A network problem processing method and device based on intelligent clustering

Abstract

The present invention discloses a network problem processing method and device based on intelligent clustering, which belongs to the field of network technology. The method includes: collecting various network problem data; clustering common problems in various network problem data to obtain a first clustering result; clustering the source points of the problems in various network problem data to obtain a second clustering result; generating a work order and dispatching the work order according to the first clustering result and the second clustering result. In the present invention, the problem cell screening is not simply dependent on a "one-size-fits-all" rule, which improves the accuracy; and reduces the time spent on repeated processing of common network problems, which improves the processing efficiency of subsequent work orders; at the same time, similar problems are merged, which reduces the number of work orders and reduces costs; and new clustering dimensions can be configured, which has good scalability.

Description

Technical Field

[0001] The present invention relates to the field of network technology, and in particular to a method and device for processing network problems by intelligent clustering. Background Art

[0002] In recent years, LTE (Long Term Evolution) networks have been rapidly deployed and implemented, and the number of users has also grown rapidly. In the daily optimization process of LTE networks, screening and tracking abnormal network elements is a basic task. It is usually based on the key indicators (Key Performance Indicator, referred to as KPI) to formulate threshold-based discrimination rules, so as to screen out abnormal network elements, and then generate corresponding work orders and execute the optimization process. Among them, in the process of formulating KPI discrimination rules, it is necessary to clarify the verification granularity and threshold of each indicator, and then formulate threshold discrimination rules based on the optimization implementation experience of various provinces.

[0003] The existing daily optimization process of LTE network is usually carried out in cells. First, abnormal network elements are screened, including: 1) Collection and aggregation of cell performance KPI indicators, that is, obtaining XML files from the wireless operation and maintenance center (OMC), parsing performance data files, realizing the collection of performance indicators, and summarizing data after collecting performance indicators, including summarizing time granularities such as hours, days, weeks, and months, as well as summarizing cell, district, and city granularities. 2) Formulation of cell problem rules. In order to screen abnormal network elements, it is necessary to formulate screening rules to realize cell screening rules that distinguish cities and scenes, so as to perform scheduling and execution according to the formulated rules and screen out abnormal network elements. Generally, the formulated cell rules support screening according to threshold, accumulation, TOP (ranking in descending order and taking the top), etc., and summarize and judge according to different time granularities; support rules for KPI problems such as low connection, high disconnection, and poor switching; support different time granularities, select the judgment time range of different rules; support time period cumulative acquisition of city TOP screening. 3) Screen out abnormal network elements according to the established problem rules. Secondly, generate corresponding work orders based on the screened abnormal network elements; finally, dispatch the orders and track the processing.

[0004] However, the screening of abnormal network elements and the generation of corresponding work orders are completed in a "one-size-fits-all" manner directly based on the formulated problem rules. From the above description, it can be seen that the problem rules are often very fine-grained. Therefore, on the one hand, the number of work orders finally generated is very large, which increases the cost; on the other hand, it leads to a large number of work orders for similar problems and a large number of work orders in the same area, resulting in a lot of repetitive work and reducing productivity and efficiency; on the other hand, there is no distinction between types of work orders, which reduces management efficiency and processing efficiency. Summary of the invention

[0005] According to an embodiment of the present invention, a method and device for processing network problems based on intelligent clustering are provided.

[0006] On the one hand, the present invention provides a network problem processing method based on intelligent clustering, comprising:

[0007] Step S1: Collecting data of various network problems;

[0008] Step S2: clustering common problems in the network problem data to obtain a first clustering result;

[0009] Step S3: clustering the problem source points in the network problem data to obtain a second clustering result;

[0010] Step S4: Generate a work order and dispatch it according to the first clustering result and the second clustering result.

[0011] Optionally, the step S1 is specifically as follows: collecting network problem data from electronic operation and maintenance system data, road test data, interference data, performance data and other data through a problem engine.

[0012] Optionally, the step S2 is specifically: clustering the common problems in the network problem data according to the value dimension, the difficulty dimension, the root cause dimension, and the geographical dimension to obtain a first clustering result.

[0013] Optionally, common problems in the network problem data are clustered according to a value dimension, specifically: value clustering is performed on problems triggered by core areas and core figures, as well as problems with high call volume and high flow in the network problem data;

[0014] Optionally, the common problems in the network problem data are clustered according to the difficulty dimension, specifically: difficulty clustering is performed on the problems with high recurrence in the network problem data;

[0015] Optionally, the common problems in the network problem data are clustered according to the root cause dimension, specifically: problems with the same root cause in the network problem data are clustered according to the root cause;

[0016] Optionally, the common problems in the network problem data are clustered according to the geographical dimension, specifically: the occurrence points of the problems in the network problem data are associated with the geographic information system to obtain problem-intensive areas, and the problems in the problem-intensive areas are geographically clustered.

[0017] Optionally, the step S3 is specifically: clustering the source points of the problems in the network problem data according to the performance rule, the quality rule, the black spot rule, and the room division rule to obtain a second clustering result.

[0018] Optionally, the step S4 specifically includes:

[0019] Step A1: Obtain a first clustering result and a second clustering result within a first preset time period;

[0020] Step A2: Initialize the information of the work order to be generated, and cache the work order information within a second preset time period;

[0021] Step A3: Compare the first clustering result and the second clustering result obtained with the cached work order information, mark the status of each clustering result according to the comparison result and place it in a corresponding queue;

[0022] Step A4: perform corresponding problem appending or work order generation operations according to the status of the clustering results in each queue, update each queue and dispatch the generated work orders.

[0023] In another aspect, the present invention provides a network problem processing device based on intelligent clustering, comprising:

[0024] The collection module is used to collect data on various network problems;

[0025] A first clustering module, used for clustering common problems in the network problem data collected by the collection module to obtain a first clustering result;

[0026] A second clustering module, used for clustering the source points of the problems in the network problem data collected by the collection module to obtain a second clustering result;

[0027] A generation module, configured to generate a work order according to a first clustering result obtained by the first clustering module and a second clustering result obtained by the second clustering module;

[0028] The dispatching module is used to dispatch the work orders generated by the generating module.

[0029] Optionally, the collection module is specifically used to collect network problem data from electronic operation and maintenance system data, road test data, interference data, performance data and other data through a problem engine.

[0030] Optionally, the first clustering module is specifically used to cluster common problems in the network problem data collected by the collection module according to a value dimension, a difficulty dimension, a root cause dimension, and a geographic dimension to obtain a first clustering result.

[0031] Optionally, the first clustering module is specifically used to:

[0032] Performing value clustering on the network problem data collected by the collection module, the problems triggered by core areas and core figures, and the problems with high call volume and high flow;

[0033] Clustering the difficulty of the highly recurring problems in the network problem data collected by the collection module;

[0034] Clustering the problems with the same root cause in the network problem data collected by the collection module;

[0035] The problem occurrence points in the network problem data collected by the collection module are associated with the geographic information system to obtain a problem-intensive area, and the problems in the problem-intensive area are geographically clustered.

[0036] Optionally, the second clustering module is specifically used to cluster the source points of the problems in the network problem data according to performance rules, quality rules, black spot rules, and room division rules to obtain a second clustering result.

[0037] Optionally, the generation module specifically includes: an acquisition submodule, an initialization submodule, a cache submodule, a comparison submodule, a marking submodule, an execution submodule and an update submodule;

[0038] The acquisition submodule is used to acquire the first clustering result and the second clustering result within a first preset time period;

[0039] The initialization submodule is used to initialize the information of the work order to be generated;

[0040] The cache submodule is used to cache the work order information within a second preset time period;

[0041] The comparison submodule is used to compare the first clustering result and the second clustering result obtained by the acquisition submodule with the work order information cached by the cache submodule;

[0042] The marking submodule is used to mark the status of each clustering result according to the comparison result of the comparison submodule and place it in a corresponding queue;

[0043] The execution submodule is used to perform corresponding problem appending or work order generation operations according to the status of the clustering results in each queue;

[0044] Update submodule, used to update each queue;

[0045] Correspondingly, the dispatching module is specifically used to dispatch the work orders generated by the execution submodule.

[0046] The advantages of the present invention are:

[0047] In the present invention, common problems in network problem data are clustered from the dimensions of value, difficulty, root cause, geography, etc., and the source points of the problems are clustered. Work orders are generated or problems are added based on the clustering results, and a priority processing mechanism is provided. Compared with the prior art, there are at least the following advantages:

[0048] 1) High efficiency: Automatic problem clustering not only reduces the time spent on manual post-analysis, but also reduces the time spent on repeated processing of common network problems, greatly improving the efficiency of subsequent work order processing; and based on the clustering results, the severity of the problem is clarified in the form of priority, so that serious problems can be dealt with first.

[0049] 2) High accuracy: Instead of simply relying on a "one-size-fits-all" rule to screen problem cells, network problems are discovered through problem clustering, which can more truly reflect the network status, discover areas with serious problems, and more effectively locate the cause of the problem.

[0050] 3) Low cost: Instead of simply limiting problems through threshold control, similar problems are merged by clustering common problems and the source points of problems, which greatly reduces the number of work orders and reduces costs.

[0051] 4) Good scalability: New clustering dimensions can be configured, with good scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Attached Figure 1 A flow chart of a network problem processing method based on intelligent clustering provided by the present invention;

[0054] Attached Figure 2 A clustering use case diagram in a network problem processing method based on intelligent clustering provided by the present invention;

[0055] Attached Figure 3 A block diagram of the modules of a network problem processing device based on intelligent clustering provided by 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 disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0057] Embodiment 1

[0058] According to an embodiment of the present invention, a network problem processing method based on intelligent clustering is provided. Figure 1 As shown, including:

[0059] Step 101: Collecting data of various network problems;

[0060] Step 102: clustering common problems in the collected network problem data to obtain a first clustering result;

[0061] Step 103: clustering the source points of the problems in the collected network problem data to obtain a second clustering result;

[0062] Step 104: Generate a work order based on the first clustering result and the second clustering result and dispatch the work order.

[0063] According to an implementation of the present invention, step 101 specifically includes: collecting network problem data from the Electric Operation Maintenance System (EOMS) data, road test data, interference data, performance data and other data through a problem engine.

[0064] Among them, road test data is also called black spot data; performance data includes: call volume, flow, etc.; other data includes: latitude and longitude, warning information, etc.

[0065] According to an implementation manner of the present invention, step 102 specifically includes: clustering common problems in the collected network problem data according to the value dimension, the difficulty dimension, the root cause dimension, and the geographic dimension to obtain a first clustering result.

[0066] According to an embodiment of the present invention, common problems in the collected network problem data are clustered according to the value dimension, specifically: problems triggered by core areas and core figures in the collected network problem data, as well as problems with high call volume and high flow are clustered according to value;

[0067] More specifically, in this embodiment, the clustering conditions for clustering common problems in the collected network problem data according to the value dimension include:

[0068] Import high-value scenarios and define high-value descriptions; for example, key locations and key base stations are considered high-value scenarios;

[0069] Ranking and filtering all the cells in the network according to the traffic volume; preferably, in this embodiment, the cells in the network are ranked in descending order according to the traffic volume, and the cells in the top 5% are filtered out;

[0070] Access external data sources; for example, access the base station with the highest revenue in the entire network.

[0071] According to an embodiment of the present invention, common problems in the collected network problem data are clustered according to the difficulty dimension, specifically: difficulty clustering is performed on the highly recurring problems in the collected network problem data;

[0072] More specifically, the frequently recurring cells in the network problem data are merged, and the problems that occur repeatedly in the frequently recurring cells in the historical data are checked, so as to obtain the frequently recurring problems in the entire network;

[0073] Preferably, cells that appeared for 3 days or more in the last month are determined as high-recurrence cells.

[0074] According to an embodiment of the present invention, common problems in the collected network problem data are clustered according to the root cause dimension, specifically: problems with the same root cause in the collected network problem data are clustered according to the root cause;

[0075] More specifically, based on different root causes such as weak coverage and high interference, the number of cells that have corresponding problems is counted every day, and warnings are issued for a type of problem corresponding to a sudden increase in the number of cells, and rectification work orders are issued;

[0076] According to an implementation of the present invention, common problems in the collected network problem data are clustered according to the geographical dimension. Specifically, the problem occurrence points in the collected network problem data are associated with the geographic information system to obtain problem-intensive areas, and the problem-intensive areas are geographically clustered.

[0077] Specifically, the latitude and longitude of the occurrence points of each problem in the collected network problem data are marked in the geographic information system to obtain multiple black points, and the black points in the geographic information system are shrunk and aggregated;

[0078] The shrinking aggregation specifically includes: determining whether the distance between all points and their nearest points is less than a preset threshold, and performing initial aggregation on the points whose distance is less than the threshold to obtain an aggregated block; determining whether each aggregated block has an adjacent aggregated block, and aggregating the adjacent aggregated blocks until there is no adjacent aggregated block;

[0079] Preferably, in this embodiment, the preset threshold is 500 meters.

[0080] Furthermore, in this embodiment, when the common problems in the collected network problem data are clustered according to the geographical dimension, it also includes: introducing a hierarchical ordering mode for various types of problems according to different problem characteristics, regional characteristics, division of responsibility, problem severity, etc.; correspondingly, the mode of dispatching work orders includes: three types of work order levels: problem point level (community, black spot grid class in geographic information system), district level, and prefecture-level city level:

[0081] Among them, the problem point level (community, black spot grid type) is specifically: for a single community, a single problem black spot, a single grid (the grid size can be defined according to needs), according to a certain time period (for example, one week as the problem aggregation period), the centralized optimization work order management platform automatically aggregates problems based on the Common Gateway Interface (CGI) or geographic grid identifier as the only association. After aggregation, all problems found in the early stage will be mapped according to CGI, black spot or grid, and finally present a set of problems with unique identifiers, that is, fully showing a multi-dimensional problem that exists within a certain period.

[0082] Among them, at the regional level (administrative district, grid): for multiple communities or black spots that meet the regional dispatching rules, they are aggregated by region based on the concentration of problem areas (optimization areas), consistency of solutions, and other dimensions, and finally form a work order dispatch branch to perform basic network optimization processing on site. Regional-level aggregation also considers the division of responsibilities of the front-line branches by region and the support analysis of the corresponding market. Before dispatching work orders, the problem points are aggregated to improve the efficiency of the front-line branch optimization personnel processing.

[0083] Municipal level: For a type of problem in a municipal branch, if the overall index drops seriously or the proportion of communities (problem points) is too high, a municipal level work order will be issued.

[0084] Furthermore, in this embodiment, after step 102, the method further includes: saving the first clustering result to a database.

[0085] According to an implementation manner of the present invention, step 103 specifically comprises: clustering the source points of the problems in the collected network problem data according to the performance rule, the quality rule, the black spot rule, and the room division rule to obtain a second clustering result.

[0086] Among them, the sources of the problem include communities, computer rooms, equipment, etc.

[0087] For example, the performance rule includes a subway scenario, and the subway scenario defines a rule for a cell with poor connection rate, a rule for a cell with poor dropped call, and a rule for a cell with poor handover success rate, then the poor cells found by these three rules are merged.

[0088] It should be noted that when multiple rules are triggered for the same cell, they will be merged into the same work order for processing. For example, if a cell triggers both the quality rule and the room division rule, in the subsequent work order generation process, two work orders will not be generated for the same cell, but will be merged and processed to generate one work order.

[0089] Furthermore, in this embodiment, when clustering the source points of problems in each network problem data, it also includes: defining the category of network clustering, which is an attribute of the rule, and the rule is the condition that determines the merging of problems and the generation of work orders, and is also a key element of the dispatching logic.

[0090] For example, Figure 2 The clustering use case diagram shown defines network clustering into large categories and small categories according to the needs of optimization analysis.

[0091] It should be noted that Figure 2 It is for illustration only and not for limitation.

[0092] Furthermore, after step 103, the method further includes: saving the second clustering result to a database.

[0093] According to an embodiment of the present invention, in step 104, generating a work order according to the first clustering result and the second clustering result specifically includes:

[0094] Step A1: Obtain a first clustering result and a second clustering result within a first preset time period;

[0095] Specifically, a first clustering result and a second clustering result within a first preset time period are obtained in a database; preferably, the first preset time period is 24 hours.

[0096] Step A2: Initialize the information of the work order to be generated, and cache the work order information within a second preset time period;

[0097] Specifically, the work order number, authority, processing time limit and other information of the work order to be generated are initialized.

[0098] Preferably, the second preset time period is one month.

[0099] Step A3: Compare the first clustering result and the second clustering result obtained with the cached work order information, mark the status of each clustering result according to the comparison result and place it in a corresponding queue;

[0100] Specifically, the first clustering result and the second clustering result obtained are compared with the cached work order information to determine whether there are clustering results that need to be added with questions. If so, the status of the corresponding clustering results is marked as "merged" and placed in the merge queue, and the status of the clustering results that do not need to be added with questions is marked as "generated" and placed in the generation queue; otherwise, the status of each clustering result is marked as "generated" and placed in the generation queue;

[0101] The present invention provides a problem adding mechanism. For problems in each clustering result, if there is a work order with the same network element and the same problem, which has been generated but is in an unclosed loop state, the deterioration time and deterioration situation are added to the corresponding work order, and no new work order corresponding to the clustering result is generated.

[0102] Among them, work orders that have been generated but are in an unclosed-loop state include: work orders that have been generated but not assigned; work orders that have been generated and assigned but are in an unfinished state within the processing period, etc.

[0103] Step A4: Execute corresponding problem appending or work order generation operations according to the status of the clustering results in each queue, and update each queue.

[0104] Furthermore, in this embodiment, a fault tolerance mechanism is provided, that is, step A4 further includes: simulating transactions to roll back when an error occurs;

[0105] Specifically, considering the rollback failure, for the erroneous work order, the existing data cannot be destroyed, that is, when adding a problem or generating a work order, if the work order to be added or generated already exists, it will be skipped. For the cached work order information, if the current work order is an alarm from one month ago, the work order generation or problem addition is performed directly in the database; and in step A4, after the problem addition or work order generation operation is completed, the newly added item is put into the cache list, where the cache list uses a dictionary and the intId class is used as the key to improve the query speed.

[0106] Furthermore, the present invention also provides a priority processing mechanism. When a work order is generated, by searching historical work orders, frequently occurring problems and cells where problems frequently occur are discovered, and the priority of the same type of problems or the same network elements that are currently occurring is increased for priority processing.

[0107] Embodiment 2

[0108] According to an embodiment of the present invention, a network problem processing device based on intelligent clustering is provided. Figure 3 As shown, including:

[0109] The collection module 201 is used to collect various network problem data;

[0110] A first clustering module 202 is used to cluster common problems in the network problem data collected by the collection module to obtain a first clustering result;

[0111] The second clustering module 203 is used to cluster the locations where the problems occur in the network problem data collected by the collection module 201 to obtain a second clustering result;

[0112] A generating module 204, configured to generate a work order according to the first clustering result obtained by the first clustering module 202 and the second clustering result obtained by the second clustering module 203;

[0113] The dispatching module 205 is used to dispatch the work orders generated by the generating module 204 .

[0114] According to an embodiment of the present invention, the collection module 201 is specifically used to collect network problem data from electronic operation and maintenance system data, road test data, interference data, performance data and other data through a problem engine.

[0115] Among them, road test data is also called black spot data; performance data includes: call volume, flow, etc.; other data includes: latitude and longitude, warning information, etc.

[0116] According to an embodiment of the present invention, the first clustering module 202 is specifically used to cluster the common problems in the network problem data collected by the collection module 201 according to the value dimension, difficulty dimension, root cause dimension, and geographic dimension to obtain a first clustering result.

[0117] According to an embodiment of the present invention, the first clustering module 202 is specifically configured to:

[0118] Performing value clustering on the network problem data collected by the collection module 201, the problems triggered by the core areas and core persons, and the problems with high call volume and high flow;

[0119] Performing difficulty clustering on the highly recurring problems in the network problem data collected by the collection module 201;

[0120] Clustering the problems with the same root cause in the network problem data collected by the collection module 201;

[0121] The problem occurrence points in the network problem data collected by the collection module 201 are associated with the geographic information system to obtain a problem-intensive area, and the problems in the problem-intensive area are geographically clustered.

[0122] According to an embodiment of the present invention, the device further includes: a saving module, configured to save the first clustering result obtained by the first clustering module 202 to a database.

[0123] According to an embodiment of the present invention, the second clustering module 203 is specifically used to cluster the source points of the problems in the collected network problem data according to performance rules, quality rules, black spot rules, and room division rules to obtain a second clustering result.

[0124] Among them, the sources of problems include communities, computer rooms, equipment, etc.

[0125] In this embodiment, the saving module is further used to save the second clustering result obtained by the second clustering module 203 to the database.

[0126] According to an embodiment of the present invention, the generation module 204 includes: an acquisition submodule, an initialization submodule, a cache submodule, a comparison submodule, a marking submodule, an execution submodule and an update submodule;

[0127] The acquisition submodule is used to acquire the first clustering result and the second clustering result saved by the saving module within the first preset time period;

[0128] Initialization submodule, used to initialize the information of the work order to be generated;

[0129] A cache submodule, used to cache work order information within a second preset time period;

[0130] A comparison submodule, used to compare the first clustering result and the second clustering result obtained by the acquisition submodule with the work order information cached by the cache submodule;

[0131] The marking submodule is used to mark the status of each clustering result according to the comparison result of the comparison submodule and put it into the corresponding queue;

[0132] The execution submodule is used to perform corresponding problem appending or work order generation operations according to the status of the clustering results in each queue;

[0133] Update submodule, used to update each queue;

[0134] Correspondingly, the dispatching module 205 is specifically used to dispatch the work orders generated by the execution submodule.

[0135] The first preset time period is preferably 24 hours; the second preset time period is preferably one month.

[0136] According to an embodiment of the present invention, it also includes: a fault-tolerant module, which is used to simulate transactions and roll back when an error occurs during the process of generating a work order by the generating module 204.

[0137] According to an embodiment of the present invention, it also includes: a priority processing module, which is used to retrieve historical work orders when the generation module 204 generates a work order, to find frequently occurring problems and cells where problems frequently occur, and to increase the priority of the same type of problems or the same network elements that are currently occurring for priority processing.

[0138] In the present invention, common problems in network problem data are clustered from the dimensions of value, difficulty, root cause, geography, etc., and the source points of the problems are clustered. Work orders are generated or problems are added based on the clustering results, and a priority processing mechanism is provided. On the one hand, the time-consuming post-analysis is reduced, the time-consuming repeated processing of common network problems is reduced, and the severity of the problem is clarified in the form of priority, which greatly improves the processing efficiency of subsequent work orders; on the other hand, it no longer simply relies on a "one-size-fits-all" rule to screen problem cells, which improves accuracy; on the other hand, similar problems are merged, the number of work orders is reduced, and the cost is reduced; and new clustering dimensions can be configured, which has good scalability.

[0139] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A network problem processing method based on intelligent clustering, characterized in that: include: Step S1: Collecting data of various network problems; Step S2: clustering common problems in the network problem data to obtain a first clustering result; Step S3: clustering the problem source points in the network problem data to obtain a second clustering result, wherein the problem source point is any one of the following: a cell, a computer room or a device; Step S4: generating a work order and dispatching the work order according to the first clustering result and the second clustering result; Cluster the common problems in the network problem data according to the value dimension, specifically: cluster the problems triggered by core areas and core figures, as well as problems with high call volume and high flow in the network problem data by value; cluster the common problems in the network problem data according to the difficulty dimension, specifically: cluster the problems with high recurrence in the network problem data by difficulty; cluster the common problems in the network problem data according to the root cause dimension, specifically: cluster the problems with the same root cause in the network problem data by root cause; cluster the common problems in the network problem data according to the geographic dimension, specifically: cluster the network The problem occurrence points in the problem data are associated with the geographic information system to obtain a problem-intensive area, and the problems in the problem-intensive area are geographically clustered; wherein the geographic clustering specifically includes: marking the latitude and longitude of the occurrence points of each problem in the collected network problem data in the geographic information system to obtain multiple black points, and shrinking and aggregating the black points in the geographic information system; wherein the shrinking and aggregating specifically includes: judging whether the distance between all points and their nearest points is less than a preset threshold, and initially aggregating the points whose distance is less than the threshold to obtain an aggregated block; judging whether each aggregated block has an adjacent aggregated block, and aggregating the adjacent aggregated blocks until there is no adjacent aggregated block; Step A1: Obtain the first clustering result and the second clustering result within the first preset time period; Step A2: Initialize the information of the work order to be generated, and cache the work order information within the second preset time period; Step A3: Compare the first clustering result and the second clustering result obtained with the cached work order information to determine whether there are clustering results that need to be added with questions. If yes, mark the status of the corresponding clustering results as "merge" and put them in the merge queue, and mark the status of the clustering results that do not need to be added with questions as "generate" and put them in the generate queue; otherwise, mark the status of each clustering result as "generate" and put them in the generate queue; step A4 :According to the status of the clustering results in each queue, the corresponding problem addition or work order generation operation is performed, each queue is updated and the generated work order is dispatched; the problem addition mechanism, for the problems in each clustering result, if there is a work order with the same network element and the same problem, which has been generated but is in an unclosed loop state, the deterioration time and deterioration situation will be added to the corresponding work order, and no new work order corresponding to the clustering result will be generated; among them, the work orders that have been generated but are in an unclosed loop state include: work orders that have been generated but not dispatched; work orders that have been generated and dispatched but are in an unfinished state within the processing period; priority processing mechanism, when the work order is generated, by searching the historical work orders, the frequently occurring problems and the cells with frequently occurring problems are found, and the priority of the current problems of the same type or the same network element is increased for priority processing.

2. The method according to claim 1, characterized in that: The step S1 specifically includes: collecting network problem data from electronic operation and maintenance system data, road test data, interference data, performance data and other data through a problem engine.

3. The method according to claim 1, characterized in that The step S3 is specifically: clustering the source points of the problems in the network problem data according to the performance rule, the quality rule, the black spot rule, and the room division rule to obtain a second clustering result.

4. A network problem processing device based on intelligent clustering, characterized in that: include: The collection module is used to collect data on various network problems; A first clustering module, used for clustering common problems in the network problem data collected by the collection module to obtain a first clustering result; Specifically, the common problems in the network problem data are clustered according to the value dimension, the difficulty dimension, the root cause dimension, and the geographical dimension to obtain a first clustering result; A second clustering module is used to cluster the source points of the problems in the network problem data collected by the collection module to obtain a second clustering result, wherein the source point of the problem is any one of the following: a cell, a computer room or a device; A generation module, configured to generate a work order according to a first clustering result obtained by the first clustering module and a second clustering result obtained by the second clustering module; An order dispatching module, used for dispatching the work orders generated by the generating module; The first clustering module is specifically used for: Performing value clustering on the network problem data collected by the collection module, the problems triggered by core areas and core figures, and the problems with high call volume and high flow; Clustering the difficulty of the highly recurring problems in the network problem data collected by the collection module; Clustering the problems with the same root cause in the network problem data collected by the collection module; The problem occurrence points in the network problem data collected by the collection module are associated with the geographic information system to obtain a problem-intensive area, and the problems in the problem-intensive area are geographically clustered; wherein the geographic clustering specifically includes: marking the latitude and longitude of the occurrence points of each problem in the collected network problem data in the geographic information system to obtain multiple black points, and shrinking and aggregating the black points in the geographic information system; wherein the shrinking and aggregating specifically includes: determining whether the distance between all points and their nearest points is less than a preset threshold, and initially aggregating the points whose distance is less than the threshold to obtain an aggregated block; determining whether each aggregated block has an adjacent aggregated block, and aggregating the adjacent aggregated blocks until there is no adjacent aggregated block; The generation module includes: an acquisition submodule, an initialization submodule, a cache submodule, a comparison submodule, a marking submodule, an execution submodule and an update submodule; The acquisition submodule is used to acquire the first clustering result and the second clustering result within a first preset time period; The initialization submodule is used to initialize the information of the work order to be generated; The cache submodule is used to cache the work order information within a second preset time period; The comparison submodule is used to compare the first clustering result and the second clustering result obtained by the acquisition submodule with the work order information cached by the cache submodule; The marking submodule is used to determine whether there is a clustering result that needs to be supplemented with questions according to the comparison results of the comparison submodule, and if so, mark the status of the corresponding clustering result as "merge" and put it in the merge queue, and mark the status of the clustering result that does not need to be supplemented with questions as "generate" and put it in the generate queue; otherwise, mark the status of each clustering result as "generate" and put it in the generate queue; The execution submodule is used to perform corresponding problem appending or work order generation operations according to the status of the clustering results in each queue; Update submodule, used to update each queue; The dispatching module is specifically used to dispatch the work orders generated by the execution submodule; Problem addition mechanism: For problems in each clustering result, if there are already generated work orders with the same network element and the same problem but in an unclosed loop state, the deterioration time and deterioration situation of the corresponding work orders will be added, and no new work orders corresponding to the clustering results will be generated; among them, the work orders that have been generated but not assigned include: work orders that have been generated and assigned, but are not completed within the processing period; The priority processing mechanism, when a work order is generated, can identify frequently occurring problems and cells where problems frequently occur by searching historical work orders, and increase the priority of the same type of problems or the same network elements that are currently occurring for priority processing.

5. The device according to claim 4, characterized in that The collection module is specifically used to collect network problem data from electronic operation and maintenance system data, road test data, interference data, performance data and other data through a problem engine.

6. The device according to claim 4, characterized in that The second clustering module is specifically used to cluster the source points of the problems in the network problem data according to performance rules, quality rules, black spot rules, and room division rules to obtain a second clustering result.

Images