CN113489602A - Communication fault positioning method and system based on data mining - Google Patents
Communication fault positioning method and system based on data mining Download PDFInfo
- Publication number
- CN113489602A CN113489602A CN202110681583.9A CN202110681583A CN113489602A CN 113489602 A CN113489602 A CN 113489602A CN 202110681583 A CN202110681583 A CN 202110681583A CN 113489602 A CN113489602 A CN 113489602A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- event
- causal
- cause
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000004891 communication Methods 0.000 title claims abstract description 45
- 238000007418 data mining Methods 0.000 title claims abstract description 23
- 230000001364 causal effect Effects 0.000 claims description 43
- 238000010586 diagram Methods 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 230000009021 linear effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 238000003745 diagnosis Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- JXASPPWQHFOWPL-UHFFFAOYSA-N Tamarixin Natural products C1=C(O)C(OC)=CC=C1C1=C(OC2C(C(O)C(O)C(CO)O2)O)C(=O)C2=C(O)C=C(O)C=C2O1 JXASPPWQHFOWPL-UHFFFAOYSA-N 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
-
- 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
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a communication fault positioning method and system based on data mining, which solve the problems of long time consumption and low accuracy of the implementation process of the current communication fault positioning method.
Description
Technical Field
The invention relates to the technical field of communication service, in particular to a communication fault positioning method and system based on data mining.
Background
In a communication network, due to the fact that the number of people using the internet is increased dramatically, data sources are diversified, data dimensionality is high, manual troubleshooting is time-consuming and labor-consuming, when the communication network breaks down, a system cannot timely troubleshoot correct failure root causes, the failure cannot be repaired timely, the breakdown of the whole network is easily caused, and the loss difficult to calculate is caused.
Further, it is assumed that several fault alarms have occurred and it is desired to resolve the target alarm with priority. Conventionally, algorithm processing is performed on the basis of the correlation relationship, and results with strong correlation with target alarms are obtained, and the processing results interfered by a large number of related candidate factors bring huge maintenance cost to the global network, and even exceed the processing load of a machine if too many alarms are given, so that the method is not feasible.
In 2019, 19.4.9, a chinese patent invention (publication No. CN109656793A) discloses a method for three-dimensional monitoring of information system performance based on multi-source heterogeneous data fusion, which includes the following steps: (1) collecting performance index monitoring data of an information system; performing data fusion processing on the obtained multi-source heterogeneous index data; (3) detecting abnormal information of each performance index data by the fused index data through an information system performance evaluation model, and carrying out fault root positioning on the abnormal information; (4) predicting the data value of each index at the next moment, and sensing the performance situation of the system in advance; (5) the fault information is accessed to an alarm platform and is subjected to unified formatting treatment, then the similar mining and merging compression are carried out on the alarm information through an associated mining strategy, and finally the compressed alarm information is sent to relevant personnel for processing. The information system performance evaluation model comprises an anomaly detection module and a fault positioning module, the core foundation of the fault positioning module is a fault diagnosis tree submodule, the fault positioning module is used for carrying out deep excavation and final locking on suspected root causes of current anomaly indexes according to a fault diagnosis tree formed by knowledge experience of layer-by-layer diagnosis and step-by-step exploration on the anomaly indexes in the past, and the patent scheme realizes multi-azimuth monitoring on the performance of an information system through a diversified information system performance data acquisition platform. The fault diagnosis tree method can generally find out the event of the suspected fault root, but is time-consuming, and in addition, the accuracy of a new fault event needs to be improved.
Disclosure of Invention
In order to solve the problems of long time consumption and low accuracy in the implementation process of the current communication fault positioning method, the invention provides a communication fault positioning method and system based on data mining, the method is high in operation speed, and the simplified and rapid positioning of communication faults is realized.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
a communication fault positioning method based on data mining at least comprises the following steps:
s1, collecting event data in a communication service system, wherein the event data comprises daily monitoring data, log data and historical data, and preprocessing the event data;
s2, determining a component with a fault according to the log data, namely determining the fault in the event corresponding to the event data;
s3, taking the fault as a father node and the event as a child node, and analyzing the relation between the father node and the child node, namely, determining the reason of the fault of the event;
s4, combining the output of the step S3, introducing variables, constructing a causal full-connection diagram with observed values, and processing the irrelevant condition redundancy relation in the causal full-connection diagram to obtain a fault connection diagram;
s5, determining the direction of the boundary of the fault connection diagram to obtain a component KPI causal diagram;
s6, determining a fault cause set corresponding to the event, taking the fault cause set corresponding to the event as the input of the KPI causal graph, outputting a fault root set through the KPI causal graph, and confirming the possibility that the fault cause is the root cause;
and S7, tracing the root cause of the fault by combining a weight distribution method, thereby positioning the fault.
Preferably, before collecting the event data in step S1, the knowledge of the communication service is learned, where the communication service includes the topology, configuration information, and traffic rules of the communication system.
Preferably, the types of event data include structured data, semi-structured data, and unstructured data.
Preferably, the preprocessing method in step S1 is normalization processing.
Here, since various data have different sources, in order to eliminate differences, normalization processing is performed on the data, and correspondence between the data is sorted.
Preferably, when the independent condition redundancy relationship processing in the causal fully-connected graph is performed in step S4, a condition independence check is performed on two adjacent variables, where the condition independence check is based on a partial correlation coefficient and has an expression:
wherein r is12、r13、r23Respectively represent a correlation coefficient between a variable x1 and a variable x2, a correlation coefficient between a variable x1 and a variable x2, and a correlation coefficient between a variable x2 and a variable x 3; r is12(3)When the net correlation between variables x1 and x2 is analyzed, the first order partial correlation coefficient between x1 and x2 when the linear action of variable x3 is controlled;
and if the two adjacent variables have condition independence, deleting the edge between the two adjacent variables in the full-connected graph, and rejecting the irrelevant condition redundancy relation in the causal full-connected graph.
The PC algorithm is used for composition, the PC algorithm is a classical and strong constraint learning-based method, and the PC algorithm based on the independence test of partial correlation is very optimistic in operation speed
Preferably, the process of determining the direction of the fault connection map boundary in step S5 is:
let two variables in the fault connection graph be v1And v2，v1And v2There is a direct causal connection between them; inferring v from asymmetries present in event data1And v2Causal direction between, i.e. to distinguish v in fault connection graphs1And v2Causal direction between v1→v2Is also v1←v2。
Preferably, in step S7, when tracing the source of the root cause causing the failure, the root cause paths on the KPI cause-and-effect graph are sorted, and the root cause paths are determined according to the highest priority in the sorting.
Preferably, when sorting the root cause paths, the greater the sum of the weights of all edges of the paths on the KPI cause and effect graph, the higher the priority.
Preferably, the shorter the path length on the KPI cause and effect graph, the higher the priority when ordering the root cause path.
The invention also provides a communication fault positioning system based on data mining, which is used for realizing the communication fault positioning method based on data mining and comprises the following steps:
the event data acquisition and preprocessing module is used for acquiring and preprocessing event data in the communication service system, including daily monitoring data, log data and historical data;
the failure component confirmation module is used for determining a failed component according to the log data, namely confirming the failure in the event corresponding to the event data;
the fault reason analysis module is used for taking the fault as a father node and taking the event as a child node, analyzing the relation between the father node and the child node and determining the reason of the fault of the event;
the fault connection diagram construction module is used for constructing a cause and effect full connection diagram with an observation value, and processing the irrelevant condition redundancy relation in the cause and effect full connection diagram to obtain a fault connection diagram;
the boundary direction confirmation module is used for determining the direction of the boundary of the fault connection diagram to obtain a component KPI causal diagram;
the root cause inference module is used for determining a fault cause set corresponding to the event, taking the fault cause set corresponding to the event as the input of the KPI causal graph, outputting a fault root cause set through the KPI causal graph, and confirming the possibility that the fault cause is the root cause;
and the fault positioning module is used for tracing the root cause causing the fault by combining a weight distribution method, so that the fault is positioned.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention provides a communication fault positioning method and system based on data mining, wherein the method comprises the processes of acquisition and processing of basic data, construction of a KPI causal graph for fault positioning and fault root factor output, in the process of construction of the KPI causal graph for fault positioning, condition independence inspection is adopted to eliminate redundant relation, the defect of long time consumption of the traditional method for fault diagnosis tree operation is avoided, then a weight distribution method is combined, the KPI causal graph is used for outputting the fault root factor, the method has the unique advantages of source tracing, the accuracy is high, the method operation speed is high, and the simplified and rapid positioning of communication faults can be realized.
Drawings
Fig. 1 is a schematic flow chart illustrating a communication fault location method based on data mining according to an embodiment of the present invention;
fig. 2 is a block diagram of a communication fault location system based on data mining according to an embodiment of the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for better illustration of the present embodiment, certain parts of the drawings may be omitted, enlarged or reduced, and do not represent actual dimensions;
it will be understood by those skilled in the art that certain well-known descriptions of the figures may be omitted.
The positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
the technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Examples
The invention provides a communication fault positioning method based on data mining with high operation speed, which aims to realize simplified fault and quick positioning in a communication system facing a huge and complex fault network when a fault occurs.
The method provided by the invention comprises three stages of model knowledge acquisition, fault model construction and fault root factor output; the model knowledge acquisition mainly comprises three steps of business knowledge (communication business) learning, event data collection and data preprocessing; the fault model construction (KPI causal graph) mainly comprises two steps of condition independence inspection and component KPI causal graph output; the output fault root mainly comprises two steps of outputting the most possible influencing factors causing the fault and positioning the fault root.
Specifically, referring to a flowchart of a communication fault location method based on data mining shown in fig. 1, the method includes the following steps:
s1, collecting event data in a communication service system, wherein the event data comprises daily monitoring data, log data and historical data, and preprocessing the event data;
s2, determining a component with a fault according to the log data, namely determining the fault in the event corresponding to the event data;
s3, taking the fault as a father node and the event as a child node, and analyzing the relation between the father node and the child node, namely, determining the reason of the fault of the event;
s4, combining the output of the step S3, introducing variables, constructing a causal full-connection diagram with observed values, and processing the irrelevant condition redundancy relation in the causal full-connection diagram to obtain a fault connection diagram;
s5, determining the direction of the boundary of the fault connection diagram to obtain a component KPI causal diagram;
s6, determining a fault cause set corresponding to the event, taking the fault cause set corresponding to the event as the input of the KPI causal graph, outputting a fault root set through the KPI causal graph, and confirming the possibility that the fault cause is the root cause;
and S7, tracing the root cause of the fault by combining a weight distribution method, thereby positioning the fault.
In this embodiment, before collecting event data in step S1, knowledge of communication services including communication system topology, configuration information, and flow rules is also learned, so as to lay a foundation for the subsequent KPI causal graph construction.
In this embodiment, the types of the event data include structured data, semi-structured data, and unstructured data.
Due to multi-source isomerism among various data, in order to eliminate difference, normalization processing is carried out on the data, and the corresponding relation among the data is combed. In this embodiment, the preprocessing method described in step S1 is normalization processing.
When the irrelevant condition redundant relationship processing in the causal full-connected graph is performed in the step S4, the conditional independence test is performed on two adjacent variables, the conditional independence test is based on a partial correlation coefficient, and the expression is as follows:
wherein r is12、r13、r23Respectively represent a correlation coefficient between a variable x1 and a variable x2, a correlation coefficient between a variable x1 and a variable x2, and a correlation coefficient between a variable x2 and a variable x 3; r is12(3)When the net correlation between variables x1 and x2 is analyzed, the first order partial correlation coefficient between x1 and x2 when the linear action of variable x3 is controlled;
and if the two adjacent variables have condition independence, deleting the edge between the two adjacent variables in the full-connected graph, and rejecting the irrelevant condition redundancy relation in the causal full-connected graph.
In this embodiment, the process of determining the direction of the fault connection map boundary in step S5 is as follows:
let two variables in the fault connection graph be v1And v2，v1And v2There is a direct causal connection between them; inferring v from asymmetries present in event data1And v2Causal direction between, i.e. to distinguish v in fault connection graphs1And v2Causal direction between v1→v2Is also v1←v2。
In this embodiment, the probability formula for confirming that the failure cause is the root cause in step S6 is:
where 1 is an indicator function representing a rule set
Whether or not there is
Or sample SiWhether or not to include I0And e0；ε0For all events occurring within a certain time, e0Is an event occurring therein; i is0Represents the root failure cause set, p (I)0) Representing the probability of the root cause.
In this embodiment, when tracing the source of the root cause causing the failure in step S7 by using the weight assignment method, the root cause paths on the KPI cause and effect graph are sorted, and the root cause path is determined according to the highest priority of the sorting.
Here, the weight distribution method may use an analytic hierarchy process, a principal component analysis process, or a priority graph process to calculate the weight as needed, and is not limited to these three processes, and will not be described herein again.
When the root cause path is confirmed according to the highest priority of the ranking, the following two rules can be selected for ranking the root cause path:
rule one is as follows:
when the root cause paths are sorted, the larger the sum of the weights of all edges of the paths on the KPI causal graph is, the higher the priority is.
Rule two:
when sorting the root cause paths, the shorter the path length on the KPI cause and effect graph, the higher the priority.
As shown in fig. 2, the present invention further provides a communication fault location system based on data mining, where the system is configured to implement the communication fault location method based on data mining, and the method includes:
the event data acquisition and preprocessing module is used for acquiring and preprocessing event data in the communication service system, including daily monitoring data, log data and historical data;
the failure component confirmation module is used for determining a failed component according to the log data, namely confirming the failure in the event corresponding to the event data;
the fault reason analysis module is used for taking the fault as a father node and taking the event as a child node, analyzing the relation between the father node and the child node and determining the reason of the fault of the event;
the fault connection diagram construction module is used for constructing a cause and effect full connection diagram with an observation value, and processing the irrelevant condition redundancy relation in the cause and effect full connection diagram to obtain a fault connection diagram;
the boundary direction confirmation module is used for determining the direction of the boundary of the fault connection diagram to obtain a component KPI causal diagram;
the root cause inference module is used for determining a fault cause set corresponding to the event, taking the fault cause set corresponding to the event as the input of the KPI causal graph, outputting a fault root cause set through the KPI causal graph, and confirming the possibility that the fault cause is the root cause;
and the fault positioning module is used for tracing the root cause causing the fault by combining a weight distribution method, so that the fault is positioned.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A communication fault positioning method based on data mining is characterized by at least comprising the following steps:
s1, collecting event data in a communication service system, wherein the event data comprises daily monitoring data, log data and historical data, and preprocessing the event data;
s2, determining a component with a fault according to the log data, namely determining the fault in the event corresponding to the event data;
s3, taking the fault as a father node and the event as a child node, and analyzing the relation between the father node and the child node, namely, determining the reason of the fault of the event;
s4, combining the output of the step S3, introducing variables, constructing a causal full-connection diagram with observed values, and processing the irrelevant condition redundancy relation in the causal full-connection diagram to obtain a fault connection diagram;
s5, determining the direction of the boundary of the fault connection diagram to obtain a component KPI causal diagram;
s6, determining a fault cause set corresponding to the event, taking the fault cause set corresponding to the event as the input of the KPI causal graph, outputting a fault root set through the KPI causal graph, and confirming the possibility that the fault cause is the root cause;
and S7, tracing the root cause of the fault by combining a weight distribution method, thereby positioning the fault.
2. The method for locating communication faults based on data mining of claim 1, wherein the knowledge of communication services including communication system topology, configuration information and traffic rules is learned before the event data is collected in step S1.
3. The data mining-based communication fault location method of claim 1, wherein the types of event data include structured data, semi-structured data, and unstructured data.
4. The method for locating communication failure based on data mining of claim 3, wherein the preprocessing manner of step S1 is normalization processing.
5. The communication fault location method based on data mining of claim 4, wherein when the irrelevant condition redundancy relationship processing in the causal fully-connected graph is performed in step S4, the conditional independence check is performed on two adjacent variables, wherein the conditional independence check is based on a partial correlation coefficient, and the expression is as follows:
wherein r is12、r13、r23Respectively represent a correlation coefficient between a variable x1 and a variable x2, a correlation coefficient between a variable x1 and a variable x2, and a correlation coefficient between a variable x2 and a variable x 3; r is12(3)When the net correlation between variables x1 and x2 is analyzed, the first order partial correlation coefficient between x1 and x2 when the linear action of variable x3 is controlled;
and if the two adjacent variables have condition independence, deleting the edge between the two adjacent variables in the full-connected graph, and rejecting the irrelevant condition redundancy relation in the causal full-connected graph.
6. The method for locating communication failure based on data mining of claim 5, wherein the step S5 is to determine the direction of the boundary of the failure connection graph by:
let two variables in the fault connection graph be v1And v2，v1And v2There is a direct causal connection between them; inferring v from asymmetries present in event data1And v2Causal direction between, i.e. to distinguish v in fault connection graphs1And v2Causal direction between v1→v2Is also v1←v2。
7. The method according to claim 6, wherein the step S7 is performed by sorting the root cause paths on the KPI causal graph and confirming the root cause paths according to the highest priority when tracing the root cause of the failure in combination with the weight distribution method.
8. The method of claim 7, wherein the ranking of the root cause paths is such that the greater the sum of the weights of all edges of a path on a KPI causal graph, the higher the priority.
9. The method of claim 7, wherein ranking root cause paths gives higher priority to shorter path lengths on KPI causal graphs.
10. A data mining-based communication fault location system, wherein the system is used for implementing the data mining-based communication fault location method according to any one of claims 1 to 8, and comprises:
the event data acquisition and preprocessing module is used for acquiring and preprocessing event data in the communication service system, including daily monitoring data, log data and historical data;
the failure component confirmation module is used for determining a failed component according to the log data, namely confirming the failure in the event corresponding to the event data;
the fault reason analysis module is used for taking the fault as a father node and taking the event as a child node, analyzing the relation between the father node and the child node and determining the reason of the fault of the event;
the fault connection diagram construction module is used for constructing a cause and effect full connection diagram with an observation value, and processing the irrelevant condition redundancy relation in the cause and effect full connection diagram to obtain a fault connection diagram;
the boundary direction confirmation module is used for determining the direction of the boundary of the fault connection diagram to obtain a component KPI causal diagram;
the root cause inference module is used for determining a fault cause set corresponding to the event, taking the fault cause set corresponding to the event as the input of the KPI causal graph, outputting a fault root cause set through the KPI causal graph, and confirming the possibility that the fault cause is the root cause;
and the fault positioning module is used for tracing the root cause causing the fault by combining a weight distribution method, so that the fault is positioned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110681583.9A CN113489602A (en) | 2021-06-18 | 2021-06-18 | Communication fault positioning method and system based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110681583.9A CN113489602A (en) | 2021-06-18 | 2021-06-18 | Communication fault positioning method and system based on data mining |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113489602A true CN113489602A (en) | 2021-10-08 |
Family
ID=77934118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110681583.9A Pending CN113489602A (en) | 2021-06-18 | 2021-06-18 | Communication fault positioning method and system based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113489602A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115514627A (en) * | 2022-09-21 | 2022-12-23 | 深信服科技股份有限公司 | Fault root cause positioning method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090232007A1 (en) * | 2008-03-17 | 2009-09-17 | Comcast Cable Holdings, Llc | Method for detecting video tiling |
| CN106571963A (en) * | 2016-10-27 | 2017-04-19 | 北京汇通金财信息科技有限公司 | Method for positioning fault between information network and communication network |
| CN110955575A (en) * | 2019-11-14 | 2020-04-03 | 国网浙江省电力有限公司信息通信分公司 | Business system fault positioning method based on correlation analysis model |
| CN111541559A (en) * | 2020-03-23 | 2020-08-14 | 广东工业大学 | Fault positioning method based on causal rule |
| US20210011890A1 (en) * | 2019-07-11 | 2021-01-14 | Exfo Inc. | Automatic Root Cause Diagnosis in Networks Based on Hypothesis Testing |
-
2021
- 2021-06-18 CN CN202110681583.9A patent/CN113489602A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090232007A1 (en) * | 2008-03-17 | 2009-09-17 | Comcast Cable Holdings, Llc | Method for detecting video tiling |
| CN106571963A (en) * | 2016-10-27 | 2017-04-19 | 北京汇通金财信息科技有限公司 | Method for positioning fault between information network and communication network |
| US20210011890A1 (en) * | 2019-07-11 | 2021-01-14 | Exfo Inc. | Automatic Root Cause Diagnosis in Networks Based on Hypothesis Testing |
| CN110955575A (en) * | 2019-11-14 | 2020-04-03 | 国网浙江省电力有限公司信息通信分公司 | Business system fault positioning method based on correlation analysis model |
| CN111541559A (en) * | 2020-03-23 | 2020-08-14 | 广东工业大学 | Fault positioning method based on causal rule |
Non-Patent Citations (1)
| Title |
|---|
| 靖宇涵: ""基于多阶段机器学习的KPI异常检测与相关性模型研究"", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技I辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115514627A (en) * | 2022-09-21 | 2022-12-23 | 深信服科技股份有限公司 | Fault root cause positioning method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111342997B (en) | Construction method of deep neural network model, fault diagnosis method and system | |
| CN113344134B (en) | Low-voltage distribution monitoring terminal data acquisition abnormality detection method and system | |
| CN111126437B (en) | Abnormal group detection method based on weighted dynamic network representation learning | |
| CN115508672B (en) | Power grid main equipment fault tracing reasoning method, system, equipment and medium | |
| CN111541559A (en) | Fault positioning method based on causal rule | |
| CN112217674B (en) | Alarm root cause identification method based on causal network mining and graph attention network | |
| CN111949480B (en) | Log anomaly detection method based on component perception | |
| CN105975797A (en) | Product early-fault root cause recognition method based on fuzzy data processing | |
| CN110032463A (en) | A kind of system fault locating method and system based on Bayesian network | |
| CN115237717A (en) | Micro-service abnormity detection method and system | |
| CN112464439A (en) | Three-layer data mining-based power system fault type analysis method and device | |
| CN116771576A (en) | Comprehensive fault diagnosis method for hydroelectric generating set | |
| Lyu et al. | A data-driven approach for identifying possible manufacturing processes and production parameters that cause product defects: A thin-film filter company case study | |
| CN115544519A (en) | Method for carrying out security association analysis on threat information of metering automation system | |
| CN116541782A (en) | Power marketing data anomaly identification method | |
| CN113489602A (en) | Communication fault positioning method and system based on data mining | |
| CN117076915B (en) | Intelligent fault attribution analysis method and system for FPSO crude oil process system | |
| CN116611523B (en) | Method and system for predicting interpretable faults of turbofan engine | |
| CN117221087A (en) | Alarm root cause positioning method, device and medium | |
| Adamova et al. | Machine Learning in Action: An Analysis of its Application for Fault Detection in Wireless Sensor Networks | |
| KR102667861B1 (en) | heavy electrical equipment treatment apparatus using deep learning-based prediction model and method therefor | |
| CN112699927B (en) | Pipeline fault diagnosis method and system | |
| CN114492877B (en) | Operation and maintenance analysis method and device of business system | |
| Dong et al. | Log fusion technology of power information system based on fuzzy reasoning | |
| CN116957361A (en) | Ship task system health state detection method based on virtual-real combination |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211008 |
|
| RJ01 | Rejection of invention patent application after publication |