A method, device and network equipment for detecting network anomaly
By constructing a scatter plot of signal strength information and feature extraction, a detection feature library is formed, and the limitations of network abnormality detection and information loss problems in the prior art are solved, and the effect of quickly troubleshooting network problems and optimizing network quality is achieved.
Patent Information
- Application Number
- CN202011154046.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-10-26
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2040-10-26
AI Technical Summary
In the prior art, network anomaly detection methods have limitations and information loss, and complex models cannot be established. They are cost-effective and difficult based on historical data and set thresholds.
By obtaining measurement report data and engineering parameter data, a scatter plot of signal intensity information is constructed, and the plane and two-dimensional characteristics of image statistical features, geometric distribution are extracted to form a detection feature library, and network abnormality detection is performed.
You can quickly troubleshoot network problems without accurate prior information and professional experience, optimize network quality, carry a large amount of user behavior information, and improve the accuracy and efficiency of network detection.
Smart Images

Figure CN114501520B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and in particular to a method, a device and a network equipment for detecting network anomalies. Background Art
[0002] In the existing technology, the detection of network anomalies mainly adopts reasonable empirical thresholds for certain characteristics based on historical data. When the threshold conditions are met, it is determined that the network is abnormal. For the inspection of work parameters, it is necessary to go on-site inspection and verification, or use drones and machine vision methods for inspection, which is costly and difficult.
[0003] However, the method of anomaly detection based on historical data, artificial division and optimization of thresholds is subjective, and it is impossible to establish a complex model. It can only make judgments based on a limited number of features, which has certain limitations and information loss problems. Summary of the invention
[0004] The present invention provides a network anomaly detection method, device and network equipment to solve the problems of limitations and information loss in the network anomaly detection method in the prior art.
[0005] To solve the above technical problems, the embodiments of the present invention provide the following solutions:
[0006] An embodiment of the present invention provides a method for detecting network anomalies, comprising:
[0007] Acquire measurement report data and engineering parameter data of cells within the first area;
[0008] Construct a signal strength information scatter plot based on measurement report data and engineering parameter data;
[0009] Extract features from the signal strength information scatter plot and build a detection feature library;
[0010] Perform network anomaly detection based on the detection feature library.
[0011] Optionally, feature extraction is performed on the signal strength information scatter plot to construct a detection feature library, including:
[0012] Based on at least one of image statistical features, planar characteristics of geometric distribution, and two-dimensional characteristics of geometric distribution, feature extraction is performed on the signal strength information scatter plot;
[0013] The extracted features are processed according to a preset format or sequence to obtain a detection feature library.
[0014] Optionally, the image statistical features include at least one of the following: scatter point centroid coordinates, scatter point fitting line slope, signal intensity difference mean, signal intensity difference median, signal intensity difference mode and scatter point number.
[0015] Optionally, based on the plane characteristics of the geometric distribution, feature extraction is performed on the signal strength information scatter plot, including:
[0016] Based on the planar characteristics of geometric distribution, the signal strength information scatter plot is divided into m*n regional grids;
[0017] The number of scattered points in each regional grid is counted to obtain an m*n dimensional feature vector of the signal strength information scatter diagram.
[0018] Optionally, based on the two-dimensional characteristics of the geometric distribution, feature extraction is performed on the signal strength information scatter plot, including:
[0019] Based on the plane characteristics of geometric distribution, the horizontal axis of the signal strength information scatter plot is divided into p intervals, and the vertical axis is divided into q intervals;
[0020] The number of scattered points falling in the p intervals of the horizontal axis and the q intervals of the vertical axis are counted respectively to obtain the horizontal axis feature vector and the vertical axis feature vector of the signal strength information scatter diagram.
[0021] Optionally, network anomaly detection is performed based on the detection feature library, including:
[0022] Perform clustering processing according to the features in the detection feature library to obtain clustering results;
[0023] According to the clustering result, a corresponding network abnormal state is determined.
[0024] Optionally, determining a corresponding network abnormal state according to the clustering result includes at least one of the following:
[0025] When the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold and the slope of the scattered point fitting line is less than the second threshold, it is determined that the distance between the base stations is unreasonable or the base station antennas are not in the right direction;
[0026] When the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold, the slope of the scattered point fitting line is less than the second threshold, and the distance between the base stations is reasonable and the base station antenna directions are opposite, it is determined that the engineering parameters are unreasonable;
[0027] When the clustering result is that there are scattered points whose distance from the category center is greater than the third threshold, it is determined that there is an abnormal neighboring area.
[0028] Optionally, the measurement report data includes at least one of the following parameters: a neighboring cell frequency, a physical cell identifier PCI, and a cell signal strength parameter, wherein the cell signal strength parameter includes: at least one of a reference signal received power RSRP, a reference signal received quality RSRQ, and a signal to interference and noise ratio SINR;
[0029] The engineering parameter data includes at least one of the following parameters: cell site height, cell longitude and latitude, cell direction angle, and cell downtilt angle.
[0030] Optionally, constructing a signal strength information scatter plot according to the measurement report data and the engineering parameter data includes:
[0031] Preprocessing the measurement report data and the engineering parameter data to obtain a serving cell-neighboring cell signal quality value group;
[0032] A signal strength information scatter plot is constructed according to the serving cell-neighboring cell signal quality value group.
[0033] Optionally, preprocessing the measurement report data and the engineering parameter data to obtain a serving cell-neighboring cell signal quality value group includes:
[0034] Determine a base station cell identifier ECI of a neighboring cell according to the neighboring cell frequency and PCI in the measurement report data and the engineering parameter data;
[0035] The measurement report data is grouped based on the ECI to obtain a serving cell-neighboring cell signal quality value group.
[0036] Optionally, obtaining measurement report data of cells in the first area includes:
[0037] Receive measurement report data reported by a first terminal, where the first terminal includes: terminals in all cells within the first area, and the first area is a plurality of continuous areas.
[0038] The embodiment of the present invention further provides a network anomaly detection device, comprising:
[0039] An acquisition module, used to acquire measurement report data and engineering parameter data of cells in the first area;
[0040] A first construction module is used to construct a signal strength information scatter plot according to the measurement report data and the engineering parameter data;
[0041] The second construction module is used to extract features from the signal strength information scatter plot and construct a detection feature library;
[0042] The detection module is used to perform network anomaly detection based on the detection feature library.
[0043] An embodiment of the present invention further provides a network device, comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the above method is executed.
[0044] An embodiment of the present invention further provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the above method.
[0045] The above solution of the present invention includes at least the following beneficial effects:
[0046] The above-mentioned scheme of the present invention, by constructing graphs and extracting structured information from measurement report data and engineering parameter data, carries a large amount of user behavior information and can check network anomalies without precise prior information and professional experience. It can quickly troubleshoot network problems in the early stage of network construction and optimize and improve network quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 A schematic diagram of a flow chart of a method for detecting network anomalies according to an embodiment of the present invention;
[0048] Figure 2 Another schematic diagram of a flow chart of a method for detecting network anomalies according to an embodiment of the present invention;
[0049] Figure 3 One of the scatter plots drawn based on the serving cell-neighboring cell RSRP value group according to an embodiment of the present invention;
[0050] Figure 4 The second scatter plot is drawn based on the serving cell-neighboring cell RSRP value group according to an embodiment of the present invention;
[0051] Figure 5 The third scatter plot is drawn based on the serving cell-neighboring cell RSRP value group according to an embodiment of the present invention;
[0052] Figure 6 A schematic diagram of scattered point clustering according to an embodiment of the present invention;
[0053] Figure 7 for Figure 6 Schematic diagram of signal intensity clustering for cluster categories in the middle circle;
[0054] Figure 8 A schematic diagram of a module of a device for detecting network anomalies according to an embodiment of the present invention;
[0055] Fig. 9 The figure is a structural block diagram of a network device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0056] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.
[0057] like Figure 1 As shown, an embodiment of the present invention provides a method for detecting network anomalies, comprising:
[0058] Step 11: Obtain measurement report data and engineering parameter data of cells in the first area.
[0059] The first area is a plurality of continuous areas, and the first area includes a plurality of cells. The measurement report data may include at least one of the following parameters: neighboring cell frequency, physical cell ID (PCI) and cell signal strength parameters. The cell signal strength parameters include at least one of reference signal received power (RSRP), reference signal received quality (RSRQ) and signal to interference plus noise ratio (SINR). The engineering parameter data includes at least one of the following parameters: cell site height, cell longitude and latitude, cell azimuth angle and cell downtilt angle.
[0060] Step 12: Construct a signal strength information scatter plot based on the measurement report data and engineering parameter data.
[0061] The signal strength information scatter plot is a scatter plot of signal strength information of all cells in the first area measured and reported by all terminals in all cells in the first area, and can be used to characterize the actual signal strength (cell communication quality) of each cell in the first area.
[0062] Step 13: Extract features from the signal strength information scatter plot and build a detection feature library.
[0063] Among them, step 13 may include: based on at least one of image statistical features, planar characteristics of geometric distribution and two-dimensional characteristics of geometric distribution, extracting features from the signal strength information scatter plot; processing the extracted features in a preset format or order to obtain a detection feature library.
[0064] Step 14: Perform network anomaly detection based on the detection feature library.
[0065] By extracting the structured features of the signal strength information scatter plot, a detection feature library is formed. Combined with additional information such as the engineering parameter data of each cell and specific strategies, several feature sets are selected for anomaly detection analysis, and the located network abnormal neighboring area combination is output.
[0066] like Figure 2 As shown, the method for detecting network anomalies in an embodiment of the present invention specifically includes:
[0067] Step 21: Data collection.
[0068] Data collection is to obtain measurement report data and engineering parameter data of cells in the first area. That is, measurement report data (Measurement Report, MR) reported by all terminals in all cells in a contiguous area within a period of time and engineering parameter data of corresponding cells are collected. Among them, the step of obtaining measurement report data of cells in the first area includes: receiving measurement report data reported by a first terminal, the first terminal includes: terminals in all cells in the first area, and the first area is a plurality of continuous areas.
[0069] Step 22: Data preprocessing.
[0070] Step 22 includes: pre-processing the measurement report data and the engineering parameter data to obtain a serving cell-neighboring cell signal quality value group.
[0071] The step of preprocessing the measurement report data and the engineering parameter data to obtain a serving cell-neighboring cell signal quality value group includes: determining a neighboring cell base station cell identifier (eNB Cell ID, ECI) according to the neighboring cell frequency and PCI in the measurement report data and the engineering parameter data; and grouping the measurement report data based on the ECI to obtain a serving cell-neighboring cell signal quality value group.
[0072] Optionally, since the neighboring cell measurement information reported in the MR only includes the frequency and PCI of the neighboring cell, its value cannot uniquely determine the neighboring cell, and a certain method is required to map it into a unique identification ID of the cell, such as ECI. According to the neighboring cell frequency and PCI in the measurement report data and the engineering parameter data, the step of determining the ECI of the neighboring cell can be: for a certain MR measurement sample, based on the engineering parameter table, search for all cells within a preset distance (for example, 3 kilometers) around the serving cell that meet the frequency and PCI corresponding to the neighboring cell measured by the MR. The one closest to the serving cell that meets the conditions is considered to be the neighboring cell measured by the sample, and then the ECI of the neighboring cell is obtained from the engineering parameter table.
[0073] The step of grouping the measurement report data based on the ECI to obtain the signal quality value group of the serving cell-neighboring cell may be: for each serving cell SC in the area i, according to the frequency and PCI of the neighboring cell in the MR data, SC i The ECI values mapped by the MR reported by all terminals in the group are grouped, and the RSRP values of each group of serving cells and neighboring cells are extracted, that is, for each pair of serving cells SC i and neighboring cell NC j , forming a serving cell-neighboring cell RSRP value group {{RSRP n _SC i},{RSRP n _NC j}}.
[0074] Step 23: Graph construction and structured feature extraction.
[0075] The step of constructing a signal strength information scatter plot according to the measurement report data and the engineering parameter data includes: preprocessing the measurement report data and the engineering parameter data to obtain a signal quality value group of a serving cell-neighboring cell; and constructing a signal strength information scatter plot according to the signal quality value group of the serving cell-neighboring cell.
[0076] The step of constructing a signal strength information scatter plot according to the signal quality value group of the serving cell-neighboring cell includes: based on the RSRP value group of the serving cell-neighboring cell {{RSRP n _SC i},{RSRP n _NC j}}, draw the RSRP n _SC i The sequence is the horizontal axis value, RSRP n _NC j A scatter plot of signal strength information with the sequence as the vertical axis value.
[0077] Step 24: Build a feature library.
[0078] Step 24 includes: extracting features from the signal strength information scatter plot to construct a detection feature library. This step may be implemented in a variety of ways depending on the analysis target, or multiple methods may be implemented simultaneously to construct a combined feature library. Possible implementation methods are as follows: extracting features from the signal strength information scatter plot based on at least one of the following: image statistical features, planar characteristics of geometric distribution, and two-dimensional characteristics of geometric distribution; processing the extracted features in a preset format or sequence to obtain a detection feature library. The following will further explain these three construction methods.
[0079] Method 1: Extraction based on image statistical features
[0080] Based on the serving cell-neighboring cell RSRP value group {{RSRP n _SC i},{RSRPn _NC j}}Draw a scatter plot with RSRP n _SC i The sequence is the horizontal axis value, RSRP n _NC j The sequence is the ordinate value, such as Figure 3 As shown. The image statistical features include at least one of the following: the coordinates of the centroid of the scattered points, the slope of the scattered point fitting line, the mean of the signal strength difference, the median of the signal strength difference, the mode of the signal strength difference, and the number of scattered points. Then, according to the serving cell-neighboring cell RSRP value group {{RSRP n _SC i},{RSRP n _NC j}} and the statistical information of the scatter plot, extract the representative features of the scatter plot, such as the coordinates of the scatter point centroid, the scatter point fitting line and the slope, etc. The key features and their meanings that may be included are as follows in Table 1:
[0081] Table 1
[0082]
[0083] Method 2: Plane feature extraction based on geometric distribution
[0084] The step of extracting features from a signal strength information scatter plot based on the planar characteristics of geometric distribution includes: dividing the signal strength information scatter plot into m*n regional grids based on the planar characteristics of geometric distribution; counting the number of scatter points in each regional grid to obtain an m*n dimensional feature vector of the signal strength information scatter plot.
[0085] Similarly, based on the serving cell-neighboring cell RSRP value group {{RSRP n _SC i},{RSRP n _NC j}}, with RSRP n _SC i The sequence is the horizontal axis value, RSRP n _NC j Draw a scatter plot with the sequence as the ordinate value, unify the scatter plots of all service cells with the same range of horizontal and vertical coordinates, divide each scatter plot into m*n regional grids, and count the number of scattered points in each grid in turn, so that a grid feature vector of length m*n can be obtained from the scatter plot. Figure 4 As shown in the figure, the scatter plot is divided into 8*8 grids, and the number of scattered points in each small grid is calculated to form a feature vector. The 64-dimensional feature vector of the scatter plot can be obtained as V_SC i _NC j=[0,0,…,86,107,121,…,0,0] m*n .
[0086] Method 3: 2D feature extraction based on geometric distribution
[0087] Based on the two-dimensional characteristics of geometric distribution, the step of extracting features from the signal strength information scatter plot includes: based on the planar characteristics of geometric distribution, dividing the horizontal axis of the signal strength information scatter plot into p intervals and the vertical axis into q intervals; respectively counting the number of scatter points falling in the p intervals of the horizontal axis and the q intervals of the vertical axis to obtain the horizontal axis feature vector and the vertical axis feature vector of the signal strength information scatter plot. Similar to the second method, the scatter plots of all service cells are unified in the range of horizontal and vertical coordinates, such as Figure 5 As shown, the horizontal axis and vertical axis are divided into p and q intervals respectively, and the scatter plot is projected in both the horizontal and vertical directions. The number of scattered points falling in the p intervals of the horizontal axis and the q intervals of the vertical axis are counted respectively to form two feature vectors of the horizontal and vertical axes: Vx_SC i _NC j =[0,0,79,514,1082,679,101,0] m , Vy_SC i _NC j =[1,1,182,1135,1294,550,93,0] n .
[0088] The signal strength information scatter plot is feature extracted by at least one of the above three methods, and then the extracted structured features are organized into a feature library in a certain format and order, and necessary feature preprocessing is performed, such as normalization, combination, dimensionality reduction, etc.
[0089] Step 25: Perform feature selection in the feature library.
[0090] Step 26: Based on the selected features, perform anomaly detection.
[0091] Among them, steps 23, 25, and 26 are performed and implemented based on their respective policy controls. Steps 25 and 26 are: network anomaly detection based on the detection feature library, which includes: clustering according to the features in the detection feature library to obtain clustering results; and determining the corresponding network anomaly state based on the clustering results. Optionally, it is assumed that the slope k of the scatter fit straight line and the difference diff_avg between the horizontal and vertical coordinates of the center of mass are extracted and combined into clustering objects (ki, diff_avgi), and a hierarchical clustering algorithm is used for clustering. Clustering according to the features in the detection feature library to obtain clustering results may include: (1) treating each object as a class and calculating the minimum distance between each pair; (2) merging the two classes with the smallest distance into a new class; (3) recalculating the distance between the new class and all classes; (4) repeating (2) and (3) until the specified classification end condition, such as a given number of classes, or reaching the minimum distance threshold between two classes, is obtained. Figure 6 The clustering results are shown in Figure 1. Among them, points with different gray levels represent different categories (k i ,diff_avg i ), that is, the neighboring area relationships of different categories, and further anomaly detection is performed based on the clustering results.
[0092] Step 27: Output the results of anomaly detection.
[0093] Based on a certain strategy, select the full set or subset of features in the feature library, and use certain judgment rules or unsupervised models to perform anomaly detection. For example, for a certain category in the clustering result, such as Figure 6 As shown in the circle, this category is characterized by a large difference in the horizontal and vertical coordinates of the scatter plot centroid and a small slope of the fitted line, such as Figure 7 As shown, the RSRP of the serving cell and the neighboring cell are weakly correlated. Then, the corresponding network abnormal state is determined according to the clustering result, and this step includes at least one of the following:
[0094] When the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold and the slope of the scattered point fitting line is less than the second threshold, it is determined that the distance between the base stations is unreasonable or the base station antennas are not in the right direction; the engineering parameter configuration rules of the main service cell and the neighboring cell of this category are analyzed. Usually, the distance between the base stations is far or the antenna direction angles are not in the right direction.
[0095] When the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold, the slope of the scattered point fitting line is less than the second threshold, the distance between base stations is reasonable, and the base station antenna directions are opposite, it is determined that the engineering parameters are unreasonable; when the above-mentioned cluster distribution occurs, and the cells in the existing network clustering are checked for this type of neighboring area relationship, if there is a situation in which the antennas in the engineering parameters are opposite or the angle overlap is high, and the base station locations are close, there may be a problem with the filling of the engineering parameters, which is a network abnormality and the accuracy of the engineering parameters needs to be checked.
[0096] When the clustering result shows that there are scattered points whose distance from the category center is greater than the third threshold, it is determined that there is an abnormal neighboring area. This method is to take a specific threshold, find outlier sample points whose distance from the center of each category is greater than the threshold and judge them as abnormal neighboring areas, and focus on and troubleshoot possible problems in combination with the outlier point parameter configuration.
[0097] In the method for detecting network anomalies of an embodiment of the present invention, by constructing a graph and extracting structured information from measurement report data and engineering parameter data, a large amount of user behavior information is carried, and network anomalies can be checked without accurate prior information and professional experience. Network problems can be quickly checked in the early stage of network construction, and network quality can be optimized and improved.
[0098] The above describes an embodiment of a method for detecting network anomalies. The following will further describe an embodiment of a device corresponding to the method in conjunction with the accompanying drawings.
[0099] The embodiment of the present invention also provides a network anomaly detection device, such as Figure 8 As shown, the device comprises:
[0100] An acquisition module 810 is used to acquire measurement report data and engineering parameter data of cells in the first area;
[0101] A first construction module 820 is used to construct a signal strength information scatter plot according to the measurement report data and the engineering parameter data;
[0102] The second construction module 830 is used to extract features from the signal strength information scatter plot and construct a detection feature library;
[0103] The detection module 840 is used to perform network anomaly detection based on the detection feature library.
[0104] Optionally, the second building module 830 includes:
[0105] A first extraction submodule is used to extract features from the signal strength information scatter plot based on at least one of the following: image statistical features, planar characteristics of geometric distribution, and two-dimensional characteristics of geometric distribution;
[0106] The first processing submodule is used to process the extracted features according to a preset format or sequence to obtain a detection feature library.
[0107] Optionally, the image statistical features include at least one of the following: scatter point centroid coordinates, scatter point fitting line slope, signal intensity difference mean, signal intensity difference median, signal intensity difference mode and scatter point number.
[0108] Optionally, the first extraction submodule includes:
[0109] A first segmentation unit is used to segment the signal strength information scatter diagram into m*n area grids based on the plane characteristics of geometric distribution;
[0110] The first statistical unit is used to count the number of scattered points in each area grid to obtain an m*n dimensional feature vector of the signal strength information scatter diagram.
[0111] Optionally, the first extraction submodule further includes:
[0112] A second segmentation unit is used to segment the horizontal axis of the signal strength information scatter diagram into p intervals and the vertical axis into q intervals based on the plane characteristics of the geometric distribution;
[0113] The second statistical unit is used to count the number of scattered points falling in the p intervals of the horizontal axis and the q intervals of the vertical axis respectively, and obtain the horizontal axis feature vector and the vertical axis feature vector of the signal strength information scatter diagram.
[0114] Optionally, the detection module 840 includes:
[0115] The clustering submodule is used to perform clustering processing according to the features in the detection feature library to obtain clustering results;
[0116] The determination submodule is used to determine the corresponding network abnormal state according to the clustering result.
[0117] Optionally, the determining submodule includes at least one of the following:
[0118] A first determination unit is used to determine that the distance between base stations is unreasonable or the base station antennas are not oriented correctly when the clustering result shows that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than a first threshold and the slope of the scattered point fitting line is less than a second threshold;
[0119] The second determination unit is used to determine that the engineering parameters are unreasonable when the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold, the slope of the scattered point fitting line is less than the second threshold, and the distance between the base stations is reasonable and the base station antenna directions are opposite;
[0120] The third determining unit is used to determine the existence of an abnormal neighboring area when the clustering result shows that there are scattered points whose distance from the category center is greater than a third threshold.
[0121] Optionally, the measurement report data includes at least one of the following parameters: a neighboring cell frequency, a physical cell identifier PCI, and a cell signal strength parameter, wherein the cell signal strength parameter includes: at least one of a reference signal received power RSRP, a reference signal received quality RSRQ, and a signal to interference and noise ratio SINR;
[0122] The engineering parameter data includes at least one of the following parameters: cell site height, cell longitude and latitude, cell direction angle, and cell downtilt angle.
[0123] Optionally, the first building module 820 includes:
[0124] The second processing submodule is used to pre-process the measurement report data and the engineering parameter data to obtain a serving cell-neighboring cell signal quality value group;
[0125] The construction submodule is used to construct a signal strength information scatter plot according to the signal quality value group of the serving cell-neighboring cell.
[0126] Optionally, the second processing submodule includes:
[0127] A fourth determining unit, configured to determine a base station cell identifier ECI of a neighboring cell according to the neighboring cell frequency point and PCI and engineering parameter data in the measurement report data;
[0128] The grouping unit is used to group the measurement report data based on the ECI to obtain a signal quality value group of the serving cell-neighboring cell.
[0129] Optionally, the acquisition module 810 includes:
[0130] The receiving submodule is used to receive measurement report data reported by the first terminal, where the first terminal includes: terminals in all cells in a first area, where the first area is a plurality of continuous areas.
[0131] The device embodiment of the embodiment of the present invention is a product embodiment corresponding to the above-mentioned method embodiment. All application examples of the above-mentioned method embodiment are applicable to the device embodiment and can achieve the same or similar technical effects, so they are not repeated here.
[0132] An embodiment of the present invention further provides a network device, such as Fig. 9 As shown, the network device includes: a processor 910 and a memory 920 storing a computer program, and when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.
[0133] The embodiment of the present invention further provides a computer-readable storage medium, including instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.
[0134] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0136] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0139] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.
[0140] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.
[0141] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.
[0142] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for detecting network anomalies, characterized in that: include: Acquire measurement report data and engineering parameter data of cells in the first area, the measurement report data including at least one of the following parameters: neighboring cell frequency, physical cell identifier PCI, and cell signal strength parameter; the engineering parameter data including at least one of the following parameters: cell site height, cell longitude and latitude, cell direction angle, and cell downtilt angle; Constructing a signal strength information scatter plot according to the measurement report data and the engineering parameter data; Extracting features from the signal strength information scatter plot to construct a detection feature library; Based on the detection feature library, perform network anomaly detection; Wherein, constructing a signal strength information scatter plot according to the measurement report data and the engineering parameter data includes: Determine a base station cell identifier ECI of a neighboring cell according to the neighboring cell frequency and PCI in the measurement report data and the engineering parameter data; Grouping the measurement report data based on the ECI to obtain a serving cell-neighboring cell signal quality value group; A signal strength information scatter plot is constructed according to the serving cell-neighboring cell signal quality value group.
2. The method for detecting network anomalies according to claim 1, characterized in that: Extracting features from the signal strength information scatter plot and building a detection feature library include: Based on at least one of image statistical features, planar characteristics of geometric distribution, and two-dimensional characteristics of geometric distribution, feature extraction is performed on the signal strength information scatter plot; The extracted features are processed according to a preset format or sequence to obtain a detection feature library.
3. The method for detecting network anomalies according to claim 2, characterized in that: The image statistical features include at least one of the following: scatter point centroid coordinates, scatter point fitting line slope, signal intensity difference mean, signal intensity difference median, signal intensity difference mode and scatter point number.
4. The method for detecting network anomalies according to claim 2, characterized in that: Based on the plane characteristics of geometric distribution, feature extraction is performed on the signal strength information scatter plot, including: Based on the planar characteristics of geometric distribution, the signal strength information scatter plot is divided into m*n regional grids; The number of scattered points in each regional grid is counted to obtain an m*n dimensional feature vector of the signal strength information scatter diagram.
5. The method for detecting network anomalies according to claim 2, characterized in that: Based on the two-dimensional characteristics of geometric distribution, feature extraction is performed on the signal strength information scatter plot, including: Based on the plane characteristics of geometric distribution, the horizontal axis of the signal strength information scatter plot is divided into p intervals, and the vertical axis is divided into q intervals; The number of scattered points falling in the p intervals of the horizontal axis and the q intervals of the vertical axis are counted respectively to obtain the horizontal axis feature vector and the vertical axis feature vector of the signal strength information scatter diagram.
6. The method for detecting network anomalies according to claim 1, characterized in that: Based on the detection feature library, network anomaly detection is performed, including: Perform clustering processing according to the features in the detection feature library to obtain clustering results; According to the clustering result, a corresponding network abnormal state is determined.
7. The method for detecting network anomalies according to claim 6, characterized in that: Determining a corresponding network abnormal state according to the clustering result includes at least one of the following: When the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold and the slope of the scattered point fitting line is less than the second threshold, it is determined that the distance between the base stations is unreasonable or the base station antennas are not in the right direction; When the clustering result is that the difference between the horizontal and vertical coordinates of the scattered point centroid is greater than the first threshold, the slope of the scattered point fitting line is less than the second threshold, and the distance between the base stations is reasonable and the base station antenna directions are opposite, it is determined that the engineering parameters are unreasonable; When the clustering result is that there are scattered points whose distance from the category center is greater than the third threshold, it is determined that there is an abnormal neighboring area.
8. The method for detecting network anomalies according to any one of claims 1 to 7, characterized in that: The cell signal strength parameter includes: at least one of a reference signal received power RSRP, a reference signal received quality RSRQ and a signal to interference and noise ratio SINR.
9. The method for detecting network anomalies according to claim 1, characterized in that: Acquiring measurement report data of cells in the first area, including: Receive measurement report data reported by a first terminal, where the first terminal includes: terminals in all cells within the first area, and the first area is a plurality of continuous areas.
10. A network anomaly detection device, characterized in that: include: An acquisition module is used to acquire measurement report data and engineering parameter data of cells in the first area, wherein the measurement report data includes at least one of the following parameters: neighboring cell frequency, physical cell identifier PCI, and cell signal strength parameter; the engineering parameter data includes at least one of the following parameters: cell station height, cell longitude and latitude, cell direction angle, and cell downtilt angle; A first construction module, configured to construct a signal strength information scatter plot according to the measurement report data and the engineering parameter data; The second construction module is used to extract features from the signal strength information scatter plot and construct a detection feature library; A detection module, used for performing network anomaly detection based on the detection feature library; Wherein, the first building block includes: A fourth determining unit, configured to determine a base station cell identifier ECI of a neighboring cell according to the neighboring cell frequency and PCI in the measurement report data and the engineering parameter data; A grouping unit, configured to group the measurement report data based on the ECI to obtain a serving cell-neighboring cell signal quality value group; The construction submodule is used to construct a signal strength information scatter plot according to the serving cell-neighboring cell signal quality value group.
11. A network device, characterized in that: include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 9 is performed.
12. A computer-readable storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 9.
Citation Information
Patent Citations
Method and system for positioning terminal on high-speed railway and the monitoring method and system for high-speed railway network
CN106535114A
Method for distinguishing indoor and outdoor measurement reports and network equipment
CN108616900A
Indoor positioning method and device based on WiFi latitude and longitude
CN110267209A
Outdoor unmanned aerial vehicle positioning method and system based on LoRa
CN111065046A
Network quality abnormity positioning method and device
CN111817868A
