex and the base stations as the out-vertices, construct the base station handover graph. Among them, the edge weight between the out-vertex and the in-vertex is the handover feature vector; the edge weight is used to represent the handover relationship between the target base station and the base stations in the base station handover graph.

[0120] Combine Figure 3As shown, before executing S1021 - S1025, referring to the previous embodiment, execute S101 to determine the base station location map; after executing S1021 - S1025, referring to the previous embodiment, execute S103 - S104 to determine the base station location abnormal data and the base station handover abnormal data.

[0121] In this embodiment, according to the user identification in the base station handover data, the base station handover data is classified to obtain the data sets corresponding to the respective user identifications. The base station handover data in the data set is sorted in ascending order of time to obtain the data sequences corresponding to the respective user identifications, so as to clearly show the base station handover situation of the user at different time points; then the data in the data sequences is statistically analyzed to respectively determine the statistical results corresponding to the target base station and the base stations in multiple feature dimensions, which can comprehensively reflect the handover characteristics between the target base station and the base stations and be used to determine the handover feature vectors between the target base station and the base stations. Taking the base station as the center and the handover feature vectors as the edge weights, a base station handover map corresponding to the base station is constructed, which can clearly show the actual handover relationship between the base stations and improve the accuracy of abnormal base station identification.

[0122] See Figure 4 , which is a schematic flowchart of another embodiment of a method for identifying base station abnormal data provided by an embodiment of the present application. Different from Figure 1B , Figure 4 shows a specific implementation manner of "respectively comparing the base station location map of the base station with the base station handover map of the base station in S103 to determine the abnormal base station", which is specifically introduced in combination with Figure 4 in S1031.

[0123] S1031: Use a pre-configured base station abnormal handover detection and identification model to compare the base station handover relationships in the base station location map and the base station handover map, and determine the base stations with inconsistent comparisons as abnormal base stations.

[0124] Among them, the pre-configured base station abnormal handover detection and identification model is obtained by comparing and training the historical base station location map and the historical base station handover map using a rule model according to preset rules.

[0125] In this embodiment, the pre-configured base station abnormal handover detection and identification model is obtained by comparing and training the historical base station location map and the historical base station handover map using a rule model according to preset rules. Since the base station location map already contains all possible handover relationships, when the handover relationship in the base station handover map cannot be successfully compared in the base station location map, then the base station is considered an abnormal base station. Specifically, the abnormal base stations may include base stations with inaccurate positions, base stations with missing handover relationships, base stations with handover errors, and so on.

[0126] In this embodiment, a pre-configured base station abnormal handover detection and recognition model is used to compare the base station handover relationships in the base station location map and the base station handover map, avoiding the errors that may be brought by a single data source, and being able to accurately identify the base stations with inconsistent comparisons, thereby improving the accuracy of abnormal base station detection.

[0127] Combined with Figure 4 As shown, before executing S1031, referring to the previous embodiment, execute S101 - S102 to determine the base station location map and the base station handover map; after executing S1031, referring to the previous embodiment, execute S104 to determine the base station location abnormal data and the base station handover abnormal data.

[0128] Further, based on the above embodiment, the method may further include:

[0129] According to the manual verification results of the base station location abnormal data and the base station handover abnormal data, label the base station location abnormal data and the base station handover abnormal data; and perform feature extraction on the labeled data, and then use machine learning models, such as random forest, logistic regression, XGBoost, LightGBM, to train the model with the feature vectors and labels, and use the grid search algorithm to optimize the parameters, so as to obtain a prediction model; specifically, this prediction model is used to optimize the distance threshold setting in the process of constructing the base station location map.

[0130] Refer to Figure 5 , this figure is a schematic structural diagram of an embodiment of an identification device for base station abnormal data provided by an embodiment of the present application. As Figure 5 shown, the device 50 includes: a base station location map construction module 51, a base station handover map construction module 52, an abnormal base station determination module 53, and an abnormal data determination module 54.

[0131] Among them, the base station location map construction module 51 is used to determine the base station location map corresponding to each base station among the multiple base stations associated with the base station location data set, and the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station;

[0132] The base station handover map construction module 52 is used to determine the base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set, and the base station handover map indicates the actual handover relationship between each target base station and the base station after multiple terminal devices perform base station handover with the base station as the source base station;

[0133] The abnormal base station determination module 53 is used to compare the base station location map of the base station with the base station handover map of the base station respectively to determine the abnormal base station;

[0134] An abnormal data determination module 54, configured to determine base station location abnormal data from a base station location data set and determine base station handover abnormal data from a base station handover data set based on an abnormal base station.

[0135] The base station abnormal data identification device provided by an embodiment of the present application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, and will not be elaborated here.

[0136] Further, on the basis of the above embodiments, the base station location map construction module 51 is specifically configured to determine adjacent base stations corresponding to a base station from multiple base stations based on the longitude and latitude information and network mode information of the base stations in the base station location data set; determine the weights corresponding to the adjacent base stations according to the distances between the adjacent base stations and the base station; construct a base station location map between the base station and the adjacent base stations with the base station as the center and the weights corresponding to the adjacent base stations as edge weights; the edge weights are used to represent the distances between the adjacent base stations and the base station in the base station location map.

[0137] The base station abnormal data identification device provided by an embodiment of the present application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, and will not be elaborated here.

[0138] Further, on the basis of the above embodiments, the base station location map construction module 51 is specifically configured to determine the attached base station of the base station according to the longitude and latitude information of the base station; the distance between the attached base station and the base station is less than a preset threshold; based on the longitude and latitude information and network mode information of the base station, determine adjacent base stations from multiple base stations.

[0139] The base station abnormal data identification device provided by an embodiment of the present application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, and will not be elaborated here.

[0140] Further, on the basis of the above embodiments, the base station location map construction module 51 is specifically configured to calculate the proximity coefficient corresponding to each base station among multiple base stations based on the longitude and latitude information and network mode information of the base station; the proximity coefficient is used to represent the possibility of handover between each base station among multiple base stations and the base station; the proximity coefficient is negatively correlated with the distance and is related to the network mode information; with the base station as the center, divide multiple detection ranges according to a preset angle; determine the base station with the largest proximity coefficient and a distance less than or equal to the farthest communication distance of the base station from each of the multiple detection ranges as the adjacent base station.

[0141] The base station abnormal data identification device provided by an embodiment of the present application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, and will not be elaborated here.

[0142] Further, based on the above embodiments, the base station handover map construction module 52 is specifically configured to classify the base station handover data according to the user identifiers in the base station handover data to obtain data sets corresponding to the respective user identifiers; sort the base station handover data in the data sets in ascending order of time to obtain data sequences corresponding to the respective user identifiers; perform statistical analysis on the data in the data sequences to respectively determine the statistical results corresponding to the target base station and the base stations in multiple feature dimensions; the feature dimensions include the maximum value, minimum value, average value, and variance of the handover frequency within a preset time; according to the statistical results corresponding to the target base station and the base stations in multiple feature dimensions, obtain the handover feature vector between the target base station and the base stations; with the base station as the center and the handover feature vector as the edge weight, construct the base station handover map corresponding to the base station.

[0143] The base station abnormal data identification device provided by the embodiments of the present application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, and will not be elaborated here.

[0144] Further, based on the above embodiments, the abnormal base station determination module 53 is specifically configured to use a pre-configured base station abnormal handover detection and identification model to compare the base station handover relationships in the base station location map and the base station handover map, and determine the base stations with inconsistent comparisons as abnormal base stations; the pre-configured base station abnormal handover detection and identification model is obtained by comparing and training the historical base station location map and the historical base station handover map using a rule model according to preset rules.

[0145] The base station abnormal data identification device provided by the embodiments of the present application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, and will not be elaborated here.

[0146] See Figure 6 , which is a schematic structural diagram of an embodiment of an electronic device provided by an embodiment of the present application. The electronic device 60 may include: a processor 61 and a memory 62.

[0147] Wherein, the processor 61 is communicatively connected to the memory 62, and the memory 62 is used to store computer execution instructions; the processor 61 is configured to execute the technical solutions in any of the foregoing method embodiments by executing the computer execution instructions stored in the memory 62.

[0148] Optionally, the memory 62 may be either independent or integrated with the processor 61. Optionally, when the memory 62 is a device independent of the processor 61, the electronic device 60 may further include: a bus for connecting the above devices.

[0149] The electronic device is used to execute the technical solutions in any of the foregoing method embodiments. The implementation principles and technical effects are similar and will not be elaborated herein.

[0150] An embodiment of the present application also provides a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium. When the computer-executable instructions are executed by a processor, they are used to implement the foregoing method. The implementation principles and technical effects are similar and will not be elaborated herein.

[0151] It should be noted that the embodiments in this specification are all described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments. The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated. The components indicated as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0152] As described above, this is only a specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying abnormal data of a base station, characterized in that, Including: Determine a base station location map corresponding to each base station among the multiple base stations associated with the base station location data set, where the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station; Determine a base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set, where the base station handover map indicates the actual handover relationship between each target base station and the base station after multiple terminal devices perform a base station handover with the base station as the source base station; Compare the base station location map of the base station with the base station handover map of the base station respectively, and determine abnormal base stations; Based on the abnormal base stations, determine base station location abnormal data from the base station location data set and determine base station handover abnormal data from the base station handover data set; The determining a base station location map corresponding to each base station among the multiple base stations associated with the base station location data set includes: Based on the base station longitude and latitude information and network mode information in the base station location data set, determine the adjacent base stations corresponding to the base station from the multiple base stations; Determine the weight corresponding to the adjacent base stations according to the distance between the adjacent base stations and the base station; With the base station as the center and the weight corresponding to the adjacent base stations as the edge weight, construct a base station location map between the base station and the adjacent base stations; the edge weight is used to represent the distance between the adjacent base stations and the base station in the base station location map.

2. The method according to claim 1, wherein The adjacent base stations include attached base stations and neighboring base stations. The determining the adjacent base stations corresponding to the base station from the multiple base stations based on the base station longitude and latitude information and network mode information in the base station location data set includes: Determine the attached base station of the base station according to the base station longitude and latitude information; the distance between the attached base station and the base station is less than a preset threshold; Based on the base station longitude and latitude information and network mode information, determine neighboring base stations from the multiple base stations.

3. The method according to claim 2, wherein The determining neighboring base stations from the multiple base stations based on the base station longitude and latitude information and network mode information includes: Calculate a proximity coefficient corresponding to each base station among the multiple base stations based on the base station longitude and latitude information and network mode information; the proximity coefficient is used to represent the possibility of handover between each base station among the multiple base stations and the base station; the proximity coefficient is negatively correlated with the distance and is related to the network mode information; With the base station as the center, divide multiple detection ranges according to a preset angle; Determine, from each of the multiple detection ranges, the base station with the largest proximity coefficient and the distance less than or equal to the maximum communication distance of the base station as the neighboring base station.

4. The method according to claim 3, characterized in that, The proximity coefficient being related to the network mode information includes: The network mode is inversely proportional to the maximum communication distance of the base station and is directly proportional to the weight factor; The proximity coefficient is positively correlated with the maximum communication distance of the base station and is positively correlated with the weight factor.

5. The method according to claim 1, characterized in that, The determining a base station handover map corresponding to each base station among the multiple base stations associated with the base station handover data set includes: Classify the base station handover data according to the user identifiers in the base station handover data to obtain the data sets corresponding to the respective user identifiers; Sort the base station handover data in the data set in ascending order of time to obtain the data sequences corresponding to the respective user identifiers; Perform statistical analysis on the data in the data sequence to respectively determine the statistical results corresponding to the target base station and the base station in multiple feature dimensions; the feature dimensions include the maximum value, minimum value, average value, and variance of the handover frequency within a preset time; Obtain the handover feature vector between the target base station and the base station according to the statistical results corresponding to the target base station and the base station in multiple feature dimensions; With the base station as the center and the handover feature vector as the edge weight, construct the base station handover map corresponding to the base station.

6. The method according to claim 1, characterized in that, The comparing the base station location map of the base station with the base station handover map of the base station respectively to determine the abnormal base station includes: Use a pre-configured base station abnormal handover detection and recognition model to compare the base station handover relationships in the base station location map and the base station handover map, and determine the base stations with inconsistent comparisons as abnormal base stations; the pre-configured base station abnormal handover detection and recognition model is obtained by comparing and training the historical base station location map and the historical base station handover map using a rule model according to preset rules.

7. An identification device for abnormal data of a base station, characterized in that, Including: A base station location map construction module, configured to determine the base station location map corresponding to each base station in the multiple base stations associated with the base station location data set, where the base station location map indicates all adjacent base stations that can establish a handover relationship with the base station; A base station handover map construction module, configured to determine the base station handover map corresponding to each base station in the multiple base stations associated with the base station handover data set, where the base station handover map indicates the actual handover relationships between each target base station and the base station after multiple terminal devices perform base station handovers with the base station as the source base station; An abnormal base station determination module, configured to compare the base station location map of the base station with the base station handover map of the base station respectively to determine the abnormal base station; An abnormal data determination module, configured to determine base station location abnormal data from the base station location data set and determine base station handover abnormal data from the base station handover data set based on the abnormal base station; When determining the base station location map corresponding to each base station in the multiple base stations associated with the base station location data set, the base station location map construction module is configured to determine the adjacent base stations corresponding to the base station from the multiple base stations based on the longitude and latitude information and network mode information of the base stations in the base station location data set; determine the weights corresponding to the adjacent base stations according to the distances between the adjacent base stations and the base station; With the base station as the center and the weights corresponding to the adjacent base stations as the edge weights, construct the base station location map between the base station and the adjacent base stations; the edge weights are used to represent the distances between the adjacent base stations and the base station in the base station location map.

8. An electronic device, characterized in that, The device includes: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 6.

Images