CN107644256A - A kind of method that diagnosis rule storehouse is formed based on machine learning mode - Google Patents
A kind of method that diagnosis rule storehouse is formed based on machine learning mode Download PDFInfo
- Publication number
- CN107644256A CN107644256A CN201710828211.8A CN201710828211A CN107644256A CN 107644256 A CN107644256 A CN 107644256A CN 201710828211 A CN201710828211 A CN 201710828211A CN 107644256 A CN107644256 A CN 107644256A
- Authority
- CN
- China
- Prior art keywords
- failure
- diagnosis rule
- rule storehouse
- machine learning
- learning mode
- 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
Landscapes
- Test And Diagnosis Of Digital Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention is more particularly directed to a kind of method that diagnosis rule storehouse is formed based on machine learning mode.This forms the method in diagnosis rule storehouse based on machine learning mode, obtains fault message and solution first, extracts diagnosis rule storehouse field;Then random forests algorithm is used, automatic identification failure simultaneously excavates phenomenon of the failure and the relation of diagnosis rule;Experts' evaluation finally is carried out to the failure automatically identified, effective phenomenon of the failure and processing scheme are generated into diagnosis rule, are stored in diagnosis rule storehouse.This forms the method in diagnosis rule storehouse based on machine learning mode, one diagnosis rule storehouse is formed according to the rule of fault routine and treating method, when failure occurs again, the information checked in diagnosis rule storehouse can find corresponding solution, substantially increase the efficiency of malfunction elimination.
Description
Technical field
The present invention relates to Computer Applied Technology field, more particularly to one kind forms diagnosis rule based on machine learning mode
The method in storehouse.
Background technology
With the development in epoch, the improvement of people's living standards, the life style and working method of people are all become
Change, computer has become equipment irreplaceable in people's daily life.
When computer breaks down, technical staff can only be very time-consuming by checking that log information is investigated.And
There is a lot, log information enormous amount because computer operating system component is relatively complicated, the reason for caused failure.When
, it is necessary to which technical staff checks that log information is analyzed manually when computer breaks down, corresponding fault message is found, is solved
The failure problems of appearance, therefore it is extremely difficult that technical staff, which wants rapid determination failure cause,.
Prior art is without the general diagnosis rule storehouse of use, the artificial row that can only be wasted time and energy when computer breaks down
Look into.For such case, the present invention devises a kind of method that diagnosis rule storehouse is formed based on machine learning mode.
The content of the invention
The defects of present invention is in order to make up prior art, there is provided a kind of simply efficiently to be formed based on machine learning mode
The method in diagnosis rule storehouse.
The present invention is achieved through the following technical solutions:
A kind of method that diagnosis rule storehouse is formed based on machine learning mode, it is characterised in that comprise the following steps:
(1)Failure training set is chosen, and obtains fault message and solution, extracts diagnosis rule storehouse field;
(2)Machine learning algorithm is trained, and using random forests algorithm, automatic identification failure simultaneously excavates phenomenon of the failure and diagnosis rule
Relation;
(3)Expert judging typing diagnosis rule, experts' evaluation is carried out to the failure that automatically identifies, by effective phenomenon of the failure and
Processing scheme generates diagnosis rule, is stored in diagnosis rule storehouse.
The step(1)In, it is by curstomer's site, research and development department, test organization and O&M people that failure training set, which is chosen,
The fault message and solution that member obtains, extract diagnosis rule storehouse field;Meanwhile the data in training set are accurately positioned
Specific equipment, analyse in depth failure cause.
Diagnosis rule storehouse field includes failure title, machine models, operating system, trouble location, fault model, therefore
Hinder type, daily record rank, daily record details, keyword, log path, problem description and solution.
When data in training set are accurately positioned CPU and memory failure, CPU events and internal memory event, parsing are read
Mcelog, position failure CPU and core position;PCIE failures are positioned, read PCIE events, according to the machine silk-screen table of comparisons,
Allot corresponding slot Information;CallTrace failure error-reporting routine sections are positioned, analyze CallTrace event logs, excavate function
Call stack, analyse in depth failure cause.
The step(2)In, machine learning algorithm training, using random forests algorithm, generate be made up of decision tree it is gloomy
Woods, merger processing is carried out to fault message, phenomenon of the failure voted by more decision trees, failure judgement, and take phase
The solution answered.
Beneficial effects of the present invention:This forms the method in diagnosis rule storehouse based on machine learning mode, according to fault routine
Rule and treating method formed a diagnosis rule storehouse, when failure occurs again, the information checked in diagnosis rule storehouse is i.e.
Corresponding solution can be found, substantially increases the efficiency of malfunction elimination.
Brief description of the drawings
Accompanying drawing 1 forms the method schematic diagram in diagnosis rule storehouse for the present invention based on machine learning mode.
Embodiment
In order that technical problems, technical solutions and advantages to be solved are more clearly understood, tie below
Drawings and examples are closed, the present invention will be described in detail.It should be noted that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
This forms the method in diagnosis rule storehouse based on machine learning mode, including:Failure training set is chosen, and machine learning is calculated
Method is trained and expert judging typing diagnosis rule three parts.
The failure training set chooses the event for referring to obtain by curstomer's site, research and development department, test organization, operation maintenance personnel
Hinder information and solution, extract diagnosis rule storehouse field, ensure the completeness and accuracy of fault diagnosis;In training set
Data are accurately positioned specific equipment, such as when positioning CPU and memory failure, read CPU events and internal memory event, parsing
Mcelog, position failure CPU and core position;PCIE failures are positioned, read PCIE events, according to the machine silk-screen table of comparisons,
Allot corresponding slot Information;CallTrace failure error-reporting routine sections are positioned, analyze CallTrace event logs, excavate function
Call stack, analyse in depth failure cause.
Diagnosis rule storehouse field includes failure title, machine models, operating system, trouble location, fault model, failure classes
Type, daily record rank, daily record details, keyword, log path, problem description, solution.
The machine learning algorithm training refers to use random forests algorithm, realizes the automatic identification of failure, excavate failure
The relation of phenomenon and diagnosis rule.Based on random forests algorithm rule, the forest being made up of decision tree is generated, fault message is entered
Row merger is handled, and phenomenon of the failure is voted by more decision trees, failure judgement, taken appropriate measures.Using machine
The method automatic identification failure of learning algorithm training, the thing system of giving being accomplished manually is automatically performed, can save O&M
Cost, improve operating efficiency.
The expert judging typing diagnosis rule refers to carry out experts' evaluation to the failure automatically identified, by effective event
Hinder phenomenon and processing scheme generation diagnosis rule, be stored in diagnosis rule storehouse.When failure occurs again, failure is checked
Information in rule base can find corresponding solution, substantially increase the efficiency of malfunction elimination.
Claims (5)
- A kind of 1. method that diagnosis rule storehouse is formed based on machine learning mode, it is characterised in that comprise the following steps:(1)Failure training set is chosen, and obtains fault message and solution, extracts diagnosis rule storehouse field;(2)Machine learning algorithm is trained, and using random forests algorithm, automatic identification failure simultaneously excavates phenomenon of the failure and diagnosis rule Relation;(3)Expert judging typing diagnosis rule, experts' evaluation is carried out to the failure that automatically identifies, by effective phenomenon of the failure and Processing scheme generates diagnosis rule, is stored in diagnosis rule storehouse.
- 2. the method according to claim 1 that diagnosis rule storehouse is formed based on machine learning mode, it is characterised in that:It is described Step(1)In, the selection of failure training set is the failure by curstomer's site, research and development department, test organization and operation maintenance personnel acquisition Information and solution, extract diagnosis rule storehouse field;It is deep meanwhile the data in training set are accurately positioned specific equipment Enter analyzing failure cause.
- 3. the method according to claim 1 or 2 that diagnosis rule storehouse is formed based on machine learning mode, it is characterised in that: Diagnosis rule storehouse field includes failure title, machine models, operating system, trouble location, fault model, fault type, Daily record rank, daily record details, keyword, log path, problem description and solution.
- 4. the method according to claim 2 that diagnosis rule storehouse is formed based on machine learning mode, it is characterised in that:Training When the data of concentration are accurately positioned CPU and memory failure, CPU events and internal memory event are read, parses mcelog, positions failure CPU and core position;PCIE failures are positioned, read PCIE events, according to the machine silk-screen table of comparisons, match corresponding slot letter Breath;CallTrace failure error-reporting routine sections are positioned, analyze CallTrace event logs, excavate function call stack, are analysed in depth Failure cause.
- 5. the method according to claim 1 that diagnosis rule storehouse is formed based on machine learning mode, it is characterised in that:It is described Step(2)In, machine learning algorithm training, using random forests algorithm, the forest being made up of decision tree is generated, to fault message Merger processing is carried out, phenomenon of the failure is voted by more decision trees, failure judgement, and take corresponding solution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710828211.8A CN107644256A (en) | 2017-09-14 | 2017-09-14 | A kind of method that diagnosis rule storehouse is formed based on machine learning mode |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710828211.8A CN107644256A (en) | 2017-09-14 | 2017-09-14 | A kind of method that diagnosis rule storehouse is formed based on machine learning mode |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107644256A true CN107644256A (en) | 2018-01-30 |
Family
ID=61111745
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710828211.8A Pending CN107644256A (en) | 2017-09-14 | 2017-09-14 | A kind of method that diagnosis rule storehouse is formed based on machine learning mode |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107644256A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109800127A (en) * | 2019-01-03 | 2019-05-24 | 众安信息技术服务有限公司 | A kind of system fault diagnosis intelligence O&M method and system based on machine learning |
CN110321243A (en) * | 2018-03-29 | 2019-10-11 | 国际商业机器公司 | Use method, system and the storage medium of the system maintenance of the unified cognition basic reason analysis for multiple fields |
CN111274056A (en) * | 2018-11-20 | 2020-06-12 | 河南许继仪表有限公司 | Self-learning method and device for intelligent electric energy meter fault library |
CN112307076A (en) * | 2019-08-02 | 2021-02-02 | 深圳中集智能科技有限公司 | Production equipment operation and maintenance system and method based on cloud and end fusion |
CN115543665A (en) * | 2022-09-23 | 2022-12-30 | 超聚变数字技术有限公司 | Memory reliability evaluation method and device and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080208487A1 (en) * | 2007-02-23 | 2008-08-28 | General Electric Company | System and method for equipment remaining life estimation |
CN101833497A (en) * | 2010-03-30 | 2010-09-15 | 山东高效能服务器和存储研究院 | Computer fault management system based on expert system method |
CN102081562A (en) * | 2009-11-30 | 2011-06-01 | 华为技术有限公司 | Equipment diagnosis method and system |
CN103198000A (en) * | 2013-04-02 | 2013-07-10 | 浪潮电子信息产业股份有限公司 | Method for positioning faulted memory in linux system |
CN103699489A (en) * | 2014-01-03 | 2014-04-02 | 中国人民解放军装甲兵工程学院 | Software remote fault diagnosis and repair method based on knowledge base |
CN104155596A (en) * | 2014-08-12 | 2014-11-19 | 北京航空航天大学 | Artificial circuit fault diagnosis system based on random forest |
CN106383760A (en) * | 2016-09-19 | 2017-02-08 | 郑州云海信息技术有限公司 | Computer fault management method and apparatus |
-
2017
- 2017-09-14 CN CN201710828211.8A patent/CN107644256A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080208487A1 (en) * | 2007-02-23 | 2008-08-28 | General Electric Company | System and method for equipment remaining life estimation |
CN102081562A (en) * | 2009-11-30 | 2011-06-01 | 华为技术有限公司 | Equipment diagnosis method and system |
CN101833497A (en) * | 2010-03-30 | 2010-09-15 | 山东高效能服务器和存储研究院 | Computer fault management system based on expert system method |
CN103198000A (en) * | 2013-04-02 | 2013-07-10 | 浪潮电子信息产业股份有限公司 | Method for positioning faulted memory in linux system |
CN103699489A (en) * | 2014-01-03 | 2014-04-02 | 中国人民解放军装甲兵工程学院 | Software remote fault diagnosis and repair method based on knowledge base |
CN104155596A (en) * | 2014-08-12 | 2014-11-19 | 北京航空航天大学 | Artificial circuit fault diagnosis system based on random forest |
CN106383760A (en) * | 2016-09-19 | 2017-02-08 | 郑州云海信息技术有限公司 | Computer fault management method and apparatus |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110321243A (en) * | 2018-03-29 | 2019-10-11 | 国际商业机器公司 | Use method, system and the storage medium of the system maintenance of the unified cognition basic reason analysis for multiple fields |
CN110321243B (en) * | 2018-03-29 | 2023-02-10 | 勤达睿公司 | Method, system, and storage medium for system maintenance using unified cognitive root cause analysis for multiple domains |
CN111274056A (en) * | 2018-11-20 | 2020-06-12 | 河南许继仪表有限公司 | Self-learning method and device for intelligent electric energy meter fault library |
CN111274056B (en) * | 2018-11-20 | 2023-10-03 | 河南许继仪表有限公司 | Self-learning method and device for fault library of intelligent electric energy meter |
CN109800127A (en) * | 2019-01-03 | 2019-05-24 | 众安信息技术服务有限公司 | A kind of system fault diagnosis intelligence O&M method and system based on machine learning |
CN112307076A (en) * | 2019-08-02 | 2021-02-02 | 深圳中集智能科技有限公司 | Production equipment operation and maintenance system and method based on cloud and end fusion |
CN115543665A (en) * | 2022-09-23 | 2022-12-30 | 超聚变数字技术有限公司 | Memory reliability evaluation method and device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107644256A (en) | A kind of method that diagnosis rule storehouse is formed based on machine learning mode | |
Yuan et al. | Automated known problem diagnosis with event traces | |
CN102804147B (en) | Perform the code check executive system of the code check of ABAP source code | |
CN111930903A (en) | System anomaly detection method and system based on deep log sequence analysis | |
CN107608813A (en) | A kind of method that failure is automatically analyzed based on linux operation system informations | |
KR101696694B1 (en) | Method And Apparatus For Analysing Source Code Vulnerability By Using TraceBack | |
CN117331730A (en) | Fault diagnosis method, device, electronic equipment and storage medium | |
CN112882899B (en) | Log abnormality detection method and device | |
Wang et al. | Smart contract vulnerability detection using code representation fusion | |
CN107679159B (en) | Method and device for generating fault diagnosis question response, server and storage medium | |
CN112417852B (en) | Method and device for judging importance of code segment | |
CN101373506B (en) | Method for detecting software loophole model based on loophole model | |
CN113064811A (en) | Workflow-based automatic testing method and device and electronic equipment | |
CN112540925A (en) | New characteristic compatibility detection system and method, electronic device and readable storage medium | |
CN114969334B (en) | Abnormal log detection method and device, electronic equipment and readable storage medium | |
CN111324718A (en) | Conversation flow testing method and device, electronic equipment and readable storage medium | |
CN116302984A (en) | Root cause analysis method and device for test task and related equipment | |
CN115757062A (en) | Log anomaly detection method based on sentence embedding and Transformer-XL | |
Chen et al. | Fault diagnosis for open source software based on dynamic tracking | |
CN112905493B (en) | Structured fuzzy test method based on conversion test | |
JP2021176091A5 (en) | ||
CN114465875A (en) | Fault processing method and device | |
Kof | Translation of textual specifications to automata by means of discourse context modeling | |
Li et al. | Software misconfiguration troubleshooting based on state analysis | |
Mao et al. | Extracting the representative failure executions via clustering analysis based on Markov profile model |
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: 20180130 |
|
RJ01 | Rejection of invention patent application after publication |