A cell parameter configuration method, device and network side equipment

Abstract

The present invention provides a method, device and network-side equipment for configuring cell parameters, which solve the problems of the existing method for configuring cell parameters, which has high classification complexity and insufficient interpretability of clustering results. The method of the present invention comprises: after obtaining the initial configuration information of the first parameter for the target cell, obtaining the first classification result of the first parameter of the target cell and the relevant information of the first parameters of M cells of the same category as the first classification result; determining the configuration information of the first parameters of N cells according to the first classification result and the relevant information of the first parameters of the M cells; and determining the final configuration information of the first parameters of the target cell. The present invention can realize the differentiated configuration of cell parameters, reduce the complexity of classification, and make the coupling between the classification results and the corresponding parameters higher, thereby improving the interpretability of the classification results.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a cell parameter configuration method, device and network side equipment. Background Art

[0002] Existing wireless networks involve a lot of wireless parameter configuration (including initial configuration, configuration update / modification) in network maintenance, optimization and other management work. A considerable number of these parameters are cell-level parameters, which support differentiated configuration at the cell-level granularity, so that parameter configuration can better match the coverage scenarios, networking methods, service types and other characteristics of different cells, thereby optimizing the cell network and service performance as much as possible and improving user experience.

[0003] However, the existing configuration of cell parameters often involves classifying cells based on the multi-dimensional features of all cell parameters, which will cause the feature dimension to be too high, thereby causing the problem of high complexity of dimensionality reduction and clustering algorithms; in addition, when a new configuration parameter type is added, all multi-dimensional features need to be re-combined, reduced in dimension, and clustered, which will trigger a series of subsequent adaptation and adjustment work, resulting in poor flexibility of the solution; and because various types of features are input at the same time, the clustering results will be very complex, reducing the interpretability of the clustering results. Summary of the invention

[0004] The purpose of the present invention is to provide a cell parameter configuration method, device and network side equipment, which are used to solve the problems of high classification complexity and insufficient interpretability of clustering results in the existing cell parameter configuration method.

[0005] In order to achieve the above object, the present invention provides a cell parameter configuration method, comprising:

[0006] After obtaining initial configuration information of the first parameter for the target cell, obtaining a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer;

[0007] Determine, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of N cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer;

[0008] Final configuration information of the first parameter of the target cell is determined, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells.

[0009] The obtaining of the first classification result of the first parameter of the target cell and the related information of the first parameters of M cells of the same category as the first classification result include:

[0010] In a case where it is determined that the classification information of the parameters of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, obtaining, according to the classification information stored in the storage unit, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result;

[0011] In a case where it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the target cell is a newly built cell, based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, classify the first parameter of the target cell to obtain a first classification result of the first parameter of the target cell, and obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells;

[0012] When it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the first parameter is a newly added parameter, the configuration information of the first parameter of the target cell and other parameters related to the first parameter is used as a first input feature, the first parameter of the target cell is clustered to obtain a first classification result of the first parameter of the target cell, and relevant information of the first parameters of M cells with the same category as in the first classification result is obtained from the classification information of each parameter of each cell in all the cells.

[0013] The first classification result and / or the relevant information of the first parameter of the M cells include a plurality of key performance indicators associated with the first parameter;

[0014] The determining, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of the N cells includes:

[0015] Sorting the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determining the top N cells;

[0016] Obtain configuration information of the first parameter of the N cells.

[0017] The determining of the final configuration information of the first parameter of the target cell includes:

[0018] In a case where the initial configuration information is within a configuration range corresponding to the configuration information of the first parameter of the N cells, using the initial configuration information as the final configuration information;

[0019] When the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameters of the N cells, the final configuration information of the first parameter of the target cell is determined according to the configuration information of the first parameters of the N cells and according to a preset rule.

[0020] The preset rule includes one of the following:

[0021] Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information;

[0022] Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal;

[0023] The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

[0024] Wherein, the method further comprises:

[0025] For each parameter of each cell in all cells, clustering is performed respectively with configuration information of each parameter and other parameters related to the parameter as input features, and classification results corresponding to each parameter are obtained and stored in the storage unit as classification information.

[0026] The present invention also provides a cell parameter configuration device, comprising:

[0027] an acquisition module, configured to, after acquiring initial configuration information of a first parameter for a target cell, acquire a first classification result of the first parameter of the target cell and related information of first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer;

[0028] A first processing module, configured to determine configuration information of the first parameters of N cells according to the first classification result and relevant information of the first parameters of the M cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer;

[0029] The second processing module is used to determine final configuration information of the first parameter of the target cell, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells.

[0030] The present invention also provides a network side device, comprising a processor and a transceiver, wherein the transceiver receives and sends data under the control of the processor, and the processor is used to perform the following operations:

[0031] After obtaining initial configuration information of the first parameter for the target cell, obtaining a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer;

[0032] Determine, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of N cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer;

[0033] Final configuration information of the first parameter of the target cell is determined, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells.

[0034] Wherein, the processor is further used for:

[0035] In a case where it is determined that the classification information of the parameters of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, obtaining, according to the classification information stored in the storage unit, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result;

[0036] In a case where it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the target cell is a newly built cell, based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, classify the first parameter of the target cell to obtain a first classification result of the first parameter of the target cell, and obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells;

[0037] When it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the first parameter is a newly added parameter, the configuration information of the first parameter of the target cell and other parameters related to the first parameter is used as a first input feature, the first parameter of the target cell is clustered to obtain a first classification result of the first parameter of the target cell, and relevant information of the first parameters of M cells with the same category as in the first classification result is obtained from the classification information of each parameter of each cell in all the cells.

[0038] The first classification result and / or the related information of the first parameter of the M cells include a plurality of key performance indicators associated with the first parameter; and the processor is further configured to:

[0039] Sorting the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determining the top N cells;

[0040] Obtain configuration information of the first parameter of the N cells.

[0041] Wherein, the processor is further used for:

[0042] In a case where the initial configuration information is within a configuration range corresponding to the configuration information of the first parameter of the N cells, using the initial configuration information as the final configuration information;

[0043] When the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameters of the N cells, the final configuration information of the first parameter of the target cell is determined according to the configuration information of the first parameters of the N cells and according to a preset rule.

[0044] The preset rule includes one of the following:

[0045] Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information;

[0046] Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal;

[0047] The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

[0048] Wherein, the processor is further used for:

[0049] For each parameter of each cell in all cells, clustering is performed respectively with configuration information of each parameter and other parameters related to the parameter as input features, and classification results corresponding to each parameter are obtained and stored in the storage unit as classification information.

[0050] The present invention also provides a network side device, comprising a memory, a processor and a program stored in the memory and executable on the processor; when the processor executes the program, the cell parameter configuration method as described above is implemented.

[0051] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the cell parameter configuration method as described above are implemented.

[0052] The above technical solution of the present invention has at least the following beneficial effects:

[0053] In an embodiment of the present invention, after obtaining initial configuration information of a first parameter for a target cell, a first classification result of the first parameter of the target cell and relevant information of the first parameters of M cells of the same category as in the first classification result are obtained, where M≥1, and M is a positive integer; according to the first classification result and relevant information of the first parameters of the M cells, configuration information of the first parameters of N cells is determined, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer; final configuration information of the first parameter of the target cell is determined, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells. In this way, the classification result obtained based on the low-dimensional features of the cell parameters in this dimension and relevant information of the parameters of other cells of the same category in the classification result can realize differentiated configuration of the cell parameters, reduce classification complexity, make the classification results more highly coupled with the corresponding parameters, and improve the interpretability of the classification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram showing a flow chart of a method for configuring cell parameters according to an embodiment of the present invention;

[0055] Figure 2 A schematic diagram showing a module of a cell parameter configuration device according to an embodiment of the present invention;

[0056] Figure 3 A schematic diagram showing the structure of a network side device according to an embodiment of the present invention;

[0057] Figure 4 A schematic diagram showing the results of the network management system according to an embodiment of the present invention;

[0058] Figure 5The second flowchart of the method for configuring cell parameters according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0060] The present invention aims at solving the problems of high classification complexity and insufficient interpretability of clustering results in existing cell parameter configuration methods, and provides a cell parameter configuration method, device and network side equipment.

[0061] In order to enable those skilled in the art to better understand the method of the embodiment of the present invention, the following description is first made.

[0062] When the maintenance and optimization of the existing network is actually carried out, it is difficult to perform fine-grained parameter configuration at the cell level in many scenarios due to factors such as limited manpower input and time requirements.

[0063] When using network automation / intelligent technologies such as Self-Organizing Network (SON) or network planning and optimization auxiliary tools, the automated differentiated configuration of cell parameters can be achieved to a certain extent. However, considering the complexity of the algorithm, it is usually only possible to classify the basic characteristics of the cells at a coarse granularity and give parameter configuration suggestions or ranges based on expert experience. On the other hand, in order to realize the automated differentiated configuration of cell parameters, the above-mentioned technologies or tools often need to introduce manual configuration requirements for new cell-level parameters such as strategy parameters and threshold parameters when applied, which increases manual input and limits their application effect.

[0064] With the development of artificial intelligence and machine learning technologies, the industry has also begun to apply them to the feature classification of wireless networks to support differentiated optimization configuration of wireless network parameters. However, the existing classification of cells is often based on the multi-dimensional features of all cell parameters, which will cause the feature dimension to be too high, thus causing the problem of high complexity of dimensionality reduction and clustering algorithms; in addition, when a new configuration parameter type is added, all multi-dimensional features need to be recombined, reduced, and clustered, which will trigger a series of subsequent adaptation and adjustment work, resulting in poor solution flexibility; and because various types of features are input at the same time, the clustering results will be very complex, reducing the interpretability of the clustering results.

[0065] Based on this, Figure 1 As shown, the cell parameter configuration method provided by the embodiment of the present invention is applied to a network side device, and the method may include:

[0066] Step 101, after obtaining initial configuration information of a first parameter for a target cell, obtaining a first classification result of the first parameter of the target cell and related information of first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer;

[0067] In this step, initial configuration information for the first parameter of the target cell may be obtained by receiving a configuration operation or configuration command of the user on the first parameter of the target cell. Here, the user specifically refers to an operation and maintenance personnel.

[0068] It should be noted that the parameters mentioned in this embodiment are numerical parameters, that is, the parameter value can be a real number, a continuous value, a discrete value or an enumeration value. Non-numerical parameters such as Boolean type and string are not considered in this embodiment.

[0069] Here, the target cell and the first parameter form a tuple, i.e., <target cell, first parameter>. The first classification result corresponding to the tuple is a classification result obtained after clustering based on the low-dimensional features on the parameter dimension (rather than all multidimensional features of all parameters).

[0070] The relevant information of the first parameter of the M cells of the same category as the first classification result, i.e., belonging to the same category, includes but is not limited to: the cell identifiers of the M cells, the configuration value of the first parameter, the key performance indicator K associated with the first parameter, and other data. It should be noted that there may be more than one M cells and indicator K.

[0071] Step 102: determining configuration information of the first parameters of N cells according to the first classification result and the related information of the first parameters of the M cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer;

[0072] In this step, the first classification result of the first parameter of the target cell and the related information of the first parameters of the M cells include the configuration information of the first parameter. Based on this, the configuration information of the first parameters of the N cells is determined according to the predetermined screening rules. The purpose is to provide a reference for determining the final configuration information of the first parameter of the target cell in the subsequent steps.

[0073] Step 103: determine final configuration information of the first parameter of the target cell, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells.

[0074] The cell parameter configuration method of an embodiment of the present invention obtains the first classification result of the first parameter of the target cell and the relevant information of the first parameters of M cells of the same category as the first classification result after obtaining the initial configuration information of the first parameter for the target cell, M≥1, and M is a positive integer; according to the first classification result and the relevant information of the first parameters of the M cells, the configuration information of the first parameters of N cells is determined, and the N cells are N cells among M+1 cells including M cells and the target cell, 1≤N≤M+1, and N is a positive integer; the final configuration information of the first parameter of the target cell is determined, and the final configuration information is one of the N+1 configuration information including the initial configuration information and the configuration information of the first parameters of the N cells. In this way, the classification result obtained based on the low-dimensional features of the cell parameters on this dimension and the relevant information of the parameters of other cells of the same category in the classification result can realize the differentiated configuration of the cell parameters, reduce the complexity of classification, and the coupling of the classification results with the corresponding parameters is higher, thereby improving the interpretability of the classification results.

[0075] As an optional implementation, step 101 of the embodiment of the present invention may specifically include:

[0076] In a case where it is determined that the classification information of the parameters of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, obtaining, according to the classification information stored in the storage unit, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result;

[0077] It should be noted that all cells specifically refer to all cells managed by the network side device.

[0078] Here, the classification information of each parameter of each cell in all cells is stored in the storage unit in an index cluster in the form of a <cell, parameter> tuple.

[0079] Specifically, the corresponding classification information can be queried in the storage unit through the index determined by the <target cell, first parameter> tuple.

[0080] This scenario directly uses the pre-stored classification information of each parameter of each cell in all cells to obtain the first classification result of the first parameter of the target cell and the relevant information of the first parameters of M cells of the same category as the first classification result. It is fast and convenient and can improve the efficiency of cell parameter configuration.

[0081] In a case where it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the target cell is a newly built cell, based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, classify the first parameter of the target cell to obtain a first classification result of the first parameter of the target cell, and obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells;

[0082] Here, optionally, the preset classification algorithm is a K-Nearest Neighbor classification (KNN) algorithm.

[0083] That is, when the target cell is a newly built cell, the first parameter of the target cell can be classified based on a preset classification algorithm using the existing classification information of the first parameter of other cells to obtain a first classification result corresponding to the first parameter of the target cell.

[0084] When it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the first parameter is a newly added parameter, the configuration information of the first parameter of the target cell and other parameters related to the first parameter is used as a first input feature, the first parameter of the target cell is clustered to obtain a first classification result of the first parameter of the target cell, and relevant information of the first parameters of M cells with the same category as in the first classification result is obtained from the classification information of each parameter of each cell in all the cells.

[0085] In this scenario, the first parameter is a newly added parameter, which means that the classification information of the parameters of each cell in all pre-stored cells does not include the classification information of the first parameter. At this time, only low-dimensional feature clustering of the newly added parameters and their associated parameters is required. There is no need to re-cluster all the parameters, and no subsequent series of adaptation and adjustment work is required, which can improve the flexibility of the solution.

[0086] As an optional implementation manner, the first classification result and / or the relevant information of the first parameters of the M cells include multiple key performance indicators associated with the first parameters; accordingly, in step 102 of the method of the embodiment of the present invention, determining the configuration information of the first parameters of the N cells according to the first classification result and the relevant information of the first parameters of the M cells may include:

[0087] Sorting the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determining the top N cells;

[0088] Specifically, the M+1 cells may be ranked from best to worst according to the multiple key performance indicators, or the M+1 cells may be ranked from best to worst according to weighted results of the multiple key performance indicators.

[0089] Here, the minimum value of the key performance indicator associated with the first parameter in the N cells is greater than a preset performance indicator threshold.

[0090] Obtain configuration information of the first parameter of the N cells.

[0091] Here, the configuration information of the first parameters of the N cells may be obtained from the classification information of the first parameters of the M+1 cells.

[0092] In one example, when determining the configuration value of the Cell Individual Offset (CIO) parameter for cell A, the <cell A, CIO parameter> tuple is used to query other similar cells {Q1, Q2, ..., Qm} of cell A from the <cell, CIO parameter> classification result in the storage unit, as well as {K_switching success rate 1, K_switching success rate 2, ..., K_switching success rate m} (KPI indicators associated with the CIO configuration parameters) of each cell, and then {K_switching success rate} is sorted from high to low, the TopN (i.e., the top N) cells are selected, and the CIO configuration values ​​{CIO_Top1, CIO_Top2, ..., CIO_TopN} corresponding to the TopN cells are obtained.

[0093] As an optional implementation, step 103 of the method in the embodiment of the present invention determines the final configuration information of the first parameter of the target cell, which may include:

[0094] In a case where the initial configuration information is within a configuration range corresponding to the configuration information of the first parameter of the N cells, using the initial configuration information as the final configuration information;

[0095] Here, the initial configuration information is within the configuration range corresponding to the configuration information of the first parameter of the N cells, indicating that the initial configuration information issued by the operation and maintenance personnel can meet the cell performance requirements.

[0096] When the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameters of the N cells, the final configuration information of the first parameter of the target cell is determined according to the configuration information of the first parameters of the N cells and according to a preset rule.

[0097] Here, the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameter of the N cells, that is, the initial configuration information is outside the configuration range corresponding to the configuration information of the first parameter of the N cells, indicating that the initial configuration information issued by the operation and maintenance personnel cannot meet the cell performance requirements.

[0098] It should be noted that since the cell performance represented by the key performance indicators associated with the first parameter in the N cells is better, determining one of the configuration information of the first parameters of the N cells as the final configuration information of the first parameter of the target cell can meet the cell performance requirements.

[0099] Optionally, the preset rule includes one of the following:

[0100] Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information;

[0101] Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal;

[0102] The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

[0103] The cell parameter configuration method of the embodiment of the present invention can effectively improve the refinement level of cell-level parameters in the existing network configuration and reduce manual input as much as possible.

[0104] Optionally, according to a preset rule, the step of determining final configuration information of the first parameter of the target cell may include:

[0105] Using the intermediate configuration information of the first parameter of the target cell determined according to a preset rule, the initial configuration information and the preset configuration information as candidate configuration information;

[0106] Based on a selection operation of a user, final configuration information of the first parameter of the target cell is determined from the candidate configuration information.

[0107] It should be noted that the implementation of step 101 of the embodiment of the present invention is based on the classification information of each parameter of each cell in all cells pre-stored in the storage unit, and how to obtain this classification information can be implemented in the following manner. Specifically, as an optional implementation manner, the method of the embodiment of the present invention may also include:

[0108] For each parameter of each cell in all cells, clustering is performed respectively with configuration information of each parameter and other parameters related to the parameter as input features, and classification results corresponding to each parameter are obtained and stored in the storage unit as classification information.

[0109] Here, specifically, for each parameter of each cell in all cells, the configuration information of each parameter and other parameters related to the parameter is used as input features, and clustering is performed separately according to a preset clustering algorithm to obtain the classification results corresponding to each parameter and store them in a storage unit as classification information.

[0110] It should be noted that according to the configuration information of the full parameters of all cells stored in the storage unit, clustering is performed according to the dimension of the parameters, that is, based on the configuration information of each parameter and other corresponding related parameters, to obtain the classification results, that is, the classification results of parameter clustering are layered or clustered; then, the classification results corresponding to each parameter are clustered and stored in the storage unit according to <cell, parameter> as the index.

[0111] Here, the input features of the clustering process include, but are not limited to, parameters and configuration information of other parameters related to the parameters, for example, cell public information, etc.

[0112] For example, in the work of wireless network handover performance optimization, the CIO parameter configuration of the cell is often used, and clustering can be performed based on <cell, CIO>. Based on expert experience, the input features can include parameters that characterize the basic characteristics of the cell, such as cell ID, cell scenario type, cell engineering parameters, and handover KPI indicators related to CIO, such as handover success rate, number of handovers per unit time, etc. The selection of input features can be obtained based on artificial intelligence algorithms such as knowledge graphs or correlation coefficient calculations, and no specific restrictions are made here.

[0113] Here, the clustering algorithm includes but is not limited to K-means.

[0114] It should be noted that, after step 103, the method of the embodiment of the present invention may further include:

[0115] The final configuration information of the first parameter of the target cell is sent to a target base station corresponding to the target cell.

[0116] That is, the target base station receives the final configuration information of the first parameter of the target cell, and performs the first parameter configuration on the target cell based on the final configuration information.

[0117] The cell parameter configuration method of an embodiment of the present invention obtains the first classification result of the first parameter of the target cell and the relevant information of the first parameters of M cells of the same category as the first classification result after obtaining the initial configuration information of the first parameter for the target cell, M≥1, and M is a positive integer; according to the first classification result and the relevant information of the first parameters of the M cells, the configuration information of the first parameters of N cells is determined, and the N cells are N cells among M+1 cells including M cells and the target cell, 1≤N≤M+1, and N is a positive integer; the final configuration information of the first parameter of the target cell is determined, and the final configuration information is one of the N+1 configuration information including the initial configuration information and the configuration information of the first parameters of the N cells. In this way, the classification result obtained based on the low-dimensional features of the cell parameters on this dimension and the relevant information of the parameters of other cells of the same category in the classification result can realize the differentiated configuration of the cell parameters, reduce the complexity of classification, and the coupling of the classification results with the corresponding parameters is higher, thereby improving the interpretability of the classification results.

[0118] like Figure 2 As shown, an embodiment of the present invention further provides a cell parameter configuration device, the device comprising:

[0119] The acquisition module 201 is used to acquire, after acquiring initial configuration information of the first parameter for the target cell, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer;

[0120] A first processing module 202 is configured to determine configuration information of first parameters of N cells according to the first classification result and relevant information of the first parameters of the M cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer;

[0121] The second processing module 203 is used to determine final configuration information of the first parameter of the target cell, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells.

[0122] Optionally, the acquisition module 201 includes:

[0123] A first acquisition unit is configured to acquire, when it is determined that the classification information of each parameter of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result according to the classification information stored in the storage unit;

[0124] a second acquisition unit, configured to classify the first parameter of the target cell based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, to obtain a first classification result of the first parameter of the target cell, and to obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells, when it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell and the target cell is a newly built cell;

[0125] A third acquisition unit is used to cluster the first parameter of the target cell using the configuration information of the first parameter of the target cell and other parameters related to the first parameter as the first input feature to obtain a first classification result of the first parameter of the target cell when it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell and the first parameter is a newly added parameter, and obtain relevant information of the first parameters of M cells with the same category as in the first classification result from the classification information of each parameter of each cell in all the cells.

[0126] Optionally, the first classification result and / or the relevant information of the first parameter of the M cells includes a plurality of key performance indicators associated with the first parameter; accordingly, the first processing module 202 includes:

[0127] A first processing unit is configured to sort the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determine the N cells ranked in the top N positions;

[0128] The first acquisition unit is used to acquire configuration information of the first parameters of the N cells.

[0129] Optionally, the second processing module 203 includes:

[0130] A second processing unit, configured to use the initial configuration information as the final configuration information when the initial configuration information is within a configuration range corresponding to the configuration information of the first parameter of the N cells;

[0131] The third processing module is used to determine the final configuration information of the first parameter of the target cell according to the configuration information of the first parameter of the N cells and according to preset rules when the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameter of the N cells.

[0132] Optionally, the preset rule includes one of the following:

[0133] Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information;

[0134] Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal;

[0135] The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

[0136] Optionally, the device further comprises:

[0137] The clustering module is used to cluster the parameters of each cell in all cells, taking the configuration information of each parameter and other parameters related to the parameter as input features, respectively, to obtain the classification results corresponding to each parameter and store them in the storage unit as classification information.

[0138] The cell parameter configuration device of the embodiment of the present invention obtains the first classification result of the first parameter of the target cell and the relevant information of the first parameters of M cells of the same category as the first classification result after obtaining the initial configuration information of the first parameter for the target cell, M≥1, and M is a positive integer; according to the first classification result and the relevant information of the first parameters of the M cells, the configuration information of the first parameters of N cells is determined, and the N cells are N cells among M+1 cells including M cells and the target cell, 1≤N≤M+1, and N is a positive integer; the final configuration information of the first parameter of the target cell is determined, and the final configuration information is one of the N+1 configuration information including the initial configuration information and the configuration information of the first parameters of the N cells. In this way, the classification result obtained based on the low-dimensional features of the cell parameters on this dimension and the relevant information of the parameters of other cells of the same category in the classification result can realize the differentiated configuration of the cell parameters, reduce the complexity of classification, and the coupling of the classification results with the corresponding parameters is higher, thereby improving the interpretability of the classification results.

[0139] It should be noted here that the above-mentioned device provided in the embodiment of the present invention can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

[0140] In order to better achieve the above goals, Figure 3 As shown, an embodiment of the present invention further provides a network side device, including a processor 300 and a transceiver 310, wherein the transceiver 310 receives and sends data under the control of the processor, and the processor 300 is used to perform the following process:

[0141] After obtaining initial configuration information of the first parameter for the target cell, obtaining a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer;

[0142] Determine, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of N cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer;

[0143] Final configuration information of the first parameter of the target cell is determined, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells.

[0144] Optionally, the processor 300 is further configured to:

[0145] In a case where it is determined that the classification information of the parameters of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, obtaining, according to the classification information stored in the storage unit, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result;

[0146] In a case where it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the target cell is a newly built cell, based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, classify the first parameter of the target cell to obtain a first classification result of the first parameter of the target cell, and obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells;

[0147] When it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the first parameter is a newly added parameter, the configuration information of the first parameter of the target cell and other parameters related to the first parameter is used as a first input feature, the first parameter of the target cell is clustered to obtain a first classification result of the first parameter of the target cell, and relevant information of the first parameters of M cells with the same category as in the first classification result is obtained from the classification information of each parameter of each cell in all the cells.

[0148] Optionally, the first classification result and / or the relevant information of the first parameter of the M cells includes a plurality of key performance indicators associated with the first parameter; and the processor 300 is further configured to:

[0149] Sorting the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determining the top N cells;

[0150] Obtain configuration information of the first parameter of the N cells.

[0151] Optionally, the processor 300 is further configured to:

[0152] In a case where the initial configuration information is within a configuration range corresponding to the configuration information of the first parameter of the N cells, using the initial configuration information as the final configuration information;

[0153] When the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameters of the N cells, the final configuration information of the first parameter of the target cell is determined according to the configuration information of the first parameters of the N cells and according to a preset rule.

[0154] Optionally, the preset rule includes one of the following:

[0155] Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information;

[0156] Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal;

[0157] The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

[0158] Optionally, the processor 300 is further configured to:

[0159] For each parameter of each cell in all cells, clustering is performed respectively with configuration information of each parameter and other parameters related to the parameter as input features, and classification results corresponding to each parameter are obtained and stored in the storage unit as classification information.

[0160] The network side device of the embodiment of the present invention obtains the first classification result of the first parameter of the target cell and the relevant information of the first parameters of M cells of the same category as the first classification result after obtaining the initial configuration information of the first parameter for the target cell, M≥1, and M is a positive integer; according to the first classification result and the relevant information of the first parameters of the M cells, the configuration information of the first parameters of N cells is determined, and the N cells are N cells among M+1 cells including M cells and the target cell, 1≤N≤M+1, and N is a positive integer; the final configuration information of the first parameter of the target cell is determined, and the final configuration information is one of the N+1 configuration information including the initial configuration information and the configuration information of the first parameters of the N cells. In this way, the classification result obtained based on the low-dimensional features of the cell parameters on this dimension and the relevant information of the parameters of other cells of the same category in the classification result can realize the differentiated configuration of the cell parameters, reduce the complexity of classification, and the coupling of the classification results with the corresponding parameters is higher, thereby improving the interpretability of the classification results.

[0161] An embodiment of the present invention also provides a network side device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the various processes in the cell parameter configuration method embodiment as described above are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0162] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, each process in the cell parameter configuration method embodiment described above is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0163] The embodiment of the present invention also provides a network management system for configuring cell parameters, such as Figure 4 As shown, the network management system includes a configuration unit, an analysis unit and a storage unit.

[0164] Among them, the configuration unit is used to receive the configuration operations / commands of the operation and maintenance personnel and send them to the target configuration cell. At the same time, it also interacts with the analysis unit, provides the analysis unit with parameter configuration information and other data, and receives parameter configuration verification results and recommended configuration information and other data provided by the analysis unit.

[0165] The analysis unit is used to receive the parameter configuration information provided by the configuration unit, analyze it and feed back the analysis results, such as parameter configuration verification results and recommended configuration information, to the configuration unit. At the same time, it also interacts with the storage unit to request cell and parameter configuration related information, including but not limited to cell public data, configuration parameter data, cell and parameter association classification data, key performance indicator data, etc., and provides the analysis results and the execution result records of the configuration unit to the storage unit.

[0166] The storage unit is used to store the above-mentioned cell and parameter configuration related information for use by the analysis unit.

[0167] Based on the network management system, refer to Figure 4 and Figure 5 , illustrating the implementation process of the cell parameter configuration method of an embodiment of the present invention.

[0168] S1: After the configuration unit receives the configuration instruction of parameter X of cell A sent by the operation and maintenance personnel, the configuration instruction is sent to the analysis unit;

[0169] It should be noted that the configuration instruction carries the initial configuration value of parameter X of cell A.

[0170] S2: The analysis unit requests the storage unit for classification information corresponding to the index determined by the <cell, parameter> tuple;

[0171] It should be noted that the storage unit pre-stores classification information of various parameters of each cell in all cells.

[0172] S3: The storage unit determines whether the classification information of <cell A, parameter X> is stored according to the index determined by the <cell A, parameter X> binary group;

[0173] If yes, execute step S4, otherwise, execute step S5;

[0174] S4: The storage unit sends the classification result corresponding to the classification information of <cell A, parameter X> and the relevant information of <other cells, parameter X> belonging to the same category to the analysis unit;

[0175] S5: The analyzing unit classifies <cell A, parameter X> according to the classification information of <other cells, parameter X> stored in the storage unit and based on a preset classification algorithm to obtain a classification result, and obtains relevant information of <other cells, parameter X> belonging to the same category from the storage unit;

[0176] It should be noted that the cell A corresponding to this situation is a newly built cell. For the situation where the parameter X is a newly added parameter, specific reference may be made to the description of the relevant parts in the above embodiment, which will not be repeated here.

[0177] S6: After the analysis unit obtains the classification result corresponding to the classification information of <cell A, parameter X> and the relevant information of <other cells, parameter X> belonging to the same category, it sorts the key performance indicators or weighted results of multiple key performance indicators associated with parameter X from best to worst, and obtains the configuration value of parameter X of the top N cells;

[0178] S7: Determine whether the initial configuration value of parameter X of cell A sent by the operation and maintenance personnel is within the configuration value range of parameter X of Top N cells;

[0179] If so, execute step S8; otherwise, execute step S9.

[0180] S8: The analysis unit determines that the initial configuration value of the parameter X of the cell A sent by the operation and maintenance personnel passes the verification, and sends the verification result to the configuration unit;

[0181] S9: The analysis unit determines that the initial configuration value of the parameter X of the cell A sent by the operation and maintenance personnel does not pass the verification, and gives a recommended configuration value of the parameter X of the cell A according to the configuration value of the parameter X of the Top N cells, and sends the verification result and the recommended configuration value to the configuration unit;

[0182] Here, the method for calculating the recommended configuration value may be to take an average value, an optimal value, or a random value of the configuration values ​​of the parameter X of the Top N cells, which is not specifically limited here.

[0183] S10: The configuration unit sends the verification result and the recommended configuration value of the parameter X of the cell A that failed the verification to the operation and maintenance personnel for confirmation;

[0184] Afterwards, the configuration unit receives the confirmation result from the operation and maintenance personnel, which may be the recommended configuration, the original configuration, or other configuration values;

[0185] It should be noted that this step is optional.

[0186] S11: The configuration unit configures the configuration value of the parameter X of the cell A to the cell A for execution to take effect, and feeds back the execution result to the operation and maintenance personnel.

[0187] Specifically, the configuration unit configures the configuration value of parameter X issued by the operation and maintenance personnel (passed the verification) or recommended by the analysis unit (failed the verification but there was no manual confirmation process) or confirmed by the operation and maintenance personnel (failed the verification but introduced the manual confirmation process) to cell A for execution and effectiveness, and feeds back the execution result to the operation and maintenance personnel.

[0188] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0189] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A device that specifies functions in one or more processes and / or one or more blocks.

[0190] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a paper product including an instruction 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.

[0191] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that the computer or other programmable device executes a series of operating steps to produce a computer-implemented process, thereby providing instructions 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.

[0192] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A cell parameter configuration method, applied to a network side device, characterized in that: include: After obtaining initial configuration information of the first parameter for the target cell, obtaining a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer; Determine, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of N cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer; Determine final configuration information of the first parameter of the target cell, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells; The first classification result and / or the relevant information of the first parameter of the M cells includes a plurality of key performance indicators associated with the first parameter; The determining, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of the N cells includes: Sorting the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determining the top N cells; Obtain configuration information of the first parameter of the N cells.

2. The method according to claim 1, characterized in that The obtaining of the first classification result of the first parameter of the target cell and the related information of the first parameters of M cells of the same category as the first classification result include: In a case where it is determined that the classification information of the parameters of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, obtaining, according to the classification information stored in the storage unit, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result; In a case where it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the target cell is a newly built cell, based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, classify the first parameter of the target cell to obtain a first classification result of the first parameter of the target cell, and obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells; When it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the first parameter is a newly added parameter, the configuration information of the first parameter of the target cell and other parameters related to the first parameter is used as a first input feature, the first parameter of the target cell is clustered to obtain a first classification result of the first parameter of the target cell, and relevant information of the first parameters of M cells with the same category as in the first classification result is obtained from the classification information of each parameter of each cell in all the cells.

3. The method according to claim 1, characterized in that The determining of the final configuration information of the first parameter of the target cell includes: In a case where the initial configuration information is within a configuration range corresponding to the configuration information of the first parameter of the N cells, using the initial configuration information as the final configuration information; When the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameters of the N cells, the final configuration information of the first parameter of the target cell is determined according to the configuration information of the first parameters of the N cells and according to a preset rule.

4. The method according to claim 3, characterized in that The preset rule includes one of the following: Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information; Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal; The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

5. The method according to claim 1, characterized in that The method further comprises: For each parameter of each cell in all cells, clustering is performed respectively with configuration information of each parameter and other parameters related to the parameter as input features, and classification results corresponding to each parameter are obtained and stored in the storage unit as classification information.

6. A cell parameter configuration device, characterized in that: include: an acquisition module, configured to, after acquiring initial configuration information of a first parameter for a target cell, acquire a first classification result of the first parameter of the target cell and related information of first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer; A first processing module, configured to determine configuration information of the first parameters of N cells according to the first classification result and relevant information of the first parameters of the M cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer; A second processing module, configured to determine final configuration information of the first parameter of the target cell, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells; The first classification result and / or the related information of the first parameter of the M cells include a plurality of key performance indicators associated with the first parameter; and the first processing module includes: A first processing unit is configured to sort the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determine the N cells ranked in the top N positions; The first acquisition unit is used to acquire configuration information of the first parameters of the N cells.

7. A network side device, comprising a processor and a transceiver, wherein the transceiver receives and sends data under the control of the processor, characterized in that: The processor is configured to perform the following operations: After obtaining initial configuration information of the first parameter for the target cell, obtaining a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result, where M≥1 and M is a positive integer; Determine, according to the first classification result and the related information of the first parameters of the M cells, configuration information of the first parameters of N cells, where the N cells are N cells among M+1 cells including the M cells and the target cell, 1≤N≤M+1, and N is a positive integer; Determine final configuration information of the first parameter of the target cell, where the final configuration information is one of N+1 configuration information including the initial configuration information and configuration information of the first parameters of the N cells; The first classification result and / or the related information of the first parameter of the M cells include a plurality of key performance indicators associated with the first parameter; and the processor is further configured to: Sorting the M+1 cells according to the order of the multiple key performance indicators from best to worst, and determining the top N cells; Obtain configuration information of the first parameter of the N cells.

8. The network side device according to claim 7, characterized in that: The processor is further configured to: In a case where it is determined that the classification information of the parameters of each cell among all cells pre-stored in the storage unit includes the classification information of the first parameter of the target cell, obtaining, according to the classification information stored in the storage unit, a first classification result of the first parameter of the target cell and related information of the first parameters of M cells of the same category as the first classification result; In a case where it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the target cell is a newly built cell, based on the pre-stored classification information of the first parameter of each cell in all the cells and a preset classification algorithm, classify the first parameter of the target cell to obtain a first classification result of the first parameter of the target cell, and obtain relevant information of the first parameters of M cells of the same category as in the first classification result from the classification information of each parameter of each cell in all the cells; When it is determined that the classification information stored in the storage unit does not include the classification information of the first parameter of the target cell, and the first parameter is a newly added parameter, the configuration information of the first parameter of the target cell and other parameters related to the first parameter is used as a first input feature, the first parameter of the target cell is clustered to obtain a first classification result of the first parameter of the target cell, and relevant information of the first parameters of M cells with the same category as in the first classification result is obtained from the classification information of each parameter of each cell in all the cells.

9. The network side device according to claim 7, characterized in that: The processor is further configured to: In a case where the initial configuration information is within the configuration range corresponding to the configuration information of the first parameter of the N cells, using the initial configuration information as the final configuration information; When the initial configuration information is not within the configuration range corresponding to the configuration information of the first parameters of the N cells, the final configuration information of the first parameter of the target cell is determined according to the configuration information of the first parameters of the N cells and according to a preset rule.

10. The network side device according to claim 9, characterized in that: The preset rule includes one of the following: Randomly selecting one of the configuration information of the first parameters of the N cells as the final configuration information; Determine target configuration information in the configuration information of the first parameters of the N cells as the final configuration information, wherein the key performance indicator of the cell corresponding to the target configuration information is optimal; The configuration values ​​corresponding to the respective configuration information in the configuration information of the first parameters of the N cells are summed and averaged, and the obtained average value is used as the final configuration information.

11. The network side device according to claim 7, characterized in that: The processor is further configured to: For each parameter of each cell in all cells, clustering is performed respectively with configuration information of each parameter and other parameters related to the parameter as input features, and classification results corresponding to each parameter are obtained and stored in the storage unit as classification information.

12. A network side device, comprising a memory, a processor and a program stored in the memory and executable on the processor; characterized in that: When the processor executes the program, the cell parameter configuration method according to any one of claims 1 to 5 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the cell parameter configuration method according to any one of claims 1 to 5 are implemented.

Images