CN110635926A

CN110635926A - Method and device for determining network problems

Info

Publication number: CN110635926A
Application number: CN201810643609.9A
Authority: CN
Inventors: 张明福; 张国华; 张琪斌
Original assignee: Bright Oceans Inter Telecom Co Ltd
Current assignee: Bright Oceans Inter Telecom Co Ltd
Priority date: 2018-06-21
Filing date: 2018-06-21
Publication date: 2019-12-31
Anticipated expiration: 2038-06-21
Also published as: CN110635926B

Abstract

The invention provides a method and a device for determining network problems, wherein the method comprises the following steps: acquiring a target network representation; searching a target case matched with the target network representation in a target case base based on the target network representation; if the target case is found in the target case base, determining a network problem corresponding to the target network representation through the target case; and if the target case is not found in the target case library, determining a candidate network problem set through the target rule library and the target case library based on the target network characterization, and determining the candidate network problem with the maximum correlation with the target network characterization in the candidate network problem set as the network problem corresponding to the target network characterization. Therefore, the method and the device for determining the network problems can automatically determine the network problems by utilizing the target case base and the target rule base based on the target network representation without depending on network optimization personnel, so that the efficiency of network optimization can be improved, and the cost of network optimization is reduced.

Description

Method and device for determining network problems

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for determining a network problem.

Background

At present, the LTE network is still in a perfect network establishment phase, and in this phase, numerous network problems occur, which all need network optimization personnel to find and solve, so as to optimize the LTE network. However, the network optimization personnel usually rely on the accumulated experience of the network optimization personnel, some problems cannot be timely discovered and solved, and the number of the LTE network optimization personnel is small at present, which results in low network optimization efficiency.

Disclosure of Invention

In view of the above, the present invention provides a method and an apparatus for determining a network problem, so as to solve the problems in the prior art that network optimization efficiency is not high due to insufficient number of network optimization personnel and poor experience caused by network optimization personnel dependence on network optimization personnel, and the technical scheme is as follows:

a method of determining a network problem, comprising:

acquiring a target network representation;

searching a case matched with the target network representation in a target case base based on the target network representation to serve as a target case, wherein the target case base comprises a plurality of cases, and each case at least comprises a network problem and a network representation;

if the target case is found in the target case base, determining a network problem corresponding to the target network representation through the target case;

if the target case is not found in the target case library, determining a candidate network problem set through a target rule base and the target case library based on the target network characterization, respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, and determining the candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization, wherein the target rule base comprises a plurality of rules, and the rules are used for characterizing the matching relationship between the network characterization and the network problem.

Preferably, after obtaining the target network characterization, the method further includes:

searching a rule matched with the target network representation in the target rule base based on the target network representation to serve as a target rule;

if the target rule is found, determining a network problem corresponding to the target network representation through the target rule;

and if the target rule is not found, executing the case which is matched with the target network representation and is found in a target case base based on the target network representation.

Wherein each case in the target case base further comprises: solutions to network problems;

determining a network problem corresponding to the target network representation through the target case includes: determining the network problem in the target case as the network problem corresponding to the target network representation;

after determining the network problem corresponding to the target network representation through the target case, the method further includes: determining a solution in the target case as a solution of a network problem corresponding to the target network representation;

after determining a network problem corresponding to the target network characterization based on the target rule and the target case base, the method further includes: determining a case containing the network problem corresponding to the target network representation from the target case library, and determining a solution in the case containing the network problem corresponding to the target network representation as a solution of the network problem corresponding to the target network representation;

after determining, by the target rule, a network problem corresponding to the target network characterization, the method further includes: and determining a case containing the network problem corresponding to the target network representation from the target case library, and determining a solution in the case containing the network problem corresponding to the target network representation as the solution of the network problem corresponding to the target network representation.

The method for determining the network problem further comprises the following steps:

storing the target network representation, the network problem corresponding to the target network representation and the solution composition case of the network problem corresponding to the target network representation into the target case base;

and when the target rule is not found in the target rule base based on the target network representation, generating a rule of the target network representation and a network problem corresponding to the target network representation, and storing the generated rule in the target rule base.

Wherein the obtaining of the target network representation comprises:

obtaining a set of network performance indicators from a target communication network;

clearing the interfered network performance indexes from the network performance index set to obtain a target network performance index set;

an abnormal network performance indicator is identified from the set of target network performance indicators.

Clustering the abnormal network performance indexes to obtain a network characterization set, wherein each network characterization in the network characterization set is a type of network performance index obtained by clustering;

and acquiring the target network representation from the network representation set.

Searching a case matched with the target network representation in a target case base based on the target network representation as a target case, wherein the step of searching the case matched with the target network representation in the target case base comprises the following steps:

finding out a candidate case in the target case base based on the target network characterization, wherein the network characterization of the candidate case is the same as the target network characterization;

if the candidate case is one, calculating the similarity between the network representation of the candidate case and the target network representation; judging whether the similarity is greater than a set threshold value or not; if the similarity is larger than the set threshold, determining the candidate case as the target case;

if the candidate cases are multiple, respectively calculating the similarity between the network representation of each candidate case and the target network representation to obtain the similarity corresponding to each candidate case; determining the maximum similarity from the similarities corresponding to the candidate cases; judging whether the maximum similarity is larger than the set threshold value or not; and if the maximum similarity is larger than the set threshold, determining the case corresponding to the maximum similarity as the target case.

Wherein the determining a set of candidate network problems through the target rule base and the target case base based on the target network comprises:

determining a network characterization including at least one network performance index in the target network characterization from network characterizations corresponding to each rule in the target rule base, obtaining at least one candidate network characterization, and determining at least one network problem corresponding to the at least one candidate network characterization as a candidate network problem;

determining a network representation comprising at least one network performance index in the target network representation from each case in the target case base, obtaining at least one candidate network representation, and determining at least one network problem corresponding to the at least one candidate network representation as a candidate network problem;

and forming the determined all candidate network problems into the candidate network problem set.

A method of determining a network problem, comprising:

acquiring a target network characteristic and a target analysis mode, wherein the target analysis mode comprises one of a professional analysis mode, a mathematical analysis mode and a hybrid analysis mode;

when the target analysis mode is the professional analysis mode, determining a network problem corresponding to the target network representation through a first analysis method, wherein the first analysis method comprises the following steps: determining a rule matched with the target network representation from a target rule base as a target rule, and determining a network problem corresponding to the target network representation through the target rule, wherein the target rule base comprises a plurality of rules, and the rules are used for representing the matching relationship between the network representation and the network problem;

when the target analysis mode is the mathematical analysis mode, determining a network problem corresponding to the target network characterization through a second analysis method, wherein the second analysis method comprises the following steps: determining a case matched with the target network characterization from a target case library as a target case, determining a network problem corresponding to the target network characterization through the target case, if the target case does not exist in the target case library, determining a candidate network problem set through the target rule library and the target case library based on the target network, respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, and determining a candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization, wherein the target case library comprises a plurality of cases, and each case at least comprises a network problem and a network characterization;

and when the target analysis mode is the hybrid analysis mode, determining a network problem corresponding to the target network characterization through the first analysis method and the second analysis method.

An apparatus for determining a network problem, comprising: the device comprises an acquisition module, a search module, a first determination module and a second determination module;

the acquisition module is used for acquiring the representation of the target network;

the searching module is used for searching a case matched with the target network representation in a target case base based on the target network representation to serve as a target case, wherein the target case base comprises a plurality of cases, and each case at least comprises a network problem and a network representation;

the first determining module is configured to determine, through the target case, a network problem corresponding to the target network representation when the target case is found in the target case library;

the second determining module is configured to determine, when the target case is not found in the target case base, a candidate network problem set through a target rule base and the target case base based on the target network characterization, where the target rule base includes a plurality of rules, and the rules are used for characterizing a matching relationship between the network characterization and the network problem;

the third determining module is configured to determine a correlation between each candidate network problem in the candidate network problem set and the target network characterization;

the fourth determining module is configured to determine the candidate network problem with the largest correlation with the target network characterization as the network problem corresponding to the target network characterization.

An apparatus for determining a network problem, comprising: the device comprises an acquisition module, a first determination module, a second determination module and a third determination module;

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a target network characteristic and a target analysis mode, and the target analysis mode comprises one of a professional analysis mode, a mathematical analysis mode and a hybrid analysis mode;

a first determining module, configured to determine, when the target analysis mode is the professional analysis mode, a network problem corresponding to the target network characterization through a first analysis method, where the first analysis method includes: determining a target rule matched with the target network representation from a target rule base, and determining a network problem corresponding to the target network representation through the target rule, wherein the target rule base comprises a plurality of rules, and the rules are used for representing the matching relationship between the network representation and the network problem;

a second determining module, configured to determine, by a second analysis method, a network problem corresponding to the target network characterization when the target analysis mode is the mathematical analysis mode, where the second analysis method includes: determining a case matched with the target network characterization from a target case library as a target case, determining a network problem corresponding to the target network characterization through the target case, if the target case does not exist in the target case library, determining a candidate network problem set through the target rule library and the target case library based on the target network, respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, and determining a candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization, wherein the target case library comprises a plurality of cases, and each case at least comprises a network problem and a network characterization;

the third determining module is configured to determine, by the first analyzing method and the second analyzing method, a network problem corresponding to the target network representation when the target analyzing mode is the hybrid analyzing mode

The technical scheme has the following beneficial effects:

according to the method and the device for determining the network problems, the matching cases can be found out from the target case library through the target network characterization, the network problems are determined through the matching cases, and if the matching cases are not found out in the case library, the network problems corresponding to the target network characterization are determined through the target rule library and the target case library based on the target network characterization. Therefore, the method and the device for determining the network problems can automatically determine the network problems by utilizing the target case base and the target rule base without depending on network optimization personnel, so that the efficiency of network optimization can be improved, and the cost of network optimization is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic flowchart of a method for determining a network problem according to an embodiment of the present invention;

fig. 2 is a schematic flow chart illustrating a specific implementation process of obtaining a target network representation in the method for determining a network problem according to the embodiment of the present invention;

fig. 3 is a schematic flowchart of a specific implementation process of searching for a target case in a target case library based on a target network representation in the method for determining a network problem according to the embodiment of the present invention;

fig. 4 is another schematic flow chart of a method for determining a network problem according to an embodiment of the present invention;

fig. 5 is a further flowchart of the method for determining a network problem according to the embodiment of the present invention;

fig. 6 is a schematic structural diagram of a network problem determination apparatus according to an embodiment of the present invention;

fig. 7 is another schematic structural diagram of a device for determining a network problem according to an embodiment of the present invention.

Detailed Description

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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.

An embodiment of the present invention provides a method for determining a network problem, please refer to fig. 1, which shows a flowchart of the method for determining a network problem, and the method may include:

step S101: and acquiring a target network representation.

Wherein the target network characterization is a characterization of a network problem, which may include at least one network performance indicator. It can be understood that when a network has a problem, the network performance index is deteriorated, and the network problem can be known by analyzing the network characterization including the network performance index.

Step S102: and searching a target case in the target case library based on the target network characterization.

The target case library comprises a plurality of cases, and each case at least comprises a network characteristic and a network problem. In this embodiment, the target case is a case matching the target network representation.

The specific implementation process of this step can be referred to the description of the following embodiments.

Step S103 a: and if the target case is found in the target case library, determining a network problem corresponding to the target network representation through the target case.

Specifically, the process of determining the network problem corresponding to the target network characterization through the target case may include: and determining the network problem of the target case as the network problem corresponding to the target network representation.

Preferably, after determining the network problem corresponding to the target network representation through the target case, the method provided by this embodiment may further include: and determining the solution of the target case as the solution of the network problem corresponding to the target network characterization.

Further, after determining a network problem corresponding to the target network representation and a solution of the network problem corresponding to the target network representation through the target case, the method provided by the embodiment of the present invention may further include: and forming a new case by the target network representation, the network problem corresponding to the target network representation and the solution of the network problem corresponding to the target network representation, and storing the new case into a target case library.

Step S103 b: and if the target case is not found in the target case base, determining a candidate network problem set through the target rule base and the target case base based on the target network characterization.

The target rule base comprises a plurality of rules, and the rules are used for representing the matching relation between the network representation and the network problems.

In this embodiment, the process of determining the candidate network problem set through the target rule base and the target case base based on the target network characterization may include: determining a network characterization including at least one network performance index in the target network characterization from network characterizations corresponding to each rule in the target rule base to obtain at least one candidate network characterization, and determining at least one network problem corresponding to the at least one candidate network characterization as a candidate network problem; determining a network representation containing at least one network performance index in a target network representation from each case in a target case base, obtaining at least one candidate network representation, and determining at least one network problem corresponding to the at least one candidate network representation as a candidate network problem; and forming the determined all candidate network problems into the candidate network problem set.

Step S104 b: and respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, and determining the candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization.

Illustratively, the success rate of E-RAB establishment, the radio drop rate and the radio access rate of a cell are deteriorated, that is, the network characterization is the success rate of E-RAB establishment, the radio drop rate and the radio access rate, and it is determined through the target rule base and the target case base that the cell has two network problems, one is intermodulation interference, the other is weak coverage, and at this time, the correlation between the network characterization and the intermodulation interference and the correlation between the network characterization and the weak coverage can be calculated:

correlation coefficient R of network characterization and intermodulation interference₁：

R1 ═ R | (E-RAB establishment success rate) + | R | (wireless disconnection rate) + | R | (wireless connection rate);

correlation coefficient R of network characterization and weak coverage₂：

R₂The method comprises the following steps of (1) establishing an equal r (E-RAB success rate) + r (wireless disconnection rate) + r (wireless connection rate);

r is to be₁And R₂Normalization:

R₁’＝R₁/(R1+R₂)；R₂’＝R₁/(R₁+R₂)；

if R1 'is greater than R2', the intermodulation interference can be determined as a main network problem, and the degree of influence of the intermodulation interference on each index in the network representation is large, namely the network problem corresponding to the network representation E-RAB establishment success rate, the wireless disconnection rate and the wireless connection rate is the intermodulation interference; if R2 'is larger than R1', the network problems corresponding to the network characterization E-RAB establishment success rate, the wireless disconnection rate and the wireless connection rate can be determined to be weak coverage.

In one possible implementation, the correlation between the network problem and the network representation may be obtained by calculating a Pearson correlation coefficient (Pearson correlation coefficient) of the network problem and the network representation. The calculation formula of the Pearson correlation coefficient is as follows:

wherein, X_i、Y_iRepresenting two successive variables, E (X)_i) Represents variable X_iIs reflected in the random variable X_iAverage value of E (Y)_i) Represents the variable Y_iIs reflected in the random variable Y_iThe average value. The value range of the Pearson correlation coefficient is-1 < rho < 1, positive correlation is obtained if rho is positive number, negative correlation is obtained if rho is negative number, the absolute value | rho | of the positive correlation coefficient is closer to 1, the correlation of the two variables is larger, | rho | is more than or equal to 0.8 and is strong correlation, | rho | is less than or equal to 0.3 and is weak correlation, and | rho | is less than or equal to 0.3<|ρ|<0.8 is a general correlation, and | ρ | ═ 0 indicates that there is no linear correlation between them.

It should be noted that, after the network problem corresponding to the target network representation is determined, the most important index in the target network representation, that is, the network performance index with the highest correlation degree to the determined network problem, may be determined by calculating the correlation between each network performance index in the target network representation and the determined network problem.

Preferably, after determining the network problem corresponding to the target network representation through steps S103b and S104b, the method provided by the embodiment of the present invention may further include: and determining a solution of the network problem corresponding to the target network representation through the network problem corresponding to the target network representation and the target case library.

Further, the process of determining a solution of the network problem corresponding to the target network representation through the network problem corresponding to the target network representation and the target case library may include: and determining a case containing the network problem corresponding to the target network representation from the target case library, and determining a solution in the case containing the network problem corresponding to the target network representation as a solution of the network problem corresponding to the target network representation.

Preferably, after determining a network problem corresponding to the target network representation and a solution of the network problem corresponding to the target network representation, the method provided in the embodiment of the present invention may further include: and forming a new case by the target network representation, the network problem corresponding to the target network representation and the solution of the network problem corresponding to the target network representation, and storing the new case into a target case library so as to provide an analysis basis for the subsequent network problems.

According to the method for determining the network problem, provided by the embodiment of the invention, the matching case can be found out from the target case library through the target network characterization, the network problem is determined through the matching case, and if the matching case is not found out in the case library, the network problem of the target network characterization is determined through the target rule library and the target case library based on the target network characterization. Therefore, the method for determining the network problem provided by the embodiment of the invention can automatically determine the network problem corresponding to the target network representation by utilizing the target case base and the target rule base based on the target network representation without depending on network optimization personnel, thereby improving the efficiency of network optimization and reducing the cost of network optimization.

A specific implementation process of acquiring the target network representation in step S101 is described below, please refer to fig. 2, which shows a flowchart of the specific implementation process of acquiring the target network representation, and the specific implementation process may include:

step S201: a set of network performance indicators is obtained from a target communication network.

The set of network performance indicators includes all of the network performance indicators obtained from the target communication network.

Step S202: and clearing the interfered network performance indexes from the network performance index set to obtain a target network performance index set.

In order to reduce the false rate of the identification and clustering of the subsequent abnormal network performance indexes, the embodiment first clears the interfered network performance indexes from the network performance index set. The network performance index of the interference may include a network performance index corresponding to a test user behavior, a network performance index corresponding to a special service behavior, and a network performance index corresponding to a client active behavior.

Step S203: an abnormal network performance indicator is identified from the set of target network performance indicators.

In this embodiment, there are various ways to identify the abnormal network performance index.

In one possible implementation, the abnormal network performance indicator may be identified by presetting an abnormal threshold and comparing the network performance indicator with the abnormal threshold, for example, comparing a value of the network performance indicator with the abnormal threshold, and if the value of the network performance indicator is greater than the abnormal threshold, determining that the network performance indicator is the abnormal network performance indicator.

In another possible implementation manner, it is assumed that the target network performance indexes in the target network performance index set are normally distributed, and the abnormal network performance indexes are small-probability events therein, that is, the network performance indexes with values greater than (mean + a × standard deviation) or values less than (mean-a × standard deviation) are determined as the abnormal network performance indexes, where a is a set coefficient.

It is understood that, at some time, the target network performance indicators in the target network performance indicator set may not exhibit a normal distribution, but a positive slope distribution/a negative slope distribution/a multi-peak distribution, based on which, in yet another possible implementation, the network performance indicators with values greater than (median + a × standard deviation) or less than (median-a × standard deviation) may be determined as abnormal network performance indicators. In the process of identifying the abnormal network performance indexes in the mode, the parameter a can be adjusted according to the ratio of the number of the actually identified abnormal network performance indexes to the total number of the indexes in the target network performance index set, and the parameter a is applied to the identification of the subsequent abnormal network performance indexes. In addition, in order to reduce the false rate and the false rate, the identification can be carried out in combination with the abnormal threshold identification mode in the identification process. The median is determined by the following formula:

the median is a median, N is the number of network performance indexes in the target network performance index set, data in the target network performance index set is divided into a plurality of intervals based on the value of the network performance indexes, the median interval is determined, and L is a median interval₁At the lower bound of the median interval, freq_medianThe frequency of the median interval, i.e. the number of network performance indicators in the median interval, (∑ freq)_lThe width is the width of the median interval, which is the sum of the frequencies of all the regions lower than the median interval.

Step S204: and clustering the abnormal network performance indexes to obtain a network characterization set.

Although the abnormal network performance indexes can represent abnormal situations, the abnormal network performance indexes are split, and whether the abnormal situations are individual phenomena or group phenomena cannot be judged, and in addition, the reasons causing the abnormal situations are not consistent, for example, some abnormal situations are caused by terminal reasons, some abnormal situations are caused by cell abnormalities, some abnormal situations are caused by core network abnormalities, some abnormal situations are caused by mismatching of terminals and services, some abnormal situations are caused by SP service provider servers, and even some abnormal situations are caused by different user behavior habits. In order to determine the network problem quickly, the embodiment clusters the abnormal network performance indexes, which is equivalent to classifying the abnormal network performance indexes, for example, the abnormal network performance indexes caused by the terminal cause are grouped together to form a network representation, the abnormal network performance indexes caused by the cell abnormality are grouped together to form a network representation, and the like.

Step S205: and acquiring the target network representation from the network representation set.

Referring to fig. 3, a flow diagram of a specific implementation process of searching for a target case in a target case library based on a target network representation in step S102 is shown, and the specific implementation process may include:

step S301: and finding out candidate cases in the target case base based on the target network characterization.

Wherein the network characterization of the candidate case is the same as the target network characterization.

It should be noted that the fact that the network representation of the candidate case is the same as the target network representation means that the network performance index included in the network representation of the candidate case is the same as the network performance index included in the target network representation. Illustratively, the target network characterization includes two network performance indicators KPIs₁And KPI₂Then the network characterization of the candidate case should also include two network performance indicators, and the two network performance indicators should also be KPIs₁And KPI₂。

In addition, it should be noted that if the candidate case is not found in the target case base, it indicates that the target case is not found in the target case base, then S103b is executed: and determining a candidate network problem set through a target rule base and a target case base based on the target network characterization.

Step S302: and judging whether the candidate cases are multiple or not.

Step S303 a: and if one candidate case is available, calculating the similarity between the network representation of the candidate case and the target network representation.

Step S304 a: and judging whether the similarity between the network representation of the candidate case and the target network representation is greater than a set threshold, and if so, executing S305 a.

It should be noted that, if the similarity between the network representation of the candidate case and the target network representation is less than or equal to the set threshold, it indicates that the target case is not found in the target case library, then S103b is executed: and determining a candidate network problem set through a target rule base and a target case base based on the target network characterization.

Step S305 a: and determining the candidate case as the target case.

Step S303 b: if the candidate cases are multiple, respectively calculating the similarity between the network representation of each case in the target case library and the target network representation, and obtaining the similarity corresponding to each case.

Step S304 b: the maximum similarity is determined from the similarities corresponding to the respective cases.

Step S305 b: and judging whether the maximum similarity is larger than a set threshold value or not.

Step S306 b: and if the maximum similarity is larger than the set threshold, determining the case corresponding to the maximum similarity as the target case.

It should be noted that, if the maximum similarity is less than or equal to the set threshold, it indicates that the target case is not found in the target case library, then S103b is executed: and determining a candidate network problem set through a target rule base and a target case base based on the target network characterization.

Based on that, another method for determining a network problem is provided in an embodiment of the present invention, which determines a network problem corresponding to a target network representation preferentially through a target rule base from the viewpoint of increasing a determination speed of the network problem, and determines a network problem corresponding to the target network representation by further combining the target case base and a data analysis method when the network problem cannot be determined through the target rule base, referring to fig. 4, a flow diagram of the method for determining a network problem is shown, where the method includes:

step S401: and acquiring a target network representation.

Step S402: target rules are looked up in a target rule base based on the target network characterization.

The target rule base comprises a plurality of rules, and the rules are used for representing the matching relation between the network representation and the network problems. The target rule is a rule matching the target network representation.

The process of finding a target rule in a target rule base based on a target network characterization may include: firstly, searching candidate network representations in network representations corresponding to all rules in a target rule base, wherein the candidate network representations comprise network performance indexes in the target network representations; secondly, after the candidate network characterizations are found, if the candidate network characterizations are one, calculating the similarity between the candidate network characterizations and the target network characterizations, judging whether the calculated similarity is greater than a set value, and if so, determining a rule corresponding to the candidate network characterizations as a target rule; if the candidate network characterizations are multiple, respectively calculating the similarity between each candidate network characterization and the target network characterization, obtaining the similarity corresponding to each candidate network characterization, determining the maximum similarity from the similarities corresponding to each candidate network characterization, judging whether the maximum similarity is greater than a set value, and if so, determining a rule corresponding to the candidate network characterization corresponding to the maximum similarity as a target rule.

It should be noted that, when the similarity between the candidate network representation and the target network representation is calculated, the similarity between the network performance index in the target network table and the corresponding network performance index in the candidate network representation is calculated.

Step S403 a: if the target rule is found, determining the network problem corresponding to the target network representation through the target rule, and then executing the steps S406-S408.

Step S403 b: and if the target rule is not found, searching a target case in the target case base based on the target network representation.

The target case library comprises a plurality of cases, and each case comprises a network representation, a network problem and a solution. In this embodiment, the target case is a case matching the target network representation.

The process of searching for the target case in the target case base based on the target network characterization may be referred to the above embodiments, and is not described herein again.

Step S404 ba: if the target case is found in the target case base, determining the network problem and solution corresponding to the target network representation through the target case, and then executing steps S408 and S409.

Specifically, the network problem of the target case is determined as the network problem corresponding to the target network representation, and the solution of the target case is determined as the solution of the network problem corresponding to the target network representation.

Step S404 bb: and if the target case is not found in the target case base, determining a candidate network problem set through the target rule base and the target case base based on the target network characterization.

Step S405 bb: and respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, determining the candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization, and then executing steps S406-S409.

Step S406: after the network problem corresponding to the target network representation is determined, a case containing the network problem corresponding to the target network representation is found out from the target case base.

Step S407: and determining the solution of the case containing the network problem corresponding to the target network characterization as the solution of the network problem corresponding to the target network characterization.

Step S408: and storing the target network representation, the network problem corresponding to the target network representation and the solution composition case of the network problem corresponding to the target network representation into a target case library.

Step S409: and generating a new rule for the target network representation and the network problem corresponding to the target network representation, and storing the generated new rule in a target rule base.

In the method for determining a network problem provided in the embodiment of the present invention, in consideration of the fact that the efficiency of determining a network problem through rules in the rule base is high, a rule matching with a target network representation is first searched in the target rule base, if the rule matching with the target network representation is found, the network problem corresponding to the target network representation is determined through the rule matching with the target network representation, and if the rule matching with the target network representation is not found, the network problem corresponding to the target network representation is further determined through the target rule base and the target case base based on the target network representation. Therefore, the method for determining the network problem provided by the embodiment of the invention can automatically determine the network problem by using the target case base and the target rule base based on the target network representation without depending on network optimization personnel, thereby improving the efficiency of network optimization, reducing the cost of network optimization, and when determining the network problem, the embodiment firstly determines based on the target rule base, and then determines based on the target case base and the target rule base in combination with a data analysis method, thereby further improving the efficiency of network optimization.

The present invention also provides a method for determining a network problem, please refer to fig. 5, which shows a flow diagram of the method, and the method may include:

step S501: acquiring a target network characteristic and a target analysis mode, wherein the target analysis mode comprises one of a professional analysis mode, a mathematical analysis mode and a hybrid analysis mode;

step S502 a: and when the target analysis mode is a professional analysis mode, determining a network problem corresponding to the target network representation through a first analysis method.

Wherein the first analysis method comprises: and determining a matching rule of the target network representation from a target rule base as a target rule, and determining a network problem corresponding to the target network representation through the target rule, wherein the target rule base comprises a plurality of rules, and the rules are used for representing the matching relationship between the network representation and the network problem.

Step S502 b: and when the target analysis mode is the mathematical analysis mode, determining a network problem corresponding to the target network representation through a second analysis method.

Wherein the second analysis method comprises: determining a case matched with the target network characterization from a target case library as a target case, determining a network problem corresponding to the target network characterization through the target case, if the target case does not exist in the target case library, determining a candidate network problem set through a target rule library and the target case library based on the target network, respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, and determining the candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization, wherein the target case library comprises a plurality of cases, and each case at least comprises the network problem and the network characterization.

It should be noted that, for specific implementation processes of the first analysis method and the second analysis method, reference may be made to the foregoing embodiments, which are not described herein again.

Step S502 c: and when the target analysis mode is a hybrid analysis mode, determining a network problem corresponding to the target network representation through a first analysis method and a second analysis method.

It should be noted that, in this embodiment, specific implementation processes of the first analysis method and the second analysis method may be referred to in the foregoing embodiments, and are not described herein again.

The method for determining the network problem provided by the embodiment of the invention can analyze the target network representation based on the target analysis mode and determine the network problem corresponding to the target network representation without depending on network optimization personnel, so that the efficiency of network optimization can be improved, and the cost of network optimization is reduced.

An embodiment of the present invention further provides a device for determining a network problem, please refer to fig. 6, which shows a schematic structural diagram of the device, where the device may include: an obtaining module 601, a first searching module 602, a first determining module 603, a second determining module 604, a third determining module 605 and a fourth determining module 606. Wherein:

an obtaining module 601, configured to obtain a target network representation.

A first searching module 602, configured to search, based on the target network characterization, a case matching the target network characterization in the target case base as a target case.

The first determining module 603 is configured to determine, when the target case is found in the target case base, a network problem corresponding to the target network representation through the target case.

The target case library comprises a plurality of cases, and each case at least comprises a network problem and a network representation.

A second determining module 604, configured to determine, based on the target network characterization, a candidate network problem set through the target rule base and the target case base when the target case is not found in the target case base.

A third determining module 605, configured to determine a correlation between each candidate network problem in the candidate network problem set and the target network characterization respectively.

A fourth determining module 606, configured to determine the candidate network problem with the largest correlation with the target network characterization as the network problem corresponding to the target network characterization.

The device for determining the network problem provided by the embodiment of the invention can find out the matching case from the target case library through the target network characterization, determine the network problem through the matching case, and determine the network problem through the target rule library and the target case library based on the target network characterization if the matching case is not found in the case library. Therefore, the device for determining the network problems provided by the embodiment of the invention can automatically determine the network problems by utilizing the target case base and the target rule base based on the target network representation without depending on network optimization personnel, thereby improving the efficiency of network optimization and reducing the cost of network optimization.

The apparatus for determining a network problem provided in the foregoing embodiment may further include: a second lookup module and a fifth determination module.

And the second searching module is used for searching a target rule in the target rule base based on the target network representation after the obtaining module obtains the target network representation, wherein the target rule is a rule matched with the target network representation.

And the fifth determining module is used for determining the network problem corresponding to the target network representation through the target rule when the target rule is found.

And when the second searching module does not search the target rule, the first searching module searches the target case in the target case base on the target network representation.

In the above embodiment, each case in the target case base further includes: a solution to the network problem. In the apparatus for determining a network problem provided in the foregoing embodiment, the first determining module 603 is specifically configured to determine the network problem in the target case as the network problem corresponding to the target network representation.

The apparatus for determining a network problem provided in the foregoing embodiment may further include: and a sixth determining module.

A sixth determining module, configured to determine, after the first determining module 603 determines the network problem corresponding to the target network representation through the target case, a solution in the target case as a solution to the network problem corresponding to the target network representation.

The apparatus for determining a network problem provided in the foregoing embodiment may further include: and a seventh determining module.

A seventh determining module, configured to determine, after the fourth determining module 606 determines the network problem corresponding to the target network representation, a case including the network problem corresponding to the target network representation from the target case library, and determine a solution in the case including the network problem corresponding to the target network representation as a solution to the network problem corresponding to the target network representation.

The apparatus for determining a network problem provided in the foregoing embodiment may further include: and an eighth determining module.

And the eighth determining module is used for determining a case containing the network problem corresponding to the target network representation from the target case library after the fifth determining module determines the network problem corresponding to the target network representation through the target rule, and determining a solution in the case containing the network problem corresponding to the target network representation as a solution of the network problem corresponding to the target network representation.

The apparatus for determining a network problem provided in the foregoing embodiment may further include: the system comprises a case construction module and a case storage module. Wherein:

and the case construction module is used for forming a new case by the target network representation, the network problem corresponding to the target network representation and the solution of the network problem corresponding to the target network representation.

And the case storage module is used for storing the new case constructed by the case construction module to the target case base.

The apparatus for determining a network problem provided in the foregoing embodiment may further include: the device comprises a rule generating module and a rule storing module. Wherein:

and the rule generating module is used for generating a new rule for the network problem corresponding to the target network representation and the target network representation when the target rule is not found in the target rule base based on the target network representation.

And the rule storage module is used for storing the new rule generated by the rule generation module into the target rule base.

In the apparatus for determining a network problem provided in the foregoing embodiment, the obtaining module 601 may include: the device comprises a first obtaining submodule, an interference clearing submodule, an abnormity identification submodule, an abnormity clustering submodule and a second obtaining submodule.

The first obtaining submodule is used for obtaining a network performance index set from a target communication network.

And the interference elimination submodule is used for eliminating the interfered network performance indexes from the network performance index set to obtain a target network performance index set.

And the abnormity identification submodule is used for identifying abnormal network performance indexes from the target network performance index set.

And the abnormal clustering submodule is used for clustering the abnormal network performance indexes to obtain a network characterization set, wherein each network characterization in the network characterization set is a type of network performance index obtained by clustering.

And the second acquisition submodule is used for acquiring the target network representation from the network representation set.

In the apparatus for determining a network problem provided in the foregoing embodiment, the first lookup module 602 may include: the device comprises a searching submodule, a first calculating submodule, a first judging submodule, a first determining submodule, a second calculating submodule, a second determining submodule, a second judging submodule and a third determining submodule. Wherein:

and the searching submodule is used for finding out a candidate case from the target case library, wherein the network characterization of the candidate case is the same as the target network characterization.

And the first calculation submodule is used for calculating the similarity between the network representation of the candidate case and the target network representation when the candidate case is one.

And the first judgment submodule is used for judging whether the similarity is greater than a set threshold value.

And the first determining submodule is used for determining the candidate case as the target case when the similarity is greater than the set threshold.

And the second calculating submodule is used for respectively calculating the similarity between the network representation of each candidate case and the target network representation when the candidate cases are multiple, and obtaining the similarity corresponding to each candidate case.

And the second determining submodule is used for determining the maximum similarity from the similarities corresponding to the candidate cases.

And the second judgment submodule is used for judging whether the maximum similarity is larger than the set threshold value or not.

And the third determining submodule is used for determining the case corresponding to the maximum similarity as the target case when the maximum similarity is larger than the set threshold.

In the apparatus for determining a network problem provided in the foregoing embodiment, the second determining module 704 may include: the device comprises a first determining submodule, a second determining submodule and a combination module;

the first determining submodule is used for determining a network characterization containing at least one network performance index in the target network characterization from the network characterizations corresponding to the rules in the target rule base, obtaining at least one candidate network characterization, and determining at least one network problem corresponding to the at least one candidate network characterization as a candidate network problem.

And the second determining submodule is used for determining the network characterization containing at least one network performance index in the target network characterization from each case in the target case library, obtaining at least one candidate network characterization, and determining at least one network problem corresponding to the at least one candidate network characterization as a candidate network problem.

And the combination module is used for combining all the candidate network problems determined by the first determining submodule and the second determining submodule into a candidate network problem set.

An embodiment of the present invention further provides a device for determining a network problem, please refer to fig. 7, which shows a schematic structural diagram of the device, where the device may include: an acquisition module 701, a first determination module 702a, a second determination module 702b, and a third determination module 702 c. Wherein:

an obtaining module 701, configured to obtain a target network characteristic and a target analysis mode, where the target analysis mode includes one of a professional analysis mode, a mathematical analysis mode, and a hybrid analysis mode;

a first determining module 702a, configured to determine, when the target analysis mode is a professional analysis mode, a network problem corresponding to the target network characterization through a first analysis method, where the first analysis method includes: and determining a matching rule of the target network representation from a target rule base as a target rule, and determining a network problem corresponding to the target network representation through the target rule, wherein the target rule base comprises a plurality of rules, and the rules are used for representing the matching relationship between the network representation and the network problem.

A second determining module 702b, configured to determine, when the target analysis mode is a mathematical analysis mode, a network problem corresponding to the target network characterization through a second analysis method, where the second analysis method includes: determining a case matched with the target network characterization from a target case library as a target case, determining a network problem corresponding to the target network characterization through the target case, if the target case does not exist in the target case library, determining a candidate network problem set through a target rule library and the target case library based on a target network, respectively determining the correlation between each candidate network problem in the candidate network problem set and the target network characterization, and determining the candidate network problem with the maximum correlation with the target network characterization as the network problem corresponding to the target network characterization, wherein the target case library comprises a plurality of cases, and each case at least comprises the network problem and the network characterization.

A third determining module 702c, configured to determine, by the first analysis method and the second analysis method, a network problem corresponding to the target network representation when the target analysis mode is the hybrid analysis mode.

The device for determining the network problem provided by the embodiment of the invention can analyze the target network representation based on the target analysis mode and determine the network problem corresponding to the target network representation without depending on network optimization personnel, so that the efficiency of network optimization can be improved, and the cost of network optimization is reduced.

An embodiment of the present invention further provides a storage medium, where a program is stored in the storage medium, and the program executes the method for determining the network problem.

The embodiment of the invention also provides a processor, which is used for running the program, wherein the method for determining the network problem is executed when the program runs.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

In the several embodiments provided in the present application, it should be understood that the disclosed method, apparatus, and device may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a network problem, comprising:

acquiring a target network representation;

2. The method of claim 1, wherein after obtaining the target network characterization, the method further comprises:

3. The method of claim 2, wherein each case in the target case base further comprises: solutions to network problems;

4. The method of determining network problems of claim 3, further comprising:

5. The method according to any one of claims 1 to 4, wherein the obtaining a target network representation comprises:

identifying an abnormal network performance indicator from the set of target network performance indicators;

6. The method for determining the network problem according to any one of claims 1 to 4, wherein the searching for the case matching the target network characterization in the target case base based on the target network characterization as the target case comprises:

finding out a candidate case in the target case base based on a target network characterization, wherein the network characterization of the candidate case is the same as the target network characterization;

7. The method for determining the network problem according to any one of claims 1 to 4, wherein the determining the set of candidate network problems through the target rule base and the target case base based on the target network comprises:

8. A method for determining a network problem, comprising:

9. An apparatus for determining a network problem, comprising: the device comprises an acquisition module, a search module, a first determination module and a second determination module;

10. An apparatus for determining a network problem, comprising: the device comprises an acquisition module, a first determination module, a second determination module and a third determination module;

and the third determining module is configured to determine, by the first analysis method and the second analysis method, a network problem corresponding to the target network representation when the target analysis mode is the hybrid analysis mode.