CN113268370A - Root cause alarm analysis method, system, equipment and storage medium - Google Patents
Root cause alarm analysis method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN113268370A CN113268370A CN202110513431.8A CN202110513431A CN113268370A CN 113268370 A CN113268370 A CN 113268370A CN 202110513431 A CN202110513431 A CN 202110513431A CN 113268370 A CN113268370 A CN 113268370A
- Authority
- CN
- China
- Prior art keywords
- alarm
- root cause
- node
- analysis method
- graph
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/079—Root cause analysis, i.e. error or fault diagnosis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a root cause alarm analysis method, a system, equipment and a storage medium, wherein the root cause alarm analysis method comprises the following steps: preprocessing alarm data, mining the alarm data based on an SR-ASM algorithm to obtain an alarm sequence, and converting the alarm sequence into an alarm relation graph; according to the alarm relation graph and the alarm self-characteristics, the root cause alarm is identified by using a root cause alarm identification model SGC-RAI, and the identified root cause alarm is recommended.
Description
Technical Field
The invention belongs to the field of alarm analysis, and relates to a root cause alarm analysis method, a system, equipment and a storage medium.
Background
Tens of thousands of alarm logs constitute an alarm flood. Among the alarms, some alarms occur frequently and are reported repeatedly, and some alarms have complex association relations. If the alarm is not processed and compressed, the alarm log is directly pushed to the manager, the processing efficiency of each alarm is very low, and the processing effect is positively correlated with the experience of the manager. Therefore, the main task of the network alarm analysis is to use an algorithm to greatly reduce the alarm amount presented to the operation and maintenance personnel of the management center and only push the root cause alarm. In the past root cause analysis research, a great deal of work is carried out by researching the association and the cause-effect relationship of the alarm, and then carrying out the compression, the root cause positioning and the alarm prediction of the alarm based on the association and the cause-effect relationship. The method in this aspect is mainly divided into two categories of alarm correlation analysis and root cause analysis. The alarm correlation analysis is mainly realized by data mining correlation algorithms, and the algorithms mainly comprise clustering, frequent item mining, time sequence relation mining and the like. There are many different methods of alarm root cause analysis, among which rule-based root cause analysis systems are more commonly used in applications. The rules in such systems are expert-experienced crystallization with few and fine features. However, in the context of increasingly complex network systems, such methods are costly in terms of rules, maintenance, and updates. With the development of big data technology and data mining technology, some scholars put forward the concept of intelligent operation and maintenance, apply the machine learning algorithm to the task of root cause and fault analysis, improve the accuracy of root cause positioning, and effectively reduce the operation and maintenance cost. Such methods are the main development trend in the future, however, no specific operation process is given at the present stage.
Disclosure of Invention
The present invention is directed to overcome the above-mentioned shortcomings in the prior art, and provides a method, a system, a device and a storage medium for analyzing root cause alarms, which can efficiently identify root cause alarms and have low operation and maintenance costs.
In order to achieve the above object, the root cause alarm analysis method of the present invention comprises:
preprocessing alarm data, mining the alarm data by using an SR-ASM algorithm to obtain an alarm sequence, and converting the alarm sequence into an alarm relation graph;
and according to the alarm relation graph, identifying the root cause alarm by using a root cause alarm identification model SGC-RAI, and recommending the identified root cause alarm.
Further comprising: further judging the bidirectional edges in the alarm relation graph and endowing each pair of relations on the graph with weights according to the confidence degree and the promotion degree.
The process of preprocessing the alarm data comprises the following steps: and performing duplicate removal and sorting on the alarm data, and grouping according to the network elements and the time windows.
According to the alarm relation graph and the alarm characteristics, the specific operation process of analyzing the root cause alarm by using the root cause alarm recognition model SGC-RAI is as follows:
for a group of alarm sequences of root cause alarms to be analyzed, vectorizing text characteristics of the alarms to obtain characteristics of each alarm, extracting the relation characteristics of the alarms according to an alarm relation graph, performing supervised training on a root cause alarm recognition model SGC-RAI by using the characteristics of the alarms and the relation characteristics, and then recognizing the root cause alarms by using the trained root cause alarm recognition model SGC-RAI.
And (3) carrying out duplicate removal on the alarm group, taking text information of all alarms as a corpus to train a GloVe model and a TF-IDF model, inputting the participles of the alarm names into the trained GloVe model for an alarm log to obtain word vector characteristics of the participles of the alarm names, weighting the word vector characteristics by using the trained TF-IDF model to obtain the characteristics of the alarms, and obtaining alarm associated information according to an alarm relation graph.
The SGC-RAI comprises two layers of airspace map convolutional layers, a pooling layer and a full-link layer, wherein local information is aggregated by the two layers of airspace map convolutional layers, all fault information is extracted by the pooling layer through element-wise maximum pooling operation, the fault information is injected into an alarm to obtain new alarm representation, finally the alarm characteristic is converted into a value through the shared full-link layer, the root cause score of the alarm is obtained through Softmax normalization, and the alarm with the largest root cause score is taken as the root cause alarm.
The operation process of the two-layer airspace map convolution layer (inspired by the convolution of the relation map) is as follows:
wherein v is an alarm in the alarm sequence, and k is the k-th layer.
Is the output of the k-th layer,
in order to obtain the neighborhood information, it is,
is a learnable linear transformation. N is a radical of1(v) And N2(v) Respectively representing a set of two classes of neighbors of the node v. N is a radical of1) v) the nodes are connected with the nodes v with edges, and the direction of the edges is pointed to the neighbor nodes by the nodes v, N)2(v) The node in (1) is connected with the node v by edges, and the direction of the edges is pointed to the node v by the neighbor nodes. w (v, u) represents the corresponding prior weight of the edge from the node v to the neighboring node u in the alarm correlation diagram, and w (u, v) represents the corresponding prior weight of the edge from the neighboring node u to the node v in the alarm correlation diagram.
The operation of aggregating global information is:
wherein, G is an association diagram formed by the whole alarm sequence:
the root cause alarm prediction is calculated as:
a root cause alarm analysis system, comprising:
the mining module is used for preprocessing the alarm data, mining the alarm data by utilizing an SR-ASM algorithm to obtain an alarm sequence, and converting the alarm sequence into an alarm relation graph;
and the identification module is used for identifying the root cause alarm by utilizing a root cause alarm identification model SGC-RAI according to the alarm relation graph and the text characteristics of the alarm and recommending the identified root cause alarm. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the cause alarm analysis method when executing the computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the root cause alarm analysis method.
The invention has the following beneficial effects:
when the root cause alarm analysis method, the system, the equipment and the storage medium are operated specifically, mining alarm data based on the increase credibility and SR-ASM algorithm to obtain an alarm sequence, converting the alarm sequence into an alarm relation graph, avoiding missing alarm associated information with value, improving the identification accuracy, then, the root cause alarm recognition model SGC-RAI is used for recognizing the root cause alarm, thereby effectively reducing the dependence on expert experience, reducing the operation and maintenance cost, meanwhile, the identification efficiency is improved, and the accuracy of the training set and the test set is high through tests, meanwhile, the microF1 and the macroF1 of the invention are both higher than the prior art, namely, when the distribution of the faults is not balanced, the method has stronger capability in identifying different types of root causes, and can be widely applied to the tasks of alarm compression and root cause positioning in the field of telecommunication.
Drawings
FIG. 1 is a logic diagram of the decision of pattern growth in the SR-ASM algorithm;
FIG. 2 is a flow chart of alarm correlation mining in the present invention;
FIG. 3 is a block diagram of root cause alarm identification in the present invention;
FIG. 4 is a diagram of a root cause alarm recognition model according to the present invention;
Detailed Description
In order to make the technical solutions of the present invention better understood, 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, not all of the embodiments, and are not intended to limit the scope of the present disclosure. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The root cause alarm analysis method comprises the following steps:
1) mining and discovering the association between the alarms based on the sequence mode;
mining alarm data based on an SR-ASM algorithm to obtain an alarm sequence, converting the alarm sequence into an alarm relation graph, further judging the direction of a bidirectional edge in the alarm relation graph, and endowing each pair of relations with a weight according to confidence and promotion;
specifically, considering that the occurrence frequency difference of different alarms is large, the alarm data is mined only by the support degree index, and valuable alarm associated information is easy to omit, so the method modifies the traditional frequent sequence pattern mining algorithm Prefix span, and provides a reliability increasing concept and an alarm sequence mining algorithm SR-ASM to mine the valuable alarm sequence in the alarm data, wherein the SR-ASM algorithm takes an alarm sequence database as input and takes the valuable alarm sequence as output.
2) And identifying root cause alarms based on the graph network.
And according to the alarm relation graph, carrying out root cause alarm analysis by using a root cause alarm recognition model SGC-RAI.
Specifically, the method of the invention utilizes the graph neural network method to extract the characteristics of the alarm and judge the root cause alarm. The invention provides a root cause alarm recognition model SGC-RAI by applying the ideas of space domain graph convolution and pooling, wherein the SGC-RAI model can enable each alarm to gather local and global information so as to obtain more distinctive features, and finally, the features are transformed and normalized to obtain root cause scores.
Referring to fig. 1, the core details of SR-ASM, SR-ASM is an algorithm proposed based on prefix span, and also adopts a prefix pattern growth method to mine all valuable alarm sequences, and when prefixes grow, the invention proposes a concept of increasing the confidence level GR, where, given prefix α, a new sequence s composed of item b is combined on the basis of prefix α to form the confidence level of the valuable prefixes, and then:
the original Prefix span algorithm only judges the mode growth through the support degree, if the minimum support degree requirement is met, the prefix continues to grow, when the prefix grows, the invention considers the support degree and the growth reliability, and provides the prefix growth judging logic shown in figure 1.
SR-ASM algorithm idea
Similar to the prefix span algorithm, SR-ASM continuously performs prefix growth by a recursive method, specifically, mining starts from 1-prefix (k is 1), for each 1-prefix, projection is performed to obtain a database composed of all suffixes, and statistics is performed on the support degree of each item b in the database;
when the support degree of b is larger than or equal to the minimum support degree, continuing to increase the prefix into a (k +1) -prefix, and then performing recursive mining;
and when the support degree of b is less than the minimum support degree, calculating the growth reliability GR, if GR is more than or equal to min _ GR, continuously growing the prefix into a (k +1) -prefix, then carrying out recursive mining, and otherwise, stopping growing.
And so on, recursion is carried out until the projected database is empty or the sequence length constraint is reached.
The method sets a support degree lower bound t, and when the support degree of an item in the initial database reaches t, the item is a 1-prefix.
Fig. 2 is an alarm correlation mining process adopted by the present invention, and the specific process is as follows:
1a) constructing an alarm sequence database:
and grouping, sequencing, removing duplication and serializing the massive and discrete alarm records, wherein the input of the link is the original alarm log record, and the output is the constructed alarm sequence database S.
2a) Mining a valuable alarm sequence:
and (4) taking the database S as input, and executing an SR-ASM algorithm to obtain a valuable alarm sequence and the support degree thereof.
3a) Generating an alarm relation network:
representing the relation between alarms by adopting the alarm sequence obtained in the step 2a) in the form of a network graph, taking the alarms as nodes on the network graph, and taking the sequence as a path on the network graph. If two-way edges exist on the constructed graph and the support degree of one direction is more than twice that of the other direction, the edge with lower support degree is deleted, otherwise, both edges are deleted.
And calculating the weight of each Edge, wherein the weight Edge of the corresponding Edge from the alarm A to the alarm B (A → B)weightComprises the following steps:
referring to fig. 3, when it is necessary to determine a root cause alarm in a group of alarm sequences, two types of features are used as the input of the recognition model, where the two types of features are respectively the text feature of the alarm and the association feature between the alarms, and the output of the recognition model is the root cause alarm. Because the alarm log is in a text form, the method adopts the idea of text vectorization in a natural language processing task. The method of combining the GloVe model and the TF-IDF model is adopted to express the alarm, the alarm log is used as a corpus to train the GloVe model and the TF-IDF model, the vector length is 50, and the vector of the characteristic of one alarm is expressed as follows:
referring to FIG. 4, the root cause alarm recognition model SGC-RAI identifies a set of alarm characteristics X ∈ RN*DAnd its relation matrix A ∈ RN*NAs an input, N represents the number of alarms in the sequence and D represents the dimension of the alarm feature. Dividing a root cause alarm recognition model SGC-RAI into 3 parts from left to right, firstly using 2-layer space domain graph convolution to aggregate local information, then using element-wise maximum pooling operation to extract all fault information, injecting the fault information into an alarm, updating node information again, and finally converting alarm characteristics into root cause scores through a shared full-connection layer and normalization operation.
The convolution operation (inspired by the convolution of the relational graph) in the invention is as follows:
wherein v is an alarm in the alarm sequence, and k is the k-th layer.
Is the output of the k-th layer,
in order to obtain the neighborhood information, it is,
is a learnable linear transformation. N is a radical of1(v) And N2(v) Respectively representing a set of two classes of neighbors of the node v. N is a radical of1(v) The node in (1) is connected with a node v by edges, and the direction of the edges is pointed to a neighbor node by the node v, N2(v) The node in (1) is connected with the node v by edges, and the direction of the edges is pointed to the node v by the neighbor nodes. w (v, u) represents the corresponding prior weight of the edge from the node v to the neighboring node u in the alarm correlation diagram, and w (u, v) represents the corresponding prior weight of the edge from the neighboring node u to the node v in the alarm correlation diagram.
The operation of aggregating global information is:
wherein, G is an association diagram formed by the whole alarm sequence:
the root cause alarm prediction is calculated as:
a root cause alarm analysis system, comprising:
the mining module is used for preprocessing the alarm data, mining the alarm data by utilizing the proposed SR-ASM algorithm to obtain an alarm sequence, and converting the alarm sequence into an alarm relation graph;
and the identification module is used for identifying the root cause alarm by utilizing the provided root cause alarm identification model SGC-RAI according to the alarm relation graph and the text characteristics of the alarm and recommending the identified root cause alarm. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the cause alarm analysis method when executing the computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the root cause alarm analysis method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart 1 flow or flows and/or block 1 block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows of FIG. 1 and/or block diagram block or blocks of FIG. 1.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart 1 flow or flows and/or block 1 block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A root cause alarm analysis method is characterized by comprising the following steps:
preprocessing alarm data, mining the alarm data by using an SR-ASM algorithm to obtain an alarm sequence, and converting the alarm sequence into an alarm relation graph;
and identifying the root cause alarm by using a root cause alarm identification model SGC-RAI according to the alarm relation graph and the alarm characteristics, and recommending the identified root cause alarm.
2. The root cause alarm analysis method according to claim 1, further comprising: and judging the directions of the two-way edges in the alarm relation graph, and endowing each pair of relations on the alarm relation graph with weights according to the confidence coefficient and the promotion degree.
3. The root cause alarm analysis method according to claim 1, wherein the process of preprocessing the alarm data is as follows: and performing duplicate removal and sorting on the alarm data, and grouping according to the network elements and the time windows.
4. The root cause alarm analysis method according to claim 1, wherein the specific operation process of performing root cause alarm analysis by using a root cause alarm recognition model SGC-RAI according to the alarm relationship graph and the alarm characteristics is as follows:
vectorizing the text characteristics of the alarm to obtain the self-characteristic of the alarm for a group of alarm sequences of the root cause alarm to be analyzed, extracting the relation characteristic of the alarm according to an alarm relation graph, and performing supervised training on a root cause alarm recognition model SGC-RAI by using the self-characteristic and the relation characteristic of the alarm, wherein the label is the root cause alarm, and then performing the recognition of the root cause alarm by using the trained root cause alarm recognition model SGC-RAI.
5. The root cause alarm analysis method according to claim 1, wherein the alarm group is deduplicated, and then the text information of all alarms is used as a corpus to train a GloVe model and a TF-IDF model, wherein for an alarm log, the participles of the alarm name are input into the trained GloVe model to obtain word vector features of the alarm name participles, then the trained TF-IDF model is used to weight the word vector features to obtain the features of the alarm itself, and the association information of the alarm is obtained according to the alarm relationship graph.
6. The root cause alarm analysis method according to claim 1, wherein the SGC-RAI comprises two spatial domain graph convolution layers, a pooling layer and a full link layer, wherein the two spatial domain graph convolution layers are used to aggregate local information, the pooling layer is used to extract global fault information by using element-wise max pooling, and inject the fault information into the alarm to obtain a new representation of the alarm, and finally the alarm characteristics are converted into numerical values by the shared full link layer, and Softmax normalization is used to obtain the root cause score of the alarm, and the alarm with the largest root cause score is taken as the root cause alarm.
7. The root cause alarm analysis method of claim 6,
the operation process of the two-layer airspace map convolutional layer is as follows:
wherein v is an alarm in the alarm sequence, k is the k-th layer,
is the output of the k-th layer,
for the neighborhood information obtained, W1 (k),W2 (k),W3 (k)For a learnable linear transformation, N1(v) And N2(v) Set of two classes of neighbors, N, each representing a node v1(v) The node in (1) is connected with a node v by edges, and the direction of the edges is pointed to a neighbor node by the node v, N2(v) The nodes in the alarm association graph are connected with the node v by edges, the directions of the edges are pointed to the node v by the adjacent nodes, w (v, u) represents the corresponding prior weights of the edges from the node v to the adjacent node u in the alarm association graph, w (u, v) represents the corresponding prior weights of the edges from the adjacent node u to the node v in the alarm association graph, and aggregation is carried outThe operation of the global information is:
wherein, G is an association diagram formed by the whole alarm sequence:
the root cause alarm prediction is calculated as:
8. a root cause alarm analysis system, comprising:
the mining module is used for preprocessing the alarm data, mining the alarm data by utilizing an SR-ASM algorithm to obtain an alarm sequence, and converting the alarm sequence into an alarm relation graph;
and the identification module is used for identifying the root cause alarm by utilizing a root cause alarm identification model SGC-RAI according to the alarm relation graph and the alarm characteristics and recommending the identified root cause alarm.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the cause alarm analysis method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the root cause alarm analysis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110513431.8A CN113268370B (en) | 2021-05-11 | 2021-05-11 | Root cause alarm analysis method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110513431.8A CN113268370B (en) | 2021-05-11 | 2021-05-11 | Root cause alarm analysis method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113268370A true CN113268370A (en) | 2021-08-17 |
| CN113268370B CN113268370B (en) | 2023-05-23 |
Family
ID=77230486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110513431.8A Active CN113268370B (en) | 2021-05-11 | 2021-05-11 | Root cause alarm analysis method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113268370B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115022153A (en) * | 2022-06-07 | 2022-09-06 | 中国工商银行股份有限公司 | Fault root cause analysis method, device, equipment and storage medium |
| CN115150255A (en) * | 2022-07-12 | 2022-10-04 | 北京云集智造科技有限公司 | Self-adaptive knowledge graph-based automatic root cause positioning method for application faults |
| CN116233311A (en) * | 2023-05-08 | 2023-06-06 | 天津金城银行股份有限公司 | Automatic outbound testing method, device, computer equipment and storage medium |
| CN115150255B (en) * | 2022-07-12 | 2024-05-31 | 北京云集智造科技有限公司 | Self-adaptive knowledge-graph-based automatic root cause positioning method for application faults |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020022952A1 (en) * | 1998-03-26 | 2002-02-21 | David Zager | Dynamic modeling of complex networks and prediction of impacts of faults therein |
| CN110609759A (en) * | 2018-06-15 | 2019-12-24 | 华为技术有限公司 | Fault root cause analysis method and device |
| CN111814967A (en) * | 2020-09-11 | 2020-10-23 | 鹏城实验室 | Method, apparatus and storage medium for calculating inferential computation of neural network model |
| CN111897673A (en) * | 2020-07-31 | 2020-11-06 | 平安科技（深圳）有限公司 | Operation and maintenance fault root cause identification method and device, computer equipment and storage medium |
| CN112181758A (en) * | 2020-08-19 | 2021-01-05 | 南京邮电大学 | Fault root cause positioning method based on network topology and real-time alarm |
| CN112182387A (en) * | 2020-09-29 | 2021-01-05 | 中国人民大学 | Personalized search algorithm for enhancing time information |
| CN112312443A (en) * | 2020-10-13 | 2021-02-02 | 西安电子科技大学 | Mass alarm data processing method, system, medium, computer equipment and application |
| CN112367678A (en) * | 2020-10-15 | 2021-02-12 | 深圳力维智联技术有限公司 | Micro base station monitoring method and device and storage medium |
-
2021
- 2021-05-11 CN CN202110513431.8A patent/CN113268370B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020022952A1 (en) * | 1998-03-26 | 2002-02-21 | David Zager | Dynamic modeling of complex networks and prediction of impacts of faults therein |
| CN110609759A (en) * | 2018-06-15 | 2019-12-24 | 华为技术有限公司 | Fault root cause analysis method and device |
| CN111897673A (en) * | 2020-07-31 | 2020-11-06 | 平安科技（深圳）有限公司 | Operation and maintenance fault root cause identification method and device, computer equipment and storage medium |
| CN112181758A (en) * | 2020-08-19 | 2021-01-05 | 南京邮电大学 | Fault root cause positioning method based on network topology and real-time alarm |
| CN111814967A (en) * | 2020-09-11 | 2020-10-23 | 鹏城实验室 | Method, apparatus and storage medium for calculating inferential computation of neural network model |
| CN112182387A (en) * | 2020-09-29 | 2021-01-05 | 中国人民大学 | Personalized search algorithm for enhancing time information |
| CN112312443A (en) * | 2020-10-13 | 2021-02-02 | 西安电子科技大学 | Mass alarm data processing method, system, medium, computer equipment and application |
| CN112367678A (en) * | 2020-10-15 | 2021-02-12 | 深圳力维智联技术有限公司 | Micro base station monitoring method and device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 杨树森等: "Distributed_Stochastic_Cross-Layer_Optimization_for_Multi-Hop_Wireless_Networks_With_Cooperative_Communications", 《IEEE TRANSACTIONS ON MOBILE COMPUTING》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115022153A (en) * | 2022-06-07 | 2022-09-06 | 中国工商银行股份有限公司 | Fault root cause analysis method, device, equipment and storage medium |
| CN115022153B (en) * | 2022-06-07 | 2024-04-23 | 中国工商银行股份有限公司 | Fault root cause analysis method, device, equipment and storage medium |
| CN115150255A (en) * | 2022-07-12 | 2022-10-04 | 北京云集智造科技有限公司 | Self-adaptive knowledge graph-based automatic root cause positioning method for application faults |
| CN115150255B (en) * | 2022-07-12 | 2024-05-31 | 北京云集智造科技有限公司 | Self-adaptive knowledge-graph-based automatic root cause positioning method for application faults |
| CN116233311A (en) * | 2023-05-08 | 2023-06-06 | 天津金城银行股份有限公司 | Automatic outbound testing method, device, computer equipment and storage medium |
| CN116233311B (en) * | 2023-05-08 | 2023-07-14 | 天津金城银行股份有限公司 | Automatic outbound testing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113268370B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783100B (en) | Source code vulnerability detection method for code graph representation learning based on graph convolution network | |
| WO2021103492A1 (en) | Risk prediction method and system for business operations | |
| CN110059181B (en) | Short text label method, system and device for large-scale classification system | |
| US8676726B2 (en) | Automatic variable creation for adaptive analytical models | |
| CN110597735A (en) | Software defect prediction method for open-source software defect feature deep learning | |
| CN112507699B (en) | Remote supervision relation extraction method based on graph convolution network | |
| CN110175628A (en) | A kind of compression algorithm based on automatic search with the neural networks pruning of knowledge distillation | |
| CN109857457B (en) | Function level embedding representation method in source code learning in hyperbolic space | |
| CN112217674B (en) | Alarm root cause identification method based on causal network mining and graph attention network | |
| CN112685504B (en) | Production process-oriented distributed migration chart learning method | |
| CN107679135A (en) | The topic detection of network-oriented text big data and tracking, device | |
| CN113268370B (en) | Root cause alarm analysis method, system, equipment and storage medium | |
| CN114816497B (en) | Link generation method based on BERT pre-training model | |
| CN115858906A (en) | Enterprise searching method, device, equipment, computer storage medium and program | |
| CN113742396A (en) | Mining method and device for object learning behavior pattern | |
| CN116578336A (en) | Software clone detection method based on plagiarism-detector countermeasure | |
| CN111159328A (en) | Information knowledge fusion system and method | |
| Chen et al. | A supervised link prediction method for dynamic networks | |
| CN115544112A (en) | Big data artificial intelligence based double-created-fruit high-value patent screening method | |
| CN113821571B (en) | Food safety relation extraction method based on BERT and improved PCNN | |
| CN114036319A (en) | Power knowledge extraction method, system, device and storage medium | |
| CN112287996B (en) | Major event key factor mining method based on machine learning | |
| CN114969511A (en) | Content recommendation method, device and medium based on fragments | |
| CN111221704B (en) | Method and system for determining running state of office management application system | |
| Lv et al. | CEP rule extraction framework based on evolutionary algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |