CN111935741B - Method, device and system for detecting poor quality cell of communication network - Google Patents
Method, device and system for detecting poor quality cell of communication network Download PDFInfo
- Publication number
- CN111935741B CN111935741B CN202010801976.4A CN202010801976A CN111935741B CN 111935741 B CN111935741 B CN 111935741B CN 202010801976 A CN202010801976 A CN 202010801976A CN 111935741 B CN111935741 B CN 111935741B
- Authority
- CN
- China
- Prior art keywords
- communication network
- cell
- index parameter
- target index
- parameters
- 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
Links
- 238000004891 communication Methods 0.000 title claims abstract description 153
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000015654 memory Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 26
- 238000001514 detection method Methods 0.000 description 10
- 238000005457 optimization Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000007637 random forest analysis Methods 0.000 description 3
- 101150071746 Pbsn gene Proteins 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/22—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks comprising specially adapted graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Abstract
The invention provides a method, a device and a system for detecting a poor cell of a communication network, wherein the method comprises the following steps: acquiring a communication network operation index parameter set, wherein the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network; determining a target index parameter from the set of index parameters, wherein the state of operation of the communication network is represented only by the target index parameter; obtaining a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameter, so as to determine the cell in which the network operates poorly according to the correlation degree. The accuracy of detecting the cell with poor operation quality of the communication network is realized, the labor cost is reduced, and the effectiveness of network operation maintenance is improved.
Description
Technical Field
The present invention relates to the field of communications network technologies, and in particular, to a method, an apparatus, and a system for detecting a poor quality cell in a communications network.
Background
The optimization and fault location of poor quality cells of a communication network are important work for maintaining and optimizing the existing wireless network. Because of numerous network indexes, the network quality evaluation system can also be used for evaluating network quality indexes, for example, the number of extractable indexes in each network manager is hundreds.
At present, the wireless network optimization method basically adopts a basic manual or semi-manual mode to carry out network optimization, poor quality cell analysis and problem positioning, and the traditional network optimization method not only needs more steps and time, but also is based on experience and common knowledge in analysis.
In addition, the detection of the network poor quality cell is obtained by means of manual participation, so that the time consumption is long, and the accuracy is not high.
Disclosure of Invention
The invention provides a method, a device and a system for detecting a poor quality cell of a communication network, which are used for realizing the accuracy of detecting the poor quality cell of the communication network operation, reducing the labor cost and improving the effectiveness of the network operation maintenance.
In a first aspect, a method for detecting a poor cell in a communication network provided in an embodiment of the present invention includes:
acquiring a communication network operation index parameter set, wherein the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network;
determining a target index parameter from the set of index parameters, wherein the state of operation of the communication network is represented only by the target index parameter;
obtaining a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameter, so as to determine the cell in which the network operates poorly according to the correlation degree.
In an optional embodiment, determining the target index parameter according to the index parameter set includes:
dividing the index parameter set to obtain a plurality of sections, wherein the sections comprise a plurality of initial index parameters;
if the initial index parameter in the section meets a preset condition, reserving the section;
according to a first index parameter in a reserved interval, obtaining a value corresponding to the operation of the first index parameter in a communication network;
and determining the corresponding first index parameter when the value is greater than a preset threshold value as the target index parameter.
In an alternative embodiment, obtaining a value corresponding to the operation of the first metric parameter on the communication network comprises:
and sorting the values corresponding to the first index parameters from big to small to obtain the value in a preset sorting range.
In an optional embodiment, the preset association rule model is configured to obtain a plurality of correlations according to a communication network operating cell environment in combination with different target index parameters, and obtain a highest correlation through training by inputting a large number of target index parameters in a preset time period, where the highest correlation is at least one of the correlations.
In an optional embodiment, before the target index parameter and the preset association rule model corresponding to the cell are operated according to the communication network, and a cell with poor quality of the communication network is obtained, the method further includes:
after cleaning the data values corresponding to the target index parameters of the communication network operation cell, dividing the data values corresponding to the target index parameters to obtain a plurality of interval value sections, wherein each interval value section comprises a plurality of processed data values corresponding to the target index parameters.
In a second aspect, an apparatus for detecting a poor cell in a communication network according to an embodiment of the present invention includes:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a communication network operation index parameter set, the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network;
a determination module for determining a target index parameter from the set of index parameters, wherein the state of operation of the communication network is represented only by the target index parameter;
the obtaining module is used for obtaining a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameter, so as to determine the cell in which the network operates poorly according to the correlation degree.
In an optional embodiment, determining the target index parameter according to the index parameter set includes:
dividing the index parameter set to obtain a plurality of sections, wherein the sections comprise a plurality of initial index parameters;
if the initial index parameter in the section meets a preset condition, reserving the section;
according to a first index parameter in a reserved interval, obtaining a value corresponding to the operation of the first index parameter in a communication network;
and determining the corresponding first index parameter when the value is greater than a preset threshold value as the target index parameter.
In an alternative embodiment, obtaining a value corresponding to the operation of the first metric parameter on the communication network comprises:
and sorting the values corresponding to the first index parameters from big to small to obtain the value in a preset sorting range.
In an optional embodiment, the preset association rule model is configured to obtain a plurality of correlations according to a communication network operating cell environment in combination with different target index parameters, and obtain a highest correlation through training by inputting a large number of target index parameters in a preset time period, where the highest correlation is at least one of the correlations.
In an optional embodiment, before the target index parameter and the preset association rule model corresponding to the cell are operated according to the communication network, and a cell with poor quality of the communication network is obtained, the method further includes:
after cleaning the data values corresponding to the target index parameters of the communication network operation cell, dividing the data values corresponding to the target index parameters to obtain a plurality of interval value sections, wherein each interval value section comprises a plurality of processed data values corresponding to the target index parameters.
In a third aspect, a system for detecting a poor cell in a communication network according to an embodiment of the present invention includes: the device comprises a memory and a processor, wherein the memory stores executable instructions of the processor; wherein the processor is configured to perform the method of detecting a poor quality cell of a communication network as described in the first aspect via execution of the executable instructions.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the method for detecting a poor quality cell in a communication network according to any one of the first aspect.
The invention provides a method, a device and a system for detecting a poor cell of a communication network, wherein the method comprises the following steps: acquiring a communication network operation index parameter set, wherein the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network; determining a target index parameter from the set of index parameters, wherein the state of operation of the communication network is represented only by the target index parameter; obtaining a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameter, so as to determine the cell in which the network operates poorly according to the correlation degree. The accuracy of detecting the cell with poor operation quality of the communication network is realized, the labor cost is reduced, and the effectiveness of network operation maintenance is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting a poor cell in a communication network according to an embodiment of the present invention;
FIG. 2 is a first diagram of the value provided by the embodiment of the present invention;
FIG. 3 is a second value diagram provided by an embodiment of the present invention;
FIG. 4 is a third schematic diagram of the value provided by the present invention;
FIG. 5 is a first schematic diagram of a visualization data graph according to an embodiment of the present invention;
FIG. 6 is a second schematic diagram of a visual data diagram according to an embodiment of the present invention;
FIG. 7 is a third schematic diagram of a visualization data graph according to an embodiment of the present invention;
FIG. 8 is a fourth schematic diagram of a visual data diagram according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating discretized data values provided by embodiments of the present invention;
FIG. 10 is a diagram illustrating an initial indicator parameter according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of a target index parameter according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of a device for detecting a poor cell in a communication network according to an embodiment of the present invention;
fig. 13 is a schematic structural diagram of a system for detecting a poor cell in a communication network according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, article, or apparatus.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
In the prior art, the wireless network optimization method is basically a basic manual or semi-manual mode to perform network optimization and quality difference cell analysis and problem positioning, and the traditional network optimization method not only needs more steps and time, but also is based on experience and common sense in analysis. In addition, the detection of the network poor quality cell is obtained by means of manual participation, so that the time consumption is long, and the accuracy is not high.
Fig. 1 is a flowchart of a method for detecting a poor quality cell of a communication network according to an embodiment of the present invention, and as shown in fig. 1, the method for detecting a poor quality cell of a communication network according to this embodiment may include:
s101, obtaining a communication network operation index parameter set, wherein the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network.
Specifically, the operation state of the communication network may include high network operation quality (i.e., high quality), poor network operation quality (i.e., poor quality), network throughput, packet loss rate, reliability, and the like, and the present invention mainly detects the network operation quality, such as high quality or poor quality.
In this embodiment, a large amount of data in the busy time zone is read from the communication network operation database, for example, the data amount of the communication network during one day is up to 217 ten thousand, and even if null data is deleted, the data amount is about 64 ten thousand, and the prior art faces the reason that the huge data amount is inconvenient to find out the network operation quality difference and the factors affecting the network operation quality difference. Therefore, in the embodiment, 42 initial index parameters are read from the network operation database, and the initial index parameters can be used to represent the quality of the operation of the communication network, so that the 42 initial index parameters are recorded and stored, for example, an index parameter set in the rfdata. The self-busy hour area is not limited in this embodiment, and for example, the self-busy hour area may include a time period in which the network is not in an idle state during each hour of operation, so that each hour may be divided into a plurality of time periods.
And S102, determining target index parameters according to the index parameter set, wherein the operation state of the communication network is only represented by the target index parameters.
Specifically, with reference to the above embodiments, the index data set including 42 initial index parameters is obtained, and since all the initial index parameters are used to represent the quality of the operating state of the communication network, the accuracy is not high, because the more the factors influencing the quality of the operating state of the communication network are, in some optional embodiments, when the factors influencing the operating state of the communication network are fewer, the cells with poor operating quality of the communication network are found more easily, and the reason for poor operating quality of the network is combed out more easily.
Therefore, a few of the 42 initial index parameters are selected as target index parameters, and at least one target index parameter is used for representing the good and bad operation of the communication network and combing the reasons of poor operation of the communication network.
S103, obtaining a cell with poor communication network quality according to the target index parameter corresponding to the cell operated by the communication network and a preset association rule model.
The preset association rule model is used for determining the correlation between the cell environment in which the communication network operates and the target index parameters, so that the target index parameters corresponding to the cell in which the communication network operates are input into the preset association rule model, and the cell with poor network operation quality is determined through the correlation. The correlation degree in the preset correlation rule model represents the correlation condition of the target index parameter and the cell environment in which the communication network operates, for example, if the correlation degree is high, the correlation between the target index parameter and the cell environment in which the communication network operates is represented to be tight, that is, the target index parameter is an important factor influencing the operation quality of the communication network; if the correlation degree is low, the target index parameter is far associated with the cell environment in which the communication network operates, that is, the target index parameter cannot be used to represent an important factor influencing the operation quality of the communication network.
The embodiment of the invention realizes the accuracy of the cell detection of poor operation quality of the communication network, reduces the labor cost and improves the effectiveness of network operation maintenance.
In an alternative embodiment, determining the target index parameter according to the index parameter set includes: dividing the index parameter set to obtain a plurality of sections, wherein each section comprises a plurality of initial index parameters; if the initial index parameters in the interval accord with the preset conditions, reserving the interval; obtaining a value corresponding to the operation of the first index parameter in the communication network according to the first index parameter in the reserved interval; and determining the corresponding first index parameter when the value is greater than the preset threshold value as the target index parameter.
In this embodiment, at least one target index parameter is screened out from a plurality of initial index parameters by using a random forest algorithm, for example, a random forest belongs to a Bagging type, and by using the advantage of operating a large data set, the importance of each initial index parameter to a classification result can be evaluated.
Specifically, the index parameter set including 42 initial index parameters is discretely divided in conjunction with the above embodiment, for example, a plurality of continuous data values of each initial index parameter are respectively divided into a plurality of sections, and each section includes a plurality of data values of the initial index parameter, for example, the sections may include 0 to 100, 20 to 50, and so on. And then, if the data value of the initial index parameter in the detection section meets the preset condition through a random forest algorithm, reserving the section, such as 20-50 sections, wherein the data values are all larger than 15, and reserving the 20-50 sections. The preset condition may include that the data value belongs to a specific range, and the embodiment is not particularly limited. And then, obtaining a value corresponding to each initial index parameter in the operation of the communication network according to the initial index parameter (for example, the first index parameter) corresponding to the reserved block section, wherein the value is used for evaluating a score value of the initial index parameter in the operation process of the communication network, and the value can be obtained by the existing network search technology. And further determining a first index parameter corresponding to the value greater than the preset threshold value as a target index parameter. For example, the target indicator parameter may include CQI (Channel Quality Indication), PRB (Physical Resource Block), perceived rate (expressed as user perceived rate), and the like.
The specific procedures for obtaining the target index parameters CQI, PRB and perceived rate, for example, may be obtained by the following program code one, program code two and program code three, respectively. Wherein the program code one is
param_grids＝{'n_estimators':range(10,71,10),'min_samples_split':range(80,150,20),'min_samples_leaf':range(10,60,10),'max_features':range(3,11,2)}
[Parallel(n_jobs＝7)]:Done 2800out of 2800|elapsed:1082.5min finished
Best score:0.6936287897877829
Best parameters:{'max_features':9,'min_samples_leaf':10,'min_samples_split':80,'n_estimators':70}
The second program code is
param_grids＝{'n_estimators':range(30,71,10),'min_samples_split':range(30,91,20),'min_samples_leaf':range(5,30,10),'max_features':range(3,11,3)}
[Parallel(n_jobs＝1)]:Done 540out of 540|elapsed:181.7min finished
Best score:0.9998622677921057
Best parameters:{'max_features':9,'min_samples_leaf':5,'min_samples_split':30,'n_estimators':30}
Program code III
param_grids＝{'n_estimators':range(30,71,10),'min_samples_split':range(30,91,20),'min_samples_leaf':range(5,30,10),'max_features':range(3,11,3)}
[Parallel(n_jobs＝7)]:Done 540out of 540|elapsed:218.7min finished
Best score:0.6989001770171899
Best parameters:{'max_features':9,'min_samples_leaf':5,'min_samples_split':30,'n_estimators':70}。
And determining the initial index parameter with the value larger than the preset threshold value, such as the first index parameter, as the target index parameter through network search. For example, CQI max _ features ═ 9, min _ samples _ leaf ═ 10, min _ samples _ split ═ 80, n _ estimators ═ 70; PRB max _ features 9, min _ samples _ leaf 5, min _ samples _ split 30, n _ estimates 30; the sensing rate is max _ features ═ 9, min _ samples _ leaf ═ 5, min _ samples _ split ═ 30, and n _ estimators ═ 70. The preset threshold may be appropriately defined according to different operating conditions of the communication network, and is not limited in this embodiment.
In an alternative embodiment, the values may also be respectively visualized as fig. 2, fig. 3, and fig. 4, where fig. 2 is a first value diagram provided by the embodiment of the present invention, where the values correspond to a target index parameter CQI, fig. 3 is a second value diagram provided by the embodiment of the present invention, where the values correspond to a target index parameter PRB, and fig. 4 is a third value diagram provided by the embodiment of the present invention, where the values correspond to a target index parameter sensing rate.
In an optional embodiment, in order to prevent the influence of factors such as formula factors on the accuracy in the calculation process of each target index parameter, multiple network searches may be implemented to obtain a value, and specifically, values corresponding to the CQI, the PRB, and the sensing rate may be obtained through a program code four, a program code five, and a program code six, respectively.
Program code four is
[Parallel(n_jobs＝1)]:Done 1344out of 1344|elapsed:1328.0min finished
Best score:0.6329421008231064
Best parameters:{'max_features':8,'min_samples_leaf':3,'min_samples_split':20,'n_estimators':80}
Program code five is
[Parallel(n_jobs＝7)]:Done 1344out of 1344|elapsed:493.3min finished
Best score:0.9694077984602165
Best parameters:{'max_features':8,'min_samples_leaf':3,'min_samples_split':20,'n_estimators':60}
Program code six is
[Parallel(n_jobs＝7)]:Done 1344out of 1344|elapsed:517.6min finished
Best score:0.652443729349951
Best parameters:{'max_features':8,'min_samples_leaf':3,'min_samples_split':20,'n_estimators':80}
And wherein the index parameter set mesh is defined as param _ grids { 'n _ estimates': range (20,81,10), 'min _ samples _ split': range (20,91,10), 'min _ samples _ leaf': range (3,20,5), 'max _ features': range (5,11,3) }.
Further, obtaining a value corresponding to the operation of the first index parameter in the communication network includes: and sorting the values corresponding to the first index parameters from big to small to obtain the value in a preset sorting range. The preset sequencing range is not limited in this embodiment.
Specifically, the values corresponding to the initial index parameters, such as the first index parameter, are sorted from large to small, for example, refer to table 1, and the values in a preset sorting range are obtained from the sorted values, so as to determine the target index parameters according to the values.
TABLE 1
| CQI/value | Value of | PRB | Value of | Sensing rate | Value of |
| F0823 | 0.188424 | F0380 | 0.340415 | F0270 | 0.152776 |
| F0002 | 0.123734 | F0823 | 0.184549 | F0445 | 0.138772 |
| F0462 | 0.113359 | F0014 | 0.115795 | RANK | 0.095372 |
| F0183 | 0.093214 | F0703 | 0.055633 | F0703 | 0.087887 |
| F0813 | 0.064867 | RANK | 0.054762 | F0813 | 0.075828 |
| F0014 | 0.064029 | F0183 | 0.038309 | F0432 | 0.048896 |
| F0445 | 0.037235 | F0462 | 0.047811 | ||
| F0026 | 0.037065 | F0014 | 0.038213 | ||
| F0180 | 0.025024 | F0443 | 0.038089 | ||
| F0181 | 0.024263 | F0380 | 0.036317 | ||
| F0001 | 0.023985 | ||||
| F0002 | 0.023851 | ||||
| F0462 | 0.0181 |
Finally, F0014, F0270, F0380, F0414, F0415, F0445, F0462, F0703, F0813, F0823 indexes are used to determine CQI, PRB and perceived rate. F027: user plane PDCP layer downlink peak rate (Mbps), F0380: air interface downlink traffic flow (MByte), F0014: RRC connection average number (one), F0445: number (number) of PRBs available in downlink, F0462: average per PRB interference noise power (dBm), F0703: average CQI, F0813: average utilization (%) of downlink PRBs, F0823: the average sensing rate (Mbps) of the cell level downlink single users and the RANK ratio.
In an alternative embodiment, the accuracy for verifying the impact of CQI, PRB and perceived rate on the operation of the communication network is CQI ('F0703'): [ ' F0014', ' F0462', ' F0813', ' F0823 ], can achieve about 56.97% accuracy.
Best parameters:{'max_features':1,'min_samples_leaf':9,'n_estimators':100}
PRB ('F0813'): [ 'F0703', 'F0014', 'F0462', 'F0445', 'F0823', 'F0380', 'RANK' ], an accuracy of 97.09% can be achieved.
Perceptual rate ('F0823'): [ 'F0014', 'F0270', 'F0445', 'F0813', 'F0703', 'F0380', 'RANK' ], an accuracy of 64.10% was achieved.
Best parameters:{'max_features':2,'min_samples_leaf':10,'n_estimators':90}。
With reference to the embodiment shown in fig. 1, the preset association rule model is used to obtain a plurality of correlations according to the communication network operating cell environment in combination with different target index parameters, and a maximum correlation is obtained by inputting a large number of target index parameters in a preset time period for training, where the maximum correlation is at least one of the correlations.
Specifically, the communication network operation cell environment may include a specific scene environment in which the communication network operates, such as a residential area environment, a high-speed rail environment, an indoor environment, and the like, which is not limited in this embodiment. In the embodiment, the correlation between the communication network operation cell environment and different target index parameters can be obtained through an Apriori algorithm, and then the highest correlation is obtained through mass data training, so that a preset association rule model is generated, and the purpose that the target index parameters can be input into the preset association rule model in the subsequent detection process, and the cell with poor quality of the communication network can be output.
In this embodiment, the correlation may include a contribution degree confidence, a support degree support, a lift degree lift influence degree leveraging, and a reliability constraint, and the following description explains the meaning of each correlation.
Wherein Support represents P (AB)/ALL, and the proportion of the AB data set.
The probability of occurrence of one event and the probability of occurrence of the other event, namely the conditional probability.
P (A, B)/(P (A) P (B)), where 1 indicates that A and B are independent and the larger the Lift is, the stronger the correlation is.
Leverage P (A, B) -P (A) P (B), A and B are independent at 0, and the relationship between A and B is more close as Leverage is larger
Conduction P (A) P (| B)/P (A, | B) is used to measure the independence of A and B, and A, B is more relevant the larger the value. In this embodiment, the event a may represent one of a cell environment and a target index parameter in which the communication network operates, and the event B may also represent one of a cell environment and a target index parameter in which the communication network operates, and is different from the event a.
According to the communication network operation cell environment, combining different target index parameters to obtain corresponding correlation degrees, inputting a large number of target index parameters in a preset time period and the communication network operation cell environment into an association rule model, and training to obtain the highest correlation degree, wherein the highest correlation degree can be one of the correlation degrees and can be obtained according to the fact that the highest correlation degree is larger than a proper threshold value, and the proper threshold value is not limited in the embodiment.
The correlation degree is obtained by using Apriori algorithm for the target index parameter corresponding to the communication network operation cell, and then the cell with poor network operation quality can be determined according to the correlation degree, in an optional embodiment, the correlation degree can be the highest correlation degree, and the highest correlation degree is made to have strong reliability by acquiring a large amount of data (for example, 518 pieces of data after evacuation are acquired within 3 days) and repeatedly training, so that the preset association rule model is obtained. And then, the preset association rule model can be adopted to determine the cell with poor network operation quality, and meanwhile, the reason for poor network operation quality is combed out in the process of acquiring the preset association rule model. For example, when the communication network cell environment is a high-speed rail, the corresponding highest correlation is Leverage, and when the communication network cell environment is an indoor environment, the corresponding highest correlation is connectivity. Finally, a cell with poor operation quality of the communication network may be obtained, and a visual data graph of other parameters in the operation process of the cell may be obtained, for example, fig. 5 to 8, where fig. 5 is a first schematic diagram of a visual data graph according to an embodiment of the present invention, fig. 6 is a second schematic diagram of a visual data graph according to an embodiment of the present invention, fig. 7 is a third schematic diagram of a visual data graph according to an embodiment of the present invention, fig. 8 is a fourth schematic diagram of a visual data graph according to an embodiment of the present invention, and horizontal coordinates of fig. 5 to 8 all represent (number of users), and vertical coordinates represent data values corresponding to the number of RRC connections, traffic, average CQI, and sensing rate, respectively. In an alternative embodiment, the cells in which the communication network operates poorly are shown in table 2.
TABLE 2
The embodiment detects the network operation quality difference cell based on the communication network operation cell environment and the target index parameter, improves the accuracy of detection, reduces labor cost, and improves the effectiveness of network operation maintenance.
In an optional embodiment, before the target index parameter and the preset association rule model corresponding to the cell are operated according to the communication network, and a cell with poor quality of the communication network is obtained, the method further includes: after cleaning the data values corresponding to the target index parameters of the communication network operation cell, dividing the data values corresponding to the target index parameters to obtain a plurality of interval value sections, wherein each interval value section comprises a plurality of processed data values corresponding to the target index parameters. For example, discretization processing may be performed on data values of the target index parameters corresponding to the communication network operation cells, that is, the data are divided after being emptied and cleaned, so as to obtain a plurality of interval value segments, and then the data values of the target index parameters corresponding to each interval value segment are input to the preset association rule model, so as to obtain the cells with poor network operation quality. In an optional embodiment, the accuracy of the detection of the preset association rule model can be improved through the method, and further the effectiveness and reliability of the detection of the operation quality difference of the communication network are improved. For example, referring to fig. 9, fig. 9 is a schematic diagram of discretized data values provided by embodiments of the invention.
In an optional embodiment, in the process of obtaining the target indicator parameter from the initial indicator parameter, the discretization processing process may also be adopted, specifically refer to fig. 10, where fig. 10 is a schematic diagram of the initial indicator parameter provided in the embodiment of the present invention, and the initial indicator parameter shown in fig. 10 may include an RRC connection number, an air interface downlink traffic flow, a RANK ratio, an average per PRB interference noise power, an average CQ, an average downlink PRB remaining rate, and an average cell downlink single user sensing rate. For example, the obtained initial index parameter in the discrete interval is the target index parameter, and referring to fig. 11, fig. 11 is a schematic diagram of the target index parameter provided in the embodiment of the present invention.
Fig. 12 is a schematic structural diagram of a device for detecting a poor quality cell of a communication network according to an embodiment of the present invention, and as shown in fig. 12, the device for detecting a poor quality cell of a communication network according to this embodiment may include:
an obtaining module 21, configured to obtain a communication network operation index parameter set, where the index parameter set includes a plurality of initial index parameters, and the initial index parameters are used to represent an operation state of the communication network;
a determining module 22, configured to determine a target index parameter according to an index parameter set, wherein the operating state of the communication network is represented by the target index parameter only;
the obtaining module 23 is configured to obtain a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameter, so as to determine the cell with poor network operation quality according to the correlation degree.
In an alternative embodiment, determining the target index parameter according to the index parameter set includes:
dividing the index parameter set to obtain a plurality of sections, wherein each section comprises a plurality of initial index parameters;
if the initial index parameters in the interval accord with the preset conditions, reserving the interval;
obtaining a value corresponding to the operation of the first index parameter in the communication network according to the first index parameter in the reserved interval;
and determining the corresponding first index parameter when the value is greater than the preset threshold value as the target index parameter.
In an alternative embodiment, obtaining a value corresponding to the operation of the first metric parameter on the communication network comprises:
and sorting the values corresponding to the first index parameters from big to small to obtain the value in a preset sorting range.
In an optional embodiment, the preset association rule model is configured to obtain a plurality of correlations according to a communication network operating cell environment in combination with different target index parameters, and obtain a highest correlation through training by inputting a large number of target index parameters in a preset time period, where the highest correlation is at least one of the correlations.
In an optional embodiment, before the target index parameter and the preset association rule model corresponding to the cell are operated according to the communication network, and a cell with poor quality of the communication network is obtained, the method further includes:
after cleaning the data values corresponding to the target index parameters of the communication network operation cell, dividing the data values corresponding to the target index parameters to obtain a plurality of interval value sections, wherein each interval value section comprises a plurality of processed data values corresponding to the target index parameters.
The detection apparatus for a cell with poor communication network quality in this embodiment may execute the technical solution in the method shown in fig. 1, and for the specific implementation process and technical principle, reference is made to the relevant description in the method shown in fig. 1, which is not described herein again.
Fig. 13 is a schematic structural diagram of a system for detecting a poor cell in a communication network according to an embodiment of the present invention, and as shown in fig. 13, a path prediction system 30 according to this embodiment may include: a processor 31 and a memory 32.
A memory 32 for storing computer programs (such as application programs, functional modules, etc. implementing the above-described detection method for poor cell of a communication network), computer instructions, etc.;
the computer programs, computer instructions, etc. described above may be stored in one or more memories 32 in partitions. And the computer programs, computer instructions, data, etc. described above may be invoked by the processor 32.
A processor 31 for executing the computer program stored in the memory 32 to implement the steps of the method according to the above embodiments.
Reference may be made in particular to the description relating to the preceding method embodiment.
The processor 31 and the memory 32 may be separate structures or may be integrated structures integrated together. When the processor 31 and the memory 32 are separate structures, the memory 32 and the processor 31 may be coupled by a bus 33.
The server in this embodiment may execute the technical solution in the method shown in fig. 1, and for the specific implementation process and the technical principle, reference is made to the relevant description in the method shown in fig. 1, which is not described herein again.
In addition, an embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when at least one processor of the user equipment executes the computer-executable instructions, the user equipment performs the above possibilities.
Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in user equipment. Of course, the processor and the storage medium may reside as discrete components in a communication device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the embodiments described above may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs the steps including the above embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for detecting a poor quality cell of a communication network, comprising:
acquiring a communication network operation index parameter set, wherein the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network;
determining a target index parameter from the set of index parameters, wherein the state of operation of the communication network is represented only by the target index parameter;
obtaining a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameters so as to determine the cell with poor network operation quality according to the correlation degree, the preset association rule model is used for obtaining a plurality of correlation degrees according to the cell environment in which the communication network operates and different target index parameters, and the highest correlation degree is obtained by inputting a large number of target index parameters in a preset time period for training, wherein the highest correlation degree is at least one of the correlation degrees;
determining a target index parameter according to the index parameter set, including:
dividing the index parameter set to obtain a plurality of sections, wherein the sections comprise a plurality of initial index parameters;
if the initial index parameter in the section meets a preset condition, reserving the section;
according to a first index parameter in a reserved interval, obtaining a value corresponding to the operation of the first index parameter in a communication network;
and determining the corresponding first index parameter when the value is greater than a preset threshold value as the target index parameter.
2. The method of claim 1, wherein obtaining a value corresponding to operation of the first metric parameter on the communication network comprises:
and sorting the values corresponding to the first index parameters from big to small to obtain the value in a preset sorting range.
3. The method of claim 1, wherein before the step of operating the target index parameter and the preset association rule model corresponding to the cell according to the communication network to obtain the cell with poor quality of the communication network, the method further comprises:
after cleaning the data values corresponding to the target index parameters of the communication network operation cell, dividing the data values corresponding to the target index parameters to obtain a plurality of interval value sections, wherein each interval value section comprises a plurality of processed data values corresponding to the target index parameters.
4. An apparatus for detecting a poor quality cell in a communication network, comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a communication network operation index parameter set, the index parameter set comprises a plurality of initial index parameters, and the initial index parameters are used for representing the operation state of the communication network;
a determination module for determining a target index parameter from the set of index parameters, wherein the state of operation of the communication network is represented only by the target index parameter;
the obtaining module is used for obtaining a cell with poor communication network quality according to a target index parameter corresponding to a communication network operation cell and a preset association rule model; the preset association rule model is used for determining the correlation degree between the cell environment in which the communication network operates and the target index parameters so as to determine the cell with poor network operation quality according to the correlation degree, the preset association rule model is used for obtaining a plurality of correlation degrees according to the cell environment in which the communication network operates and different target index parameters, and the highest correlation degree is obtained by inputting a large number of target index parameters in a preset time period for training, wherein the highest correlation degree is at least one of the correlation degrees;
the determining module is specifically configured to: dividing the index parameter set to obtain a plurality of sections, wherein the sections comprise a plurality of initial index parameters;
if the initial index parameter in the section meets a preset condition, reserving the section;
according to the first index parameter in the reserved interval, obtaining a value corresponding to the operation of the first index parameter in the communication network;
and determining the corresponding first index parameter when the value is greater than a preset threshold value as the target index parameter.
5. The apparatus of claim 4, wherein before the target indicator parameter corresponding to the cell and the preset association rule model are run according to the communication network to obtain the cell with poor quality of the communication network, the apparatus further comprises:
after cleaning the data values corresponding to the target index parameters of the communication network operation cell, dividing the data values corresponding to the target index parameters to obtain a plurality of interval value sections, wherein each interval value section comprises a plurality of processed data values corresponding to the target index parameters.
6. A system for detecting poor quality cells in a communication network, comprising: the device comprises a memory and a processor, wherein the memory stores executable instructions of the processor; wherein the processor is configured to perform the method of detecting a communication network poor quality cell of any of claims 1-3 via execution of the executable instructions.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for detecting poor quality cells of a communication network according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010801976.4A CN111935741B (en) | 2020-08-11 | 2020-08-11 | Method, device and system for detecting poor quality cell of communication network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010801976.4A CN111935741B (en) | 2020-08-11 | 2020-08-11 | Method, device and system for detecting poor quality cell of communication network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111935741A CN111935741A (en) | 2020-11-13 |
| CN111935741B true CN111935741B (en) | 2022-08-05 |
Family
ID=73311128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010801976.4A Active CN111935741B (en) | 2020-08-11 | 2020-08-11 | Method, device and system for detecting poor quality cell of communication network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111935741B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113660687B (en) * | 2021-08-17 | 2023-07-04 | 中国联合网络通信集团有限公司 | Network difference cell processing method, device, equipment and storage medium |
| CN113727377B (en) * | 2021-09-02 | 2023-07-04 | 中国联合网络通信集团有限公司 | Method and equipment for judging wireless communication environment change based on base station parameters |
| CN114301803B (en) * | 2021-12-24 | 2024-03-08 | 北京百度网讯科技有限公司 | Network quality detection method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103648125A (en) * | 2013-12-25 | 2014-03-19 | 北京炎强通信技术有限公司 | Method for monitoring long term evolution (LTE) network voice services |
| CN105451261A (en) * | 2015-12-02 | 2016-03-30 | 北京泰合佳通信息技术有限公司 | VoLTE wireless network test method based on mobile intelligent terminal |
| CN106304180A (en) * | 2016-08-15 | 2017-01-04 | 中国联合网络通信集团有限公司 | A kind of method and device of the speech service quality determining user |
| CN106332209A (en) * | 2015-09-22 | 2017-01-11 | 北京智谷睿拓技术服务有限公司 | Switching method and switching device |
| CN107454633A (en) * | 2016-05-31 | 2017-12-08 | 华为终端（东莞）有限公司 | A kind of determination method and apparatus of voice communication network |
| WO2018040103A1 (en) * | 2016-09-05 | 2018-03-08 | 华为技术有限公司 | Method and terminal for voice switching and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109803295B (en) * | 2019-03-05 | 2022-03-15 | 中国联合网络通信集团有限公司 | Method and device for evaluating communication cell rectification priority |
-
2020
- 2020-08-11 CN CN202010801976.4A patent/CN111935741B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103648125A (en) * | 2013-12-25 | 2014-03-19 | 北京炎强通信技术有限公司 | Method for monitoring long term evolution (LTE) network voice services |
| CN106332209A (en) * | 2015-09-22 | 2017-01-11 | 北京智谷睿拓技术服务有限公司 | Switching method and switching device |
| CN105451261A (en) * | 2015-12-02 | 2016-03-30 | 北京泰合佳通信息技术有限公司 | VoLTE wireless network test method based on mobile intelligent terminal |
| CN107454633A (en) * | 2016-05-31 | 2017-12-08 | 华为终端（东莞）有限公司 | A kind of determination method and apparatus of voice communication network |
| CN106304180A (en) * | 2016-08-15 | 2017-01-04 | 中国联合网络通信集团有限公司 | A kind of method and device of the speech service quality determining user |
| WO2018040103A1 (en) * | 2016-09-05 | 2018-03-08 | 华为技术有限公司 | Method and terminal for voice switching and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111935741A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111935741B (en) | Method, device and system for detecting poor quality cell of communication network | |
| US6622221B1 (en) | Workload analyzer and optimizer integration | |
| CN105869022B (en) | Application popularity prediction method and device | |
| CN111294819A (en) | Network optimization method and device | |
| CN103577660B (en) | Gray scale experiment system and method | |
| CN111984544B (en) | Device performance test method and device, electronic device and storage medium | |
| CN102722577A (en) | Method and device for determining dynamic weights of indexes | |
| CN103702343B (en) | The detection method and device of a kind of inter-frequency interference cell | |
| CN111737078A (en) | Load type-based adaptive cloud server energy consumption measuring and calculating method, system and equipment | |
| CN114116828A (en) | Association rule analysis method, device and storage medium for multidimensional network index | |
| CN110348717B (en) | Base station value scoring method and device based on grid granularity | |
| CN113660687B (en) | Network difference cell processing method, device, equipment and storage medium | |
| US20230409008A1 (en) | Methods for smart gas data management, internet of things systems, and storage media | |
| CN109711555B (en) | Method and system for predicting single-round iteration time of deep learning model | |
| CN114785616A (en) | Data risk detection method and device, computer equipment and storage medium | |
| CN108964951B (en) | Method for acquiring alarm information and server | |
| WO2013026389A1 (en) | Method and device for simulation | |
| CN114219377A (en) | Service resource allocation method, device and equipment | |
| CN115915237A (en) | Energy-saving measuring and calculating method and device for base station equipment and calculating equipment | |
| CN112632364A (en) | News propagation speed evaluation method and system | |
| Lin et al. | A new approach to discrete stochastic optimization problems | |
| CN111598390A (en) | Server high availability evaluation method, device, equipment and readable storage medium | |
| CN106301880A (en) | One determines that cyberrelationship degree of stability, Internet service recommend method and apparatus | |
| CN112580908A (en) | Wireless performance index evaluation method and device | |
| CN111835541A (en) | Model aging detection method, device, equipment and system |
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 |