Building network vulnerability discovery method and device, optimization method, equipment and medium

Abstract

The embodiments of the present application relate to the field of artificial intelligence technology, and relate to a method and apparatus for discovering poor points in a building network, an optimization method, equipment, and a medium. The specific scheme is: clustering each complaint sample according to the complaint location information to obtain at least one clustering area; according to the building location information, obtaining the local buildings within the at least one clustering area; for each of the clustering areas, determining a preset number of high sampling point cells for each local building within the clustering area, and when the high sampling point cells meet the poor performance index, determining the clustering area as a network poor point. The embodiments of the present application realize the discovery of poor points in a building network based on complaint samples, can accurately locate network problems, discover large-scale poor areas in the network in advance, guide relevant personnel to conduct timely investigation and processing, avoid later complaint problems, improve the efficiency of solving complaint problems, and improve customer satisfaction.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a building network weakness discovery method and device, an optimization method, equipment and medium. Background Art

[0002] As mobile networks grow in size, multi-standard networks coexist, and network structures become increasingly complex, user complaints are also increasing. Customer service support departments typically handle complaints by analyzing and locating individual complaints before resolving user issues. This approach lacks essential correlation analysis, leading to numerous issues in complaint handling. These include significant duplication of effort, inaccurate problem location, low problem resolution efficiency, and poor complaint avoidance mechanisms. Conventional complaint handling methods are unable to accurately and efficiently address issues, resulting in a poor customer experience. Summary of the Invention

[0003] In view of the above problems of the prior art, the embodiments of the present application provide a method and device for discovering building network shortcomings, an optimization method, equipment and medium, which realize the discovery of building network shortcomings based on complaint samples, accurately locate network problems, discover large-scale shortcoming areas in the network in advance, guide relevant personnel to conduct timely investigation and processing, avoid subsequent complaints, improve the efficiency of resolving complaint problems, and enhance customer satisfaction.

[0004] To achieve the above objectives, the present application provides a first aspect of a method for discovering building network vulnerabilities, comprising:

[0005] Clustering each complaint sample according to the complaint location information to obtain at least one clustering area;

[0006] Obtaining, according to the building location information, the local buildings within the at least one clustering area;

[0007] For each cluster area, a preset number of high sampling point cells of each building within the cluster area are determined. When the high sampling point cells meet the poor performance index, the cluster area is determined to be a poor network point.

[0008] As a possible implementation of the first aspect, clustering complaint samples according to complaint location information includes:

[0009] Calculate the sample distances between complaint samples based on the complaint location information of each complaint sample;

[0010] Obtaining a first set of complaint samples that have not yet been clustered;

[0011] Using the location information of each complaint sample in the first set as a core point, respectively, obtaining a second set corresponding to each core point; wherein the sample distance from the complaint sample in the second set to the core point is less than the cluster neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement;

[0012] When the second set is obtained, the second set with the largest number of complaint samples is selected from each of the second sets as a result set of clustering areas, and the step of obtaining the first set consisting of complaint samples that have not yet been clustered is executed.

[0013] As a possible implementation of the first aspect, obtaining the local buildings within the at least one clustering area according to the building location information includes:

[0014] Obtain building location information;

[0015] When it is determined that the distance from the building location to the center point of a cluster area is less than the cluster neighborhood radius, the building is a local building within the cluster area.

[0016] As a possible implementation of the first aspect, determining a preset number of high sampling point cells for each building within the cluster area includes:

[0017] According to the identification information of the local buildings, the sampling point cells corresponding to each local building are obtained, and a preset number of cells with a higher number of sampling points are selected as the high sampling point cells of the local building.

[0018] As a possible implementation of the first aspect, the poor performance indicator includes at least one of the following:

[0019] Fault duration, high interference duration, weak coverage duration, and high load duration.

[0020] A second aspect of the present application provides a building network vulnerability discovery device, comprising:

[0021] A clustering unit, configured to cluster complaint samples according to complaint location information to obtain at least one clustering area;

[0022] a local building determining unit, configured to obtain the local buildings within the at least one clustering area according to the building location information;

[0023] The network poor point determination unit is used to determine, for each cluster area, a preset number of high sampling point cells of each building within the cluster area, and determine that the cluster area is a network poor point when the high sampling point cells meet the poor performance index.

[0024] As a possible implementation manner of the second aspect, the clustering unit is configured to:

[0025] Calculate the sample distances between complaint samples based on the complaint location information of each complaint sample;

[0026] Obtaining a first set of complaint samples that have not yet been clustered;

[0027] Using the location information of each complaint sample in the first set as a core point, respectively, obtaining a second set corresponding to each core point; wherein the sample distance from the complaint sample in the second set to the core point is less than the cluster neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement;

[0028] When the second set is obtained, the second set with the largest number of complaint samples is selected from each of the second sets as a result set of clustering areas, and the step of obtaining the first set consisting of complaint samples that have not yet been clustered is executed.

[0029] As a possible implementation of the second aspect, the local building determination unit is configured to:

[0030] Obtain building location information;

[0031] When it is determined that the distance from the building location to the center point of a cluster area is less than the cluster neighborhood radius, the building is a local building within the cluster area.

[0032] As a possible implementation of the second aspect, when the network difference determination unit is used to determine a preset number of high sampling point cells for each building within the cluster area, it is specifically used to:

[0033] According to the identification information of the local buildings, the sampling point cells corresponding to each local building are obtained, and a preset number of cells with a higher number of sampling points are selected as the high sampling point cells of the local building.

[0034] As a possible implementation of the second aspect, the poor performance indicator includes at least one of the following:

[0035] Fault duration, high interference duration, weak coverage duration, and high load duration.

[0036] A third aspect of the present application provides a building network optimization method, comprising:

[0037] Obtain samples of each complaint;

[0038] For each complaint sample, executing any of the building network shortcoming discovery methods described in the first aspect above to obtain the network shortcoming;

[0039] The network in the cluster area corresponding to the network difference is optimized.

[0040] A fourth aspect of the present application provides a computing device, including:

[0041] Communication interface;

[0042] at least one processor connected to the communication interface; and

[0043] At least one memory is connected to the processor and stores program instructions, and when the program instructions are executed by the at least one processor, the at least one processor executes any one of the methods described in the first aspect above.

[0044] In a fifth aspect, the present application provides a computer-readable storage medium having program instructions stored thereon. When the program instructions are executed by a computer, the computer is caused to execute any of the methods described in the first aspect.

[0045] These and other aspects of the invention will be apparent from and elucidated with reference to the following description of the embodiment(s). BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The following further illustrates the various features of the present invention and the relationships between the various features with reference to the accompanying drawings. The accompanying drawings are all exemplary, and some features are not shown in actual proportion. In addition, some drawings may omit features that are customary in the field to which this application relates and are not necessary for this application, or additional features that are not necessary for this application may be shown. The combination of the various features shown in the accompanying drawings is not intended to limit this application. In addition, throughout this specification, the same reference numerals refer to the same content. The specific description of the drawings is as follows:

[0047] Figure 1 A schematic diagram of an embodiment of a method for discovering building network vulnerabilities provided by an embodiment of the present application;

[0048] Figure 2 A schematic diagram of an embodiment of a method for discovering building network vulnerabilities provided by an embodiment of the present application;

[0049] Figure 3 A flow chart illustrating a clustering algorithm implementation of an embodiment of a building network vulnerability discovery method provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram illustrating the clustering algorithm results of an embodiment of the building network vulnerability discovery method provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of a simulation of cluster area-based building matching results according to an embodiment of the building network near miss discovery method provided in the present application;

[0052] Figure 6 A schematic diagram of the application effect of an embodiment of the building network vulnerability discovery method provided by the embodiment of the present application;

[0053] Figure 7 A schematic diagram of the application effect of an embodiment of the building network vulnerability discovery method provided by the embodiment of the present application;

[0054] Figure 8 A schematic diagram of the application effect of an embodiment of the building network vulnerability discovery method provided by the embodiment of the present application;

[0055] Figure 9 A schematic diagram of the application effect of an embodiment of the building network vulnerability discovery method provided by the embodiment of the present application;

[0056] Figure 10 A schematic diagram of an embodiment of a building network defect discovery device provided by an embodiment of the present application;

[0057] Figure 11 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The words "first, second, third, etc." or module A, module B, module C and other similar terms in the specification and claims are only used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that the specific order or sequence can be interchanged where permitted so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0059] In the following description, the numbers representing the steps, such as S110, S120, etc., do not necessarily mean that the steps must be executed in this manner. If permitted, the order of the steps can be interchanged or they can be executed simultaneously.

[0060] The term "comprising" as used in the specification and claims should not be construed as limiting to what is listed thereafter; it does not exclude other elements or steps. Thus, it should be interpreted as specifying the presence of the features, integers, steps, or components mentioned, but not excluding the presence or addition of one or more other features, integers, steps, or components, or groups thereof. Thus, the expression "a device comprising means A and B" should not be limited to a device consisting solely of components A and B.

[0061] References in this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "in one embodiment" or "in an embodiment" throughout this specification do not necessarily refer to the same embodiment, but may do so. Furthermore, in one or more embodiments, the particular features, structures, or characteristics may be combined in any suitable manner, as would be apparent to one of ordinary skill in the art from this disclosure.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. In the event of any inconsistency, the meanings described in this specification or the meanings derived from the contents recorded in this specification shall prevail. In addition, the terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application. In order to accurately describe the technical content in this application and to accurately understand the present invention, the following explanations or definitions are given for the terms used in this specification before describing the specific embodiments:

[0063] 1) Clustering: The process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects is called clustering. The clusters generated by clustering are a collection of data objects that are similar to objects in the same cluster and different from objects in other clusters. In the natural sciences and social sciences, there are numerous classification problems. Cluster analysis, also known as group analysis, is a statistical analysis method for studying the classification of samples or indicators. Cluster analysis originated from taxonomy, but clustering is not the same as classification. The difference between clustering and classification is that the classes required for clustering are unknown.

[0064] 2) Cartesian product: In mathematics, the Cartesian product of two sets X and Y, also called the direct product, is expressed as X×Y, where the first object is a member of X and the second object is a member of all possible ordered pairs of Y.

[0065] The following first introduces the existing methods, and then introduces the technical solution of this application in detail.

[0066] As mobile networks grow larger, multi-standard networks coexist, and network structures become increasingly complex, user complaints are also increasing. Customer service support departments typically handle complaints by analyzing and locating individual complaints before resolving user issues. This approach lacks the necessary correlation analysis during problem handling, resulting in the following deficiencies in complaint handling:

[0067] 1. Complaint handling leads to a high level of duplication: Multiple complaints involving the same issue are filed simultaneously at the same or nearby locations. Due to a lack of location-correlated analysis, the customer service support department must analyze and resolve each issue independently, significantly increasing the duplication of work.

[0068] 2. Inaccurate problem location: When analyzing individual complaint points, the analysis is often limited to the area occupied during the reported problem period. Due to memory errors during the reported problem period, analysis fails to identify the root cause. Furthermore, for most internal building complaints, field testing is impossible due to difficulties coordinating with property management, resulting in inaccurate problem location.

[0069] 3. Low problem-solving efficiency: It is impossible to conduct aggregate analysis on the large number of existing complaint data samples, resulting in low efficiency in solving problems in the same region and a long problem closure cycle.

[0070] 4. Poor complaint avoidance mechanisms: Current complaint avoidance mechanisms rely on real-time network management monitoring to issue early warnings for sudden problems such as large-scale failures and interference. This fails to effectively address historically exposed issues, preventing proactive complaint handling.

[0071] The existing technology has the following defects: large amount of repetitive work in complaint handling, inaccurate problem location, low problem solving efficiency, poor complaint avoidance mechanism, and poor customer experience.

[0072] Based on the technical problems existing in the above-mentioned prior art, the present application provides a method for discovering building network near misses. This method realizes building network near misses discovery based on the complaint location clustering algorithm, relying on the clustering of a large number of data samples, accurate matching of the performance of local buildings and high-occupancy communities, to help complaint handling become more accurate and efficient, and can effectively avoid the constraints of objective reasons such as insufficient experience of complaint handling personnel, heavy workload, incurred expenses, and long closed-loop cycles, and solve the technical problems mentioned in the prior art of large repetitive workload in complaint handling, inaccurate problem location, and low problem-solving efficiency. In addition, this method can discover the large range of near misses in the network in advance, guide the front-line network departments to conduct timely investigation and processing, avoid later complaint problems, improve customer satisfaction, and solve the technical problems mentioned in the prior art of poor complaint avoidance mechanism and poor customer experience.

[0073] Figure 1 This is a schematic diagram of an embodiment of the building network vulnerability discovery method provided by the present application. Figure 1 As shown, the building network vulnerability discovery method may include:

[0074] Step S110: clustering each complaint sample according to the complaint location information to obtain at least one clustering area;

[0075] Step S120, obtaining the local buildings within the at least one clustering area according to the building location information;

[0076] Step S130 : for each cluster area, determining a preset number of high sampling point cells of each building within the cluster area; when the high sampling point cells meet the poor performance index, determining the cluster area as a poor network point.

[0077] The embodiment of the present application collects existing complaint sample data, and the background performs location aggregation analysis based on the complaint location information to form a complaint problem clustering area, and then matches the complaint problem clustering area with the local building information, performance, faults, alarms, interference and other dimensional analysis information corresponding to the high-occupancy cells, so as to timely discover network weaknesses, guide the front-line network departments to conduct timely investigation and processing, reduce the occurrence of complaints, and improve user satisfaction.

[0078] In step S110, a sample of customer complaints regarding network services is first obtained. For example, information about the complaint sample can be obtained from a complaint ticket. The complaint sample information may include complaint location information, such as latitude and longitude. Multiple complaint samples can be clustered based on the complaint location information to obtain at least one cluster region. The resulting clustering result can be a number of cluster regions of predetermined sizes.

[0079] In step S120 , for each cluster area obtained in step S110 , the location information of the cluster area is compared with the building location information to obtain the local buildings within the cluster area.

[0080] In step S130, a preset number N is first set. For each building obtained in step S120, the N high-sampling point cells with the largest number of sampling points for each building are determined based on the sampling point data. The network performance of the high-sampling point cells is obtained, such as the duration of the fault, the duration of high interference, the duration of weak coverage, and the duration of high load. If a high-sampling point cell meets the poor performance indicator, the cluster area corresponding to the building is determined to be a poor network point. For example, if any of the N high-sampling point cells with the largest number of sampling points for a building has weak coverage for more than three days, the cluster area corresponding to the building is defined as a poor network point.

[0081] The embodiment of the present application realizes the discovery of building network weaknesses based on complaint samples, can accurately locate network problems, discover large-scale weak areas in the network in advance, guide relevant personnel to conduct timely investigation and processing, avoid subsequent complaints, improve the efficiency of resolving complaint problems, and enhance customer satisfaction.

[0082] Figure 2This is a schematic diagram of an embodiment of the building network vulnerability discovery method provided by the present application. Figure 2 As shown, in one embodiment, Figure 1 Step S110 in the embodiment of the present invention clusters the complaint samples according to the complaint location information, including:

[0083] Step S210, calculating the sample distances between complaint samples based on the complaint location information of each complaint sample;

[0084] Step S220, obtaining a first set consisting of complaint samples that have not yet been clustered;

[0085] Step S230: Using the location information of each complaint sample in the first set as a core point, obtain a second set corresponding to each core point; wherein the sample distance from the complaint sample in the second set to the core point is less than the cluster neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement;

[0086] Step S240, when the second set is obtained, select the second set with the largest number of complaint samples from each of the second sets as a result set of a clustering area, and turn to execute the step of obtaining the first set consisting of the complaint samples that have not yet been clustered.

[0087] Figure 3 This is a flow chart of the clustering algorithm implementation of an embodiment of the building network vulnerability discovery method provided by the present application. Figure 3 , an exemplary complaint location information clustering algorithm may include the following steps:

[0088] 1) The longitude and latitude points selected by frontline staff during the complaint ticket flow process and / or the longitude and latitude points collected during daily complaint handling are used as data clustering samples.

[0089] 2) Cartesian product operation is performed on the sample latitude and longitude data obtained in step 1) to obtain a combination of any two samples, and the distance dis between the two samples in the combination is calculated.

[0090] The Cartesian product calculation method is described as follows:

[0091] a={i1,i2,i3…i n}

[0092] There exists a set U that is the Cartesian product of set a with itself

[0093] U=a n ×a m

[0094] The elements of set U are ordered pairs consisting of the nth element in set a and the mth element in set a. The detailed formula is as follows:

[0095] a n ×a m ={(i n ,i m )|i n ∈a,i m ∈a}

[0096] 3) Define R as the cluster neighborhood radius, define K as the threshold of the number of samples that meet the R neighborhood radius, and use each point in the sample as the core point to calculate the number of samples that meet the conditions.

[0097] Select samples that satisfy the following correlation value calculation formula:

[0098]

[0099] The above formula is used to obtain data that meets the conditions. Specifically, each complaint sample is used as a core point, and the number of complaint samples whose distance to the core point is less than the cluster neighborhood radius R is counted. If the count is greater than the preset sample number threshold K, the complaint sample serving as the core point and the K complaint samples surrounding the core point within the cluster neighborhood radius are determined to meet the conditions.

[0100] 4) Count the number of samples that meet the conditions around the core point and sort them in descending order. Select the sample with max(count) as the first cluster area generated and add it to the cluster result set. Here, max(count) represents the maximum value of count in the data that meets the conditions.

[0101] 5) All samples included in the first clustering area selected in step 4 are removed from the subsequent sample set, and the remaining samples are calculated repeatedly in steps 3) and 4), each time selecting max(count) samples to generate a clustering area, until the remaining samples do not meet the conditional operation of the formula in step 3).

[0102] In the above algorithm, step 1) obtains complaint samples for cluster analysis from historical data. Step 2) calculates the distance between any two samples in all complaint samples used for cluster analysis. Step 3) obtains data that meets the conditions. The conditions that are met are calculated by the formula in step 3). Before the loop of the algorithm is executed for the first time, all samples are complaint samples that have not yet been clustered, so all samples constitute the first set. The location information of each complaint sample in the first set is used as the core point, and data that meets the conditions is obtained as the second set. The conditions that are met are that the sample distance from the complaint sample in the second set to the core point is less than the cluster neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement, that is, the number of complaint samples is greater than the preset sample number threshold K. In step 4), the second set with the largest number of complaint samples is selected from the obtained second sets, that is, the second set corresponding to max(count), as the result set of a clustering area.

[0103] After the first execution of the loop body of the algorithm, the algorithm turns to the step of obtaining the first set consisting of complaint samples that have not yet been clustered, and starts the second execution of the loop body. During the second and subsequent executions of the loop body, each execution removes the clustered samples from the first set, that is, removes all samples contained in the selected clustering area, and adds all samples contained in the selected clustering area to the clustering result set. The remaining complaint samples that have not yet been clustered constitute the current first set. Then repeat steps 3) and 4). If data that meets the conditions is obtained in step 3), that is, the second set is obtained, then after completing step 4), the algorithm still turns to the step of obtaining the first set consisting of complaint samples that have not yet been clustered; if data that meets the conditions is not obtained in step 3), the clustering algorithm is completed.

[0104] Figure 4 This is a schematic diagram of the clustering algorithm results of an embodiment of the building network vulnerability discovery method provided by the embodiment of the present application. Figure 4 As shown in Figure 2, a clustering algorithm can be used to obtain several clustering areas based on complaint samples.

[0105] In one embodiment, obtaining the local buildings within the at least one clustering area based on the building location information includes:

[0106] Obtain building location information;

[0107] When it is determined that the distance between the building location and the center point of a cluster area is less than the cluster neighborhood radius, the building is a local building within the cluster area. Wherein, "a cluster area" refers to a cluster area among at least one cluster area obtained through cluster analysis.

[0108] By obtaining the building location information data source, the building location center is calculated based on the maximum and minimum longitude and latitude corresponding to the building ID (identifier). The building location center can be represented by the longitude and latitude of the building center. The average of the maximum and minimum longitude and latitude is calculated as the longitude and latitude of the building center. The building data table in the building location information data source is shown in Table 1 below:

[0109] Table 1 Building data table

[0110] scene Coverage Type build_id Building ID build_name Building Name xmin Maximum longitude xmax Minimum longitude ymin Maximum latitude ymax Minimum latitude area Residential area location heights Building height Build_type Building type

[0111] Within the clustering area, further matching of building information can be performed. Specifically, the longitude and latitude of the building center are matched with the location of the clustering area center. If the following condition is met: the distance between the clustering area center and the building center is less than R, then the building is defined as a building within the clustering area. R is the radius of the clustering neighborhood.

[0112] Figure 5 This is a simulation diagram of the clustering area and building matching results of an embodiment of the building network difference discovery method provided in the present application. Figure 5 As shown, through the above matching, the local buildings within the cluster area can be obtained.

[0113] In one embodiment, determining a preset number of high sampling point cells for each building within the cluster area includes:

[0114] According to the identification information of the local buildings, the sampling point cells corresponding to each local building are obtained, and a preset number of cells with a higher number of sampling points are selected as the high sampling point cells of the local building.

[0115] When providing network communication services, the terminal will periodically report measurement reports to form sampling points, which will be recorded and stored. In the embodiment of the present application, the data of the sampling points can be used to count the high sampling point cells of the local building. If a building has a high probability of occupying a certain base station cell, that is, the base station cell reports a correspondingly large number of sampling points in the building location, then the base station cell is called the high-occupancy cell of the building, also known as the high sampling point cell.

[0116] After obtaining the building information within the cluster area, the preset number of high sampling point cells corresponding to each building can be obtained based on the building ID. In one example, the top three high sampling point cells ranked by the number of sampling points can be selected, that is, the three base station cells with the highest number of sampling points (Pointnum); the sampling time granularity can be the month before the current month. The relevant data on the number of building sampling points is shown in Table 2 below:

[0117] Table 2 Data on the number of sampling points in buildings

[0118]

[0119]

[0120] In one embodiment, the poor performance indicator includes at least one of the following:

[0121] Fault duration, high interference duration, weak coverage duration, and high load duration.

[0122] After selecting high-sampling point cells for local buildings, rule matching can be performed based on the building network performance to discover network weaknesses. For example, after summarizing and deduplicating the high-sampling point cells for all local buildings within the matched cluster area, network weaknesses can be discovered by matching the performance indicators of four dimensions: failure, high interference, weak coverage, and high load. In one example, the preset persistence time can be set to 3 days, and the specific matching rules are as follows:

[0123] 1) Fault: Extract daily granularity impact perception alarm cell-level data; match cells where service impact has persisted for three days or more.

[0124] 2) Interference: Extract daily granularity high-interference cell-level data; match cells where interference has persisted for three days or more.

[0125] 3) Weak coverage: Extract daily granularity weak coverage cell-level data; match cells where weak coverage has persisted for 3 days or more.

[0126] 4) High load: Extract daily granularity high load cell-level data to be expanded; match cells where high load has persisted for 3 days or more.

[0127] The network communication performance data used for the above matching can typically be obtained from data generated by the base station network management system. For example, obtaining the connection rate indicator can determine whether the network has low connection problems. If the buildings within the cluster area meet any of the performance indicators in the above four dimensions, the cluster area is marked as a poor network point.

[0128] Figures 6 to 9 This is a schematic diagram of the application effect of an embodiment of the building network vulnerability discovery method provided by the embodiment of the present application. Figure 6 As shown in the figure, the complaint data of the main urban area of ​​a certain city in the past month is used as a sample. According to the clustering neighborhood radius (R) of 300 meters and the complaint sample number threshold (K) ≥ 5 times, the complaint clustering operation is performed, and a total of 14 network gaps that meet the conditions are discovered. Figure 7As shown in the figure, by performing periodic clustering operations on the complaint work order data of a certain city, it was found that the XXX apartment building met the complaint clustering network difficulty standard: there were 7 network problem complaints within a 300-meter radius within a certain period of time. Figure 7 The complaint location and work order number are shown in the table below. The work order number can be used as a complaint identifier. The specific data is shown in Table 3 below:

[0129] Table 3 Complaint data of a cluster area

[0130]

[0131]

[0132] In Table 3, the “center point” is the core point. The “center point work order number” is the work order number of the complaint sample corresponding to the core point in the cluster area. The “cluster work order number” is the complaint sample in the same cluster area as the center point. The “cluster longitude” and “cluster latitude” indicate the complaint location of the complaint sample corresponding to the “cluster work order number”.

[0133] The matching building information and related network performance within the cluster area are shown in Table 4 below:

[0134] Table 4 Matching local building information and related network performance data

[0135]

[0136] Table 4 shows the buildings within the cluster, the high-sampling point cells selected for each building, and the relevant network performance indicators for the high-sampling point cells. The data in Table 4 shows that the base station cells labeled "393490-171" and "393491-174" have weak network coverage.

[0137] Further field investigations revealed that 4G internet access and calls were unavailable in Apartment Buildings 1, 2, 3, and 4 of XXX Apartment. Field testing revealed that 4G coverage in Building 1 was poor, with a cell signal strength of 393,490, and an average RSRP of -108dBm. Indoor 4G coverage in Building 2 was poor, with a cell signal strength of 393,490, and an average RSRP of -112dBm. Buildings 3 and 4 were completely disconnected from the network. These field tests were consistent with the conclusions drawn by the clustering algorithm to identify network weaknesses.

[0138] Figure 8 and Figure 9 This is a screenshot of a 4G field test. The RSRP data in the figure indicates weak network coverage in this area. Field testing can help further pinpoint issues, optimize and address them, and improve network service quality.

[0139] The present application also provides a building network optimization method, including:

[0140] Obtain samples of each complaint;

[0141] For each complaint sample, executing any of the above-mentioned building network weakness discovery methods to obtain the network weakness;

[0142] The network in the cluster area corresponding to the network difference is optimized.

[0143] Based on the discovery of network weaknesses, further exploration and processing can be carried out to optimize network services and improve customer satisfaction.

[0144] like Figure 10 As shown, the present application also provides a corresponding embodiment of a building network near-miss discovery device. For the beneficial effects or technical problems solved by the device, please refer to the description in the methods corresponding to each device, or refer to the description in the content of the invention, which will not be repeated here.

[0145] In an embodiment of the building network defect discovery device, the device includes:

[0146] The clustering unit 100 is configured to cluster complaint samples according to complaint location information to obtain at least one clustering area;

[0147] A local building determination unit 200 is configured to obtain local buildings within the at least one clustering area according to the building location information;

[0148] The network poor point determination unit 300 is configured to determine, for each cluster area, a preset number of high sampling point cells of each building within the cluster area. When the high sampling point cells meet the poor performance index, the cluster area is determined to be a network poor point.

[0149] In one embodiment, the clustering unit 100 is configured to:

[0150] Calculate the sample distances between complaint samples based on the complaint location information of each complaint sample;

[0151] Obtaining a first set of complaint samples that have not yet been clustered;

[0152] Using the location information of each complaint sample in the first set as a core point, respectively, obtaining a second set corresponding to each core point; wherein the sample distance from the complaint sample in the second set to the core point is less than the cluster neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement;

[0153] When the second set is obtained, the second set with the largest number of complaint samples is selected from each of the second sets as a result set of clustering areas, and the step of obtaining the first set consisting of complaint samples that have not yet been clustered is executed.

[0154] In one embodiment, the local building determination unit 200 is configured to:

[0155] Obtain building location information;

[0156] When it is determined that the distance from the building location to the center point of a cluster area is less than the cluster neighborhood radius, the building is a local building within the cluster area.

[0157] In one embodiment, when the network difference determination unit 300 is used to determine a preset number of high sampling point cells for each building within the cluster area, it is specifically used to:

[0158] According to the identification information of the local buildings, the sampling point cells corresponding to each local building are obtained, and a preset number of cells with the highest number of sampling points are selected as the high sampling point cells of the local building.

[0159] In one embodiment, the poor performance indicator includes at least one of the following:

[0160] Fault duration, high interference duration, weak coverage duration, and high load duration.

[0161] Figure 11 9 is a schematic structural diagram of a computing device 900 provided in an embodiment of the present application. The computing device 900 includes: a processor 910, a memory 920, and a communication interface 930.

[0162] It should be understood that Figure 11 The communication interface 930 in the computing device 900 shown in FIG. 9 may be used to communicate with other devices.

[0163] The processor 910 may be connected to a memory 920. The memory 920 may be used to store the program code and data. Therefore, the memory 920 may be a storage unit within the processor 910, an external storage unit independent of the processor 910, or a component including both a storage unit within the processor 910 and an external storage unit independent of the processor 910.

[0164] Optionally, the computing device 900 may further include a bus. The memory 920 and the communication interface 930 may be connected to the processor 910 via the bus. The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, and the like.

[0165] It should be understood that in the embodiment of the present application, the processor 910 can adopt a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. Alternatively, the processor 910 adopts one or more integrated circuits to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0166] The memory 920 may include a read-only memory and a random access memory, and provides instructions and data to the processor 910. A portion of the processor 910 may also include a non-volatile random access memory. For example, the processor 910 may also store information about the device type.

[0167] When the computing device 900 is running, the processor 910 executes the computer-executable instructions in the memory 920 to perform the operating steps of the above method.

[0168] It should be understood that the computing device 900 according to the embodiment of the present application can correspond to the corresponding subject in executing the method according to each embodiment of the present application, and the above-mentioned and other operations and / or functions of each module in the computing device 900 are respectively for implementing the corresponding processes of each method of the present embodiment. For the sake of brevity, they will not be repeated here.

[0169] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0170] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0173] In addition, each functional unit in each embodiment of 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.

[0174] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0175] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, it is used to execute a method for generating diversified questions, which includes at least one of the solutions described in the above embodiments.

[0176] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media.Computer-readable media can be computer-readable signal media or computer-readable storage media.Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof.More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connection with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination thereof.In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0177] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0178] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0179] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0180] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present application has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, all of which fall within the scope of protection of the present invention.

Claims

1. A method for discovering building network vulnerabilities, characterized in that: include: Clustering each complaint sample according to the complaint location information to obtain at least one clustering area; Obtaining, according to the building location information, the local buildings within the at least one clustering area; For each of the clustering areas, determining a preset number of high sampling point cells of each building within the clustering area, and determining that the clustering area is a poor network point when the high sampling point cells meet a poor performance index; The clustering of complaint samples according to complaint location information includes: Calculate the sample distances between complaint samples based on the complaint location information of each complaint sample; Obtaining a first set of complaint samples that have not yet been clustered; Using the location information of each complaint sample in the first set as a core point, respectively, obtaining a second set corresponding to each core point; wherein the sample distance from the complaint sample in the second set to the core point is less than the cluster neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement; When the second set is obtained, the second set with the largest number of complaint samples is selected from each of the second sets as a result set of clustering areas, and the step of obtaining the first set consisting of complaint samples that have not yet been clustered is executed.

2. The method according to claim 1, characterized in that The obtaining, based on the building location information, the local buildings within the at least one clustering area includes: Obtain building location information; When it is determined that the distance from the building location to the center point of a cluster area is less than the cluster neighborhood radius, the building is a local building within the cluster area.

3. The method according to claim 1, characterized in that The determining of a preset number of high sampling point cells for each building within the clustering area includes: According to the identification information of the local buildings, the sampling point cells corresponding to each local building are obtained, and a preset number of cells with the highest number of sampling points are selected as the high sampling point cells of the local building.

4. The method according to claim 1, wherein The poor performance indicator includes at least one of the following: Fault duration, high interference duration, weak coverage duration, and high load duration.

5. A building network vulnerability discovery device, characterized in that: include: a clustering unit for clustering complaint samples according to complaint location information to obtain at least one clustering area; wherein, clustering complaint samples according to complaint location information includes: calculating the sample distance between complaint samples according to the complaint location information of each complaint sample; obtaining a first set consisting of complaint samples that have not yet been clustered; using the location information of each complaint sample in the first set as a core point, obtaining a second set corresponding to each core point; wherein the sample distance from the complaint sample in the second set to the core point is less than the clustering neighborhood radius, and the number of complaint samples in the second set meets the threshold requirement; when the second set is obtained, selecting the second set with the largest number of complaint samples from each second set as a result set of a clustering area, and turning to the step of obtaining the first set consisting of complaint samples that have not yet been clustered; a local building determining unit, configured to obtain the local buildings within the at least one clustering area according to the building location information; The network poor point determination unit is used to determine, for each cluster area, a preset number of high sampling point cells of each building within the cluster area, and determine that the cluster area is a network poor point when the high sampling point cells meet the poor performance index.

6. The device according to claim 5, characterized in that When the network difference determination unit is used to determine a preset number of high sampling point cells of each building within the cluster area, it is specifically used to: According to the identification information of the local buildings, the sampling point cells corresponding to each local building are obtained, and a preset number of cells with the highest number of sampling points are selected as the high sampling point cells of the local building.

7. A building network optimization method, characterized in that: include: Obtain samples of each complaint; For each of the complaint samples, executing the building network near miss discovery method described in any one of claims 1 to 4 to obtain the network near miss; The network in the cluster area corresponding to the network difference is optimized.

8. A computing device, characterized in that include: Communication interface; at least one processor connected to the communication interface; as well as At least one memory connected to the processor and storing program instructions, wherein when the program instructions are executed by the at least one processor, the at least one processor executes the method according to any one of claims 1 to 4 or 7.

9. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a computer, the computer is caused to perform the method according to any one of claims 1 to 4 or 7.

Images