Cell flow control method, device, electronic device, and storage medium

Abstract

The embodiments of this specification provide a method, device, electronic device, and storage medium for cell traffic control, wherein the method includes: obtaining communication key performance indicator KPI data of multiple cells to be monitored; dividing the multiple cells to be monitored into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and pre-established traffic suppression cell identification rules; classifying the cells to be monitored using preset classification labels, and establishing user traffic models corresponding to each category according to the number of users and traffic data of non-traffic suppression cells included in each category; determining the target category of the traffic suppression cell, and regulating the traffic of the traffic suppression cell according to the user traffic model corresponding to the target category. Through this embodiment, the traffic suppression problem of the cell can be alleviated.

Description

Technical Field

[0001] This document relates to the field of communication technology, and in particular to a cell traffic control method, device, electronic device, and storage medium. Background Art

[0002] When existing network resources cannot meet the user's data traffic demand, the user's data service demand may be suppressed by wireless network problems such as poor network quality. For example, when a user is visiting a web page, he or she spends a long time waiting for the web page data to load, and the user may reduce web browsing or even give up web browsing. After the user's data service demand is suppressed by wireless network problems, the data traffic will not be completely proportional to the increase in the number of users. When the traffic data gradually reaches a certain inflection point, it will show a downward trend as the number of user connections increases, eventually leading to a loss of data traffic. The above phenomenon that the data traffic is not completely proportional to the increase in the number of users is called traffic suppression, and the cell where traffic suppression occurs is called a traffic suppression cell. At present, there is no mature method to alleviate the traffic suppression problem in the cell. Summary of the invention

[0003] The purpose of the embodiments of this specification is to provide a method, device, electronic device, and storage medium for controlling cell traffic to alleviate the problem of cell traffic suppression.

[0004] To solve the above technical problems, one or more embodiments of this specification are implemented as follows:

[0005] An embodiment of this specification provides a cell traffic control method, including:

[0006] Obtain communication key performance indicator KPI data of multiple cells to be monitored;

[0007] According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells;

[0008] Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established;

[0009] The target category of the traffic suppression cell is determined, and traffic is regulated for the traffic suppression cell according to a user traffic model corresponding to the target category.

[0010] Another embodiment of the present specification provides a cell traffic control device, including:

[0011] A data acquisition module is used to acquire communication key performance indicator KPI data of multiple cells to be monitored;

[0012] A cell identification module, configured to divide the plurality of cells to be monitored into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and a pre-established traffic suppression cell identification rule;

[0013] A model building module, used to classify the cells to be monitored using preset classification labels, and to establish a user traffic model corresponding to each category according to the number of users and traffic data of non-traffic suppression cells included in each category;

[0014] The traffic regulation module is used to determine the target category of the traffic suppression cell and to regulate the traffic of the traffic suppression cell according to the user traffic model corresponding to the target category.

[0015] Another embodiment of the present specification provides an electronic device, the device comprising: a processor and a memory arranged to store computer executable instructions, the computer executable instructions, when executed by the processor, enable the processor to implement the following process:

[0016] Obtain communication key performance indicator KPI data of multiple cells to be monitored;

[0017] According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells;

[0018] Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established;

[0019] The target category of the traffic suppression cell is determined, and traffic is regulated for the traffic suppression cell according to a user traffic model corresponding to the target category.

[0020] Another embodiment of the present specification provides a storage medium for storing computer executable instructions, wherein the computer executable instructions implement the following process when executed by a processor:

[0021] Obtain communication key performance indicator KPI data of multiple cells to be monitored;

[0022] According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells;

[0023] Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established;

[0024] The target category of the traffic suppression cell is determined, and traffic is regulated for the traffic suppression cell according to a user traffic model corresponding to the target category.

[0025] The cell flow control method, device, electronic device, and storage medium provided in one or more embodiments of this specification, after acquiring the communication key performance indicator KPI data of multiple cells to be monitored, divide the multiple cells to be monitored into flow suppression cells and non-flow suppression cells according to the KPI data of the cells to be monitored and the pre-established flow suppression cell identification rules, classify the cells to be monitored using preset classification labels, establish user flow models corresponding to each category according to the number of users and flow data of the non-flow suppression cells included in each category, determine the target category of the flow suppression cell, and adjust the flow of the flow suppression cell according to the user flow model corresponding to the target category. It can be seen that through this embodiment, it is possible to efficiently identify the flow suppression cell from the cells to be monitored, and adjust the flow of the flow suppression cell, thereby alleviating the flow suppression problem of the cell. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A flowchart of a cell flow control method provided in an embodiment of this specification;

[0028] Figure 2 The FP tree and item header provided in one embodiment of this specification are schematically shown;

[0029] Figure 3 A schematic diagram of a user traffic model obtained by fitting using a linear regression algorithm model provided in an embodiment of this specification;

[0030] Figure 4 A schematic diagram of the module composition of a cell flow control device provided in an embodiment of this specification;

[0031] Figure 5 A schematic diagram of the structure of an electronic device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the technical solutions in this document, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this document, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0033] Figure 1 A flow chart of a cell flow control method provided in an embodiment of this specification is shown as follows: Figure 1 As shown, the process includes:

[0034] Step S102, obtaining communication key performance indicator KPI data of multiple cells to be monitored;

[0035] Step S104, dividing the multiple cells to be monitored into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules;

[0036] Step S106, using preset classification labels to classify the cells to be monitored, and establishing a user traffic model corresponding to each category according to the number of users and traffic data of non-traffic suppressed cells included in each category;

[0037] Step S108, determining the target category of the traffic suppression cell, and adjusting the traffic of the traffic suppression cell according to the user traffic model corresponding to the target category.

[0038] In this embodiment, after obtaining the communication key performance indicator KPI data of multiple cells to be monitored, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, and the cells to be monitored are classified using preset classification labels. According to the number of users and traffic data of the non-traffic suppression cells included in each category, a user traffic model corresponding to each category is established, and the target category of the traffic suppression cell is determined. According to the user traffic model corresponding to the target category, the traffic suppression cell is regulated. It can be seen that through this embodiment, the traffic suppression cell can be efficiently identified from the cells to be monitored, and the traffic suppression cell can be regulated, thereby alleviating the traffic suppression problem of the cell.

[0039] In the above step S102, the communication key performance indicator KPI data of multiple cells to be monitored are obtained. Among them, the cells to be monitored should include non-traffic suppression cells and traffic suppression cells, and the number of non-traffic suppression cells should be sufficient to support the establishment of the above-mentioned user traffic model. KPI (Key Performance Indicator) data can be selected according to actual conditions. KPI data is an indicator that can reflect the network connection status of the cell. The following Table 1 is a schematic table of KPI data indicators in an embodiment.

[0040] Table 1

[0041]

[0042] In the above step S104, multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules. In one embodiment, the traffic suppression cell identification rules include multiple rule entries, and the rule entries include a predetermined KPI data range and a traffic suppression confidence corresponding to the KPI data range. The specific process of establishing the traffic suppression cell identification rules includes:

[0043] (a1) obtaining KQI data of multiple sample cells, and marking the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples;

[0044] (a2) Associating the KPI data of the sample cell with the sample marking result to obtain the associated data corresponding to the sample cell;

[0045] (a3) Perform frequent item set mining on the associated data corresponding to the sample cells to obtain various rule entries, and combine the various rule entries to obtain traffic suppression cell identification rules.

[0046] In the above action (a1), the KQI data of multiple sample cells are obtained, and the sample cells are marked according to the KQI data of the sample cells. The sample marking results include traffic suppression samples and traffic non-suppression samples. Among them, KQI (Key Quality Indicators) data is an indicator that can reflect the user experience. According to whether it will cause the user experience to deteriorate, the indicator is divided into intervals, and the indicator data collected by the sample cells is analyzed. If the indicator data is within the interval that will cause the user experience to deteriorate, the sample is marked as a positive sample, that is, a traffic suppression cell. If it is outside the interval that will cause the user experience to deteriorate, the sample is marked as a negative sample, that is, a non-traffic suppression cell. In one embodiment, the KQI data includes the proportion of users with abnormal latency and the proportion of users with abnormal large packet download rate. Based on the above KQI data, analysis is performed to obtain the proportion of target abnormal users due to wireless reasons. The target abnormal user proportion can be the average of the proportion of users with abnormal latency and the proportion of users with abnormal large packet download rate. It is stipulated that the cell with a target abnormal user proportion greater than 50% is a positive sample, i.e., a traffic suppression cell, and the cell with a target abnormal user proportion less than 50% is a negative sample, i.e., a non-traffic suppression cell.

[0047] In the above action (a2), the KPI data of the sample cell and the sample marking result are associated to obtain the associated data corresponding to the sample cell. In a specific embodiment, the KPI data of the sample cell and the sample marking result are associated to obtain the associated data corresponding to the sample cell, and the associated data includes the KPI data of the sample cell and the marking result of the sample cell. Among them, the association can be performed by the cell name and the data collection time. The following Table 2 is a schematic table of KPI data indicators of the sample cell, the following Table 3 is a schematic table of sample marking results of the sample cell, and the following Table 4 is a schematic table of associated data of the sample cell. It can be understood that in the actually obtained associated data, the sample marking result is a positive sample or a negative sample.

[0048] Table 2

[0049]

[0050] Table 3

[0051]

[0052] Table 4

[0053]

[0054] In the above action (a3), frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain the traffic suppression cell identification rule. Frequent item set mining can be performed using any mining algorithm. In one embodiment, the FP-Growth algorithm is used to perform frequent item set mining on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain the traffic suppression cell identification rule. The specific process of frequent item set mining includes:

[0055] (b1) According to the KPI indicator segmentation rule, each KPI indicator obtained above is divided into multiple intervals;

[0056] (b2) According to the KPI indicator filtering rules, for each KPI indicator, each interval obtained by the above segmentation is filtered;

[0057] (b3) Generate a header table based on the collected KPI data of the sample cells and the intervals obtained after filtering;

[0058] (b4) Sort the item header table from large to small according to the support count;

[0059] (b5) Using the association data and header table corresponding to the sample cells to build a FP (Frequent Pattern) tree;

[0060] (b6) Based on the sorted item header table, perform data mining on the FP tree to obtain all frequent items and their corresponding support counts.

[0061] (b7) According to the support count corresponding to each frequent item, the confidence corresponding to the frequent item is calculated, and a set consisting of a frequent item and its confidence is used as a rule entry. All rule entries are combined as a traffic suppression cell identification rule.

[0062] In the above action (b1), the KPI data of a large number of sample cells are obtained, and the KPI data of each sample cell includes indicator data of multiple KPI indicators. The KPI segmentation rules can be determined according to experience, so for each KPI indicator obtained above, the segmentation method of the KPI indicator is manually determined, and the KPI indicator is divided into multiple intervals. For example, for example, a KPI indicator is the average delay of user-plane downlink packets (milliseconds / packet). According to experience, when the average delay of user-plane downlink packets is >60 milliseconds / packet, it will cause the user experience to deteriorate. Then, the KPI indicator is divided into the average delay of user-plane downlink packets >60 milliseconds / packet, and the average delay of user-plane downlink packets <=60 milliseconds / packet.

[0063] In the above action (b2), according to the KPI indicator filtering rules, for each KPI indicator, the intervals obtained by the above segmentation are filtered, and the intervals that may cause user experience to deteriorate are retained, and other intervals are filtered out. For example, in the previous example, the average downlink packet delay of the user plane is divided into two intervals: greater than 60 milliseconds / packet and less than or equal to 60 milliseconds / packet. Here, the interval greater than 60 milliseconds / packet is removed, and the interval less than or equal to 60 milliseconds / packet is retained.

[0064] In the above action (b3), a header table is generated based on the collected KPI data of the sample cell and the interval obtained after filtering. The header table includes multiple records, each of which contains: the interval obtained by filtering, and the support count corresponding to the interval. The process of statistical support count specifically includes: for any record, analyzing the KPI data of the sample cell, when there is a KPI indicator value located in the interval of the record, the support count corresponding to the interval is increased by 1.

[0065] In the above action (b5), the associated data corresponding to the sample cell and the header table are used to establish a FP (Frequent Pattern) tree. The specific process of establishing the FP tree is as follows: read the associated data corresponding to the sample cell one by one, insert them into the FP tree, and insert them into the FP tree in the sorting order of the header table. The nodes at the front of the sorting order are ancestor nodes, and the nodes at the back of the sorting order are descendant nodes. If there is a common ancestor, the corresponding common ancestor node count is increased by 1. After the insertion, if a new node appears, the node corresponding to the header table will be linked to the new node through the node linked list. The establishment of the FP tree is completed until all the data is inserted into the FP tree. Figure 2 The FP tree and item header provided in an embodiment of this specification are schematically shown. The established FP tree is as follows: Figure 2 As shown, Figure 2 The letters in represent the KPI data interval, and the numbers after the letters represent the number of samples in the KPI data interval, that is, the support count of the KPI data interval.

[0066] In the above action (b6), data mining is performed on the FP tree according to the sorted header table to obtain all frequent items and the support counts corresponding to the frequent items. The specific process of data mining is: mining from the bottom item of the header table upwards in sequence, and finding its conditional pattern base for each item in the header table corresponding to the FP tree. The conditional pattern base is the FP subtree corresponding to the leaf node of the node to be mined. After obtaining this FP subtree, the count of each node in the subtree is set to the count of the leaf node, and the nodes with counts lower than the minimum support count are deleted; by mining the conditional pattern base for each node in the FP tree, all frequent items and the support counts of each frequent item can be obtained; wherein, the minimum support count can be selected according to the situation.

[0067] In the above action (b7), the confidence corresponding to each frequent item is calculated according to the support count corresponding to the frequent item, and the set consisting of all frequent items and their confidences is used as the traffic suppression cell identification rule.

[0068] In a specific embodiment, Table 4 is a schematic table of the suppressed cell identification rules provided in the embodiment, as shown in Table 4, wherein Rule 1 indicates that when the downlink PRB utilization is greater than 70%, the RRC connection reconstruction ratio is greater than 10%, and the average delay of the user plane downlink packet is greater than 60 milliseconds, the probability of user perception deterioration is 100%; Rule 2 indicates that when the downlink PRB average utilization is greater than 70%, and the downlink PRB average utilization is greater than 10%, the probability of user perception deterioration is 100%.

[0069] Table 4

[0070]

[0071] In the above step S104, multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules. In one embodiment, multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, and the specific process includes:

[0072] (c1) searching for an entry in the traffic suppression cell identification rule whose KPI data range matches the KPI data of the cell to be monitored;

[0073] (c2) if found, judging whether the cell to be monitored is a traffic suppression cell or a traffic non-suppression cell according to the traffic suppression confidence in the found entry and a preset confidence threshold;

[0074] (c3) If no traffic is found, the cell to be monitored is classified as a non-traffic suppression cell.

[0075] In the above action (c1), an entry whose KPI data range matches the KPI data of the cell to be monitored is searched in the traffic suppression cell identification rule. Among them, an entry in the traffic suppression cell identification rule may contain one or more KPI data ranges. For example, a traffic suppression cell identification rule may be that the downlink PRB utilization is greater than 70%, the RRC connection reconstruction ratio is greater than 10%, and the average delay of the user plane downlink packet is greater than 60 milliseconds; it may also be that the RRC connection reconstruction ratio is greater than 10%. When an entry in the traffic suppression cell identification rule contains a KPI data range, if the KPI data of the cell to be monitored is within the data range, it is determined that the entry matches the KPI data of the cell to be monitored. When an entry in the traffic suppression cell identification rule contains multiple KPI data ranges, if the KPI data of the cell to be monitored is within each data range, it is determined that the entry matches the KPI data of the cell to be monitored. For any cell to be monitored, there may be one or more matching target entries.

[0076] In the above action (c2), if it is found, the cell to be monitored is judged as a traffic suppression cell or a non-traffic suppression cell according to the traffic suppression confidence in the found entry and the preset confidence threshold. For any cell to be monitored, if it matches one target entry and the traffic suppression confidence in the entry is greater than the preset confidence threshold, the cell to be monitored is determined to be a traffic suppression cell; if the traffic suppression confidence in the entry is less than or equal to the preset confidence threshold, the cell to be monitored is determined to be a non-traffic suppression cell. For any cell to be monitored, if it matches multiple target entries, and the traffic suppression confidence in any one of the entries is greater than the preset confidence threshold, the cell to be monitored is determined to be a traffic suppression cell; if the traffic suppression confidence in each matching entry is less than or equal to the preset confidence threshold, the cell to be monitored is determined to be a non-traffic suppression cell. Among them, the confidence threshold is set according to the actual situation.

[0077] In the above action (c3), if no entry matching the cell to be monitored is found, the cell to be monitored is classified as a non-traffic suppression cell.

[0078] In the above step S106, the preset classification labels include first-class labels and second-class labels. The cells to be monitored are classified using the preset classification labels. In one embodiment, the specific classification process includes:

[0079] (d1) determining a first label value of the cell to be monitored under the first label according to information related to the first label of the cell to be monitored;

[0080] (d2) clustering the communication data of the cell to be monitored under the second type of label to obtain a second label value of the cell to be monitored under the second type of label;

[0081] (d3) Classifying cells to be monitored that have the same first label value and second label value into the same category.

[0082] In the above action (d1), the first label value of the cell to be monitored under the first label is determined according to the information related to the first label of the cell to be monitored. The first label includes labels such as the scene of the cell, the frequency band of the cell network facilities, and the bandwidth of the cell network facilities. For the label of the scene of the cell, the information related to the first label of the cell to be monitored can be information such as the geographical location of the cell to be monitored, and the first label value includes: commercial center, town center, residential area, university, transportation hub, rural area, etc. For the frequency band of the cell network facilities, the information related to the first label of the cell to be monitored can be the network frequency band value of the cell to be monitored, and the first label value includes: 2.1G, 1800M, etc. For the bandwidth of the cell network facilities, the information related to the first label of the cell to be monitored can be the network bandwidth value of the cell to be monitored, and the first label value includes: 20M, 15M, etc. In this step, since the information related to the first label of the cell to be monitored is not quantifiable, the first label value of the cell to be monitored under the first label can be determined by artificial experience.

[0083] In the above action (d2), the communication data of the monitored cell under the second type of label is clustered to obtain the second label value of the monitored cell under the second type of label. Among them, the second type of label includes labels such as the information collection period, the number of people in the cell, and the average size of the data packet. Correspondingly, the communication data of the monitored cell under the second type of label includes the information collection time, the number of people in the cell, and the size of the transmitted data packet. The second label value under the second type of label is determined according to the clustering result. Taking the second type of label as the information collection period as an example, each monitored cell can be clustered according to the information collection time of each monitored cell through a general clustering method, and the identifiers of each class obtained by clustering are used as the second label values ​​of each monitored cell in the corresponding class. Taking the second type of label as the cell population size as an example, each monitored cell can be clustered according to the number of people in each monitored cell through a general clustering method, and the identifiers of each class obtained by clustering are used as the second label values ​​of each monitored cell in the corresponding class. Taking the second category label as the average data packet size as an example, each cell to be monitored can be clustered in a common clustering manner according to the size of the data packet transmitted by each cell to be monitored, and the identifier of each class obtained by clustering is used as the second label value of each cell to be monitored in the corresponding class.

[0084] In the above action (d3), the monitored cells with the same first label value and second label value are classified into the same category. When there are multiple classification labels, the monitored cells with the same label values ​​of multiple classification labels are classified into the same category.

[0085] In one embodiment, after the cells to be monitored are classified using preset classification labels, the following actions are also included:

[0086] (f1) If, among the various categories obtained by the division, there is a first target category whose number of cells to be monitored is less than a preset threshold, a clustering algorithm with a penalty coefficient is used to determine a third target category associated with the first target category in each second target category; wherein the second target category is a category other than the first target category in the various categories obtained by the division;

[0087] (f2) Merging the cells to be monitored in the first target category and the third target category into the same category.

[0088] In the above action (f1), if there is a first target category in each of the divided categories that contains a number of cells to be monitored that is less than a preset threshold, a clustering algorithm with a penalty coefficient is used to determine a third target category associated with the first target category in each of the second target categories; wherein the second target category is a category other than the first target category in each of the divided categories. Wherein, using a clustering algorithm with a penalty coefficient to determine a third target category associated with the first target category in each of the second target categories specifically includes:

[0089] (1) calculating the standardized characteristic value of each cell to be monitored in the first category according to the KPI data of each cell to be monitored in the first target category;

[0090] (2) calculating a standardized feature value of each cell to be monitored in each second target category according to the KPI data of each cell to be monitored in each second target category;

[0091] (3) for any standardized feature value in the first target category and any standardized feature value in any second target category, determining a penalty coefficient between the two standardized feature values ​​according to the source cells corresponding to the two standardized feature values;

[0092] (4) for each second target category, calculating the distance between the first target category and the second target category according to each standardized feature value in the first target category, each standardized feature value in the second target category, and a penalty coefficient between each standardized feature value in the first target category and each standardized feature value in the second target category;

[0093] (5) Based on the distance, determine, among the second target categories, the second target category that is closest to the first target category as the third target category.

[0094] In action (1), for each cell in the first target category, the KPI data of the cell is standardized to obtain a standardized feature value, and the standardized feature value is a feature value representing the feature of the cell. Therefore, each cell in the first target category has its own feature value.

[0095] In action (2), for any second target category, for each cell in the category, the KPI data of the cell is standardized to obtain a standardized feature value, and the standardized feature value is a feature value representing the feature of the cell. Therefore, each cell in each second target category has its own feature value.

[0096] In action (3), taking the standardized eigenvalue x1 and the standardized eigenvalue x2 as examples, the standardized eigenvalue x1 comes from the first target category, and the standardized eigenvalue x2 comes from any second target category. If x1 and x2 are eigenvalues ​​corresponding to KPI data collected in different time periods for the same cell, then the penalty coefficient p between x1 and x2 is determined to be equal to 1. If x1 and x2 are eigenvalues ​​corresponding to different cells, then the penalty coefficient p between x1 and x2 is determined to be equal to 0.

[0097] In action (4), for each second target category, the distance between the first target category and the second target category is calculated according to each standardized feature value in the first target category, each standardized feature value in the second target category, and the penalty coefficient between each standardized feature value in the first target category and each standardized feature value in the second target category, specifically: .in, represents each normalized feature value in the first target category, represents each normalized feature value in the second target category, express and The penalty coefficient between .

[0098] In action (5), based on the distance between the first target category and each second target category, the second target category closest to the first target category is determined as the third target category among the second target categories.

[0099] In the above step S106, based on the number of users and traffic data of non-traffic suppression cells included in each category, a user traffic model corresponding to each category is established. In one embodiment, the traffic data includes traffic values, and establishing a user traffic model corresponding to each category specifically includes:

[0100] (g1) fitting the number of users and traffic data of non-traffic suppression cells in each category respectively; wherein the traffic data includes traffic values;

[0101] (g2) The data relationship between the number of users and the traffic data obtained by fitting is determined as the user traffic model corresponding to each category.

[0102] In the above action (g1), the number of users and the traffic value of the non-traffic suppression cells included in each category are fitted respectively. Any fitting algorithm can be used for fitting. In a specific embodiment, in order to increase robustness, a linear regression algorithm model is used, that is, f(x) = kx+b. Where f(x) is the traffic value and x is the number of users. Figure 3 A schematic diagram of a user traffic model obtained by fitting a linear regression algorithm model is provided for an embodiment of this specification, wherein the vertical axis represents the traffic value, the horizontal axis represents the number of users, the scatter points represent the number of users and traffic values ​​of non-traffic suppression cells included in the category, and the oblique line represents the user traffic model established by fitting the number of users and traffic values ​​of the above-mentioned non-traffic suppression cells.

[0103] In the above step S108, the target category of the traffic suppression cell is determined, and the traffic of the traffic suppression cell is adjusted according to the user traffic model corresponding to the target category. In one embodiment, the traffic of the traffic suppression cell is adjusted according to the user traffic model corresponding to the target category, specifically including:

[0104] (h1) Obtaining the number of users and actual traffic data of the traffic suppression cell; the actual traffic data includes the actual traffic value;

[0105] (h2) determining ideal traffic data of the traffic suppression cell according to the number of users in the traffic suppression cell and the user traffic model corresponding to the target category; the ideal traffic data includes an ideal traffic value;

[0106] (h3) Based on the actual traffic data and ideal traffic data of the traffic suppressed cell, the traffic capacity of the traffic suppressed cell is expanded.

[0107] In the above action (h2), the ideal traffic data of the traffic suppressed cell is determined according to the number of users in the traffic suppressed cell and the user traffic model corresponding to the target category. The classification of the traffic suppressed cell and the establishment of the user traffic model are as in step S106, which will not be explained here. The ideal traffic data refers to the traffic data calculated by substituting the number of users into the user traffic model.

[0108] In the above action (h3), the traffic capacity of the traffic-suppressed cell is expanded according to the actual traffic data and ideal traffic data of the traffic-suppressed cell. The ideal traffic data is subtracted from the actual traffic data to obtain the suppressed traffic value of the cell. According to the suppressed traffic size of the cell, the traffic capacity is expanded to accurately guide operators to invest resources in the relevant areas covered by the traffic-suppressed cell, and alleviate the traffic suppression problem through cell optimization, capacity expansion, new sites, etc.

[0109] In summary, the cell traffic regulation method in this embodiment has at least the following advantages:

[0110] (1) Aiming at the evaluation and analysis of the causes of data traffic suppression in wireless cells, the cell traffic control method provided in the embodiments of this specification calculates the potential space of the suppressed traffic supply in the cell. The ultimate goal is to locate the threshold of cell traffic suppression and accurately guide operators to expand cell resources.

[0111] (2) Compared with the prior art, the cell traffic control method provided in the embodiments of this specification can timely identify the traffic suppression cells and the size of their suppressed traffic in the network, accurately guide operators to invest limited resources in the relevant areas covered by the traffic suppression cells, and alleviate the cell traffic suppression problem with fewer resources through cell optimization, capacity expansion, new stations, etc.

[0112] (3) In the current 5G network construction phase, the cell traffic control method provided in the embodiments of this specification is used, while considering the 5G cell network and traffic characteristics, and taking the construction of 5G site resources as an opportunity, the 4G traffic suppression problem is solved and shared from the perspectives of coverage and capacity limitations. On the one hand, it promotes the coordination of 4 / 5G network construction, and on the other hand, it stimulates the suppressed data traffic of the existing 4G network and guides the deployment of 4 / 5G resources to key areas.

[0113] Corresponding to the cell flow control method provided in the above embodiment, based on the same idea, the embodiment of this specification also provides a cell flow control device, which is used to execute the cell flow control method provided in the above embodiment. Figure 4 A schematic diagram of the module composition of a cell flow control device provided in an embodiment of this specification, such as Figure 4 As shown, the device specifically includes:

[0114] The data acquisition module 41 is used to acquire the communication key performance indicator KPI data of multiple cells to be monitored;

[0115] The cell identification module 42 is used to divide the multiple cells to be monitored into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules;

[0116] The model building module 43 is used to classify the monitored cells using preset classification labels, and to establish a user traffic model corresponding to each category according to the number of users and traffic data of the non-traffic suppressed cells included in each category;

[0117] The traffic regulation module 44 is used to determine the target category of the traffic suppression cell and to regulate the traffic of the traffic suppression cell according to the user traffic model corresponding to the target category.

[0118] Optionally, the traffic suppression cell identification rule includes a plurality of rule entries, and the rule entry includes a predetermined KPI data range and a traffic suppression confidence corresponding to the KPI data range; the cell identification module 42 is specifically used for:

[0119] Search the traffic suppression cell identification rule for an entry whose KPI data range matches the KPI data of the cell to be monitored;

[0120] If found, the cell to be monitored is determined to be a traffic suppression cell or a traffic non-suppression cell according to the traffic suppression confidence in the found entry and a preset confidence threshold;

[0121] If not found, the cell to be monitored will be classified as a non-traffic suppression cell.

[0122] Optionally, the cell identification module 42 is specifically used for:

[0123] Acquire KQI data of multiple sample cells, and mark the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples;

[0124] Correlate the KPI data of the sample cell with the sample marking result to obtain the correlation data corresponding to the sample cell;

[0125] Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain traffic suppression cell identification rules.

[0126] Optionally, the preset classification labels include first-category labels and second-category labels; the model building module 43 is specifically used for:

[0127] Determine, according to the information related to the first type of label of the cell to be monitored, a first label value of the cell to be monitored under the first type of label;

[0128] Clustering the communication data of the cell to be monitored under the second type of label to obtain the second label value of the cell to be monitored under the second type of label;

[0129] The cells to be monitored that have the same first label value and second label value are classified into the same category.

[0130] Optionally, the model building module 43 is specifically used for:

[0131] After the cells to be monitored having the same first label value and the same second label value are divided into the same category, if there is a first target category in each of the divided categories, the number of cells to be monitored included in which is less than a preset threshold, a clustering algorithm with a penalty coefficient is used to determine a third target category associated with the first target category in each of the second target categories; wherein the second target category is a category other than the first target category in each of the divided categories;

[0132] The cells to be monitored in the first target category and the third target category are merged into the same category.

[0133] Optionally, the model building module 43 is specifically used for:

[0134] Fitting the number of users and traffic data of non-traffic suppressed cells in each category respectively;

[0135] The data relationship between the number of users and the traffic data obtained by fitting is determined as the user traffic model corresponding to each category.

[0136] Optionally, the flow regulating module 44 is specifically used for:

[0137] Obtain the number of users and actual traffic data in traffic-suppressed cells;

[0138] Determine the ideal traffic data of the traffic suppression cell according to the number of users in the traffic suppression cell and the user traffic model corresponding to the target category;

[0139] According to the actual traffic data and ideal traffic data of the traffic suppressed cell, the traffic capacity of the traffic suppressed cell is expanded.

[0140] The cell flow control device provided in the embodiments of this specification has at least the following beneficial effects:

[0141] After acquiring the communication key performance indicator KPI data of multiple cells to be monitored, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, and the cells to be monitored are classified using preset classification labels. According to the number of users and traffic data of non-traffic suppression cells included in each category, a user traffic model corresponding to each category is established, and the target category of the traffic suppression cell is determined. According to the user traffic model corresponding to the target category, the traffic suppression cell is regulated. It can be seen that through this embodiment, the traffic suppression cell can be efficiently identified from the cells to be monitored, and the traffic suppression cell can be regulated, thereby alleviating the traffic suppression problem of the cell.

[0142] Figure 4 The device provided in the illustrated embodiment can implement all the method steps of the above-mentioned cell traffic control method embodiment and achieve the same functions and effects, which will not be repeated here.

[0143] Corresponding to the cell flow control method provided in the above embodiment, based on the same idea, an embodiment of this specification also provides an electronic device, which is used to execute the cell flow control method provided in the above embodiment. Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification, such as Figure 5 As shown, the electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors 1001 and memory 1002, and the memory 1002 may store one or more storage applications or data. Among them, the memory 1002 may be a short-term storage or a permanent storage. The application stored in the memory 1002 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instruction information in the electronic device. Furthermore, the processor 1001 may be configured to communicate with the memory 1002 to execute a series of computer executable instruction information in the memory 1002 on the electronic device. The electronic device may also include one or more power supplies 1003, one or more wired or wireless network interfaces 1004, one or more input and output interfaces 1005, one or more keyboards 1006, etc.

[0144] In a specific embodiment, the electronic device includes a processor and a memory arranged to store computer executable instructions, wherein when the computer executable instructions are executed, the processor implements the following process:

[0145] Obtain communication key performance indicator KPI data of multiple cells to be monitored;

[0146] According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells;

[0147] Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established;

[0148] The target category of the traffic suppression cell is determined, and traffic is regulated for the traffic suppression cell according to a user traffic model corresponding to the target category.

[0149] Optionally, when the computer executable instructions are executed, the traffic suppression cell identification rule includes a plurality of rule entries, and the rule entry includes a predetermined KPI data range and a traffic suppression confidence corresponding to the KPI data range; and according to the KPI data of the cell to be monitored and the pre-established traffic suppression cell identification rule, the plurality of cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells, including:

[0150] Search the traffic suppression cell identification rule for an entry whose KPI data range matches the KPI data of the cell to be monitored;

[0151] If found, the cell to be monitored is determined to be a traffic suppression cell or a traffic non-suppression cell according to the traffic suppression confidence in the found entry and a preset confidence threshold;

[0152] If not found, the cell to be monitored will be classified as a non-traffic suppression cell.

[0153] Optionally, when the computer executable instructions are executed, the traffic suppression cell identification rule is determined in the following manner:

[0154] Acquire KQI data of multiple sample cells, and mark the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples;

[0155] Correlate the KPI data of the sample cell with the sample marking result to obtain the correlation data corresponding to the sample cell;

[0156] Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain traffic suppression cell identification rules.

[0157] Optionally, when the computer executable instructions are executed, the preset classification labels include first-category labels and second-category labels; and classifying the cells to be monitored using the preset classification labels includes:

[0158] Determine, according to the information related to the first type of label of the cell to be monitored, a first label value of the cell to be monitored under the first type of label;

[0159] Clustering the communication data of the cell to be monitored under the second type of label to obtain the second label value of the cell to be monitored under the second type of label;

[0160] The cells to be monitored that have the same first label value and second label value are classified into the same category.

[0161] Optionally, when the computer executable instructions are executed, after classifying the cells to be monitored having the same first label value and the same second label value into the same category, the following can be achieved:

[0162] If there is a first target category in each of the divided categories, the number of cells to be monitored contained in it is less than a preset threshold, a clustering algorithm with a penalty coefficient is used to determine a third target category associated with the first target category in each of the second target categories; wherein the second target category is a category other than the first target category in each of the divided categories;

[0163] The cells to be monitored in the first target category and the third target category are merged into the same category.

[0164] Optionally, when the computer executable instructions are executed, based on the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established, including:

[0165] Fitting the number of users and traffic data of non-traffic suppressed cells in each category respectively;

[0166] The data relationship between the number of users and the traffic data obtained by fitting is determined as the user traffic model corresponding to each category.

[0167] Optionally, when the computer executable instructions are executed, traffic regulation is performed on the traffic suppression cell according to a user traffic model corresponding to the target category, including:

[0168] Obtain the number of users and actual traffic data in traffic-suppressed cells;

[0169] Determine the ideal traffic data of the traffic suppression cell according to the number of users in the traffic suppression cell and the user traffic model corresponding to the target category;

[0170] According to the actual traffic data and ideal traffic data of the traffic suppressed cell, the traffic capacity of the traffic suppressed cell is expanded.

[0171] The electronic device provided by the embodiments of this specification has at least the following beneficial effects:

[0172] After acquiring the communication key performance indicator KPI data of multiple cells to be monitored, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, and the cells to be monitored are classified using preset classification labels. According to the number of users and traffic data of non-traffic suppression cells included in each category, a user traffic model corresponding to each category is established, and the target category of the traffic suppression cell is determined. According to the user traffic model corresponding to the target category, the traffic suppression cell is regulated. It can be seen that through this embodiment, the traffic suppression cell can be efficiently identified from the cells to be monitored, and the traffic suppression cell can be regulated, thereby alleviating the traffic suppression problem of the cell.

[0173] Figure 5 The electronic device provided in the illustrated embodiment can implement all the method steps of the above-mentioned cell traffic control method embodiment and achieve the same functions and effects, which will not be repeated here.

[0174] Corresponding to the cell flow control method provided in the above embodiment, based on the same idea, the embodiment of this specification also provides a storage medium for executing the cell flow control method provided in the above embodiment. In a specific embodiment, the storage medium can be a USB flash drive, an optical disk, a hard disk, etc. The storage medium is used to store computer executable instructions, and the executable instructions implement the following process when executed by the processor:

[0175] Obtain communication key performance indicator KPI data of multiple cells to be monitored;

[0176] According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells;

[0177] Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established;

[0178] The target category of the traffic suppression cell is determined, and traffic is regulated for the traffic suppression cell according to a user traffic model corresponding to the target category.

[0179] Optionally, when the executable instruction is executed by the processor, the traffic suppression cell identification rule includes multiple rule entries, and the rule entry includes a predetermined KPI data range and a traffic suppression confidence corresponding to the KPI data range; according to the KPI data of the cell to be monitored and the pre-established traffic suppression cell identification rule, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells, including:

[0180] Search the traffic suppression cell identification rule for an entry whose KPI data range matches the KPI data of the cell to be monitored;

[0181] If found, the cell to be monitored is determined to be a traffic suppression cell or a traffic non-suppression cell according to the traffic suppression confidence in the found entry and a preset confidence threshold;

[0182] If not found, the cell to be monitored will be classified as a non-traffic suppression cell.

[0183] Optionally, when the executable instruction is executed by the processor, the traffic suppression cell identification rule is determined in the following manner:

[0184] Acquire KQI data of multiple sample cells, and mark the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples;

[0185] Correlate the KPI data of the sample cell with the sample marking result to obtain the correlation data corresponding to the sample cell;

[0186] Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain traffic suppression cell identification rules.

[0187] Optionally, when the executable instruction is executed by the processor, the preset classification label includes a first category label and a second category label; and classifying the cells to be monitored using the preset classification label includes:

[0188] Determine, according to the information related to the first type of label of the cell to be monitored, a first label value of the cell to be monitored under the first type of label;

[0189] Clustering the communication data of the cell to be monitored under the second type of label to obtain the second label value of the cell to be monitored under the second type of label;

[0190] The cells to be monitored that have the same first label value and second label value are classified into the same category.

[0191] Optionally, when the executable instruction is executed by the processor, after classifying the cells to be monitored having the same first label value and the same second label value into the same category, the following can be achieved:

[0192] If there is a first target category in each of the divided categories, the number of cells to be monitored contained in it is less than a preset threshold, a clustering algorithm with a penalty coefficient is used to determine a third target category associated with the first target category in each of the second target categories; wherein the second target category is a category other than the first target category in each of the divided categories;

[0193] The cells to be monitored in the first target category and the third target category are merged into the same category.

[0194] Optionally, when the executable instructions are executed by the processor, a user traffic model corresponding to each category is established according to the number of users and traffic data of non-traffic suppressed cells included in each category, including:

[0195] Fitting the number of users and traffic data of non-traffic suppressed cells in each category respectively;

[0196] The data relationship between the number of users and the traffic data obtained by fitting is determined as the user traffic model corresponding to each category.

[0197] Optionally, when the executable instruction is executed by the processor, the flow of the traffic suppression cell is adjusted according to the user flow model corresponding to the target category, including:

[0198] Obtain the number of users and actual traffic data in traffic-suppressed cells;

[0199] Determine the ideal traffic data of the traffic suppression cell according to the number of users in the traffic suppression cell and the user traffic model corresponding to the target category;

[0200] According to the actual traffic data and ideal traffic data of the traffic suppressed cell, the traffic capacity of the traffic suppressed cell is expanded.

[0201] The storage medium provided in the embodiments of this specification has at least the following beneficial effects:

[0202] After acquiring the communication key performance indicator KPI data of multiple cells to be monitored, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, and the cells to be monitored are classified using preset classification labels. According to the number of users and traffic data of non-traffic suppression cells included in each category, a user traffic model corresponding to each category is established, and the target category of the traffic suppression cell is determined. According to the user traffic model corresponding to the target category, the traffic suppression cell is regulated. It can be seen that through this embodiment, the traffic suppression cell can be efficiently identified from the cells to be monitored, and the traffic suppression cell can be regulated, thereby alleviating the traffic suppression problem of the cell.

[0203] The computer executable instruction information stored in the storage medium provided in the embodiment of this specification can implement all the method steps of the above-mentioned cell traffic control method embodiment when executed by the processor, and achieve the same functions and effects, which will not be repeated here.

[0204] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0205] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0206] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0207] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0208] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0209] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0210] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instruction information. These computer program instruction information can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instruction information executed by the processor of the computer or other programmable data processing device generates instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0211] These computer program instruction information can also be stored in a computer readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instruction information stored in the computer readable memory produces a manufactured product including an instruction information device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0212] These computer program instruction information can also be loaded into a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instruction information executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0213] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0214] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0215] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instruction information, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0216] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0217] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0218] The present application may be described in the general context of computer-executable instruction information executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0219] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0220] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A cell flow control method, characterized in that: include: Obtain communication key performance indicator KPI data of multiple cells to be monitored; According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells; Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established; Determine a target category of the traffic suppression cell, and adjust the traffic of the traffic suppression cell according to a user traffic model corresponding to the target category; The traffic suppression cell identification rule is determined in the following manner: Acquire KQI data of a plurality of sample cells, and perform sample marking on the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples; Associating the KPI data of the sample cell with the sample marking result to obtain associated data corresponding to the sample cell; Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain the traffic suppression cell identification rule.

2. The method according to claim 1, characterized in that The traffic suppression cell identification rule includes a plurality of rule entries, wherein the rule entry includes a predetermined KPI data range and a traffic suppression confidence corresponding to the KPI data range; and according to the KPI data of the cell to be monitored and the pre-established traffic suppression cell identification rule, the plurality of cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells, including: Searching for an entry in the traffic suppression cell identification rule whose KPI data range matches the KPI data of the cell to be monitored; If found, judging whether the cell to be monitored is a traffic suppression cell or a traffic non-suppression cell according to the traffic suppression confidence in the found entry and a preset confidence threshold; If not found, the cell to be monitored is classified as a non-traffic suppression cell.

3. The method according to claim 1, characterized in that The preset classification labels include first-class labels and second-class labels; using the preset classification labels, classifying the cells to be monitored includes: Determine, according to the information of the cell to be monitored related to the first type of label, a first label value of the cell to be monitored under the first type of label; Clustering the communication data of the cell to be monitored under the second type of label to obtain a second label value of the cell to be monitored under the second type of label; The cells to be monitored for which the first label value and the second label value are the same are classified into the same category.

4. The method according to claim 3, characterized in that: After classifying the cells to be monitored having the same first label value and the same second label value into the same category, the method further includes: If there is a first target category in each of the divided categories, the number of cells to be monitored contained in the category is less than a preset threshold, a clustering algorithm with a penalty coefficient is used to determine a third target category associated with the first target category in each of the second target categories; wherein the second target category is a category other than the first target category in each of the divided categories; The cells to be monitored in the first target category and the third target category are merged into the same category.

5. The method according to claim 1, characterized in that According to the number of users and traffic data of non-traffic suppression cells in each category, a user traffic model corresponding to each category is established, including: Fitting the number of users and traffic data of non-traffic suppressed cells in each category respectively; The data relationship between the number of users and the traffic data obtained by fitting is determined as the user traffic model corresponding to each category.

6. The method according to claim 1, characterized in that According to the user traffic model corresponding to the target category, traffic regulation is performed on the traffic suppression cell, including: Obtain the number of users and actual traffic data of the traffic suppression cell; Determining ideal traffic data of the traffic suppression cell according to the number of users of the traffic suppression cell and the user traffic model corresponding to the target category; According to the actual traffic data and the ideal traffic data of the traffic suppressed cell, the traffic capacity of the traffic suppressed cell is expanded.

7. A cell flow control device, characterized in that: include: A data acquisition module is used to acquire communication key performance indicator KPI data of multiple cells to be monitored; A cell identification module, configured to divide the plurality of cells to be monitored into traffic suppression cells and non-traffic suppression cells according to the KPI data of the cells to be monitored and a pre-established traffic suppression cell identification rule; A model building module, used to classify the cells to be monitored using preset classification labels, and to establish a user traffic model corresponding to each category according to the number of users and traffic data of non-traffic suppression cells included in each category; A traffic regulation module, used to determine the target category of the traffic suppression cell, and to regulate the traffic of the traffic suppression cell according to a user traffic model corresponding to the target category; The traffic suppression cell identification rule is determined in the following manner: Acquire KQI data of a plurality of sample cells, and perform sample marking on the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples; Associating the KPI data of the sample cell with the sample marking result to obtain associated data corresponding to the sample cell; Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain the traffic suppression cell identification rule.

8. An electronic device, characterized in that: The device comprises: a processor and a memory arranged to store computer executable instructions, wherein when the computer executable instructions are executed by the processor, the processor implements the following process: Obtain communication key performance indicator KPI data of multiple cells to be monitored; According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells; Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established; Determine a target category of the traffic suppression cell, and adjust the traffic of the traffic suppression cell according to a user traffic model corresponding to the target category; The traffic suppression cell identification rule is determined in the following manner: Acquire KQI data of a plurality of sample cells, and perform sample marking on the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples; Associating the KPI data of the sample cell with the sample marking result to obtain associated data corresponding to the sample cell; Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain the traffic suppression cell identification rule.

9. A storage medium, characterized in that: Used to store computer executable instructions, which implement the following process when executed by a processor: Obtain communication key performance indicator KPI data of multiple cells to be monitored; According to the KPI data of the cells to be monitored and the pre-established traffic suppression cell identification rules, the multiple cells to be monitored are divided into traffic suppression cells and non-traffic suppression cells; Using preset classification labels, the cells to be monitored are classified, and according to the number of users and traffic data of non-traffic suppressed cells included in each category, a user traffic model corresponding to each category is established; Determine a target category of the traffic suppression cell, and adjust the traffic of the traffic suppression cell according to a user traffic model corresponding to the target category; The traffic suppression cell identification rule is determined in the following manner: Acquire KQI data of a plurality of sample cells, and perform sample marking on the sample cells according to the KQI data of the sample cells, wherein the sample marking results include flow suppression samples and flow non-suppression samples; Associating the KPI data of the sample cell with the sample marking result to obtain associated data corresponding to the sample cell; Frequent item set mining is performed on the associated data corresponding to the sample cells to obtain various rule entries, and the various rule entries are combined to obtain the traffic suppression cell identification rule.

Images