Ultra-busy cell processing method and apparatus, storage medium, and electronic device

Abstract

Embodiments of the present application provide a super busy cell processing method, device, storage medium and electronic equipment, the method comprising: obtaining a first network service parameter group of a to-be-detected cell; performing clustering processing on the to-be-detected cell based on the first network service parameter group to obtain a cell type of the to-be-detected cell; if the to-be-detected cell is a super busy cell type, obtaining a second network service parameter group of the super busy cell; and calculating a traffic suppression value of the super busy cell based on the second network service parameter group. The technical scheme of the embodiments of the present application can on the one hand obtain a cell type of the to-be-detected cell with higher adaptation after performing clustering processing on the to-be-detected cell based on the first network service parameter group, and on the other hand, can calculate the traffic suppression value of the super busy cell based on the second network service parameter group, so as to facilitate maintenance personnel to implement expansion of the super busy cell according to the traffic suppression value, and ensure the rational use of resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, in particular to a super busy cell method, device, storage medium and electronic equipment. BACKGROUND

[0002] With the continuous upgrading of communication technology, in the process of deploying a new generation of mobile data network, due to the needs of communication operators to reduce the cost of initial deployment of new generation of mobile data network and fast networking, the network bearing service capacity of new generation of mobile data network in most areas is weak. As the user quantity increases and the user network demand improves, in places with large crowds such as schools and shopping malls, the new generation of mobile data network often appears super busy phenomenon, so that users cannot obtain the required network service, thereby causing great inconvenience to users.

[0003] However, there are many factors that induce super busy phenomenon, and part of the causes of super busy phenomenon are false super busy causes such as incorrect base station parameter setting or abnormal interoperation, which affect the repair speed of maintenance personnel for super busy phenomenon and cause waste of resources, so how to identify the area where super busy phenomenon really occurs and how to ensure that resources are reasonably used become current problems to be solved. SUMMARY

[0004] To solve the above technical problems, the embodiments of the present application provide a super busy cell processing method, device, storage medium and electronic equipment.

[0005] According to an aspect of the embodiments of the present application, a super busy cell processing method is provided, comprising: acquiring a first network service parameter group of a to-be-detected cell, the first network service parameter group comprising network service parameter values of multiple types; performing clustering processing of the to-be-detected cell based on the first network service parameter group to obtain a cell type of the to-be-detected cell; if the to-be-detected cell is of a super busy cell type, acquiring a second network service parameter group of the super busy cell, the second network service parameter group comprising network service parameter values of multiple types; and calculating a traffic suppression value of the super busy cell based on the second network service parameter group.

[0006] According to an aspect of some embodiments of the present application, a device for handling an ultra-busy cell is provided, comprising: an obtaining module configured to obtain a first set of network service parameters of a to-be-detected cell, the first set of network service parameters comprising network service parameter values of multiple types; a clustering module configured to perform clustering processing on the to-be-detected cell based on the first set of network service parameters, to obtain a cell type of the to-be-detected cell; an identifying module configured to, if the to-be-detected cell is of an ultra-busy cell type, obtain a second set of network service parameters of the ultra-busy cell, the second set of network service parameters comprising network service parameter values of multiple types; and a processing module configured to calculate a traffic suppression value of the ultra-busy cell based on the second set of network service parameters.

[0007] In some embodiments of the present application, based on the foregoing scheme, the processing module is further configured to, after calculating the traffic suppression value of the ultra-busy cell based on the second set of network service parameters, detect a relationship between the traffic suppression value of the ultra-busy cell and multiple preset traffic suppression intervals, to obtain a detection result; determine a target expansion strategy based on the detection result; wherein different preset traffic suppression intervals correspond to different expansion strategies; and expand the ultra-busy cell based on the target expansion strategy.

[0008] In some embodiments of the present application, based on the foregoing scheme, the clustering module is further configured to: perform elimination processing on abnormal network service parameter values contained in the first set of network service parameters, to obtain an eliminated first set of network service parameters; perform clustering processing on the to-be-detected cell based on the eliminated first set of network service parameters, to obtain a cell type of the to-be-detected cell; and the processing module is further configured to: perform elimination processing on abnormal network service parameter values contained in the second set of network service parameters, to obtain an eliminated second set of network service parameters; and calculate a traffic suppression value of the ultra-busy cell based on the eliminated second set of network service parameters.

[0009] In some embodiments of the present application, based on the foregoing scheme, in the case that the to-be-detected cell is multiple, the clustering module is further configured to: determine an initial clustering center based on the first set of network service parameters of the multiple to-be-detected cells; perform iterative clustering on the first set of network service parameters of the multiple to-be-detected cells based on the initial clustering center, until an iterative clustering exit condition is met, to obtain cell types of the multiple to-be-detected cells.

[0010] In some embodiments of the present application, based on the foregoing scheme, the clustering module is further configured to: in each round of clustering process, calculate a value function value corresponding to the current round of clustering center; if a difference between the value function value corresponding to the current round of clustering center and a value function value corresponding to a last round of clustering center is less than a preset value function threshold, determine that an iteration clustering exit condition is met, and obtain the cell type of the plurality of to-be-detected cells.

[0011] In some embodiments of the present application, based on the foregoing scheme, the processing module is further configured to: obtain an abnormal traffic value corresponding to the super-busy cell; based on the abnormal traffic value and the second network service parameter group, calculate to obtain a weight group of the second network service parameter group; based on the weight group and the second network service parameter group, calculate to obtain an actual traffic suppression value of the super-busy cell.

[0012] In some embodiments of the present application, based on the foregoing scheme, the clustering module is further configured to: input the first network service parameter group into a super-busy cell judgment model, so as to perform clustering processing of the to-be-detected cell based on the first network service parameter group through the super-busy cell judgment model, and obtain the cell type of the to-be-detected cell; and the processing module is further configured to: input the second network service parameter group into a super-busy cell traffic suppression restoration model, so as to calculate the traffic suppression value of the super-busy cell based on the second network service parameter group through the super-busy cell traffic suppression restoration model.

[0013] According to an aspect of an embodiment of the present application, a storage medium having computer readable instructions stored thereon is provided, when the computer readable instructions are executed by a processor of a computer, the computer is caused to perform the super-busy cell processing method as described in the above embodiments.

[0014] According to an aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the electronic device is caused to implement the super-busy cell processing method as described in the above embodiments.

[0015] In the technical scheme of the embodiments of the present application:

[0016] On the one hand, by obtaining the first network service parameter group of the to-be-detected cell, and then performing clustering processing of the to-be-detected cell based on the first network service parameter group, and the first network service parameter group including a plurality of types of network service parameter values, the parameters in the clustering processing are more comprehensive, so that the cell type of the to-be-detected cell is more accurate and has higher adaptability.

[0017] In one aspect, if it is determined that the to-be-detected cell is of the super-busy cell type, a second network service parameter group of the super-busy cell is obtained, a traffic suppression value of the super-busy cell is calculated based on the second network service parameter group, and the traffic suppression value of the super-busy cell calculated based on the second network service parameter group is more accurate due to the multiple types of network service parameter values included in the second network service parameter group, thereby providing strong support for a maintenance personnel to determine whether the super-busy cell needs to be expanded immediately and to select an expansion scheme suitable for the super-busy cell based on the traffic suppression value, avoiding secondary expansion, and ensuring that resources are reasonably used. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application. It is to be expressly understood, however, that the drawings are included herein for illustrative purposes only and do not represent a limitation of the application. By turning to the drawings, in which like reference characters represent like parts throughout the several views, the exemplary embodiments of the present application will be described in detail.

[0019] Figure 1 is a flowchart of a super-busy cell processing method according to an example embodiment of the present application.

[0020] Figure 2 is a flowchart of a super-busy cell processing method according to another example embodiment of the present application.

[0021] Figure 3 is Figure 1 is a flowchart of step S120 in the example embodiment shown in FIG. 1.

[0022] Figure 4 is Figure 3 is a flowchart of step S320 in the example embodiment shown in FIG. 3.

[0023] Figure 5 is Figure 1 is a flowchart of step S140 in the example embodiment shown in FIG. 4.

[0024] Figure 6 is a block diagram of a super-busy cell processing apparatus according to an example embodiment of the present application.

[0025] Figure 7 is a structural schematic diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0026] Example implementations are now described with reference to the drawings. Example implementations can, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example implementations to those skilled in the art.

[0027] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the

[0028] The block diagrams in the drawings show only the functionality of the example implementations and do not imply any particular physical or architectural arrangement of the example implementations. For example, functions shown as discrete blocks in the example implementations can be implemented in one or more physical or logical blocks, and each block can be implemented in hardware, software, or a combination of hardware and software.

[0029] The flow diagrams depicted in the figures are merely exemplary and do not necessarily include all of the steps or operations, nor do they necessarily indicate the order in which the steps or operations can be performed. For example, some operations can be performed in parallel, some operations can be omitted, and some operations can be performed in a different order than depicted in the figures.

[0030] It should be noted that the term "a plurality" or "a plurality of" means two or more. The term "and / or" describes associated objects in association with the objects associated therewith, which means that there can be three cases, for example, A and / or B means that there are three cases of A alone, A and B, and B alone. The character " / " generally represents an "or" relationship between the associated objects before and after it.

[0031] In the related art, in the process of deploying a mobile data network, due to the needs of communication operators to reduce the cost of initial deployment of the mobile data network and quickly network, the network bearing service capability of the mobile data network in most areas is weak. As the user quantity increases and the user network demand improves, in places such as schools and shopping malls where people gather, the mobile data network often appears to be super busy, that is, users cannot obtain the required network service, which greatly disturbs the users and reduces the user's satisfaction with the mobile data network.

[0032] However, there are many factors inducing the super busy phenomenon, and some of the super busy phenomenon are caused by false super busy inducements such as incorrect base station parameter setting or abnormal interoperation, which affects the repair speed of the super busy phenomenon for maintenance personnel and causes waste of resources. Therefore, how to identify the area where the super busy phenomenon really occurs and how to ensure that resources are reasonably used become problems to be solved.

[0033] Therefore, the technical scheme of the embodiment of the present application proposes a super busy cell processing method, which is specifically described with reference to Figure 1 The method can be executed by a super busy cell processing device accessing a mobile data network, of course, it can also be executed by other devices in the mobile data network, which is not limited herein. The method at least includes steps S110 to S140, which are described in detail as follows:

[0034] In step S110, a first network service parameter group of a to-be-detected cell is acquired.

[0035] First of all, it needs to be pointed out that the mobile data network is based on the network base station deployed to provide network services for users, and the network base station has a certain coverage range. If the user leaves the coverage range of the current network base station, the network base station covering the current location of the user will be switched to, so as to obtain the network service provided by the mobile data network.

[0036] Among them, the to-be-detected cell is divided based on the coverage range of the mobile data network. The to-be-detected cell can be divided according to the range covered by a single network base station, or can be divided according to the range covered by a combination of multiple network base stations.

[0037] The first network service parameter group includes multiple types of network service parameter values. The network service parameter represents the network service situation of the current cell, for example, the number of users, peak traffic, PRB utilization rate, bandwidth, user data to be sent, service type, user rate expectation, BSR state, etc.

[0038] In addition, since there are many types of network service parameter values, in addition to forming the first network service parameter group by all types of network service parameter values, a part of types of network service parameter values with higher demand correlation can also be selected from all types of network service parameter values to form the first network service parameter group according to actual needs, so as to shorten the data processing time while meeting the needs.

[0039] For example, if the current demand is to determine whether the type of the cell is a super busy cell type, the network service parameter values with higher correlation to the demand can be selected, so that the number of users, peak traffic, PRB utilization rate, bandwidth, user data to be sent, service type and user rate expectation each correspond to the parameter values as the network service parameter values included in the first network service parameter group.

[0040] In the embodiments of the present application, in order to determine whether the cell is in the super busy phenomenon, a first network service parameter group of the cell to be detected can be acquired.

[0041] The manner of acquiring the first network service parameter group of the cell to be detected can be flexibly set according to actual needs. In an example, a corresponding detection device can be set in a single cell, so as to collect multiple types of network service parameter values of the cell in real time through the set detection device and upload feedback, thereby generating a corresponding first network service parameter group according to the multiple types of network service parameter values of the cell fed back by the detection device, and thus achieving the purpose of acquiring the first network service parameter group of the cell to be detected while reducing the influence on the existing network equipment by not processing the multiple network service parameter values through the existing network equipment.

[0042] In another example, the multiple types of network service parameter values of a single cell can be fed back in real time based on the existing network equipment of the cell, so as to generate a corresponding first network service parameter group according to the multiple network service parameter values of the cell fed back, thereby achieving the purpose of acquiring the first network service parameter group of the cell to be detected while reducing the implementation cost by not additionally arranging equipment to process the network service parameter values.

[0043] In step S120, clustering processing of the cell to be detected is performed based on the first network service parameter group, and a cell type of the cell to be detected is obtained.

[0044] In the embodiments of the present application, after the first network service parameter group of the cell to be detected is acquired, clustering processing of the cell to be detected can be performed based on the first network service parameter group, thereby obtaining the cell type of the cell to be detected.

[0045] The manner of performing clustering processing of the cell to be detected based on the first network service parameter group can be flexibly set according to actual needs. In an example, multiple types of network service parameter values corresponding to different cell types can be set in advance, and after the first network service parameter group of the cell to be detected is acquired, each network service parameter value in the first network service parameter group can be compared with each network service parameter value corresponding to different cell types, and a matching degree between each network service parameter value in the first network service parameter group and each network service parameter value corresponding to different cell types can be generated, thereby dividing the cell to be detected to the cell type with the highest matching degree to complete the clustering processing.

[0046] In another example, while acquiring the first network service parameter set of the to-be-detected cell, the first network service parameter set of the remaining cells is also acquired, and the to-be-detected cell and the remaining cells are clustered into the same cell type by comparing the first network service parameter sets of the to-be-detected cell and the remaining cells.

[0047] In addition, the mobile data network often faces occasional group traffic demand when providing the required network service for the user, which causes the user's demand for network service to increase sharply and temporarily. Therefore, in order to improve the accuracy of the clustering of the to-be-detected cell, in the embodiment of the present application, the abnormal network service parameter value in the first network service parameter set is removed to obtain the first network service parameter set after removal; and the clustering of the to-be-detected cell is performed based on the first network service parameter set after removal to obtain the cell type of the to-be-detected cell.

[0048] The abnormal network service parameter value represents the network service parameter value generated when the user's demand for network service increases sharply.

[0049] In step S130, if the to-be-detected cell is of the super-busy cell type, the second network service parameter set of the super-busy cell is acquired.

[0050] The second network service parameter set also includes a plurality of types of network service parameter values.

[0051] In the embodiment of the present application, after the clustering of the to-be-detected cell, it can be determined whether the to-be-detected cell is of the super-busy cell type, and if the to-be-detected cell is of the super-busy cell type, the second network service parameter set of the super-busy cell is acquired.

[0052] In addition, the composition of the second network service parameter set can refer to the composition of the first network service parameter set described in step S110, which will not be repeated here.

[0053] In step S140, the traffic suppression value of the super-busy cell is calculated based on the second network service parameter set.

[0054] It should be noted that the traffic suppression value represents the network service demand situation accumulated in the current cell.

[0055] In the embodiment of the present application, after the second network service parameter set is acquired, the traffic suppression value of the super-busy cell can be calculated based on the second network service parameter set to determine the network service demand situation accumulated in the super-busy cell, so that the maintenance personnel can check the traffic suppression value to determine the appropriate expansion scheme, thereby improving the maintenance expansion efficiency and avoiding secondary expansion.

[0056] In the process of calculating the traffic suppression value of the super busy cell based on the second network service parameter set, in order to reduce the influence of occasional mass traffic demand on the traffic suppression value, in the embodiments of the present application, the abnormal network service parameter values contained in the second network service parameter set can be removed to obtain a second network service parameter set after removal, and the traffic suppression value of the super busy cell is calculated based on the second network service parameter set after removal.

[0057] Through the above-mentioned embodiments, the first network service parameter set of the to-be-detected cell is clustered first according to the obtained first network service parameter set. Since each type of network service parameter value contained in the network service parameter set represents the current network service of the to-be-detected cell, the type adaptation degree of the to-be-detected cell after clustering is high, so that the cell type accuracy of the to-be-detected cell obtained after clustering is also high. After determining that the to-be-detected cell is a super busy cell, the traffic suppression value of the super busy cell is calculated according to the obtained second network service parameter set of the to-be-detected cell, so that the maintenance personnel can judge whether immediate expansion is needed and select an appropriate expansion scheme according to the traffic suppression value, avoid secondary expansion, and ensure that resources are reasonably used.

[0058] Referring to Figure 2 , Figure 2 is a super busy cell processing method according to another exemplary embodiment. As shown in Figure 2 , after step S140 in the embodiment shown in Figure 1 , the method can further include steps S210 to S230, which are described in detail as follows:

[0059] In step S210, the relationship between the traffic suppression value of the super busy cell and a plurality of preset traffic suppression intervals is detected to obtain a detection result.

[0060] In the embodiments of the present application, after the traffic suppression value of the super busy cell is calculated, the relationship between the traffic suppression value of the super busy cell and a plurality of preset traffic suppression intervals can be detected to obtain a detection result.

[0061] For example, the plurality of traffic suppression intervals include a first traffic suppression interval, a second traffic suppression interval and a third traffic suppression interval, wherein the first traffic suppression interval corresponds to a range of 100GB to 500GB, the second traffic suppression interval corresponds to a range of 500GB to 800GB, and the third traffic suppression interval corresponds to a range of 800GB or more. If the calculated traffic suppression value of the super busy cell is 520GB, in the process of detecting the relationship between the traffic suppression value of the super busy cell and the plurality of preset traffic suppression intervals, it is obvious that based on the traffic suppression value of the super busy cell, the super busy cell belongs to the second traffic suppression interval, and accordingly the detection result is that the super busy cell belongs to the second traffic suppression interval.

[0062] In step S220, a target capacity expansion strategy is determined based on the detection result.

[0063] It should be noted that the capacity expansion strategy refers to an implementation scheme for improving the network service carrying capacity of the super-busy cell, for example, implementation schemes such as newly building a base station, sharing a carrier for capacity expansion by a telecom operator, adjusting a beam, and the like.

[0064] Here, since the applicable range and implementation cost of different capacity expansion strategies are different, the capacity expansion strategies corresponding to different preset traffic suppression intervals are different.

[0065] In the embodiments of the present application, after obtaining the detection result, the target capacity expansion strategy can be determined based on the detection result.

[0066] The manner of determining the target capacity expansion strategy based on the detection result, in one example, can query the corresponding capacity expansion strategy in the preset database according to the preset traffic suppression interval to which the super-busy cell belongs in the detection result, and take the queried capacity expansion strategy as the target capacity expansion strategy, that is, the preset database stores the respective corresponding capacity expansion strategies of different preset traffic intervals.

[0067] In step S230, the super-busy cell is expanded based on the target capacity expansion strategy.

[0068] In the embodiments of the present application, after the target capacity expansion strategy is determined, the super-busy cell can be expanded based on the target capacity expansion strategy.

[0069] Referring to the above example, the capacity expansion strategy corresponding to the first traffic suppression interval is beam adjustment or replacement of aging equipment; the capacity expansion strategy corresponding to the second traffic suppression interval is sharing a carrier for capacity expansion by a telecom operator or sharing a double carrier; the capacity expansion strategy corresponding to the third traffic suppression interval is sharing an independent carrier or newly building a base station; since the traffic suppression value corresponding to the super-busy cell is 520 GB, after detection based on the traffic suppression value, the detection result is that the super-busy cell belongs to the second traffic suppression interval, so the capacity expansion strategy corresponding to the second traffic suppression interval is determined to be sharing a carrier for capacity expansion by a telecom operator or sharing a double carrier based on the detection result, the capacity expansion strategy corresponding to the second traffic suppression interval is taken as the target capacity expansion strategy of the super-busy cell, and then after the target capacity expansion strategy is determined, the scheme of sharing a carrier for capacity expansion by a telecom operator or the scheme of sharing a double carrier is implemented for the applicable range of the super-busy cell.

[0070] Referring to Figure 3 , Figure 3 is Figure 1 the flowchart of step S120 in the example embodiment. As Figure 3As shown, under the condition that the to-be-detected cells are multiple, the process of clustering the to-be-detected cells based on the first network service parameter set to obtain the cell type of the to-be-detected cells can include steps S310 to S320, which are described in detail as follows:

[0071] In step S310, an initial clustering center is determined based on the first network service parameter set of the multiple to-be-detected cells.

[0072] It should be noted that the clustering center represents a cell pool in the clustering process, and different cell pools correspond to different cell types.

[0073] In the embodiments of the present application, in order to divide the types of the to-be-detected cells, an initial clustering center can be determined based on the first network service parameter set of the multiple to-be-detected cells.

[0074] The way of determining the initial clustering center based on the first network service parameter set of the multiple to-be-detected cells can adopt a K-means (K-means) clustering algorithm or a FMC (Fuzzy c-means Algorithm) clustering algorithm.

[0075] If the K-means clustering algorithm is adopted, the first network service parameter set of any to-be-detected cell can be selected from the multiple to-be-detected cells as the initial clustering center;

[0076] If the FMC clustering algorithm is adopted, the first network service parameter set of any to-be-detected cell can be selected from the multiple to-be-detected cells, and then the first network service parameter set is calculated by the clustering center calculation formula corresponding to the FMC clustering algorithm to obtain the initial clustering center.

[0077] Considering that there may be occasional group large flow demand in the to-be-detected cells, a flow difference index is added in the process of calculating the clustering center corresponding to the first network service parameter set by the clustering center calculation formula, so as to improve the accuracy of the calculated value function value. The specific formula is as follows:

[0078]

[0079] wherein, e i is the i-th initial clustering center; E is the number of to-be-detected cells; u ik is the membership degree between the k-th to-be-detected cell and the i-th initial clustering center; is the flow difference index between the k-th to-be-detected cell and the i-th initial clustering center, and the greater the flow difference index value is, the greater the probability of the occurrence of the occasional group large flow demand of the k-th to-be-detected cell in the i-th initial clustering center is; d ikis the Euclidean distance between the kth to-be-detected cell and the ith initial clustering center; m is a fuzzy index, and m is usually 2; A k is the first network service parameter group of the kth to-be-detected cell.

[0080] Correspondingly, the calculation formula of d ik in the FMC clustering algorithm is as follows:

[0081]

[0082] wherein N is the number of initial clustering centers.

[0083] The calculation formula of d ij in the FMC clustering algorithm is as follows:

[0084] (d ij ) 2 =||A i -A j || 2 =(A i -A j ) T (A i -A j )

[0085] wherein A i represents the first network service parameter group corresponding to a to-be-detected cell; A j represents the first network service parameter group corresponding to another to-be-detected cell; d ij represents the Euclidean distance between A i and A j .

[0086] In step S320, the first network service parameters of the plurality of to-be-detected cells are iteratively clustered based on the initial clustering centers until the iteration clustering exit condition is met, and the cell types of the plurality of to-be-detected cells are obtained.

[0087] Since only the first network service parameter groups of the plurality of to-be-detected cells are classified by the initial clustering centers, the types of the cells obtained are more, which leads to low accuracy and long time consumption when the cell types of the to-be-detected cells are divided. Therefore, in the embodiments of the present application, after the initial clustering centers are determined, the first network service parameters of the plurality of to-be-detected cells can be iteratively clustered based on the initial clustering centers until the iteration clustering exit condition is met, and the cell types of the plurality of to-be-detected cells are obtained.

[0088] In the K-means clustering algorithm, the iterative clustering manner can be that, for each first network service parameter set of the to-be-detected cell, the distance between each first network service parameter set and the preselected plurality of initial clustering centers is calculated, each first network service parameter set is classified into the initial clustering center with the minimum distance, the center point classified into each initial clustering center is then calculated to update each initial clustering center, and the above steps are repeated for iterative clustering until the iterative clustering exit condition is met, which can be the number of iterations or the difference between adjacent two center points being less than a preset center point threshold.

[0089] In the FMC clustering algorithm, the iterative clustering manner can be that, for each first network service parameter set of the to-be-detected cell, the membership between each first network service parameter set and the preselected plurality of initial clustering centers is calculated, and the initial clustering centers are then recalculated based on the memberships, and the above steps are repeated for iterative clustering until the iterative clustering exit condition is met, which can be the number of iterations or the difference between the value function values of adjacent two initial clustering centers being less than a preset value function threshold by calculating the value function value of each round of initial clustering center.

[0090] Referring to Figure 4 , Figure 4 is Figure 3 the flowchart of step S320 in the embodiment shown. As Figure 4 shown, the process of performing iterative clustering on the first network service parameters of the plurality of to-be-detected cells based on the initial clustering centers until the iterative clustering exit condition is met to obtain the cell types of the plurality of to-be-detected cells can include steps S410 to S420, which are described in detail as follows:

[0091] In step S410, in each round of clustering process, the value function value corresponding to the current round of clustering center is calculated.

[0092] In the embodiments of the present application, in order to perform iterative clustering on the first network service parameters of the plurality of to-be-detected cells based on the initial clustering centers, the value function value corresponding to the current round of clustering center can be calculated in each round of clustering process.

[0093] Considering that there will be occasional group large traffic demand in the to-be-detected cells, the traffic difference index is also added in the process of calculating the value function value corresponding to the current round of clustering center to improve the accuracy of the calculated value function value.

[0094] For example, when the iterative clustering manner adopts the FMC clustering algorithm, the calculation formula of the value function can be improved as:

[0095]

[0096] wherein, N is the number of to-be-detected cells; e is the number of initial clustering centers; is the value of the value function; U is an array composed of the membership degrees between the N to-be-detected cells and the e initial clustering centers; E is an array composed of the e initial clustering centers; is an array composed of the traffic difference index values between the N to-be-detected cells and the e initial clustering centers.

[0097] In step S420, if the difference between the value function value corresponding to the current round of clustering centers and the value function value corresponding to the last round of clustering centers is less than the preset value function threshold, it is determined that the iteration clustering exit condition is met, and the cell types of the plurality of to-be-detected cells are obtained.

[0098] It should be noted that when the difference between the value function value corresponding to the current round of clustering centers and the value function value corresponding to the last round of clustering centers is too small, it means that the difference between the current round of clustering centers and the last round of clustering centers is small, and the current round of clustering centers has already reached the optimal solution, so there is no need to waste computing resources to continue iteration calculation.

[0099] In the embodiments of the present application, after the value function value corresponding to the current round of clustering centers is calculated, it can be determined whether the value function value corresponding to the current round of clustering centers is less than the preset value function threshold. If it is determined that the value function value corresponding to the current round of clustering centers is less than the preset value function threshold, it is determined that the iteration clustering exit condition is met, and the cell types of the plurality of to-be-detected cells are obtained.

[0100] In the FMC clustering algorithm, before comparing the value function value corresponding to the current round of clustering centers with the value function of the last round of clustering centers, the extreme value corresponding to the value function corresponding to each round of clustering centers needs to be obtained for comparison, and the minimum value is usually used to ensure the consistency of the data.

[0101] In addition, the algorithm for calculating the minimum value of the value function corresponding to each round of clustering centers can be the Lagrange multiplier method, and the specific calculation method can refer to the following formula:

[0102]

[0103] wherein, λ1, λ2 are Lagrange factors.

[0104] And the constraint condition in the above formula is:

[0105]

[0106]

[0107] In the embodiments of the present application, in order to facilitate the maintenance personnel to obtain the cell type of the to-be-detected cell based on the first network service parameter group of the to-be-detected cell; the super busy cell processing method further comprises: inputting the first network service parameter group into the super busy cell judgment model, so as to perform clustering processing on the to-be-detected cell based on the first network service parameter group by the super busy cell judgment model, and obtain the cell type of the to-be-detected cell.

[0108] That is, the above calculation process based on the first network service parameter group is integrated into the super busy cell judgment model, so that after the first network service parameter group is input into the super busy cell judgment model, the corresponding calculation process of clustering processing on the to-be-detected cell based on the first network service parameter group by the super busy cell judgment model is directly performed, and the obtained cell type of the to-be-detected cell is output.

[0109] Referring to Figure 5 , Figure 5 In the embodiment shown in Figure 1 The flowchart of step S140 in an exemplary embodiment. As Figure 4 shown, the process of calculating the traffic suppression value of the super busy cell based on the second network service parameter group can include steps S510 to S540, which are described in detail as follows:

[0110] In step S510, the abnormal traffic value corresponding to the super busy cell is obtained.

[0111] It should be noted that the abnormal traffic value represents the traffic value generated when occasional group large traffic demand occurs.

[0112] In the embodiments of the present application, in the process of calculating the traffic suppression value of the super busy cell, the abnormal traffic value corresponding to the super busy cell can be obtained first.

[0113] Among them, in an example, the network traffic value of each period of the user can be obtained first, and then the average traffic value is calculated based on the network traffic value of each period. If the difference between the network traffic value of any period and the average traffic value is higher than the preset traffic difference value, the network traffic value of the period is obtained as the abnormal traffic value.

[0114] In step S520, the weight set of the second network service parameter group is calculated based on the abnormal traffic value and the second network service parameter group.

[0115] Among them, the weight set of the second network service parameter group is the influence weight of each type of network service parameter included in the second network service parameter group on the traffic suppression value.

[0116] In the embodiments of the present application, after the abnormal traffic value is obtained, the weight set of the second network service parameter set can be calculated based on the abnormal traffic value and the second network service parameter set.

[0117] The manner of calculating the weight set of the second network service parameter set can adopt a multiple linear regression algorithm.

[0118] In the multiple linear regression algorithm, a traffic suppression restoration expression corresponding to each super busy cell needs to be established, which is specifically as follows:

[0119] Y = a0 + a1X1 + a2X2 + … + a n X n + β

[0120] Wherein, a0-a n is the weight set corresponding to each network service parameter value in the second network service parameter set; X1-X n is each network service parameter value in the second network service parameter set of the super busy cell; β is the abnormal traffic value; and Y is the predicted traffic suppression value of the super busy cell.

[0121] Since the predicted traffic suppression value corresponding to each super busy cell, each network service parameter value in the second network service parameter set, and the abnormal traffic value are all different, the weight set calculated based on each network service parameter value in each second network service parameter set is also different.

[0122] Therefore, the least square method is adopted to determine the optimal weight value, and the specific formula is as follows:

[0123]

[0124] Wherein, N is the number of super busy cells; Q(a0 ` ,a1 ` ,a2 ` ,...,a n ` ) is the optimal weight value in each super busy cell; Y i is the predicted traffic suppression value of the i-th super busy cell; X i1 -X in is each network service parameter value in the second network service parameter set of the i-th super busy cell.

[0125] In step S530, the actual traffic suppression value of the super busy cell is calculated based on the weight set and the second network service parameter set.

[0126] In the embodiments of the present application, after the weight set of the second network service parameter set is calculated, the actual traffic suppression value of the super busy cell can be calculated again based on the weight set and the second network service parameter set, so as to obtain the actual traffic suppression value of the super busy cell.

[0127] In the embodiments of the present application, in order to facilitate the maintenance personnel to obtain the traffic suppression value of the super busy cell based on the second network service parameter set of the super busy cell; the super busy cell processing method further comprises: inputting the second network service parameter set into the super busy cell traffic suppression value restoration model, so as to calculate the traffic suppression value of the super busy cell based on the second network service parameter set through the super busy cell traffic suppression value restoration model.

[0128] That is, the above calculation process based on the second network service parameter set is integrated into the super busy cell traffic suppression value restoration model, so that after the second network service parameter set is input into the super busy cell traffic suppression value restoration model, the process of calculating the traffic suppression value of the super busy cell based on the second network service parameter set through the super busy cell traffic suppression value restoration model is achieved, and the purpose of outputting the calculated traffic suppression value of the super busy cell is achieved.

[0129] Through the above-mentioned embodiments, considering that the actual traffic value generated when the super busy cell appears occasional group large traffic demand will have a large deviation, the abnormal traffic value is obtained before calculating the actual traffic suppression value of the super busy cell, and the abnormal traffic value is added to the calculation process of calculating the actual traffic suppression value of the super busy cell, so as to avoid the deviation of the actual traffic suppression value of the super busy cell caused by occasional group large traffic demand.

[0130] The device embodiments of the present application are introduced below, which can be used to execute the super busy cell processing method in the above-mentioned embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the above-mentioned embodiments of the super busy cell processing method of the present application.

[0131] Figure 6 A block diagram of a super busy cell processing device 600 according to an embodiment of the present application is shown.

[0132] Referring to Figure 6 As shown in the figure, the super busy cell processing device 600 according to an embodiment of the present application comprises: an acquisition module 610 configured to acquire a first network service parameter set of a to-be-detected cell, the first network service parameter set comprising multiple types of network service parameter values; a clustering module 620 configured to perform clustering processing on the to-be-detected cell based on the first network service parameter set, to obtain a cell type of the to-be-detected cell; an identification module 630 configured to, if the to-be-detected cell is of a super busy cell type, acquire a second network service parameter set of the super busy cell, the second network service parameter set comprising multiple types of network service parameter values; and a processing module 640 configured to calculate a traffic suppression value of the super busy cell based on the second network service parameter set.

[0133] In some embodiments of the present application, based on the foregoing scheme, the processing module 640 is further configured to: after calculating the traffic suppression value of the super-busy cell based on the second network service parameter group, detect the relationship between the traffic suppression value of the super-busy cell and a plurality of preset traffic suppression intervals to obtain a detection result; determine a target expansion strategy based on the detection result; wherein different preset traffic suppression intervals correspond to different expansion strategies; and expand the super-busy cell based on the target expansion strategy.

[0134] In some embodiments of the present application, based on the foregoing scheme, the clustering module 620 is further configured to: perform elimination processing on the abnormal network service parameter values contained in the first network service parameter group to obtain an eliminated first network service parameter group; and perform clustering processing on the to-be-detected cell based on the eliminated first network service parameter group to obtain the cell type of the to-be-detected cell; and the processing module 640 is further configured to: perform elimination processing on the abnormal network service parameter values contained in the second network service parameter group to obtain an eliminated second network service parameter group; and calculate the traffic suppression value of the super-busy cell based on the eliminated second network service parameter group.

[0135] In some embodiments of the present application, based on the foregoing scheme, under the condition that the to-be-detected cell is a plurality of cells, the clustering module 620 is further configured to: determine an initial clustering center based on the first network service parameter groups of the plurality of to-be-detected cells; and perform iterative clustering on the first network service parameters of the plurality of to-be-detected cells based on the initial clustering center until the iterative clustering exit condition is met to obtain the cell types of the plurality of to-be-detected cells.

[0136] In some embodiments of the present application, based on the foregoing scheme, the clustering module 620 is further configured to: in each round of clustering process, calculate a value function value corresponding to the current round clustering center; and if the difference between the value function value corresponding to the current round clustering center and the value function value corresponding to the last round clustering center is less than a preset value function threshold, it is determined that the iterative clustering exit condition is met, and the cell types of the plurality of to-be-detected cells are obtained.

[0137] In some embodiments of the present application, based on the foregoing scheme, the processing module 640 is further configured to: obtain an abnormal traffic value corresponding to the super-busy cell; calculate a weight group of the second network service parameter group based on the abnormal traffic value and the second network service parameter group; and calculate the actual traffic suppression value of the super-busy cell based on the weight group and the second network service parameter group.

[0138] In some embodiments of the present application, based on the foregoing scheme, the clustering module 620 is further configured to: input the first network service parameter group into the super busy cell judgment model, so as to perform clustering processing on the to-be-detected cell based on the first network service parameter group through the super busy cell judgment model, and obtain the cell type of the to-be-detected cell; and the processing module 640 is further configured to: input the second network service parameter group into the super busy cell traffic suppression value restoration model, so as to calculate the traffic suppression value of the super busy cell based on the second network service parameter group through the super busy cell traffic suppression value restoration model.

[0139] It should be noted that the super busy cell processing apparatus 600 provided by the above embodiments and the super busy cell processing method provided by the above embodiments belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiments, and will not be described here.

[0140] Figure 7 A structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown.

[0141] It should be noted that, Figure 7 The computer system 700 of the electronic device shown is only an example, and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0142] As Figure 7 shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 702 or programs loaded from a storage portion 708 into a random access memory (RAM) 703, such as performing the methods described in the above embodiments. In the RAM 703, various programs and data required for system operation are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0143] The following components are connected to the I / O interface 705: an input part 706 including a keyboard, a mouse, etc.; an output part 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage part 708 including a hard disk, etc.; and a communication part 709 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part 707 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as necessary. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read out therefrom is installed in the storage part 708 as necessary.

[0144] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, various functions defined in the system of the present application are executed.

[0145] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus or device. In this application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable computer programs. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, transmit, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. The computer programs contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination thereof.

[0146] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In the flowcharts or block diagrams, each block can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] The units described in the embodiments of the present application can be implemented by software, or by hardware, or by a combination of software and hardware. The units described can also be located in a single processor. In some cases, the names of the units do not limit the units themselves.

[0148] As another aspect, the present application provides a computer readable medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the method described in the above embodiments.

[0149] It should be noted that although several modules or units for performing actions are mentioned in the above detailed description, the division into the modules or units is not mandatory. In fact, according to the embodiments of the present application, features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, features and functions of one module or unit described above can be further divided into a plurality of modules or units.

[0150] From the above description of the embodiments, those skilled in the art will readily appreciate that the example embodiments described herein can be implemented by software and / or by hardware coupled with software. Accordingly, the technical solutions of the embodiments of the present application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, or the like) or on a network, and includes a number of instructions for causing a computing device (which can be a personal computer, a server, a terminal, or a network device, etc.) to perform the methods according to the embodiments of the present application.

[0151] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such

[0152] It should be understood that the present application is not limited to the precise construction that has been described above and illustrated in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present application. The scope of the present application is limited only by the appended claims.

Claims

1. A method for handling an ultra-busy cell, the method comprising: The method comprises: acquiring a first network service parameter group of a to-be-detected cell, the first network service parameter group comprising network service parameter values of multiple types; performing clustering processing on the to-be-detected cell based on the first network service parameter group to obtain a cell type of the to-be-detected cell; if the to-be-detected cell is of an ultra-busy cell type, acquiring a second network service parameter group of the ultra-busy cell, the second network service parameter group comprising network service parameter values of multiple types; calculating a traffic suppression value of the ultra-busy cell based on the second network service parameter group; wherein the to-be-detected cell is multiple; the clustering processing on the to-be-detected cell based on the first network service parameter group to obtain the cell type of the to-be-detected cell comprises: determining an initial clustering center based on the first network service parameter groups of the multiple to-be-detected cells; in each round of clustering process, calculating a value function value corresponding to the current round of clustering center; if the difference between the value function value corresponding to the current round of clustering center and the value function value corresponding to the last round of clustering center is less than a preset value function threshold, it is determined that the iteration clustering exit condition is met, and the cell type of the multiple to-be-detected cells is obtained; wherein determining the initial clustering center based on the first network service parameter groups of the multiple to-be-detected cells comprises: selecting the first network service parameter group of any to-be-detected cell from the multiple to-be-detected cells, and then expanding the calculation of the first network service parameter group through the clustering center calculation formula corresponding to the fuzzy C-means clustering algorithm to obtain the initial clustering center; the initial clustering center is calculated by the following formula: wherein e i is the ith initial clustering center; E is the number of to-be-detected cells; u ik is the membership between the kth to-be-detected cell and the ith initial clustering center; is the traffic difference index between the kth to-be-detected cell and the ith initial clustering center, and the greater the traffic difference index value is, the greater the probability that the kth to-be-detected cell has a sporadic group of large traffic demand in the ith initial clustering center is; d i′ k is the Euclidean distance between the kth to-be-detected cell and the ith initial clustering center; m is a fuzzy index, and m is 2; A k is the first network service parameter group of the kth to-be-detected cell.

2. The method of claim 1, wherein, after the calculation of the traffic suppression value of the ultra-busy cell based on the second network service parameter group, the method further comprises: detecting the relationship between the traffic suppression value of the ultra-busy cell and multiple preset traffic suppression intervals to obtain a detection result; determining a target expansion strategy based on the detection result; wherein the expansion strategies corresponding to different preset traffic suppression intervals are different; expanding the ultra-busy cell based on the target expansion strategy.

3. The method of claim 1, wherein, The clustering processing on the to-be-detected cell based on the first network service parameter group to obtain the cell type of the to-be-detected cell comprises: performing elimination processing on abnormal network service parameter values contained in the first network service parameter group to obtain an eliminated first network service parameter group; performing clustering processing on the to-be-detected cell based on the eliminated first network service parameter group to obtain the cell type of the to-be-detected cell; The calculation of the traffic suppression value of the ultra-busy cell based on the second network service parameter group comprises: performing elimination processing on abnormal network service parameter values contained in the second network service parameter group to obtain an eliminated second network service parameter group; calculating the traffic suppression value of the ultra-busy cell based on the eliminated second network service parameter group.

4. The method of claim 1, wherein, The calculation of the traffic suppression value of the ultra-busy cell based on the second network service parameter group comprises: acquiring an abnormal traffic value corresponding to the ultra-busy cell; Based on the abnormal traffic value and the second network service parameter group, a weight group of the second network service parameter group is calculated; Based on the weight group and the second network service parameter group, an actual traffic suppression value of the super busy cell is calculated.

5. An apparatus for handling an ultra-busy cell, the apparatus comprising: Comprising: An acquisition module configured to acquire a first network service parameter group of a to-be-detected cell, the first network service parameter group comprising a plurality of types of network service parameter values; A clustering module configured to perform clustering processing on the to-be-detected cell based on the first network service parameter group to obtain a cell type of the to-be-detected cell; An identification module configured to, if the to-be-detected cell is a super busy cell type, acquire a second network service parameter group of the super busy cell; A processing module configured to calculate a traffic suppression value of the super busy cell based on the second network service parameter group; Wherein, the to-be-detected cell is a plurality of; the clustering module is further configured to perform clustering processing on the to-be-detected cell based on the first network service parameter group to obtain a cell type of the to-be-detected cell, comprising: determining an initial clustering center based on the first network service parameter group of the plurality of to-be-detected cells; in each round of clustering process, calculating a value function value corresponding to the current round clustering center; if the difference between the value function value corresponding to the current round clustering center and the value function value corresponding to the last round clustering center is less than a preset value function threshold, it is determined that the iteration clustering exit condition is met, and the cell type of the plurality of to-be-detected cells is obtained; wherein, determining the initial clustering center based on the first network service parameter group of the plurality of to-be-detected cells comprises: selecting the first network service parameter group of any to-be-detected cell from the plurality of to-be-detected cells, and then expanding the calculation of the first network service parameter group through the clustering center calculation formula corresponding to the fuzzy C-means clustering algorithm to obtain the initial clustering center; the initial clustering center is calculated by the following formula: wherein e i is the ith initial clustering center; E is the number of to-be-detected cells; u ik is the membership between the kth to-be-detected cell and the ith initial clustering center; is the traffic difference index between the kth to-be-detected cell and the ith initial clustering center, and the greater the traffic difference index value is, the greater the probability that the kth to-be-detected cell is a group of large traffic demand that occurs sporadically in the ith initial clustering center is; d i′ k is the Euclidean distance between the kth to-be-detected cell and the ith initial clustering center; m is a fuzzy index, and m is 2; A k is the first network service parameter group of the kth to-be-detected cell.

6. A storage medium, characterized by It has computer readable instructions stored thereon, when the computer readable instructions are executed by the processor of the computer, the computer executes the super busy cell processing method in any one of claims 1 to 4.

7. An electronic device, comprising: Comprising: One or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements the super busy cell processing method as claimed in any one of claims 1 to 4.

Images