CN108271176B - Method and system for determining the root cause of poor quality of base station cells - Google Patents

Method and system for determining the root cause of poor quality of base station cells Download PDF

Info

Publication number
CN108271176B
CN108271176B CN201611270477.7A CN201611270477A CN108271176B CN 108271176 B CN108271176 B CN 108271176B CN 201611270477 A CN201611270477 A CN 201611270477A CN 108271176 B CN108271176 B CN 108271176B
Authority
CN
China
Prior art keywords
root cause
quality difference
quality
preliminary
difference root
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201611270477.7A
Other languages
Chinese (zh)
Other versions
CN108271176A (en
Inventor
王希
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Group Fujian Co Ltd
Original Assignee
China Mobile Group Fujian Co Ltd
China Mobile Communications Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Mobile Group Fujian Co Ltd, China Mobile Communications Corp filed Critical China Mobile Group Fujian Co Ltd
Priority to CN201611270477.7A priority Critical patent/CN108271176B/en
Publication of CN108271176A publication Critical patent/CN108271176A/en
Application granted granted Critical
Publication of CN108271176B publication Critical patent/CN108271176B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
    • H04W88/08—Access point devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

A method and system for determining a root cause of cell quality difference of a base station is disclosed. The method for determining the cause of the cell quality difference of the base station comprises the following steps: acquiring the problem type of a base station cell; determining at least one preliminary quality difference root cause in a plurality of preset preliminary quality difference root causes aiming at the problem type; forming a quality difference root cause matrix according to the at least one preliminary quality difference root cause; acquiring a quality difference root cause analysis matrix corresponding to the question type; and determining the final quality difference root cause through the quality difference root cause matrix and the quality difference root cause analysis matrix.

Description

Method and system for determining base station cell quality difference root cause
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and a system for determining a cause of cell quality difference in a base station.
Background
In general, a base station cell may have poor quality due to various problems, which may degrade the service quality of the base station cell. In order to solve the problem of poor quality of the base station cell, the poor quality root cause needs to be analyzed, and the root cause causing the poor quality problem needs to be determined, so that the problem is solved in a targeted manner.
Conventionally, when a base station cell is poor, the most likely cause of the poor quality is generally determined by performing manual analysis on a plurality of indexes. Therefore, the manual investment is large, the pure manual calculation is easy to have errors, the judgment is related to the personal optimization level and the capability of a technician, the technician must be very familiar with a plurality of quality factors, and when the quality factors exist simultaneously, the most possible quality factor needs to be given according to personal experience.
Disclosure of Invention
The invention provides a method and a system for determining a cause of cell quality difference of a base station.
According to an aspect of the present disclosure, there is provided a method for determining a cause of cell quality difference of a base station, including: acquiring the problem type of a base station cell; determining at least one preliminary quality difference root cause in a plurality of preset preliminary quality difference root causes aiming at the problem type; forming a quality difference root cause matrix according to the at least one preliminary quality difference root cause; acquiring a quality difference root cause analysis matrix corresponding to the question type; and determining the final quality difference root cause through the quality difference root cause matrix and the quality difference root cause analysis matrix.
According to another aspect of the present disclosure, there is provided a system for determining a cause of cell quality difference of a base station, comprising: a problem type acquisition unit that acquires a problem type of a base station cell; a preliminary quality difference root cause determination unit that determines at least one preliminary quality difference root cause of a plurality of preset preliminary quality difference root causes for a problem type; the quality difference root cause matrix forming unit forms a quality difference root cause matrix according to at least one preliminary quality difference root cause; a quality difference root cause analysis matrix acquisition unit that acquires a quality difference root cause analysis matrix corresponding to the type of the problem; and a final quality difference root cause determination unit that determines a final quality difference root cause from the quality difference root cause matrix and the quality difference root cause analysis matrix.
According to yet another aspect of the present disclosure, there is provided a system for determining a cause of cell quality difference of a base station, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: acquiring the problem type of a base station cell; determining at least one preliminary quality difference root cause in a plurality of preset preliminary quality difference root causes aiming at the problem type; forming a quality difference root cause matrix according to the at least one preliminary quality difference root cause; acquiring a quality difference root cause analysis matrix corresponding to the question type; and determining the final quality difference root cause through the quality difference root cause matrix and the quality difference root cause analysis matrix.
According to the method, the problem type of the base station cell is obtained, at least one preliminary quality difference root cause in a plurality of preset preliminary quality difference root causes is determined according to the problem type, a quality difference root cause matrix is formed according to the at least one preliminary quality difference root cause, a quality difference root cause analysis matrix obtained by utilizing a probabilistic neural network algorithm training sample is obtained, and a quality final difference root cause is determined according to the quality difference root cause matrix and the quality difference root cause analysis matrix, so that the analysis process can be matriculated, dependence on the capability of optimization personnel is reduced, and the analysis efficiency of the quality difference root causes is improved.
Drawings
The invention may be better understood from the following description of specific embodiments thereof taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic diagram illustrating a probabilistic neural network algorithm;
fig. 2 is a flowchart illustrating a method of determining a root cause of cell quality of a base station according to an embodiment of the present invention;
FIG. 3 is a block diagram illustrating a system for determining a root cause of cell quality differences in a base station in accordance with an embodiment of the present invention;
fig. 4 is a block diagram illustrating an exemplary hardware architecture of a computing device capable of implementing the method and system for determining a root cause of base station cell quality according to embodiments of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present disclosure are described in detail below. The following description encompasses numerous specific details in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a clearer understanding of the present invention by illustrating examples of the present invention. The present invention is by no means limited to any specific configuration set forth below, but covers any modifications, substitutions, and improvements of the relevant elements or components without departing from the spirit of the invention.
The Probabilistic Neural Network (PNN) is a feedforward type Neural Network developed from a Radial Basis Function (RBF) model. Unlike traditional RBFs, PNN is an artificial neural network dedicated to solving classification problems, the theoretical basis of which is the bayesian minimum risk criterion (i.e., Bayes decision theory). The PNN places Bayes estimation in a feedforward neural network, the essence of which is a classifier, and Bayes decision is made according to the non-parameter estimation of probability density so as to obtain a classification result. PNNs are widely used in the fields of classification and pattern recognition.
The hierarchical model of PNN includes: the basic structure of the system comprises an input layer, a mode layer, a summation layer and a decision layer, wherein the basic structure is shown in figure 1.
An input layer: the transfer function is linear, passing only the input samples completely unchanged to the nodes of the mode layer.
Mode layer: the input layer is connected with the input layer through a connecting weight, weighted summation is carried out, and the weighted summation is transmitted to the summation layer after being operated through a nonlinear operator. The number of pattern layer neurons is the same as the number of input sample vectors.
And a summation layer: the input from the mode layer with the same class in the corresponding sample (the probability of belonging to a certain class) is simply accumulated to obtain the maximum possibility that the input sample belongs to the class.
A decision layer: and receiving the probabilities output from the summation layer, wherein the neuron with the highest probability density outputs 1, namely the corresponding neuron is the mode category of the sample to be recognized, and the outputs of other neurons are all 0.
PNN has the following major advantages: (1) the training is quick, and the training time is only slightly longer than the time for reading data; (2) no matter how complex the classification problem is, as long as enough training data are available, the optimal solution under the Bayesian criterion can be obtained; (3) allowing for the addition or subtraction of training data without requiring a long training session to be repeated.
The method comprises the steps of obtaining a problem type of a base station cell, determining at least one preliminary quality difference root cause in a plurality of preset preliminary quality difference root causes aiming at the problem type, forming a quality difference root cause matrix according to the at least one preliminary root cause, obtaining a quality difference root cause analysis matrix obtained by utilizing a probabilistic neural network algorithm training sample, and determining a final quality difference root cause according to the quality difference root cause matrix and the quality difference root cause analysis matrix, so that an analysis process can be matrixed, dependence on the capability of optimization personnel is reduced, and the analysis efficiency of the quality difference root causes is improved. The following describes a method and a system for determining a cause of cell quality difference of a base station in detail according to an embodiment of the present invention with reference to the accompanying drawings.
Fig. 2 is a flowchart illustrating a method of determining a root cause of cell quality of a base station according to an embodiment of the present invention. As shown in fig. 2, in step 201, the problem type of the base station cell is acquired. In one embodiment, the problem type of the base station cell may be one of a plurality of preset problem types. The preset problem types may include test problems, low radio access rates, high radio drop rates, low handover success rates, high per traffic redirection, low Physical Resource Block (PRB) throughput rates, low Channel Quality Indication (CQI) fraction, high downlink block errors, deep coverage, zero traffic, dormancy, and complaint problems. It should be understood that the preset issue type may also include any other suitable issue type.
In one embodiment, the type of problem for the base station cell may be a low radio access rate, i.e. the base station cell is a low radio access rate cell. For example, it may be determined from the data in the LTE performance table that the base station cell is a low radio access rate cell.
In step 202, at least one preliminary poor quality root cause of a plurality of preset preliminary poor quality root causes is determined for the problem type. In one embodiment, there may be a plurality of pre-set preliminary quality root causes. For example, the plurality of predetermined preliminary poor root causes may include, but are not limited to, severe weak coverage, mild weak coverage, over coverage, overlapping coverage, cross-slot interference, device blocking interference, telecommunications Frequency Division Duplex (FDD) spur interference, telecommunications Time Division Duplex (TDD) spur interference, global system for mobile communications (GSM) intermodulation interference, Personal Handyphone System (PHS) interference, other interference, high interference ratio overrun, high interference Resource Block (RB) number overrun, utilization overrun, hard frequency point, connection number overrun, soft expansion, reference signal power, initial received target power, non-persistent scheduling desired power, cell bias, cell reselection hysteresis value, intra-system pilot a2, inter-system pilot a2 threshold (blind expansion), cell selection minimum access level, pilot/pilot system measurement start threshold, serving low priority reselection threshold, The method comprises the following steps of frequency point low-priority reselection threshold of a Universal Terrestrial Radio Access Network (UTRAN), GSM/EDGE wireless communication network (GERAN), intersystem pilot frequency A2 threshold (GSM), antenna port signal power ratio, maximum power of cell selection User Equipment (UE), Power Amplifier (PA) value when a cell Physical Downlink Shared Channel (PDSCH) adopts fixed power distribution, uplink and downlink subframe configuration, special subframe mode, cross-area coverage remote common frequency, communication TDD stray interference, common station leakage configuration, over-close leakage configuration, Measurement Report (MR) leakage configuration, adjacent cell leakage configuration, inconsistency of frequency point/physical layer cell identification (PCI) and a current network, adjacent cell common frequency common PCI, TOP adjacent cell switching difference and the like. In one embodiment, parameter values of a plurality of preset preliminary quality difference root causes may be compared with corresponding threshold conditions, and a preliminary quality difference root cause meeting the corresponding threshold conditions may be selected from the plurality of preset preliminary quality difference root causes as at least one preliminary quality difference root cause according to a comparison result. Each of the predetermined preliminary qualitative difference root causes may have more than one parameter value, and the parameter values may be compared with corresponding threshold conditions to select the preliminary qualitative difference root causes meeting the threshold conditions. For example, when the problem type of the base station cell is low radio access rate, the final quality difference root cause can be determined to be severe weak coverage and over-coverage by comparing parameter values of a plurality of preset preliminary quality difference root causes with corresponding threshold conditions.
In step 203, a quality difference root cause matrix is formed from the at least one preliminary quality difference root cause. In one embodiment, characteristic values may be set for a plurality of preset preliminary quality-difference root factors, wherein the characteristic value corresponding to at least one preliminary quality-difference root factor is set to a first value, and the characteristic values of the remaining preliminary quality-difference root factors are set to a second value, and the characteristic values are used as matrix elements to form a quality-difference root factor matrix. For example, in the case that 47 preliminary quality difference root causes are determined, the 47 preliminary quality difference root causes may be assigned with corresponding eigenvalues, and a row matrix having these eigenvalues as elements may be formed. In one embodiment, the first value may be 1 and the second value may be 2. According to the at least one preliminary poor-quality root factor determined above, the poor-quality root factor matrix may be [1, 0, 1, 0, 0,. talka.., 0], wherein two "1" correspond to severe weak coverage and over coverage, respectively.
In step 204, a quality difference root cause analysis matrix corresponding to the type of problem is obtained. In one embodiment, the quality root cause analysis matrix may be determined by training a sample quality root cause matrix for the problem type and a corresponding sample final quality root cause using a probabilistic neural network algorithm. For example, a sample quality difference root cause matrix and a corresponding sample final quality difference root cause matrix may be trained using a data training function net in a probabilistic neural network algorithm, where B is the sample quality difference root cause matrix, D is the corresponding sample final quality difference root cause matrix (i.e., a matrix composed of elements corresponding to a plurality of preset preliminary quality difference root causes, where the element corresponding to the final quality difference root cause is set to a first value (e.g., 1), the remaining elements are set to a second value (e.g., 0)), and the parameter N is a smoothing factor, e.g., 0.5. It should be understood that different N may be chosen for different samples. The sample quality difference root cause matrix and the corresponding sample final quality difference root cause are correct data obtained through manual analysis in the past, and can be continuously updated and reset according to practical results. Through the training, a quality difference root cause analysis matrix, namely net, can be obtained for subsequent use in the process of determining the root cause aiming at the quality difference problem.
In step 205, a final cause of the quality difference is determined from the cause of the quality difference matrix and the cause of the quality difference analysis matrix. In one embodiment, the final root cause of the quality may be determined by operating on the matrix of root causes of the quality and the matrix of root cause analysis of the quality using a probabilistic neural network algorithm. For example, with a function D ═ sim (net, B) ]', where net is a quality difference root cause analysis matrix, B is a quality difference root cause matrix, and D is a final quality difference root cause matrix obtained by calculation, the quality difference root cause corresponding to the element of the final quality difference root cause matrix D whose value is the first numerical value (for example, 1) is determined to be the final quality difference root cause of the base station cell. For example, in the previous example, when the final quality root cause matrix D is [0, 0, 1, 0, 0,... 0], the quality root cause is over-coverage.
In one embodiment, when the root cause of the quality difference is correct, the determined at least one preliminary root cause of the quality difference and the corresponding final root cause of the quality difference can be used as new samples of corresponding problem types, the new samples are added into the original samples, and the probabilistic neural network algorithm is used for training the new sample set so as to optimize a corresponding root cause analysis matrix of the quality difference and improve the accuracy.
According to the method for determining the quality difference root cause of the base station cell, the problem type of the base station cell is obtained, at least one preliminary quality difference root cause in a plurality of preset preliminary quality difference root causes is determined according to the problem type, the quality difference root cause matrix is formed according to the at least one preliminary quality difference root cause, the quality difference root cause analysis matrix obtained by utilizing the probabilistic neural network algorithm training sample is obtained, and the final quality difference root cause is determined according to the quality difference root cause matrix and the quality difference root cause analysis matrix, so that the analysis process can be matriculated, dependence on the capability of an optimizer is reduced, and the analysis efficiency of the quality difference root causes is improved.
A system for determining a root cause of base station cell quality in accordance with the present disclosure is described below. The system may be used to perform the method according to the present disclosure as described above. Details not disclosed for system embodiments are consistent with the disclosed method embodiments.
Fig. 3 is a block diagram illustrating a system 300 for determining a root cause of cell quality for a base station in accordance with an embodiment of the present invention. As shown in fig. 3, the system 300 for determining the cause of the cell quality of the base station may include a problem type obtaining unit 301, a preliminary cause of quality determining unit 302, a cause of quality matrix forming unit 303, a cause of quality analysis matrix obtaining unit 304, and a final cause of quality determining unit 305.
The problem type acquisition unit 301 acquires the problem type of the base station cell. In one embodiment, the problem type of the base station cell may be one of a plurality of preset problem types. The plurality of preset problem types may include test problems, low wireless turn-on rate, high wireless drop-off rate, low handover success rate, unit traffic high redirection, low Physical Resource Block (PRB) throughput rate, low Channel Quality Indication (CQI) fraction, downlink high block error, deep coverage, zero traffic, dormancy, and complaint problems. Note that the plurality of preset issue types may also include any other suitable issue types.
The preliminary quality difference root cause determination unit 302 determines at least one preliminary quality difference root cause among a plurality of preset preliminary quality difference root causes for the problem type. In one embodiment, there may be a plurality of pre-set preliminary quality root causes. The parameter values of the plurality of preset preliminary quality difference root causes may be compared with corresponding threshold conditions, and a preliminary quality difference root cause meeting the corresponding threshold conditions may be selected as the at least one preliminary quality difference root cause from the plurality of preset preliminary quality difference root causes according to the comparison result.
The quality difference root cause matrix forming unit 303 forms a quality difference root cause matrix from the at least one preliminary quality difference root cause. In one embodiment, the quality factor matrix forming unit 303 may set feature values for a plurality of preset preliminary quality factors, wherein the feature value corresponding to at least one preliminary quality factor is set to a first value, and the feature values of the remaining preliminary quality factors are set to a second value, and the feature values are used as matrix elements to form the quality factor matrix.
The quality difference root cause analysis matrix acquisition unit 304 acquires a quality difference root cause analysis matrix corresponding to the type of the problem. In one embodiment, the quality root cause analysis matrix is determined by training a sample quality root cause matrix for the problem type and a corresponding sample final quality root cause using a probabilistic neural network algorithm.
The final cause-of-deterioration determination unit 305 determines a final cause-of-deterioration from the cause-of-deterioration matrix and the cause-of-deterioration analysis matrix. In one embodiment, the final cause of deterioration determination unit 305 determines the final cause of deterioration by operating the cause of deterioration matrix and the cause of deterioration analysis matrix using a probabilistic neural network algorithm.
It should be understood that, when the system for determining a root cause of cell quality difference of a base station provided in the foregoing embodiment implements the method for determining a root cause of cell quality difference of a base station, only the above-mentioned division of each functional unit is illustrated, and in practical applications, the above-mentioned function allocation may be completed by different functional units according to actual needs, that is, the content structure of the system may be divided into different functional units to complete all or part of the above-mentioned functions. In addition, with regard to the system in the above-described embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
Fig. 4 is a block diagram illustrating an exemplary hardware architecture of a computing device capable of implementing the method and system for determining a root cause of base station cell quality according to embodiments of the present invention. As shown in fig. 4, computing device 400 includes an input device 401, an input interface 402, a central processor 403, a memory 404, an output interface 405, and an output device 406. The input interface 402, the central processing unit 403, the memory 404, and the output interface 405 are connected to each other through a bus 410, and the input device 401 and the output device 406 are connected to the bus 410 through the input interface 402 and the output interface 405, respectively, and further connected to other components of the computing device 400. Specifically, the input device 401 receives input information from the outside and transmits the input information to the central processor 403 through the input interface 1302; the central processor 403 processes the input information based on computer-executable instructions stored in the memory 404 to generate output information, stores the output information temporarily or permanently in the memory 404, and then transmits the output information to the output device 406 through the output interface 405; output device 406 outputs the output information outside of computing device 400 for use by a user.
The system 300 for determining a root cause of base station cell quality as illustrated in fig. 3 may also be implemented to include: a memory storing computer-executable instructions; and a processor which, when executing the computer executable instructions, may implement the method of determining a root cause of base station cell quality described in connection with fig. 2.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
The present invention may be embodied in other specific forms without departing from its spirit or essential characteristics. For example, the algorithms described in the specific embodiments may be modified without departing from the basic spirit of the invention. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

Claims (15)

1.一种确定基站小区质差根因的方法，其特征在于，所述方法包括：1. A method for determining the root cause of poor quality of base station cells, characterized in that the method comprises: 获取所述基站小区的问题类型；Obtain the problem type of the base station cell; 针对所述问题类型确定多个预设初步质差根因中的至少一个初步质差根因；determining at least one preliminary root cause of poor quality among a plurality of preset preliminary root causes of poor quality for the problem type; 根据所述至少一个初步质差根因形成质差根因矩阵；forming a quality difference root cause matrix according to the at least one preliminary quality difference root cause; 获取与所述问题类型相对应的质差根因分析矩阵；以及obtaining a quality root cause analysis matrix corresponding to the question type; and 通过所述质差根因矩阵和所述质差根因分析矩阵确定最终质差根因；Determine the final quality difference root cause through the quality difference root cause matrix and the quality difference root cause analysis matrix; 所述质差根因分析矩阵是通过使用概率神经网络算法训练针对所述问题类型的样本质差根因矩阵和相应的样本最终质差根因确定的，其中，添加质差根因为正确的初步质差根因和最终质差根因至原有样本，形成新的样本，并对新样本进行训练。The quality difference root cause analysis matrix is determined by using a probabilistic neural network algorithm to train the sample quality difference root cause matrix for the problem type and the corresponding sample final quality difference root cause, wherein adding the quality difference root cause is correct preliminary. The root cause of poor quality and the final root cause of poor quality are transferred to the original sample to form a new sample, and the new sample is trained. 2.如权利要求1所述的方法，其特征在于，所述问题类型是多个预设问题类型中的一个。2. The method of claim 1, wherein the question type is one of a plurality of preset question types. 3.如权利要求2所述的方法，其特征在于，所述多个预设问题类型包括测试问题、低无线接通率、高无线掉线率、低切换成功率、单位流量高重定向、低物理资源块(PRB)吞吐率、低信道质量指示(CQI)占比、下行高误块、深度覆盖、零流量、休眠、和投诉问题。3. The method of claim 2, wherein the plurality of preset question types include test questions, low wireless connection rate, high wireless drop rate, low handover success rate, high redirection per unit traffic, Low physical resource block (PRB) throughput, low channel quality indicator (CQI) ratio, high downlink error block, deep coverage, zero traffic, dormancy, and complaints. 4.如权利要求1所述的方法，其特征在于，针对所述问题类型确定多个预设初步质差根因中的至少一个初步质差根因包括：4. The method of claim 1, wherein determining at least one preliminary root cause of poor quality among a plurality of preset preliminary root causes of poor quality for the problem type comprises: 将所述多个预设初步质差根因的参数值与相应的阈值条件进行比较；以及comparing the parameter values of the plurality of preset preliminary poor quality root causes with corresponding threshold conditions; and 根据比较结果从所述多个预设初步质差根因中选择符合相应的阈值条件的初步质差根因作为所述至少一个初步质差根因。According to the comparison result, a preliminary quality difference root cause that meets the corresponding threshold condition is selected from the plurality of preset preliminary quality difference root causes as the at least one preliminary quality difference root cause. 5.如权利要求1所述的方法，其特征在于，根据所述至少一个初步质差根因形成质差根因矩阵包括：5. The method of claim 1, wherein forming a quality difference root cause matrix according to the at least one preliminary quality difference root cause comprises: 为所述多个预设初步质差根因设定特征值，其中对应于所述至少一个初步质差根因的特征值被设置为第一数值，其余初步质差根因的特征值被设置为第二数值；Setting eigenvalues for the plurality of preset preliminary quality difference root causes, wherein the eigenvalue corresponding to the at least one preliminary quality difference root cause is set as the first value, and the eigenvalues of the remaining preliminary quality difference root causes are set is the second value; 以所述特征值作为矩阵元素来形成所述质差根因矩阵。The quality difference root cause matrix is formed with the eigenvalues as matrix elements. 6.如权利要求5所述的方法，其特征在于，所述第一数值为1，第二数值为0。6. The method of claim 5, wherein the first value is 1 and the second value is 0. 7.如权利要求1所述的方法，其特征在于，通过所述质差根因矩阵和所述质差根因分析矩阵确定最终质差根因包括：7. The method of claim 1, wherein determining the final quality difference root cause through the quality difference root cause matrix and the quality difference root cause analysis matrix comprises: 使用概率神经网络算法对所述质差根因矩阵和所述质差根因分析矩阵进行运算从而确定所述最终质差根因。The final quality difference root cause is determined by operating the quality difference root cause matrix and the quality difference root cause analysis matrix using a probabilistic neural network algorithm. 8.一种确定基站小区质差根因的系统，其特征在于，所述系统包括：8. A system for determining the root cause of poor quality of base station cells, wherein the system comprises: 问题类型获取单元，所述问题类型获取单元获取所述基站小区的问题类型；a problem type acquisition unit, the problem type acquisition unit acquires the problem type of the base station cell; 初步质差根因确定单元，所述初步质差根因确定单元针对所述问题类型确定多个预设初步质差根因中的至少一个初步质差根因；a preliminary quality poor root cause determination unit, which determines at least one preliminary poor quality root cause among a plurality of preset preliminary poor quality root causes for the problem type; 质差根因矩阵形成单元，所述质差根因矩阵形成单元根据所述至少一个初步质差根因形成质差根因矩阵；a quality difference root cause matrix forming unit, the quality difference root cause matrix forming unit forms a quality difference root cause matrix according to the at least one preliminary quality difference root cause; 质差根因分析矩阵获取单元，所述质差根因分析矩阵获取单元获取与所述问题类型相对应的质差根因分析矩阵；以及a quality difference root cause analysis matrix obtaining unit, the quality difference root cause analysis matrix obtaining unit obtaining a quality difference root cause analysis matrix corresponding to the problem type; and 最终质差根因确定单元，所述最终质差根因确定单元通过所述质差根因矩阵和所述质差根因分析矩阵确定最终质差根因；a final quality difference root cause determination unit, the final quality difference root cause determination unit determines the final quality difference root cause through the quality difference root cause matrix and the quality difference root cause analysis matrix; 所述质差根因分析矩阵是通过使用概率神经网络算法训练针对所述问题类型的样本质差根因矩阵和相应的样本最终质差根因确定的，其中，添加质差根因为正确的初步质差根因和最终质差根因至原有样本，形成新的样本，并对新样本进行训练。The quality difference root cause analysis matrix is determined by using a probabilistic neural network algorithm to train the sample quality difference root cause matrix for the problem type and the corresponding sample final quality difference root cause, wherein adding the quality difference root cause is correct preliminary. The root cause of poor quality and the final root cause of poor quality are transferred to the original sample to form a new sample, and the new sample is trained. 9.如权利要求8所述的系统，其特征在于，所述问题类型是多个预设问题类型中的一个。9. The system of claim 8, wherein the question type is one of a plurality of preset question types. 10.如权利要求9所述的系统，其特征在于，所述多个预设问题类型包括测试问题、低无线接通率、高无线掉线率、低切换成功率、单位流量高重定向、低物理资源块(PRB)吞吐率、低信道质量指示(CQI)占比、下行高误块、深度覆盖、零流量、休眠、和投诉问题。10. The system of claim 9, wherein the plurality of preset question types include test questions, low wireless connection rate, high wireless drop rate, low handover success rate, high redirection per unit traffic, Low physical resource block (PRB) throughput, low channel quality indicator (CQI) ratio, high downlink error block, deep coverage, zero traffic, dormancy, and complaints. 11.如权利要求8所述的系统，其特征在于，所述初步质差根因确定单元被配置为将所述多个预设初步质差根因的参数值与相应的阈值条件进行比较，以及根据比较结果从所述多个预设初步质差根因中选择符合相应的阈值条件的初步质差根因作为所述至少一个初步质差根因。11. The system of claim 8, wherein the preliminary quality poor root cause determination unit is configured to compare the parameter values of the plurality of preset preliminary poor quality root causes with corresponding threshold conditions, And according to the comparison result, a preliminary quality difference root cause that meets the corresponding threshold condition is selected from the plurality of preset preliminary quality difference root causes as the at least one preliminary quality difference root cause. 12.如权利要求8所述的系统，其特征在于，所述质差根因矩阵形成单元被配置为为所述多个预设初步质差根因设定特征值，其中对应于所述至少一个初步质差根因的特征值被设置为第一数值，其余初步质差根因的特征值被设置为第二数值，以及以所述特征值作为矩阵元素来形成所述质差根因矩阵。12. The system of claim 8, wherein the quality difference root cause matrix forming unit is configured to set eigenvalues for the plurality of preset preliminary quality difference root causes, wherein corresponding to the at least The eigenvalue of one preliminary quality difference root cause is set as a first numerical value, the eigenvalues of the remaining preliminary quality difference root cause are set as a second numerical value, and the quality difference root cause matrix is formed with the eigenvalues as matrix elements . 13.如权利要求12所述的系统，其特征在于，所述第一数值为1，第二数值为0。13. The system of claim 12, wherein the first value is one and the second value is zero. 14.如权利要求8所述的系统，其特征在于，所述最终质差根因确定单元被配置为使用概率神经网络算法对所述质差根因矩阵和所述质差根因分析矩阵进行运算从而确定所述最终质差根因。14. The system of claim 8, wherein the final quality difference root cause determination unit is configured to perform the quality difference root cause matrix and the quality difference root cause analysis matrix using a probabilistic neural network algorithm. Operations are performed to determine the final quality poor root cause. 15.一种确定基站小区质差根因的系统，其特征在于，所述系统包括：15. A system for determining the root cause of poor quality of base station cells, characterized in that the system comprises: 处理器；processor; 用于存储所述处理器可执行指令的存储器；a memory for storing the processor-executable instructions; 其中，所述处理器被配置为：wherein the processor is configured to: 获取所述基站小区的问题类型；Obtain the problem type of the base station cell; 针对所述问题类型，确定多个预设初步质差根因中的至少一个初步质差根因；For the problem type, determine at least one preliminary root cause of poor quality among multiple preset initial root causes of poor quality; 根据所述至少一个初步质差根因形成质差根因矩阵；forming a quality difference root cause matrix according to the at least one preliminary quality difference root cause; 获取与所述问题类型相对应的质差根因分析矩阵；以及obtaining a quality root cause analysis matrix corresponding to the question type; and 通过所述质差根因矩阵和所述质差根因分析矩阵确定最终质差根因。The final quality difference root cause is determined through the quality difference root cause matrix and the quality difference root cause analysis matrix.
CN201611270477.7A 2016-12-30 2016-12-30 Method and system for determining the root cause of poor quality of base station cells Active CN108271176B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611270477.7A CN108271176B (en) 2016-12-30 2016-12-30 Method and system for determining the root cause of poor quality of base station cells

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611270477.7A CN108271176B (en) 2016-12-30 2016-12-30 Method and system for determining the root cause of poor quality of base station cells

Publications (2)

Publication Number Publication Date
CN108271176A CN108271176A (en) 2018-07-10
CN108271176B true CN108271176B (en) 2021-05-04

Family

ID=62770551

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611270477.7A Active CN108271176B (en) 2016-12-30 2016-12-30 Method and system for determining the root cause of poor quality of base station cells

Country Status (1)

Country Link
CN (1) CN108271176B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111212440B (en) * 2018-11-21 2021-09-03 华为技术有限公司 Method and network equipment for realizing quality difference root cause analysis
CN111246524B (en) * 2018-11-28 2022-03-04 中国移动通信集团山东有限公司 A quality switching processing method and device based on CQI information
CN111327450B (en) * 2018-12-17 2022-09-27 中国移动通信集团北京有限公司 Method, device, equipment and medium for determining quality difference reason
CN111339211B (en) * 2018-12-19 2023-09-19 中国移动通信集团重庆有限公司 Method, device, equipment and medium for analyzing network problems
CN110661648B (en) * 2019-08-30 2023-01-13 北京拓明科技有限公司 Method and device for determining wireless network problem root cause based on self-learning reasoning matrix
CN112087334B (en) * 2020-09-09 2022-10-18 中移（杭州）信息技术有限公司 Alarm root cause analysis method, electronic device and storage medium
CN114630423B (en) * 2020-12-10 2024-10-29 中国联合网络通信集团有限公司 Resource allocation method, device, equipment and medium
CN112637880B (en) * 2020-12-23 2022-11-15 北京东土拓明科技有限公司 Problematic cell processing method and device
CN113676945B (en) * 2021-08-12 2024-02-23 锐捷网络股份有限公司 Method, system, access controller and storage medium for identifying bad terminal
CN115842754B (en) * 2021-08-20 2025-03-21 中国电信股份有限公司 Packet loss location method and device, storage medium, and electronic device

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101149819A (en) * 2007-10-31 2008-03-26 山东省科学院海洋仪器仪表研究所 Meteorological element real time data singular value elimination method
CN102083081A (en) * 2009-11-30 2011-06-01 中国移动通信集团广东有限公司 Method and system for detecting overshooting of wireless network
WO2015044931A1 (en) * 2013-09-30 2015-04-02 Telefonaktiebolaget L M Ericsson (Publ) Enhancement on radio link failure report to record necessary timing details for a dual-threshold handover trigger event
CN104835103A (en) * 2015-05-11 2015-08-12 大连理工大学 Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation
CN105791034A (en) * 2016-05-15 2016-07-20 北京联合大学 Browse type service perception analysis method
CN105828365A (en) * 2016-06-01 2016-08-03 武汉虹信技术服务有限责任公司 LTE cell overlapping coverage analysis method based on MR data
CN105913026A (en) * 2016-04-12 2016-08-31 江苏大学 Passenger detecting method based on Haar-PCA characteristic and probability neural network
CN106211186A (en) * 2015-05-05 2016-12-07 普天信息技术有限公司 A kind of method judging community problem in wireless network planning

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101149819A (en) * 2007-10-31 2008-03-26 山东省科学院海洋仪器仪表研究所 Meteorological element real time data singular value elimination method
CN102083081A (en) * 2009-11-30 2011-06-01 中国移动通信集团广东有限公司 Method and system for detecting overshooting of wireless network
WO2015044931A1 (en) * 2013-09-30 2015-04-02 Telefonaktiebolaget L M Ericsson (Publ) Enhancement on radio link failure report to record necessary timing details for a dual-threshold handover trigger event
EP3053375A1 (en) * 2013-09-30 2016-08-10 Telefonaktiebolaget LM Ericsson (publ) Enhancement on radio link failure report to record necessary timing details for a dual-threshold handover trigger event
CN106211186A (en) * 2015-05-05 2016-12-07 普天信息技术有限公司 A kind of method judging community problem in wireless network planning
CN104835103A (en) * 2015-05-11 2015-08-12 大连理工大学 Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation
CN105913026A (en) * 2016-04-12 2016-08-31 江苏大学 Passenger detecting method based on Haar-PCA characteristic and probability neural network
CN105791034A (en) * 2016-05-15 2016-07-20 北京联合大学 Browse type service perception analysis method
CN105828365A (en) * 2016-06-01 2016-08-03 武汉虹信技术服务有限责任公司 LTE cell overlapping coverage analysis method based on MR data

Also Published As

Publication number Publication date
CN108271176A (en) 2018-07-10

Similar Documents

Publication Publication Date Title
CN108271176B (en) Method and system for determining the root cause of poor quality of base station cells
EP3225046B1 (en) Method and apparatus for determining cell states to adjust antenna configuration parameters
US9769689B2 (en) Method and apparatus for optimizing cell specific antenna configuration parameters
US10772048B2 (en) Method and device for real time transmission power control in wireless communication system
US20160165469A1 (en) Method and apparatus for determining cell states to adjust antenna configuration parameters
CN109845310A (en) The method and unit of wireless resource management are carried out using intensified learning
CN111328084B (en) Method and device for evaluating cell capacity
EP3849231B1 (en) Configuration of a communication network
CN114095856B (en) Processing method and processing device for saving energy of base station
CN111225391B (en) Network parameter processing method and equipment
Svahn et al. Inter-frequency radio signal quality prediction for handover, evaluated in 3GPP LTE
Chen et al. Root cause analysis for self-organizing cellular network: An active learning approach
EP4150861B1 (en) Determining cell upgrade
Sanchez-Gonzalez et al. A rule-based solution search methodology for self-optimization in cellular networks
WO2020135157A1 (en) Wireless system performance evaluation method and device
WO2020098679A1 (en) Method for recognizing network scene, and access network device
CN111093229A (en) Method, device, equipment and medium for determining load balancing parameters
Liao et al. A statistical algorithm for multi-objective handover optimization under uncertainties
Feriani Meta multi-objective reinforcement learning for communication load balancing
CN114079957B (en) Method and device for detecting abnormal state of cell
CN114501529B (en) Downlink SINR correction method, device, electronic device and storage device
CN118764891B (en) Wireless capacity optimization method, device, system and storage medium based on large model
Koblitz et al. Reducing the Environmental Impact of Wireless Communication via Probabilistic Machine Learning
EP4369782A1 (en) Method and device for performing load balance in wireless communication system
WO2024013433A1 (en) Method, apparatus and computer program

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant