Wireless network complaint classification processing method, device, equipment and medium

Abstract

The invention provides a wireless network complaint classification processing method and device, equipment and a medium, and relates to the technical field of data processing, wireless network complaint data is acquired, and the coverage radius of each base station is set based on current network base station operation data and according to a coverage type and a scene type; determining the distance between the complaint work order and each base station, and according to the distance and the coverage radius of the base station, determining whether the complaint work order data is outside or inside the range of the buffer area of the base station; clustering the complaint work order data outside the buffer area range of the base station to obtain a clustering center, and determining a base station construction scheme according to the clustering center; and matching different network data for the complaint work order data in the buffer area range of the base station in sequence, and determining a base station maintenance, capacity expansion and optimization scheme. Therefore, the complaint data is deeply mined and sorted, the complaint data is automatically classified, network problems are output, and high efficiency and accuracy of complaint processing are realized.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and medium for classifying and processing wireless network complaints. Background Art

[0002] At present, it is common for mobile phone users to file complaints through the operator's customer service hotline. After receiving the user's complaint, the system or customer service personnel will make a preliminary record and classification to understand the specific cause and impact of the problem. According to the nature and urgency of the complaint, the customer service personnel will generally assign the complaint to relevant departments such as network optimization, network construction, and network maintenance for processing.

[0003] The existing network complaint handling process relies on the level of detail and accuracy of the description of network problems by mobile phone users, the accuracy of customer service personnel pushing the processing department, and the technical capabilities of the technical personnel in the complaint handling department. If there is a problem in any of the above three links, user complaints will not be handled in a timely manner, which may lead to escalation of complaints, reduced user satisfaction, and affect the reputation of the operator's network. In addition, the complaint handling department collects the complaint list provided by the customer service department. It is generally necessary to geographically display the distribution of complaints based on the complaint information, and then manually check them one by one in combination with the existing network base station resources. Due to the large amount of complaint and network resource data, and the high work experience requirements of complaint handling personnel for complaint analysis, and the large number of reasons for complaints, the analysis is very cumbersome, time-consuming and labor-intensive, and ultimately leads to inaccurate solutions and certain deviations. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a wireless network complaint classification and processing method, device, equipment and medium, which can automatically classify complaint data and output network problems through deep mining and sorting of complaint data, so as to achieve efficient and accurate complaint processing.

[0005] In a first aspect, an embodiment of the present application provides a method for classifying and processing wireless network complaints, the method comprising the following steps:

[0006] Acquire wireless network complaint data, where the wireless network complaint data includes existing network base station operation data and complaint work order data;

[0007] Based on the complaint work order data, the distribution of complaint users is displayed geographically, and based on the existing network base station operation data and according to the coverage type and scenario type, the coverage radius of each base station is set; wherein the complaint work order data includes the latitude and longitude of the complaint work order, and the existing network base station operation data includes the coverage type, scenario type and the latitude and longitude of the base station;

[0008] Determine the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determine whether the complaint work order data is outside or within the base station buffer range according to the distance and the coverage radius of the base station; if it is within the base station buffer range, further determine the base station to which the complaint work order data belongs;

[0009] The complaint work order data outside the base station buffer zone is clustered to obtain the cluster center, and the base station construction plan is determined based on the cluster center; the complaint work order data within the base station buffer zone is matched with different network data in turn to determine the base station maintenance, expansion, and optimization plans.

[0010] In some embodiments, after obtaining the wireless network complaint data, the following steps are also included:

[0011] The data processing function is used to pre-process the missing values, duplicate values ​​and invalid values ​​in the acquired wireless network complaint data.

[0012] In some embodiments, the coverage type includes indoor and outdoor, and the scene type includes at least one of urban, county, township, and rural areas; the setting of the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and the scene type includes the following steps:

[0013] Based on the existing network base station operation data, the distance between each base station and all other base stations is calculated, and the distance of each base station is sorted to determine a set number of other base stations that are closest to it, and the average distance between the base station and the other base stations is calculated, and the average distance is used as the closest station distance of the base station;

[0014] The average value of the closest station distance of all base stations in each scene type is calculated to obtain the scene station distance;

[0015] The coverage radius of each base station in different scene types under the outdoor coverage type is calculated according to the scene station spacing and the set formula; and the coverage radius of each base station in different scene types under the indoor coverage type is customized.

[0016] In some embodiments, after setting the coverage radius of each base station based on the existing base station operation data and according to the coverage type and scenario type, the following steps are also included:

[0017] The buffer zone of each base station is determined according to the coverage radius, and the buffer zone of each base station is displayed geographically; wherein the area within the coverage radius is the buffer zone of the corresponding base station.

[0018] In some embodiments, determining the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determining whether the complaint work order data is outside or within the base station buffer range according to the distance and the coverage radius of the base station, includes the following steps:

[0019] By formula Calculate the distance between each complaint ticket and each base station in turn; where data = [(lng1,lat1),(lng2,lat2),...,(lng n ,lat n )] represents the latitude and longitude of the complaint ticket, n is the number of complaint tickets, i∈[1,n], BS_data=[(BS_lng1,BS_lat1),(BS_lng2,BS_lat2),...,(BS_lng m ,BS_lat m )] represents the latitude and longitude of the base station, m is the number of base stations, j∈[1,m];

[0020] Compare the calculated distance D with the coverage radius R of each base station;

[0021] If D>R, it is determined that the complaint work order data is outside the base station buffer range; if D≤R, it is determined that the complaint work order data is within the base station buffer range, and the base station corresponding to the minimum distance is selected as the base station to which the complaint work order data belongs.

[0022] In some embodiments, clustering the complaint work order data outside the base station buffer to obtain a cluster center includes the following steps:

[0023] Set the domain radius and minimum number of points of the clustering algorithm; wherein the domain radius is used to define the neighborhood range of the complaint work order data point, and the minimum number of points is used to represent the minimum number of points required for a complaint work order data point to become a core object;

[0024] For each complaint work order data point, the number of points within its neighborhood radius is calculated; wherein, if the number of points is greater than or equal to the minimum number of points, the complaint work order data point is identified as a core object;

[0025] Starting from any of the core objects, the complaint work order data points within its neighborhood radius are continuously expanded until all complaint work order data points within the neighborhood radius are marked as belonging to the same cluster, thereby obtaining a set of clustering results;

[0026] The clustering results are subjected to cluster boundary extraction, and the cluster center is calculated based on the extracted cluster boundary to obtain the centroid coordinates of the complaint work order data cluster.

[0027] In some embodiments, the method of sequentially matching different network data with the complaint work order data within the base station buffer to determine a base station maintenance, expansion, and optimization plan includes the following steps:

[0028] Matching the complaint work order data within the base station buffer range with the network quality data, and if the match is successful, determining that the complaint work order data is a maintenance issue, and determining a base station maintenance plan;

[0029] The complaint work order data that is not determined to be a maintenance problem is matched with the high-load cell data. If the match is successful, the complaint work order data is determined to be a capacity expansion problem, and a base station expansion plan is determined; if the match is unsuccessful, the complaint work order data is determined to be an optimization problem, and a base station optimization plan is determined.

[0030] In a second aspect, an embodiment of the present application provides a wireless network complaint classification processing device, the device comprising:

[0031] An acquisition module is used to acquire wireless network complaint data, wherein the wireless network complaint data includes existing network base station operation data and complaint work order data;

[0032] A setting module, used to geographically display the distribution of complaint users based on the complaint work order data, and to set the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type; wherein the complaint work order data includes the latitude and longitude of the complaint work order, and the existing network base station operation data includes the coverage type, scenario type and the latitude and longitude of the base station;

[0033] A calculation module, used to determine the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determine whether the complaint work order data is outside the base station buffer range or within the base station buffer range according to the distance and the coverage radius of the base station; wherein, if it is within the base station buffer range, further determine the base station to which the complaint work order data belongs;

[0034] The classification processing module is used to cluster the complaint work order data outside the base station buffer range, obtain the cluster center, and determine the base station construction plan based on the cluster center; for the complaint work order data within the base station buffer range, match different network data in turn to determine the base station maintenance, expansion, and optimization plan.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the wireless network complaint classification processing method as described in any one of the first aspects are performed.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the wireless network complaint classification processing method described in any one of the above-mentioned first aspects are executed.

[0037] The present application discloses a method, device, equipment and medium for classifying and processing wireless network complaints, which obtains wireless network complaint data, including existing network base station operation data and complaint work order data; geographically displays the distribution of complaint users based on the complaint work order data, and sets the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type; determines the distance between the complaint work order and each base station based on the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determines whether the complaint work order data is outside the base station buffer range or within the base station buffer range based on the distance and the coverage radius of the base station; wherein, if it is within the base station buffer range, the base station to which the complaint work order data belongs is also determined; clusters the complaint work order data outside the base station buffer range to obtain the cluster center, and determines the base station construction plan based on the cluster center; matches the complaint work order data within the base station buffer range with different network data in turn to determine the base station maintenance, expansion and optimization plan. Thus, through deep mining and sorting of complaint data, complaint data is automatically classified, network problems are output, and the efficiency and accuracy of complaint processing are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A flowchart of the wireless network complaint classification processing method described in an embodiment of the present application is shown;

[0040] Figure 2 A schematic diagram of the geographic visualization result of the complaint work order data described in the embodiment of the present application is shown;

[0041] Figure 3 A flowchart of setting the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type according to an embodiment of the present application is shown;

[0042] Figure 4 A schematic diagram showing geographical display of the buffer zones of each base station in an embodiment of the present application is shown;

[0043] Figure 5 A flowchart of clustering the complaint work order data outside the base station buffer range to obtain the cluster center is shown in an embodiment of the present application;

[0044] Figure 6 A schematic diagram showing the cluster centers obtained in the embodiment of the present application is shown;

[0045] Figure 7 A schematic diagram showing the structure of a wireless network complaint classification processing device according to an embodiment of the present application is shown;

[0046] Figure 8 A structural block diagram of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0047] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0048] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0049] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0050] In view of the technical problems raised by the background technology, the present application provides a wireless network complaint classification and processing method, device, equipment and medium, which can automatically classify complaint data and output network problems through deep mining and sorting of complaint data, so as to achieve high efficiency and accuracy in complaint processing.

[0051] See the instruction manual Figure 1 , a wireless network complaint classification processing method provided in an embodiment of the present application includes the following steps:

[0052] S1. Obtain wireless network complaint data, where the wireless network complaint data includes existing network base station operation data and complaint work order data;

[0053] S2. Geographically display the distribution of complaint users based on the complaint work order data, and set the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type; wherein the complaint work order data includes the latitude and longitude of the complaint work order, and the existing network base station operation data includes the coverage type, scenario type and the latitude and longitude of the base station;

[0054] S3. Determine the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determine whether the complaint work order data is outside or within the base station buffer range according to the distance and the coverage radius of the base station; if it is within the base station buffer range, further determine the base station to which the complaint work order data belongs;

[0055] S4. Cluster the complaint work order data outside the base station buffer to obtain the cluster center, and determine the base station construction plan based on the cluster center; match different network data in turn for the complaint work order data within the base station buffer to determine the base station maintenance, expansion, and optimization plans.

[0056] Specifically, in step S1, the acquired wireless network complaint data includes not only network base station operation data and complaint work order data, but also base station disconnection data table and 4G industrial parameter band index data table. The existing network base station data mainly includes base station identification, cell English name, physical site name, base station name, city to which it belongs, coverage type, scenario classification, base station longitude and base station latitude and other main content information; the complaint work order data mainly includes work order serial number, service type name, work order to which it belongs, complaint work order longitude, complaint work order latitude and other main content information; the base station disconnection data table mainly includes two types of information: equipment network management name and base station name; the 4G industrial parameter band index data table includes at least key information such as base station ID, cell number, and cell busy time PRB utilization.

[0057] Furthermore, the acquired wireless network complaint data is preprocessed to identify and delete missing values, duplicate values, and invalid values ​​in the data, thereby ensuring the accuracy and consistency of the data and providing a reliable basis for subsequent analysis, processing, and clustering operations. For example, the missing values, duplicate values, and invalid values ​​in the key columns of the cell English name, coverage type, base station longitude, base station latitude, base station identification, city to which it belongs, and scene classification in the existing network base station data are preprocessed; at the same time, the abnormal data of the service type name, city to which the work order belongs, longitude of the complaint work order, and latitude of the complaint work order in the complaint work order data are eliminated; and the same data preprocessing operation is performed on the column information that must be included in the base station disconnection data table and the 4G industrial parameter band indicator data table.

[0058] In one embodiment, the obtained wireless network complaint data can be preprocessed using the df.dropna() function. This function is used in Pandas to delete rows or columns containing missing values ​​(NaN or None), and it can flexibly delete missing values ​​in the data according to different column settings. In other embodiments, the corresponding function can be flexibly used according to the specific situation of the data or combined with other data processing methods for preprocessing to improve data quality.

[0059] In step S2, the complaint work order data can be visualized according to the Folium library in Python. First, the complaint work order data is read, and the initial center of the map is determined by calculating the average of the latitude and longitude in the data set; then the complaint work order data is traversed, and a mark is added to the map for each complaint work order. The position of the mark is determined by the longitude and latitude of the complaint work order, and a pop-up window is set up, which displays the serial number, business type, and city of the complaint work order; finally, the map is saved as an HTML file, and the file is opened in a browser to see the geographic visualization results of the complaint work order data, which intuitively presents the distribution of the complaining users and related information. Among them, the geographic visualization results of the complaint work order data can be found in the attached manual. Figure 2 .

[0060] See the instruction manual Figure 3 The setting of the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type includes the following steps:

[0061] S201, based on the existing network base station operation data, calculate the distance between each base station and all other base stations, and sort the distance of each base station, determine a set number of other base stations that are closest to it, and calculate the average distance between the base station and the other base stations, and use the average distance as the closest station distance of the base station;

[0062] S202, calculating the average value of the closest station distances of all base stations in each scene type to obtain the scene station distance;

[0063] S203, calculating the coverage radius of each base station in different scene types under the outdoor coverage type according to the scene station spacing and the set formula; and customizing the coverage radius of each base station in different scene types under the indoor coverage type.

[0064] The first thing that needs to be explained here is that in this application, the coverage types of existing base stations include indoor and outdoor, and the scene types include urban areas, county towns, townships and rural areas; the coverage scene types of existing base stations can be divided into seven types: outdoor urban areas, outdoor county towns, outdoor townships, outdoor rural areas, indoor urban areas, indoor county towns and indoor rural areas.

[0065] In step S201, firstly, the distance between the base station and all other base stations is compared by the longitude and latitude information corresponding to the "base station ID" identification field in the 4G industrial parameter band index data table. For example, the longitude and latitude of base station A is (lng1, lat1) and the longitude and latitude of base station B is (lng2, lat2), and the reference formula is as follows:

[0066] D=R×arccos[sin(lat1)×sin(lat2)+cos(lat1)×cos(lat2)×cos(lat2-lat1)]

[0067] In the formula: R is the radius of the earth, which is 6371; longitude and latitude should be converted into radians, radians = degrees * π / 180; D is in km; this distance is the spherical distance.

[0068] Then, the distances calculated based on the base station are sorted. In one embodiment, the number of the closest distances is set to three, and the top three are the first closest point base station, the second closest point base station, and the third closest point base station. The average of these three distances is calculated as the closest station distance based on this base station. And so on, the closest station distances of all base stations are calculated.

[0069] In step S202, the "Scene Classification" column data corresponding to each "Base Station ID" in the 4G industrial parameter band index data table is used to calculate the arithmetic mean of the closest station distances of all base stations in each type of scene, and the station distances of the scene in the city are collected. It can be divided into four types of scenes: urban area, county town, township, and rural area, which are listed as D1, D2, D3, and D4.

[0070] In step S203, the scene station spacings D1, D2, D3, and D4 calculated in step S202 are used according to the formula R=D i / 1.5, where D i = D1, D2, D3, D4, and the base station coverage radius of four scenarios, urban area, county town, township, and rural area, is obtained, which is counted as R1, R2, R3, and R4 respectively; and a circle is drawn with the calculated coverage radius of each base station in each scenario, and the area within the range is the buffer zone of the base station, and the buffer zone of each base station is displayed geographically. The schematic diagram of the geographical display of the buffer zone of each base station can be found in the attached manual. Figure 4 .

[0071] In addition, the above steps are the calculation methods for the buffer zone of outdoor base stations. Considering that the coverage range of indoor base stations is basically concentrated in buildings, and considering that the location of wireless network complaint users may have deviations due to positioning accuracy issues, the buffer zone radius is defined according to scene classification: 20 meters in urban areas, 30 meters in county towns, and 50 meters in rural areas.

[0072] In step S3, the formula Calculate the distance between each complaint ticket and each base station in turn; where data = [(lng1,lat1),(lng2,lat2),...,(lng n ,lat n)] represents the latitude and longitude of the complaint ticket, n is the number of complaint tickets, i∈[1,n], BS_data=[(BS_lng1,BS_lat1),(BS_lng2,BS_lat2),...,(BS_lng m ,BS_lat m )] represents the latitude and longitude of the base station, m is the number of base stations, j∈[1,m]; compare the calculated distance D with the coverage radius R of each base station; if D>R, it is determined that the complaint work order data is outside the base station buffer range; if D≤R, it is determined that the complaint work order data is within the base station buffer range. Among them, the complaint work order data is within the buffer range of multiple base stations and is recorded in D_list=[D1,D2,...,D k ], select the base station corresponding to the minimum distance in D_list as the base station to which the complaint work order data belongs.

[0073] In step S4, see the attached manual Figure 5 The step of clustering the complaint work order data outside the base station buffer to obtain a cluster center includes the following steps:

[0074] S401, setting the domain radius and minimum number of points of the clustering algorithm; wherein the domain radius is used to define the neighborhood range of the complaint work order data point, and the minimum number of points is used to represent the minimum number of points required for a complaint work order data point to become a core object;

[0075] S402, calculating the number of points within the neighborhood radius for each complaint work order data point; wherein, if the number of points is greater than or equal to the minimum number of points, the complaint work order data point is identified as a core object;

[0076] S403, starting from any of the core objects, continuously expanding the complaint work order data points within its neighborhood radius until all complaint work order data points within the neighborhood radius are marked as belonging to the same cluster, thereby obtaining a set of clustering results;

[0077] S404: extract cluster boundaries from the clustering results, and calculate cluster centers based on the extracted cluster boundaries to obtain the centroid coordinates of the complaint work order data cluster.

[0078] The complaint work order data outside the base station buffer zone is considered to need to be resolved through site construction. Specifically, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is used to perform cluster analysis on the complaint work order data outside the existing base station coverage buffer zone, and the central longitude and latitude of the complaint concentration area are taken as construction requirements. The longitude and latitude of the center point are verified with the current situation and planning, and the scenario and complaint category are combined to finally determine a differentiated complaint solution. Among them, the principle of the clustering algorithm should be a technical means well known to those skilled in the art, and will not be elaborated here.

[0079] Specifically, in step S401, first, the complaint work order data outside the base station buffer needs to be prepared as a two-dimensional data set, and the data set is represented as dataset = [(lng1, lat1), (lng2, lat2), ..., (lng n ,lat n )], and then set the parameters, including the domain radius and the minimum number of points. The domain radius (ε, Epsilon) is used to determine the neighborhood range of the complaint work order data point; the minimum number of points (MinPts) is used to characterize the minimum number of points that a complaint work order data point must have to become a core object (CoreObject).

[0080] In step S402, for each complaint work order data point, the number of points in its ε neighborhood is calculated. If the number of points in the ε neighborhood of a point is greater than or equal to MinPts, the point is considered to be a core object. The formula is: N ε (p) = {q∈D|dist(p,q)≤ε}, where dist(p,q) represents the distance between point p and point q (such as Euclidean distance); Core objects: When point p is a core object.

[0081] In step S403, starting from any core object, the points in its neighborhood are continuously expanded until all points in the neighborhood are marked as belonging to the same cluster. The specific steps are as follows:

[0082] 1) Initialize an empty cluster list.

[0083] 2) For each core object p that has not been accessed:

[0084] a) Create a new cluster C and add p to C.

[0085] b) Initialize a queue Q and add p to Q.

[0086] c) When Q is not empty, repeat the following steps:

[0087] Take a point q from Q.

[0088] For all unvisited points r in the ε neighborhood of q:

[0089] If r is a core object and has not been assigned to any cluster, add r and all points in its ε neighborhood (except those that have been assigned to other clusters) to C and add these points to Q.

[0090] If r is not a core object but has not been visited, then r is marked as visited and added to C (but not to Q).

[0091] 3) Mark all points that are not classified into any cluster as noise points.

[0092] Then a set of clustering results is obtained, each cluster contains one or more data points, and the points not classified into any cluster are marked as noise points.

[0093] In step S404, since the clustering result obtained is a set of points, its centroid point is used as the center position of the complaint cluster of the complaint work order data. Therefore, it is necessary to first extract the boundary of the cluster point set, and then calculate the centroid. By analyzing the distance and angle relationship between the cluster point and its nearest point, potential edges can be detected, which usually involves setting distance and angle thresholds to determine which points should be regarded as vertices of the edge. Once the polygon is identified or fitted, the vertex coordinates can be extracted from the edge or outline of the polygon to form the cluster boundary of these cluster point sets. Among them, calculating the centroid of the polygon is a geometric problem, and its process involves operating on the coordinates of the polygon vertices. The following is a detailed polygon centroid calculation process:

[0094] (1) Prepare data: a data list consisting of cluster boundary vertices, whose coordinates are (x1, y1), (x2, y2), ..., (x n ,y n );

[0095] (2) Calculate the area and barycentric coordinates accumulator. Area accumulator: initialize a variable A to 0 to store the area of ​​the polygon; barycentric coordinate accumulator: initialize two variables C x and C y 0, used to store the accumulated value of the center of gravity coordinates;

[0096] (3) Traverse the vertices to calculate the area and centroid coordinates: For each pair of adjacent vertices (x i ,y i ) and (x i+1 ,y i+1 )(where i traverses from 1 to n-1, and x n ,yn Considered as x1, y1 to form a closed loop), perform the following operations: ① Calculate the area increment: Use vertices i and i+1 to calculate part of the area, the formula is: ② Update the total area: add ΔA to the total area A: A = A + ΔA; ③ Calculate the increment of the center of gravity coordinates: use vertices i and i+1 to calculate the increment of the center of gravity coordinates, the formula is: ④ Update the center of gravity coordinate accumulator: add ΔC x and ΔC y Add to C x and C y superior:

[0097] (4) Calculate the final center of gravity coordinates: Use the total area A to calculate the final center of gravity coordinates (C' x ',C' y '); The reason for dividing by 6×A here is that in calculating ΔC x and ΔC y , the area of ​​the triangle formed by each pair of vertices is calculated three times (each vertex and its two adjacent vertices in turn), and the coefficient of the triangle area formula is So the total coefficient is 6.

[0098] Then calculate the centroid coordinates of the complaint work order data cluster (C' x ',C' y '), i.e., the cluster center. In one embodiment, the schematic diagram of the obtained cluster center can be found in the attached diagram of the specification. Figure 6 .

[0099] The complaint ticket data outside the coverage area will obtain cluster points and discrete noise points after the DBSCAN clustering algorithm. The hot complaint class construction plan is obtained based on the complaint ticket data corresponding to the cluster points and the cluster center, and the remaining complaint ticket data is used as the general complaint class construction plan.

[0100] In addition, the complaint work order data within the base station buffer is considered to be in need of maintenance and optimization. The base station to which the complaint belongs in the coverage area can be represented as BS_name_list = [BS_name1, BS_name2, ..., BS_name n ], Due to the huge amount of original data, the efficiency of relying on traditional circular analysis methods is too low. This application adopts a binary search algorithm to match different network data to determine base station maintenance, expansion, and optimization plans.

[0101] Specifically, first match this part of the complaints with network data such as alarm cells, flash outages / delisting, and poor quality. If they can be matched within a certain range, then this part of the complaints is determined to require maintenance and a list of base stations that require maintenance is output. Secondly, match the remaining complaint data with high-load cells (i.e. cells that need to be expanded, based on the extracted industrial parameter business data and the operator's expansion indicators, high-load cells are screened out). If they can be matched within a certain range, then this part of the complaints is determined to require expansion and a list of complaints that require expansion and the corresponding expansion cells are output. Finally, the remaining complaints need to be optimized and resolved. According to the latitude and longitude information of the complaint, match the nearest cells in the surrounding area, and output the corresponding complaints that need to be optimized and resolved and the corresponding cells that need to be optimized.

[0102] Furthermore, in the analysis of flash disconnection / decommissioning maintenance data, the data is sorted in ascending order according to the "Device Network Management" column in the original data; in the analysis of expansion data, the data is sorted in ascending order according to the ID column corresponding to the "Base Station Identifier", thereby optimizing the execution efficiency of the cluster analysis algorithm. In one embodiment, the parameter settings in the maintenance and expansion data processing process include: (1) Target value (target): BS_name to be searched l1 value; (2) ordered array (BS_name_list): stores the list of base station names (or device gateway names) in each row of the original data, and the list has been sorted in ascending order; (3) left and right boundaries (left, right): initially, the left boundary left is 0, and the right boundary right is the length of the array minus 1; (4) middle index (mid): each time a search is performed, the middle index mid is calculated to access the middle element of the array, and its calculation formula is mid = left + (right - left) / 2.

[0103] The basic process is described as:

[0104] (1) Initialization: Set the target value to be searched; determine the left and right boundaries of the array to be searched. Initially, left = 0; right = array length – 1;

[0105] (2) Calculate the middle index: take the middle position of the left and right boundaries as the current search point, that is, mid = (left + night) / 2;

[0106] (3) Compare the target value with the middle element: Check whether the element in the middle position of the array is equal to the target value target; if they are equal, an index position of the target value has been found, but other index positions need to be found; if the target value is smaller than the middle element, adjust the right boundary to mid-1, and then repeat steps (2) and (3); if the target value is larger than the middle element, adjust the left boundary to mid+1, and then repeat steps (2) and (3);

[0107] (4) Handling multiple index positions: When the first matching target index is found, do not return immediately, but continue to search to the left and right until no matching elements are found; you can use two pointers to record the position of the currently found matching element, and expand to the left and right until the condition is no longer met;

[0108] (5) Termination condition: When the left boundary is greater than the right boundary, it means that there are no more target values ​​in the array and the search process ends;

[0109] (6) Return result: Return a list or set containing all found index positions.

[0110] (7) Determine whether maintenance conditions are met: Determine whether the maintenance indicators corresponding to the index position (such as the duration of station outage, the number of flash outages, etc.) meet the pre-set judgment conditions. The indexes that meet the conditions are recorded, and steps (1) to (7) are repeated until all base stations to which the complaints belong in each coverage area have completed the judgment operation. The data that meets the judgment criteria are cells that need maintenance.

[0111] (8) After the above operations are completed, the data that does not meet the maintenance category judgment condition is screened and represented as: BS_ID_list = [BS_ID1, BS_ID2, ..., BS_ID m ], replace the target in steps (1) to (6) with BS_ID l2 , replace the ordered array with BS_ID_list and re-execute (1) to (6).

[0112] (9) Determine whether the capacity expansion conditions are met: Based on whether the uplink PRB utilization rate during busy hours of the cell corresponding to the index position meets the pre-set judgment conditions (e.g., whether the uplink PRB utilization rate during busy hours of the cell is greater than 50%), the index that meets the conditions is recorded, and step (8) is repeated until each element in the BS_ID_list completes a judgment operation. The cell that meets the judgment conditions is the cell that needs to be expanded.

[0113] (10) Filter the data index locations that do not meet the expansion conditions. The remaining data are the cells that need to be optimized.

[0114] The complaint list after the above analysis is then summarized and output, and the corresponding maintenance, optimization, expansion, adjustment, new construction and other solutions for each complaint and its corresponding cell or site are given.

[0115] It can be seen that the wireless network complaint classification and processing method provided by the present application divides wireless network complaints into two forms: inside the base station buffer and outside the base station buffer. Targeted construction plans are formulated for complaints outside the buffer zone, and targeted maintenance, expansion, and optimization plans are formulated for complaints inside the buffer zone. The causes of complaints and corresponding network solutions are analyzed efficiently and accurately, thereby improving mobile phone users' satisfaction with network usage.

[0116] Based on the same inventive concept, a wireless network complaint classification and processing device is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned wireless network complaint classification and processing method, device, equipment and medium in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0117] As the instruction manual Figure 7 As shown, the present application also provides a wireless network complaint classification processing device, the device comprising:

[0118] The acquisition module 701 is used to acquire wireless network complaint data, where the wireless network complaint data includes existing network base station operation data and complaint work order data;

[0119] A setting module 702 is used to geographically display the distribution of complaint users based on the complaint work order data, and to set the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type; wherein the complaint work order data includes the latitude and longitude of the complaint work order, and the existing network base station operation data includes the coverage type, scenario type and the latitude and longitude of the base station;

[0120] The calculation module 703 is used to determine the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determine whether the complaint work order data is outside the base station buffer range or within the base station buffer range according to the distance and the coverage radius of the base station; if it is within the base station buffer range, further determine the base station to which the complaint work order data belongs;

[0121] The classification processing module 704 is used to cluster the complaint work order data outside the base station buffer range, obtain the cluster center, and determine the base station construction plan based on the cluster center; for the complaint work order data within the base station buffer range, match different network data in turn to determine the base station maintenance, expansion, and optimization plan.

[0122] In some embodiments, after the acquisition module 701 acquires the wireless network complaint data, it further includes: using a data processing function to pre-process missing values, duplicate values, and invalid values ​​in the acquired wireless network complaint data.

[0123] In some embodiments, the coverage types include indoor and outdoor, and the scene types include at least one of urban areas, county towns, towns, and rural areas; the setting module 702 sets the coverage radius of each base station based on the existing base station operation data and according to the coverage type and scene type, including: calculating the distance between each base station and all other base stations based on the existing base station operation data, and sorting the distance of each base station, determining a set number of other base stations closest to it, and calculating the average distance between the base station and the other base stations, and using the average distance as the nearest station spacing of the base station; calculating the average value of the nearest station spacing of all base stations in each scene type to obtain the scene station spacing; calculating the coverage radius of each base station in different scene types under the outdoor coverage type according to the scene station spacing and the set formula; and customizing the coverage radius of each base station in different scene types under the indoor coverage type.

[0124] In some embodiments, after the setting module 702 sets the coverage radius of each base station based on the existing base station operation data and according to the coverage type and scenario type, it also includes: determining the buffer zone of each base station according to the coverage radius, and geographically displaying the buffer zone of each base station; wherein the area within the coverage radius is the buffer zone of the corresponding base station.

[0125] In some embodiments, the calculation module 703 determines the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determines whether the complaint work order data is outside or within the base station buffer range according to the distance and the coverage radius of the base station, including: by formula Calculate the distance between each complaint ticket and each base station in turn; where data = [(lng1,lat1),(lng2,lat2),...,(lng n ,lat n )] represents the latitude and longitude of the complaint ticket, n is the number of complaint tickets, i∈[1,n], BS_data=[(BS_lng1,BS_lat1),(BS_lng2,BS_lat2),...,(BS_lng m ,BS_lat m)] represents the longitude and latitude of the base station, m is the number of base stations, j∈[1,m]; compare the calculated distance D with the coverage radius R of each base station; if D>R, it is determined that the complaint work order data is outside the base station buffer; if D≤R, it is determined that the complaint work order data is within the base station buffer, and the base station corresponding to the minimum distance is selected as the base station to which the complaint work order data belongs.

[0126] In some embodiments, the classification processing module 704 clusters the complaint work order data outside the base station buffer range to obtain the cluster center, including: setting the domain radius and minimum number of points of the clustering algorithm; wherein the domain radius is used to define the neighborhood range of the complaint work order data point, and the minimum number of points is used to represent the minimum number of points required for a complaint work order data point to become a core object; calculating the number of points within the neighborhood radius of each complaint work order data point; wherein, if the number of points is greater than or equal to the minimum number of points, the complaint work order data point is identified as a core object; starting from any of the core objects, continuously expanding the complaint work order data points within its neighborhood radius until all complaint work order data points within the neighborhood radius are marked as belonging to the same cluster, and obtaining a set of clustering results; performing cluster boundary extraction on the clustering results, and calculating the cluster center based on the extracted cluster boundaries to obtain the centroid coordinates of the complaint work order data cluster.

[0127] In some embodiments, the classification processing module 704 matches the complaint work order data within the base station buffer range with different network data in sequence to determine the base station maintenance, expansion, and optimization plans, including: matching the complaint work order data within the base station buffer range with the network quality data. If the match is successful, the complaint work order data is determined to be a maintenance-related problem, and a base station maintenance plan is determined; matching the complaint work order data that is not determined to be a maintenance-related problem with high-load cell data. If the match is successful, the complaint work order data is determined to be an expansion-related problem, and a base station expansion plan is determined; if the match is unsuccessful, the complaint work order data is determined to be an optimization-related problem, and a base station optimization plan is determined.

[0128] The present application provides a wireless network complaint classification processing device, which obtains wireless network complaint data through an acquisition module, and the wireless network complaint data includes existing network base station operation data and complaint work order data; through a setting module, the distribution of complaint users is displayed geographically based on the complaint work order data, and the coverage radius of each base station is set based on the existing network base station operation data and according to the coverage type and scenario type; through a calculation module, the distance between the complaint work order and each base station is determined according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and according to the distance and the coverage radius of the base station, it is determined whether the complaint work order data is outside the base station buffer range or within the base station buffer range; wherein, if it is within the base station buffer range, the base station to which the complaint work order data belongs is also determined; through a classification processing module, the complaint work order data outside the base station buffer range is clustered to obtain a cluster center, and a base station construction plan is determined according to the cluster center; for the complaint work order data within the base station buffer range, different network data are matched in turn to determine the base station maintenance, expansion, and optimization plans. Thus, through deep mining and sorting of complaint data, complaint data is automatically classified, network problems are output, and the efficiency and accuracy of complaint processing are achieved.

[0129] Based on the same concept of the present invention, the specification is attached Figure 8 As shown, the structure of an electronic device 800 provided in an embodiment of the present application includes: at least one processor 801, at least one network interface 804 or other user interface 803, a memory 805, and at least one communication bus 802. The communication bus 802 is used to realize the connection and communication between these components. The electronic device 800 optionally includes a user interface 803, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, a trackball (trackball), a touch pad or a touch screen, etc.).

[0130] The memory 805 may include a read-only memory and a random access memory, and provides instructions and data to the processor 801. A portion of the memory 805 may also include a non-volatile random access memory (NVRAM).

[0131] In some embodiments, the memory 805 stores the following elements, which may be protected modules or data structures, or a subset thereof, or an extended set thereof:

[0132] Operating system 8051, including various system programs, used to implement various basic services and handle hardware-based tasks;

[0133] The application module 8052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0134] In an embodiment of the present application, by calling the program or instructions stored in the memory 805, the processor 801 is used to execute steps in a wireless network complaint classification processing method, device, equipment and medium, which can automatically classify complaint data through deep mining and sorting of complaint data, output network problems, and achieve high efficiency and accuracy in complaint processing.

[0135] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the wireless network complaint classification processing method are executed.

[0136] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned wireless network complaint classification processing method can be executed.

[0137] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0140] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0141] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for classifying and processing wireless network complaints, characterized in that: The method comprises the following steps: Acquire wireless network complaint data, where the wireless network complaint data includes existing network base station operation data and complaint work order data; Based on the complaint work order data, the distribution of complaint users is displayed geographically, and based on the existing network base station operation data and according to the coverage type and scenario type, the coverage radius of each base station is set; wherein the complaint work order data includes the latitude and longitude of the complaint work order, and the existing network base station operation data includes the coverage type, scenario type and the latitude and longitude of the base station; Determine the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determine whether the complaint work order data is outside or within the base station buffer range according to the distance and the coverage radius of the base station; if it is within the base station buffer range, further determine the base station to which the complaint work order data belongs; The complaint work order data outside the base station buffer zone is clustered to obtain the cluster center, and the base station construction plan is determined based on the cluster center; the complaint work order data within the base station buffer zone is matched with different network data in turn to determine the base station maintenance, expansion, and optimization plans.

2. A wireless network complaint classification processing method according to claim 1, characterized in that: After obtaining the wireless network complaint data, the following steps are also included: The data processing function is used to pre-process the missing values, duplicate values ​​and invalid values ​​in the acquired wireless network complaint data.

3. A wireless network complaint classification processing method according to claim 2, characterized in that: The coverage type includes indoor and outdoor, and the scene type includes at least one of urban, county, township, and rural areas; the setting of the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and the scene type includes the following steps: Based on the existing network base station operation data, the distance between each base station and all other base stations is calculated, and the distance of each base station is sorted to determine a set number of other base stations that are closest to it, and the average distance between the base station and the other base stations is calculated, and the average distance is used as the closest station distance of the base station; The average value of the closest station distance of all base stations in each scene type is calculated to obtain the scene station distance; The coverage radius of each base station in different scene types under the outdoor coverage type is calculated according to the scene station spacing and the set formula; and the coverage radius of each base station in different scene types under the indoor coverage type is customized.

4. A wireless network complaint classification processing method according to claim 3, characterized in that: After the coverage radius of each base station is set based on the existing base station operation data and according to the coverage type and scenario type, the following steps are also included: The buffer zone of each base station is determined according to the coverage radius, and the buffer zone of each base station is displayed geographically; wherein the area within the coverage radius is the buffer zone of the corresponding base station.

5. A wireless network complaint classification processing method according to claim 4, characterized in that: Determining the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determining whether the complaint work order data is outside or within the base station buffer range according to the distance and the coverage radius of the base station, includes the following steps: By formula Calculate the distance between each complaint ticket and each base station in turn; where data = [(lng1,lat1),(lng2,lat2),...,(lng n ,lat n )] represents the latitude and longitude of the complaint ticket, n is the number of complaint tickets, i∈[1,n], BS_data=[(BS_lng1,BS_lat1),(BS_lng2,BS_lat2),...,(BS_lng m ,BS_lat m )] represents the latitude and longitude of the base station, m is the number of base stations, j∈[1,m]; Compare the calculated distance D with the coverage radius R of each base station; If D>R, it is determined that the complaint work order data is outside the base station buffer range; if D≤R, it is determined that the complaint work order data is within the base station buffer range, and the base station corresponding to the minimum distance is selected as the base station to which the complaint work order data belongs.

6. A wireless network complaint classification processing method according to claim 5, characterized in that: The step of clustering the complaint work order data outside the base station buffer to obtain a cluster center includes the following steps: Set the domain radius and minimum number of points of the clustering algorithm; wherein the domain radius is used to define the neighborhood range of the complaint work order data point, and the minimum number of points is used to represent the minimum number of points required for a complaint work order data point to become a core object; For each complaint work order data point, the number of points within its neighborhood radius is calculated; wherein, if the number of points is greater than or equal to the minimum number of points, the complaint work order data point is identified as a core object; Starting from any of the core objects, the complaint work order data points within its neighborhood radius are continuously expanded until all complaint work order data points within the neighborhood radius are marked as belonging to the same cluster, thereby obtaining a set of clustering results; The clustering results are subjected to cluster boundary extraction, and the cluster center is calculated based on the extracted cluster boundary to obtain the centroid coordinates of the complaint work order data cluster.

7. A wireless network complaint classification processing method according to claim 6, characterized in that: The method of sequentially matching different network data with the complaint work order data within the base station buffer range to determine base station maintenance, expansion, and optimization plans includes the following steps: Matching the complaint work order data within the base station buffer range with the network quality data, and if the match is successful, determining that the complaint work order data is a maintenance issue, and determining a base station maintenance plan; The complaint work order data that is not determined to be a maintenance problem is matched with the high-load cell data. If the match is successful, the complaint work order data is determined to be a capacity expansion problem, and a base station expansion plan is determined; if the match is unsuccessful, the complaint work order data is determined to be an optimization problem, and a base station optimization plan is determined.

8. A wireless network complaint classification processing device, characterized in that: The device comprises: An acquisition module is used to acquire wireless network complaint data, wherein the wireless network complaint data includes existing network base station operation data and complaint work order data; A setting module, used to geographically display the distribution of complaint users based on the complaint work order data, and to set the coverage radius of each base station based on the existing network base station operation data and according to the coverage type and scenario type; wherein the complaint work order data includes the latitude and longitude of the complaint work order, and the existing network base station operation data includes the coverage type, scenario type and the latitude and longitude of the base station; A calculation module, used to determine the distance between the complaint work order and each base station according to the latitude and longitude of the complaint work order and the latitude and longitude of the base station, and determine whether the complaint work order data is outside the base station buffer range or within the base station buffer range according to the distance and the coverage radius of the base station; wherein, if it is within the base station buffer range, further determine the base station to which the complaint work order data belongs; The classification processing module is used to cluster the complaint work order data outside the base station buffer range, obtain the cluster center, and determine the base station construction plan based on the cluster center; for the complaint work order data within the base station buffer range, match different network data in turn to determine the base station maintenance, expansion, and optimization plan.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the wireless network complaint classification processing method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the wireless network complaint classification processing method as described in any one of claims 1 to 7 are executed.

Images