CN117014322A - Network complaint root cause positioning method, device and application - Google Patents
Network complaint root cause positioning method, device and application Download PDFInfo
- Publication number
- CN117014322A CN117014322A CN202210470080.1A CN202210470080A CN117014322A CN 117014322 A CN117014322 A CN 117014322A CN 202210470080 A CN202210470080 A CN 202210470080A CN 117014322 A CN117014322 A CN 117014322A
- Authority
- CN
- China
- Prior art keywords
- complaint
- network
- network performance
- abnormal
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000002159 abnormal effect Effects 0.000 claims abstract description 170
- 230000005856 abnormality Effects 0.000 claims abstract description 100
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 230000000977 initiatory effect Effects 0.000 claims description 46
- 238000010276 construction Methods 0.000 claims description 44
- 230000011218 segmentation Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 16
- 238000005070 sampling Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 230000006855 networking Effects 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 8
- 238000010295 mobile communication Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Algebra (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application relates to the field of mobile communication, and provides a method, a device and an application for positioning root causes of network complaints. The method comprises the following steps: constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; determining whether the customer complaint network performance index set is abnormal or not according to the average height of the customer complaint network performance index set in the plurality of independent trees; when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of a plurality of independent trees; and determining the root cause of the network complaint according to the abnormality index. The network complaint root cause positioning method provided by the embodiment of the application can use an unsupervised method to position abnormal indexes without training an analysis model in advance, and can also quickly and efficiently identify the network complaint root cause aiming at the type of the complaint which does not appear.
Description
Technical Field
The application relates to the technical field of mobile communication, in particular to a method, a device and application for positioning root causes of network complaints.
Background
With the development of 5G communication technology, network complexity, service type, user type and data have increased rapidly, and network performance indexes related to network complaints are more, if the accuracy and the positioning efficiency of positioning results are low by a traditional manual positioning mode.
At present, in the prior art, a network fault root cause positioning method exists, and after network transmission abnormality is determined to be caused, operation data and a network topology map of each node in network transmission are collected; and judging whether abnormal nodes exist in the plurality of nodes according to the connection relation among the nodes recorded in the topological graph in a grading manner through a plurality of analysis models in the model set, and sequentially arranging the nodes causing abnormal network transmission and the abnormal root causes of the nodes.
In the method, the abnormal nodes are required to be judged through a plurality of analysis models in the model set, and in order to achieve the accuracy and the positioning speed of network fault root cause positioning, high requirements are put forward on the number of the analysis models in the model set and the accuracy of each analysis model, and corresponding abnormal nodes and abnormal root causes can be identified and positioned after new analysis models are required to be retrained according to the types of complaints which do not appear.
Disclosure of Invention
The embodiment of the application provides a method, a device and an application for positioning the root cause of network complaints, which are used for solving the technical problems that a model used for positioning the root cause of the network complaints in the prior art needs to be trained in advance and is difficult to cover the types of complaints which do not appear.
In a first aspect, an embodiment of the present application provides a method for positioning root causes of network complaints, including:
Constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
and determining the root cause of the network complaint according to the abnormality index.
In one embodiment, the determining whether the complaint network performance index set is abnormal according to the average height of the complaint network performance index set in the independent trees includes:
Calculating an anomaly score of the complaint network performance index set according to the average height of the complaint network performance index set in the plurality of independent trees;
and when the anomaly score is greater than a preset anomaly score threshold, determining that the customer complaint network performance index set is abnormal.
In one embodiment, the determining the abnormality index according to the path height of the complaint leaf node and the average height of the plurality of independent trees includes:
calculating the average height E of the plurality of independent trees M ；
The path height is smaller than a×E M The customer complaint leaf node is taken as an abnormal leaf node; wherein a E is (0, 1);
and taking the segmentation standard of the abnormal leaf node as the abnormal index.
In one embodiment, the constructing a plurality of independent trees based on the complaint network performance index set and the non-complaint network performance index set by using the isolated forest algorithm includes:
constructing a data set containing N elements; wherein N-1 elements are the network performance index set without customer complaints, 1 element is the network performance index set with customer complaints, and N is an integer greater than 2;
performing M times of element extraction on the data set, and constructing an independent tree for each extracted element to obtain a plurality of independent trees; wherein M is an integer greater than 2.
In one embodiment, the element extraction is performed M times on the data set, and an independent tree is constructed for each extracted element, so as to obtain the multiple independent trees, wherein the construction process of one independent tree is as follows:
extracting the construction elements of the independent tree in the data set according to a preset sampling proportion;
dividing the construction element according to any index in the network performance index set as a dividing reference to obtain 2 branches;
executing the steps of dividing the construction elements according to any index in the network performance index set as a dividing reference again on the construction elements under each branch until the tree dividing stop condition is met, ending the division of the construction elements under all branches, and obtaining the independent tree;
when the current branch meets the branch segmentation stopping condition, ending the segmentation of the construction element under the current branch; the branch division stop condition includes: the building element under the current branch has only 1; the tree division stop condition includes: the segmentation of the building elements under all branches has ended or the current tree height is equal to or greater than the independent tree height threshold.
In one embodiment, before constructing the plurality of independent trees based on the complaint network performance index set and the non-complaint network performance index set by using the isolated forest algorithm, the method includes:
determining the complaint cell according to the network complaint initiating position and acquiring the complaint network performance index set based on the complaint cell;
the distance between the complaint cell and the network complaint initiating position is smaller than a preset distance threshold; the complaint cell is located in a preset azimuth angle range of the network complaint initiating position.
In one embodiment, the determining the root cause of the network complaint according to the abnormality index includes:
when the abnormal index meets one of the coverage abnormal conditions, judging that the network complaint root causes comprise coverage abnormality; the coverage exception condition includes: no base station exists in a preset range of the network complaint initiating position, the abnormal index comprises an independent networking SA user coverage satisfaction index, the SA user coverage satisfaction index is smaller than an SA user coverage satisfaction threshold, the abnormal index comprises a measurement report MR coverage rate, and the MR coverage rate of a resident cell is smaller than an MR coverage rate threshold; the resident cells are cells which are ranked in the front K bits after the cells are ranked according to the sequence from the large to the small of the connection times of the user equipment; wherein K is a positive integer;
When the abnormality index meets one of the interference abnormality conditions, judging that the network complaint root causes comprise interference abnormality; the interference anomaly condition includes: the abnormal index comprises overlapping coverage rate, the overlapping coverage rate is larger than an overlapping coverage rate threshold value, the abnormal index comprises interference background noise index, and the interference background noise index is larger than an interference background noise index threshold value; the overlapping coverage rate threshold value is the average value of the overlapping coverage rate of the non-complaint cell; the interference bottom noise index threshold is the average value of the interference bottom noise indexes of the cells without complaints;
when the abnormal index meets the site fault condition, judging that the network complaint root causes comprise site faults; the site failure condition includes: the network complaint initiating position has a fault site in a preset range; the fault site is a base station in a fault site record within a preset time before the network complaint initiating time;
when the abnormality index meets a capacity abnormality condition, judging that the network complaint root causes comprise capacity abnormality; the capacity exception condition includes: the abnormal index comprises a user number index, and the user number index is larger than a user number threshold; the user number threshold is the average value of the user number indexes of the cells without customer complaints;
And when the abnormality index does not meet any one of the coverage abnormality condition, the interference abnormality condition, the site fault condition and the capacity abnormality condition, judging that the network complaint root is due to other abnormalities.
In a second aspect, an embodiment of the present application provides a network complaint root cause positioning device, including:
an independent tree construction module for: constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
an anomaly determination module for: determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
the abnormal index identification module is used for: when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
The network complaint root factor matching module is used for: and determining the root cause of the network complaint according to the abnormality index.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory storing a computer program, where the processor implements the steps of the network complaint root cause positioning method according to the first aspect when executing the program.
In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, where the computer program when executed by a processor implements the steps of the network complaint root cause positioning method of the first aspect.
According to the network complaint root cause positioning method provided by the embodiment of the application, the network performance index sets of the complaint cell and the non-complaint cell are used as the data sets constructed by the independent trees through the isolated forest algorithm, and because the outliers are defined as outliers which are easy to be isolated in the isolated forest algorithm, namely, the points which are sparse in distribution and far away from the high-density group, the non-complaint network performance index sets are used as the high-density group in the embodiment of the application, and the distances between the complaint network performance index sets and the high-density group can be obtained according to the average heights of the complaint network performance index sets in the plurality of independent trees, so that whether the complaint network performance index sets are abnormal or not is judged; after the abnormal condition of the customer complaint network performance index set is judged, an abnormal index is further found according to the path height of the customer complaint leaf node and the average height of the independent trees, the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value, and the difference of the network performance index set between the customer complaint cell and the non-customer complaint cell is obvious when the abnormal leaf node is segmented, so that the segmentation reference of the abnormal leaf node can be regarded as the abnormal index, and the abnormal index is positioned by using an unsupervised method in the process, so that an analysis model is not required to be trained in advance; under the condition that which index is abnormal is determined, the influence factors related to the index can be determined as the root cause of the network complaint, and as the corresponding relation between the index and the influence factors is easy to obtain information, the root cause of the network complaint can be rapidly and efficiently identified for the type of the complaint which does not occur.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for locating root causes of network complaints according to an embodiment of the present application;
FIG. 2 is a flow chart of an independent tree construction process provided by an embodiment of the present application;
FIG. 3 is a flowchart of a method for determining whether a customer complaint network performance index set is abnormal according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a network complaint root cause positioning device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Fig. 1 is a flow chart of a network complaint root cause positioning method according to an embodiment of the present application. Referring to fig. 1, an embodiment of the present application provides a method for locating root causes of network complaints, which may include:
s11, constructing a plurality of independent trees based on a customer complaint network performance index set and a customer complaint-free network performance index set by utilizing an isolated forest algorithm;
s12, determining whether the customer complaint network performance index set is abnormal or not according to the average height of the customer complaint network performance index set in a plurality of independent trees;
s13, when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of a plurality of independent trees;
s14, determining the root cause of the network complaint according to the abnormal index.
In step S11, the complaint network performance index set is a network performance index set of a complaint cell; the network performance index set without complaints is a network performance index set of a cell without complaints.
The customer complaint cell can be determined according to the network complaint initiating position, and is positioned in a preset range of the network complaint initiating position, wherein the preset range can comprise two dimensions of a distance and an azimuth; accordingly, a cell which is not located in a preset range of any network complaint initiating position is a cell without customer complaints.
Further, the customer complaint network performance index set and the no customer complaint network performance index set are multiple network performance index data of which the network complaint initiation time is traced back for a preset number of days, including but not limited to: the method comprises the following steps of 5G call completing rate, wireless disconnection rate, SA switching success rate, coverage fullness of independent networking users, MR coverage rate, overlapping coverage rate, interference noise floor index and user number index.
In step S12, since the outlier that is easily isolated in the isolated forest algorithm is often located at a position with a smaller height in the independent tree, it can be determined whether the complaint network performance index set is easily isolated in the plurality of independent trees according to the average height of the complaint network performance index set in the plurality of independent trees, so as to determine whether the complaint network performance index set is abnormal.
In step S13, whether the complaint leaf node is an abnormal leaf node or not may be determined according to a comparison result of the path height of the complaint leaf node in each independent tree and the average height of the plurality of independent trees, and the abnormal index is a segmentation reference of the abnormal leaf node;
the abnormal leaf nodes are complaint leaf nodes with the proportion of the path height to the average height of the plurality of independent trees smaller than a preset value; the customer complaint leaf nodes are leaf nodes where customer complaint network performance index sets are located in a plurality of independent trees.
In step S14, it is considered that the formation of the network complaint is affected by the abnormal index, so that the corresponding influencing factor can be found based on the abnormal index, and the cause of the abnormal index, that is, the root cause of the network complaint, is determined.
It should be noted that, the number of the root causes of the network complaints may be one or more, and the embodiment of the present application does not have any quantitative limitation on the root causes of the network complaints.
According to the network complaint root cause positioning method provided by the embodiment of the application, the network performance index sets of the complaint cell and the non-complaint cell are used as the data sets constructed by the independent trees through the isolated forest algorithm, and because the outliers are defined as outliers which are easy to be isolated in the isolated forest algorithm, namely, the points which are sparse in distribution and far away from the high-density group, the non-complaint network performance index sets are used as the high-density group in the embodiment of the application, and the distances between the complaint network performance index sets and the high-density group can be obtained according to the average heights of the complaint network performance index sets in the plurality of independent trees, so that whether the complaint network performance index sets are abnormal or not is judged; after the abnormal condition of the customer complaint network performance index set is judged, an abnormal index is further found according to the path height of the customer complaint leaf node and the average height of the independent trees, the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value, and the difference of the network performance index set between the customer complaint cell and the non-customer complaint cell is obvious when the abnormal leaf node is segmented, so that the segmentation reference of the abnormal leaf node can be regarded as the abnormal index, and the abnormal index is positioned by using an unsupervised method in the process, so that an analysis model is not required to be trained in advance; under the condition that which index is abnormal is determined, the influence factors related to the index can be determined as the root cause of the network complaint, and as the corresponding relation between the index and the influence factors is easy to obtain information, the root cause of the network complaint can be rapidly and efficiently identified for the type of the complaint which does not occur.
In one embodiment, prior to building the independent tree, a complaint cell may be determined from the network complaint initiation location and a set of complaint network performance metrics may be obtained based on the complaint cell.
The distance between the complaint cell and the network complaint initiating position is smaller than a preset distance threshold; the complaint cell is located in a preset azimuth angle range of the network complaint initiating position.
In the identifying process of the complaint cell, the distance between the network complaint initiating position and the cell is obtained by calculating through a Haverine formula:
wherein d represents the distance between the network complaint initiating location and the cell; r represents the earth radius; lambda (lambda) 1 Andlongitude and latitude respectively representing the location of the initiation of the network complaint; lambda (lambda) 2 And->Representing the longitude and latitude of the cell, respectively.
In the above-mentioned identification process of complaint cells, the azimuth angle between the network complaint initiation location and the cell can be calculated according to the following formula:
where θ represents the azimuth angle between the network complaint initiation location and the cell.
When d is smaller than a preset distance threshold value and theta is in a preset azimuth angle range, the current cell is indicated to be the cell corresponding to the current network complaint, namely the customer complaint cell; accordingly, a cell which is not located in a preset range of any network complaint initiating position is a cell without customer complaint, namely, the network performance index set of the cell without customer complaint is indicated that no abnormality is found.
When the complaint cells are identified, there are cases where a plurality of cells are located within a preset range of the network complaint initiation position, in which case, the cells may be sorted in order of the distance between the cells and the network complaint initiation position from small to large, and the cells in the front P-bit of the sorting are taken as the complaint cells, where the value of P is a positive integer less than or equal to 10.
It can be appreciated that the embodiment of the present application is not limited only to the preset distance threshold and the preset azimuth range, and in the actual application process, specific values of the preset distance threshold and the preset azimuth range may be set according to actual requirements.
According to the complaint cell identification method provided by the embodiment of the application, the complaint cell positioned in the preset range of the network complaint initiating position is identified by utilizing the distance information and the azimuth information between the network complaint initiating position and the cell, the accuracy of positioning the complaint cell can be improved by the judging standard of the two dimensions of the distance and the azimuth, and an accurate complaint network performance index set is obtained, so that the accuracy of positioning the network complaint root is ensured.
In one embodiment, referring to fig. 2, using an isolated forest algorithm, the process of constructing a plurality of independent trees based on a set of complaint network performance indicators and a set of complaint-free network performance indicators is as follows:
S21, constructing a data set containing N elements;
s22, performing M times of element extraction on the data set, and constructing an independent tree for each extracted element to obtain a plurality of independent trees.
In step S21, N elements may consist of N-1 complaint-free network performance index sets and 1 complaint-free network performance index set.
Wherein N is an integer greater than 2; illustratively, N may be set to 1000.
In step S22, M is an integer greater than 2; illustratively, M may be set to 100.
In one embodiment, taking an independent tree as an example, the construction process of the independent tree in step S22 is described as follows:
extracting the construction elements of the independent tree in the data set according to a preset sampling proportion;
dividing the construction element according to any index in the network performance index set as a dividing reference to obtain 2 branches;
and executing the step of dividing the construction element according to any index in the network performance index set as a dividing reference again on the construction element under each branch until the tree dividing stop condition is met, ending the division of the construction elements under all branches, and obtaining the independent tree.
Assuming that the number of elements in the data set is 1000, the number of independent trees constructed is 100, and the preset sampling ratio may be set to be 50%, that is, 500 construction elements are extracted each time to construct one independent tree, that is, each independent tree is composed of 500 construction elements.
It should be noted that, the setting of the preset sampling ratio to 50% is an example in the embodiment of the present application, and does not constitute a sole limitation of the embodiment of the present application, and specific values of the preset sampling ratio may be set according to practical situations.
The process of dividing the construction element according to any index in the network performance index set as a dividing reference specifically includes the following steps:
and taking any index in the network performance index set as a segmentation reference of the current node, taking any value from the minimum value to the maximum value of the index in the construction elements as a reference value, comparing the value of the index of each construction element with the reference value respectively, taking the value of the index as one branch smaller than the reference value and the value of the index as the other branch larger than or equal to the reference value, and dividing the construction elements into two branches.
In the process of re-splitting the construction element under each branch, the branch triggers a branch splitting stop condition to end the splitting action of splitting the current branch in advance, specifically: and when the current branch meets the branch segmentation stopping condition, ending the segmentation of the construction element under the current branch. Wherein the branch division stop condition includes: the building element under the current branch has only 1.
When there are only 1 building element under the branch, the remaining building elements do not already satisfy the minimum number of elements to perform the splitting operation, thus stopping the splitting action of the current branch.
In the embodiment of the application, the judging condition for completing the construction of the independent tree is a tree segmentation stopping condition, and the tree segmentation stopping condition comprises: the segmentation of the building elements under all branches has ended or the current tree height is equal to or greater than the independent tree height threshold.
It should be noted that, in the embodiment of the present application, the setting of the height threshold of the independent tree may be set according to actual situations, which is not limited only herein.
In the embodiment of the application, the outliers which are easy to be isolated are identified by utilizing the isolated forest algorithm, so that the abnormal index is found, the outliers are often positioned at leaf nodes with smaller path heights in the independent tree, so that the leaf nodes with smaller path heights are more likely to be abnormal points, and normal points with longer path heights are not key points in the isolated forest algorithm, the height of the independent tree is limited, and after the height of the current tree is equal to or greater than the height threshold value of the independent tree, the current tree can be regarded as normal points for subsequent segmentation, and a great amount of unnecessary segmentation work can be saved by ending the segmentation at the moment.
According to the method for constructing the independent tree, provided by the embodiment of the application, a plurality of independent trees are constructed in a sampling and extracting mode, the data processing capacity of each independent tree is reduced through sampling and extracting, the construction speed of a single independent tree is improved, and a sufficient amount of data sets which can be used for abnormality judgment and abnormality index determination of the customer network performance index set are obtained through M times of element extraction and M times of independent tree construction, so that deviation of results of abnormality judgment and abnormality index determination of the customer network performance index set caused by too small errors of the data sets is avoided.
In one embodiment, referring to fig. 3, step S12 may include:
s31, calculating an abnormal score of the complaint network performance index set according to the average height of the complaint network performance index set in a plurality of independent trees;
s32, when the abnormality score is larger than a preset abnormality threshold, determining that the customer complaint network performance index set is abnormal.
In step S31, the anomaly score S (X) of the complaint network performance index set X may be calculated according to the following calculation formula:
where E (h (X)) represents the average height of the complaint network performance index set in the plurality of independent trees and N represents the number of elements in the dataset.
In the above calculation formula, c (N) is calculated according to the following calculation formula:
where H represents a harmonic function.
When the abnormality score is larger than a preset abnormality threshold, the probability that the customer complaint network performance index set is isolated is high, and the customer complaint network performance index set is regarded as abnormality; when the abnormality score is smaller than or equal to a preset abnormality threshold, the probability that the customer complaint network performance index set is isolated is low, and the customer complaint network performance index set is regarded as normal, and network complaint root cause positioning is not needed at the moment.
In the embodiment of the present application, the preset abnormal subthreshold value may be set to 0.8, and it should be noted that the value of the preset abnormal subthreshold value is just an example value, and in practical application, the preset abnormal subthreshold value may be adjusted according to practical situations.
In one embodiment, the method for determining the abnormality index specifically includes:
calculating an average height E of the plurality of independent trees M ；
The path height is smaller than a×E M The customer complaint leaf node is taken as an abnormal leaf node; wherein a E is (0, 1); illustratively, a may take 0.2;
the segmentation reference of the abnormal leaf node is used as an abnormality index.
In the embodiment of the application, for the customer complaint network performance index set with the abnormality score larger than the preset abnormality threshold value, screening out customer complaint network performance index sets belonging to all independent trees and having the path length smaller than a×E M The leaf node of the customer complaint is used as an abnormal leaf node, and the screened leaf node of the customer complaint is located at a node position which is preferentially isolated in an independent tree, so that the classification standard of the abnormal leaf node can be used for easily distinguishing the network performance index set of the customer complaint from the network performance index set of the no-customer complaint according to the classification standard corresponding to the abnormal leaf node, and the network performance index set difference between the customer complaint cell and the no-customer complaint cell is obvious when the abnormal leaf node is classified, so that the classification standard of the abnormal leaf node can be regarded as an abnormal index.
According to the method for determining the abnormal index, provided by the embodiment of the application, the abnormal leaf nodes in the leaf nodes can be identified only based on the path height of the leaf nodes and the average height of the independent trees, and then the abnormal index is determined according to the segmentation standard of the abnormal leaf nodes.
In one embodiment, there are multiple types of network complaint root causes, including but not limited to: coverage anomalies, interference anomalies, site failures, and capacity anomalies.
The network complaint root cause may be one or more, so the embodiment of the application provides a method for determining the corresponding network complaint root cause according to the condition that the abnormality index meets, and the following description is given to the process of determining the network complaint root cause according to the abnormality index:
when the abnormal index meets one of the coverage abnormal conditions, judging that the network complaint root causes comprise coverage abnormality; the coverage exception condition includes: no base station exists in a preset range of the network complaint initiating position, the abnormal index comprises an independent networking SA user coverage satisfaction index, the SA user coverage satisfaction index is smaller than an SA user coverage satisfaction threshold, the abnormal index comprises a measurement report MR coverage rate, and the MR coverage rate of a resident cell is smaller than an MR coverage rate threshold; the resident cells are cells which are ranked in the front K bits after the cells are ranked according to the sequence from the large to the small of the connection times of the user equipment; wherein K is a positive integer;
when the abnormality index meets one of the interference abnormality conditions, judging that the network complaint root causes comprise interference abnormality; the interference anomaly condition includes: the abnormal index comprises overlapping coverage rate, the overlapping coverage rate is larger than an overlapping coverage rate threshold value, the abnormal index comprises interference background noise index, and the interference background noise index is larger than an interference background noise index threshold value; the overlapping coverage rate threshold value is the average value of the overlapping coverage rate of the non-complaint cell; the interference bottom noise index threshold is the average value of the interference bottom noise indexes of the cells without complaints;
When the abnormal index meets the site fault condition, judging that the network complaint root causes comprise site faults; the site failure condition includes: the network complaint initiating position has a fault site in a preset range; the fault site is a base station in a fault site record within a preset time before the network complaint initiating time;
when the abnormality index meets a capacity abnormality condition, judging that the network complaint root causes comprise capacity abnormality; the capacity exception condition includes: the abnormal index comprises a user number index, and the user number index is larger than a user number threshold; the user number threshold is the average value of the user number indexes of the cells without customer complaints;
and when the abnormality index does not meet any one of the coverage abnormality condition, the interference abnormality condition, the site fault condition and the capacity abnormality condition, judging that the network complaint root is due to other abnormalities.
It should be noted that, the network complaint in the embodiment of the present application may simultaneously satisfy a plurality of conditions including a coverage abnormal condition, an interference abnormal condition, a site fault condition and a capacity abnormal condition, and each time one of the conditions is satisfied, it is explained that the root of the network complaint includes a cause corresponding to the condition; if the network complaint does not meet any one of the coverage abnormality condition, the interference abnormality condition, the site fault condition and the capacity abnormality condition, but the abnormal index exists in the customer complaint network performance index set, the network complaint is indicated to have a corresponding reason, but the network complaint does not belong to any one of the coverage abnormality, the interference abnormality, the site fault and the capacity abnormality, and at the moment, the root cause of the network complaint is determined to be other abnormality.
In the process, the overlapping coverage rate threshold, the interference bottom noise index threshold and the user number threshold are calculated through the network performance index set without customer complaints, and compared with a fixed preset value, the network complaint root cause determining accuracy and reliability can be improved.
Further, the MR coverage threshold and the SA user coverage fullness threshold may also be calculated based on a set of complaint-free network performance indicators.
Further, in the embodiment of the present application, a root condition mapping table may be formed by mutually associating a plurality of exception types with index meeting conditions, and when step S14 is executed, the root condition mapping table is searched for the corresponding exception type as the root cause of the network complaint by the condition that the exception index meets.
The correspondence between the various abnormal types and the index meeting conditions can be determined according to the correspondence between the index and the influence factors, and the root cause condition mapping table can be updated in a manual adding mode.
According to the network complaint root cause positioning method provided by the embodiment of the application, the condition which is met by the abnormal index is searched based on the abnormal index, so that the network complaint root cause corresponding to the met condition can be found, namely, under the condition that which index is determined to be abnormal, the influence factor related to the index can be determined as the network complaint root cause, and the corresponding relation between the index and the influence factor is easy to acquire information, so that the network complaint root cause can be rapidly and efficiently identified for the type of complaint which does not occur.
The network complaint root cause positioning device provided by the embodiment of the application is described below, and the network complaint root cause positioning device described below and the network complaint root cause positioning method described above can be correspondingly referred to each other.
Referring to fig. 4, a network complaint root cause positioning device provided by an embodiment of the present application includes:
an independent tree construction module 410 for: constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
an anomaly determination module 420 for: determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
an anomaly index identification module 430 for: when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
The network complaint root matching module 440 is configured to: and determining the root cause of the network complaint according to the abnormality index.
In the network complaint root cause positioning device provided by the embodiment of the application, the independent tree construction module constructs a plurality of independent trees based on the network performance index sets of the complaint cell and the non-complaint cell, the average height of the complaint network performance index sets in the plurality of independent trees is combined by the abnormality judgment module, the distance between the complaint network performance index sets and the high-density group can be known, whether the complaint network performance index sets are abnormal or not is further judged, after the abnormality of the complaint network performance index sets is confirmed, the abnormality index is further found by the abnormality index identification module according to the path height of the complaint leaf node and the average height of the independent tree, the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value, therefore, the difference of the network performance index sets between the complaint cell and the non-complaint cell when the abnormal leaf node is segmented is indicated, the segmentation reference of the abnormal node can be regarded as an abnormal index, the network complaint root cause is confirmed according to the abnormal index by the abnormality index matching module, after the abnormality of the complaint network performance index sets is confirmed, the abnormality index is confirmed, the abnormality factor is used in the process, the non-supervision free method is used, and the abnormality type is not required to be analyzed according to the abnormality factors, and the abnormality factors are not can be fast recognized, and the abnormality factors are fast are not related to the abnormality factors are fast based on the abnormality factors.
In one embodiment, the independent tree construction module 410 is specifically configured to:
constructing a data set containing N elements; wherein N-1 elements are the network performance index set without customer complaints, 1 element is the network performance index set with customer complaints, and N is an integer greater than 2;
performing M times of element extraction on the data set, and constructing an independent tree for each extracted element to obtain a plurality of independent trees; wherein M is an integer greater than 2.
In one embodiment, the process of the independent tree construction module 410 constructing an independent tree is as follows:
extracting the construction elements of the independent tree in the data set according to a preset sampling proportion;
dividing the construction element according to any index in the network performance index set as a dividing reference to obtain 2 branches;
executing the steps of dividing the construction elements according to any index in the network performance index set as a dividing reference again on the construction elements under each branch until the tree dividing stop condition is met, ending the division of the construction elements under all branches, and obtaining the independent tree;
when the current branch meets the branch segmentation stopping condition, ending the segmentation of the construction element under the current branch; the branch division stop condition includes: the building element under the current branch has only 1; the tree division stop condition includes: the segmentation of the building elements under all branches has ended or the current tree height is equal to or greater than the independent tree height threshold.
In one embodiment, the anomaly determination module 420 is specifically configured to:
calculating an anomaly score of the complaint network performance index set according to the average height of the complaint network performance index set in the plurality of independent trees;
and when the anomaly score is greater than a preset anomaly score threshold, determining that the customer complaint network performance index set is abnormal.
In one embodiment, the anomaly index identification module 430 is specifically configured to:
calculating the average height E of the plurality of independent trees M ；
The path height is smaller than a×E M The customer complaint leaf node is taken as an abnormal leaf node; wherein a E is (0, 1);
and taking the segmentation standard of the abnormal leaf node as the abnormal index.
In one embodiment, network complaint root matching module 440 is specifically configured to:
when the abnormal index meets one of the coverage abnormal conditions, judging that the network complaint root causes comprise coverage abnormality; the coverage exception condition includes: no base station exists in a preset range of the network complaint initiating position, the abnormal index comprises an independent networking SA user coverage satisfaction index, the SA user coverage satisfaction index is smaller than an SA user coverage satisfaction threshold, the abnormal index comprises a measurement report MR coverage rate, and the MR coverage rate of a resident cell is smaller than an MR coverage rate threshold; the resident cells are cells which are ranked in the front K bits after the cells are ranked according to the sequence from the large to the small of the connection times of the user equipment; wherein K is a positive integer;
When the abnormality index meets one of the interference abnormality conditions, judging that the network complaint root causes comprise interference abnormality; the interference anomaly condition includes: the abnormal index comprises overlapping coverage rate, the overlapping coverage rate is larger than an overlapping coverage rate threshold value, the abnormal index comprises interference background noise index, and the interference background noise index is larger than an interference background noise index threshold value; the overlapping coverage rate threshold value is the average value of the overlapping coverage rate of the non-complaint cell; the interference bottom noise index threshold is the average value of the interference bottom noise indexes of the cells without complaints;
when the abnormal index meets the site fault condition, judging that the network complaint root causes comprise site faults; the site failure condition includes: the network complaint initiating position has a fault site in a preset range; the fault site is a base station in a fault site record within a preset time before the network complaint initiating time;
when the abnormality index meets a capacity abnormality condition, judging that the network complaint root causes comprise capacity abnormality; the capacity exception condition includes: the abnormal index comprises a user number index, and the user number index is larger than a user number threshold; the user number threshold is the average value of the user number indexes of the cells without customer complaints;
And when the abnormality index does not meet any one of the coverage abnormality condition, the interference abnormality condition, the site fault condition and the capacity abnormality condition, judging that the network complaint root is due to other abnormalities.
In one embodiment, the network complaint root cause positioning device provided by the embodiment of the application further includes a complaint cell identification module (not shown in the figure) for:
determining the complaint cell according to the network complaint initiating position and acquiring the complaint network performance index set based on the complaint cell; the distance between the complaint cell and the network complaint initiating position is smaller than a preset distance threshold; the complaint cell is located in a preset azimuth angle range of the network complaint initiating position.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: processor 510, communication interface (Communication Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may call a computer program in memory 530 to perform the steps of a network complaint root cause positioning method, including, for example:
Constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
and determining the root cause of the network complaint according to the abnormality index.
Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present application further provide a computer program product, where the computer program product includes a computer program, where the computer program may be stored on a non-transitory computer readable storage medium, where the computer program when executed by a processor is capable of executing the steps of the network complaint root cause positioning method provided in the foregoing embodiments, where the steps include:
constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
And determining the root cause of the network complaint according to the abnormality index.
In another aspect, embodiments of the present application further provide a processor-readable storage medium storing a computer program for causing a processor to execute the steps of the method provided in the above embodiments, for example, including:
constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
And determining the root cause of the network complaint according to the abnormality index.
The processor-readable storage medium may be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), semiconductor storage (e.g., ROM, EPROM, EEPROM, nonvolatile storage (NAND FLASH), solid State Disk (SSD)), and the like.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A method for locating a root cause of a network complaint, comprising:
constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
When the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
and determining the root cause of the network complaint according to the abnormality index.
2. The method of claim 1, wherein determining whether the set of complaint network performance indicators is abnormal based on an average height of the set of complaint network performance indicators in the plurality of independent trees comprises:
calculating an anomaly score of the complaint network performance index set according to the average height of the complaint network performance index set in the plurality of independent trees;
and when the anomaly score is greater than a preset anomaly score threshold, determining that the customer complaint network performance index set is abnormal.
3. The method of claim 1, wherein the determining an anomaly indicator from the path height of the complaint leaf node and the average height of the plurality of independent trees comprises:
Calculating the average height E of the plurality of independent trees M ；
The path height is smaller than a×E M The customer complaint leaf node is taken as an abnormal leaf node; wherein a E is (0, 1);
and taking the segmentation standard of the abnormal leaf node as the abnormal index.
4. The method for locating a root cause of a network complaint according to claim 1, wherein the constructing a plurality of independent trees based on the set of complaint network performance indicators and the set of non-complaint network performance indicators by using an isolated forest algorithm includes:
constructing a data set containing N elements; wherein N-1 elements are the network performance index set without customer complaints, 1 element is the network performance index set with customer complaints, and N is an integer greater than 2;
performing M times of element extraction on the data set, and constructing an independent tree for each extracted element to obtain a plurality of independent trees; wherein M is an integer greater than 2.
5. The network complaint root cause positioning method of claim 4, wherein M times of element extraction are performed on the data set, and an independent tree is constructed for each extracted element, so as to obtain the plurality of independent trees, wherein the construction process of one independent tree is as follows:
Extracting the construction elements of the independent tree in the data set according to a preset sampling proportion;
dividing the construction element according to any index in the network performance index set as a dividing reference to obtain 2 branches;
executing the steps of dividing the construction elements according to any index in the network performance index set as a dividing reference again on the construction elements under each branch until the tree dividing stop condition is met, ending the division of the construction elements under all branches, and obtaining the independent tree;
when the current branch meets the branch segmentation stopping condition, ending the segmentation of the construction element under the current branch; the branch division stop condition includes: the building element under the current branch has only 1; the tree division stop condition includes: the segmentation of the building elements under all branches has ended or the current tree height is equal to or greater than the independent tree height threshold.
6. The method for locating root causes of network complaints according to claim 1, wherein before constructing a plurality of independent trees based on the set of customer complaint network performance indexes and the set of non-customer complaint network performance indexes by using an isolated forest algorithm, the method comprises:
Determining the complaint cell according to the network complaint initiating position and acquiring the complaint network performance index set based on the complaint cell;
the distance between the complaint cell and the network complaint initiating position is smaller than a preset distance threshold; the complaint cell is located in a preset azimuth angle range of the network complaint initiating position.
7. The method for locating a root cause of a network complaint according to claim 1, wherein the determining a root cause of a network complaint according to the abnormality index includes:
when the abnormal index meets one of the coverage abnormal conditions, judging that the network complaint root causes comprise coverage abnormality; the coverage exception condition includes: no base station exists in a preset range of the network complaint initiating position, the abnormal index comprises an independent networking SA user coverage satisfaction index, the SA user coverage satisfaction index is smaller than an SA user coverage satisfaction threshold, the abnormal index comprises a measurement report MR coverage rate, and the MR coverage rate of a resident cell is smaller than an MR coverage rate threshold; the resident cells are cells which are ranked in the front K bits after the cells are ranked according to the sequence from the large to the small of the connection times of the user equipment; wherein K is a positive integer;
When the abnormality index meets one of the interference abnormality conditions, judging that the network complaint root causes comprise interference abnormality; the interference anomaly condition includes: the abnormal index comprises overlapping coverage rate, the overlapping coverage rate is larger than an overlapping coverage rate threshold value, the abnormal index comprises interference background noise index, and the interference background noise index is larger than an interference background noise index threshold value; the overlapping coverage rate threshold value is the average value of the overlapping coverage rate of the non-complaint cell; the interference bottom noise index threshold is the average value of the interference bottom noise indexes of the cells without complaints;
when the abnormal index meets the site fault condition, judging that the network complaint root causes comprise site faults; the site failure condition includes: the network complaint initiating position has a fault site in a preset range; the fault site is a base station in a fault site record within a preset time before the network complaint initiating time;
when the abnormality index meets a capacity abnormality condition, judging that the network complaint root causes comprise capacity abnormality; the capacity exception condition includes: the abnormal index comprises a user number index, and the user number index is larger than a user number threshold; the user number threshold is the average value of the user number indexes of the cells without customer complaints;
And when the abnormality index does not meet any one of the coverage abnormality condition, the interference abnormality condition, the site fault condition and the capacity abnormality condition, judging that the network complaint root is due to other abnormalities.
8. A network complaint root cause positioning device, comprising:
an independent tree construction module for: constructing a plurality of independent trees based on the customer complaint network performance index set and the non-customer complaint network performance index set by utilizing an isolated forest algorithm; the customer complaint network performance index set is a network performance index set of a customer complaint cell; the network performance index set without customer complaints is a network performance index set of a cell without customer complaints; the customer complaint cell is positioned in a preset range of a network complaint initiating position;
an anomaly determination module for: determining whether the complaint network performance index set is abnormal or not according to the average height of the complaint network performance index set in the plurality of independent trees;
the abnormal index identification module is used for: when the customer complaint network performance index set is abnormal, determining an abnormal index according to the path height of the customer complaint leaf node and the average height of the plurality of independent trees; the abnormal index is a segmentation reference of abnormal leaf nodes; the proportion of the path height of the abnormal leaf node to the average height of the plurality of independent trees is smaller than a preset value; the complaint leaf nodes are leaf nodes where the complaint network performance index sets are located in the plurality of independent trees;
The network complaint root factor matching module is used for: and determining the root cause of the network complaint according to the abnormality index.
9. An electronic device comprising a processor and a memory storing a computer program, characterized in that the processor implements the steps of the network complaint root cause positioning method of any one of claims 1 to 7 when the computer program is executed.
10. A computer program product comprising a computer program, characterized in that the computer program when executed by a processor implements the steps of the network complaint root cause positioning method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210470080.1A CN117014322A (en) | 2022-04-28 | 2022-04-28 | Network complaint root cause positioning method, device and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210470080.1A CN117014322A (en) | 2022-04-28 | 2022-04-28 | Network complaint root cause positioning method, device and application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117014322A true CN117014322A (en) | 2023-11-07 |
Family
ID=88565956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210470080.1A Pending CN117014322A (en) | 2022-04-28 | 2022-04-28 | Network complaint root cause positioning method, device and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117014322A (en) |
-
2022
- 2022-04-28 CN CN202210470080.1A patent/CN117014322A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3975048A1 (en) | Method for constructing cloud network alarm root cause relational tree model, device, and storage medium | |
| US11138163B2 (en) | Automatic root cause diagnosis in networks based on hypothesis testing | |
| CN110147387B (en) | Root cause analysis method, root cause analysis device, root cause analysis equipment and storage medium | |
| CN111339129B (en) | Remote meter reading abnormity monitoring method and device, gas meter system and cloud server | |
| CN110955550A (en) | Cloud platform fault positioning method, device, equipment and storage medium | |
| WO2023029654A1 (en) | Fault root cause determination method and device, and storage medium and electronic device | |
| CN109918313B (en) | GBDT decision tree-based SaaS software performance fault diagnosis method | |
| CN109951306B (en) | Alarm processing method, device, equipment and medium | |
| CN109063433B (en) | False user identification method and device and readable storage medium | |
| CN112769605A (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN111756560A (en) | Data processing method, device and storage medium | |
| CN109993390B (en) | Alarm association and order dispatching optimization method, device, equipment and medium | |
| CN111694752A (en) | Application testing method, electronic device and storage medium | |
| CN113660687B (en) | Network difference cell processing method, device, equipment and storage medium | |
| CN115665787A (en) | Low-overhead AMF network intelligent fault diagnosis method based on machine learning | |
| CN115599830A (en) | Method, device, equipment and medium for determining data association relation | |
| CN114416573A (en) | Defect analysis method, device, equipment and medium for application program | |
| CN112733897B (en) | Method and apparatus for determining abnormality cause of multi-dimensional sample data | |
| CN116827765B (en) | Root cause positioning method, root cause positioning device, root cause positioning equipment and storage medium | |
| Stefanidou-Voziki et al. | Feature selection and optimization of a ML fault location algorithm for low voltage grids | |
| CN117768307A (en) | Determination method and device of abnormal equipment and electronic equipment | |
| CN117014322A (en) | Network complaint root cause positioning method, device and application | |
| CN111343664B (en) | User positioning method, device, equipment and medium | |
| CN110582091B (en) | Method and apparatus for locating wireless quality problems | |
| CN117135037A (en) | Method and device for defining network traffic performance abnormality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |