CN106294076B - A kind of server relevant fault prediction technique and its system - Google Patents
A kind of server relevant fault prediction technique and its system Download PDFInfo
- Publication number
- CN106294076B CN106294076B CN201610719771.5A CN201610719771A CN106294076B CN 106294076 B CN106294076 B CN 106294076B CN 201610719771 A CN201610719771 A CN 201610719771A CN 106294076 B CN106294076 B CN 106294076B
- Authority
- CN
- China
- Prior art keywords
- fault
- failure
- frequent item
- item set
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000007257 malfunction Effects 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 3
- 239000012141 concentrate Substances 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
Abstract
The invention discloses a kind of server relevant fault prediction techniques, after being included in server fail, determine the type of failure；It is concentrated from the relevant fault obtained previously according to Apriori algorithm and obtains failure associated with failure, as subsequent prediction failure；Corresponding compensating operation is taken according to subsequent prediction failure for staff.The present invention can be after server breaks down, the relevance of fault type is concentrated according to relevant fault, predict the subsequent fault type being likely to occur, staff is set to make certain compensating operation ahead of time, the generation of consequent malfunction is avoided in time and reduces the influence to server as far as possible after consequent malfunction generation, improves the reliability, availability, processor of server.The invention also discloses a kind of server relevant fault forecasting systems, it may have above-mentioned advantage, details are not described herein.
Description
Technical field
The present invention relates to server failure administrative skill fields, more particularly to a kind of server relevant fault prediction technique
And its system.
Background technique
As computer technology develops rapidly, high performance server system increasingly becomes the need of socio-economic development
It wants, and the requirement to the safety of server also increases accordingly, and safety is mainly reflected in reliability, availability, processor.Reliability, availability, processor refers to
Be machine reliability (Reliability), availability (Availability) and serviceability (Serviceability).
RAS ability mainly sees several aspects: RAS characteristic, CPU RAS characteristic, memory RAS characteristic, the I/O RAS characteristic of System rank
Deng.
The RAS characteristic of these different stages is required when server fail, can carry out quick diagnosis to failure,
Then it executes and repairs operation, be allowed to the stable operation of influence server as few as possible, still, due to possible between different faults
There are associations, i.e., a failure may cause the generation of another failure, and current server can only after the failure occurred
Discover and handled, the diagnosis and processing to the failure of subsequent initiation are often not prompt enough, are easy to influence the RAS of server
Energy.
Therefore, how to provide a kind of reliability, availability, processor that can be improved server server relevant fault prediction technique and its
System is the current problem to be solved of those skilled in the art.
Summary of the invention
The object of the present invention is to provide a kind of server relevant fault prediction technique and its systems, can occur when server
After failure, the subsequent fault type being likely to occur is predicted, staff is made to make certain compensating operation ahead of time, improve server
Reliability, availability, processor.
In order to solve the above technical problems, the present invention provides a kind of server relevant fault prediction techniques, comprising:
After the server fail, the type of the failure is determined；
It is concentrated from the relevant fault obtained previously according to Apriori algorithm and obtains failure associated with the failure, made
For subsequent prediction failure；Corresponding compensating operation is taken according to the subsequent prediction failure for staff.
Preferably, the acquisition process of the relevant fault collection specifically:
Step s201: collecting the fault message of the server, obtain fault information database, by the fault message number
According to library as first database；Wherein, every fault message includes fault type and the time that failure occurs；
Step s202: traversing the first database, searches frequency and is greater than and sets according to the Apriori algorithm
The fault type of minimum support threshold value extracts the corresponding whole failure letters of the fault type out of described first database
Breath the first frequent item set of composition；
Step s203: traversal first frequent item set obtains the time of origin section of every kind of fault type；
Step s204: related fault type combination is determined, wherein include two in each fault type combination
There is the fault type of intersection in time of origin section；
Step s205: determine that each fault type combines corresponding two kinds of fault types in first frequent item set
The simultaneous number of failure；Wherein, if the time of origin difference of the failure of two kinds of fault types is less than preset time difference,
Then determine the failure of described two fault types while occurring；
Step s206: the fault type combination that frequency simultaneously is greater than the minimum support threshold value is chosen, determines institute
State the number that two kinds of fault types in the first frequent item set in each fault type combination occur respectively；
Step s207: by each fault type combine while frequency respectively with self-contained two kinds of failures
The number that type occurs respectively makees ratio, one group of confidence level for combining obtain two comparison results as the fault type；
Step s208: judge whether two in confidence level described in each group comparison results are all larger than according to the Apriori
The minimal confidence threshold of algorithm setting, if so, two kinds of fault types in the corresponding fault type combination of the confidence level
With relevance；
Step s209: choosing out of described first frequent item set has the corresponding failure letter of the various fault types of relevance
Breath the second frequent item set of composition, second frequent item set is the relevant fault collection.
Preferably, after obtaining second frequent item set in the step s209 further include:
Second frequent item set is determined as the first database, updates the minimum support according to preset rules
Threshold value, the minimal confidence threshold and the preset time difference, repeating said steps s202, until the second obtained frequency
Numerous item collection meets termination condition, then using the second frequent item set obtained at this time as the relevant fault collection.
Preferably, the termination condition specifically:
The obtained fault type quantity in the second frequent item set is less than preset quantity threshold value.
Preferably, the termination condition specifically:
Obtain use when the second frequent item set one group of minimum support threshold value, minimal confidence threshold and preset time
The size of difference meets default correlation threshold group.
In order to solve the above technical problems, the present invention also provides a kind of server relevant fault forecasting systems, comprising:
Fault determination module, for determining the type of the failure after the server fail；
Consequent malfunction prediction module, for concentrating acquisition and institute from the relevant fault obtained previously according to Apriori algorithm
The associated failure of failure is stated, as subsequent prediction failure；It is taken accordingly for staff according to the subsequent prediction failure
Compensating operation.
The present invention provides a kind of server relevant fault prediction technique, the preparatory Apriori algorithm of this method obtains one
Relevant fault collection can concentrate the relevance of fault type, prediction is subsequent can after server breaks down according to relevant fault
The fault type that can occur avoids consequent malfunction so that staff be enable to make certain compensating operation ahead of time in time
Occur and reduce as far as possible after consequent malfunction generation the influence to server, improves the reliability, availability, processor of server.The present invention
Additionally provide a kind of server relevant fault forecasting system, it may have above-mentioned advantage, details are not described herein.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to institute in the prior art and embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of flow chart of the process of server relevant fault prediction technique provided by the invention；
Fig. 2 is a kind of flow chart of the acquisition process of relevant fault collection provided by the invention；
Fig. 3 is a kind of structural schematic diagram of server relevant fault forecasting system provided by the invention.
Specific embodiment
Core of the invention is to provide a kind of server relevant fault prediction technique and its system, can occur when server
After failure, the subsequent fault type being likely to occur is predicted, staff is made to make certain compensating operation ahead of time, improve server
Reliability, availability, processor.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Shown in Figure 1 the present invention provides a kind of server relevant fault prediction technique, Fig. 1 is provided by the invention
A kind of flow chart of the process of server relevant fault prediction technique；This method comprises:
Step s101: after server fail, the type of failure is determined；
Step s102: it is concentrated from the relevant fault obtained previously according to Apriori algorithm and obtains event associated with failure
Barrier, as subsequent prediction failure；Corresponding compensating operation is taken according to subsequent prediction failure for staff.
Wherein, Apriori algorithm is a kind of frequent item set algorithm of Mining Association Rules, and core concept is to pass through candidate
Collection generates and the downward closing of plot detects two stages and carrys out Mining Frequent Itemsets Based.What above-mentioned relevant fault concentration included is to have
The fault type of incidence relation, and the correlation degree between each fault type can be embodied according to above-mentioned relevant fault collection,
Therefore it can predict to occur the failure of the failure possible generation later of a certain type according to relevant fault collection.
Shown in Figure 2, Fig. 2 is a kind of flow chart of the acquisition process of relevant fault collection provided by the invention；Specifically,
The acquisition process of relevant fault collection specifically:
Step s201: collecting the fault message of server, obtain fault information database, using fault information database as
First database；Wherein, every fault message includes fault type and the time that failure occurs；
Step s202: traversal first database searches minimum the supporting that frequency is greater than foundation Apriori algorithm setting
The fault type for spending threshold value extracts the corresponding whole fault messages of fault type out of first database and forms the first frequent episode
Collection；
For example, minimum support threshold value is 1, then the fault type by frequency in first database greater than 1 time is corresponding
Fault message extract composition the first frequent item set.
Step s203: the first frequent item set of traversal obtains the time of origin section of every kind of fault type；
Step s204: related fault type combination is determined, wherein include two generations in each fault type combination
Time interval has the fault type of intersection；
Wherein, time of origin section here refers to the earliest time of origin and time of origin the latest of the fault type
Section.
Step s205: determine each fault type in the first frequent item set combine corresponding two kinds of fault types failure it is same
The number of Shi Fasheng；Wherein, if the time of origin difference of the failure of two kinds of fault types is less than preset time difference, determine two
The failure of kind fault type occurs simultaneously；
Step s206: the fault type combination that frequency simultaneously is greater than minimum support threshold value is chosen, determines the first frequency
The number that two kinds of fault types in numerous item collection in each fault type combination occur respectively；
Step s207: by each fault type combine while frequency respectively with self-contained two kinds of fault types
The number occurred respectively makees ratio, one group of confidence level for combining obtain two comparison results as fault type；
Step s208: judge whether two in each group confidence level comparison results are all larger than and set according to Apriori algorithm
Minimal confidence threshold, if so, two kinds of fault types in confidence level corresponding fault type combination have relevance；
For example, type-A has occurred 4 times, B type is had occurred 2 times, and AB type has occurred 3 times simultaneously, then type-A is corresponding
Confidence level is that P (AB)/P (A)=corresponding confidence level of 3/4, B type is P (AB)/P (B)=3/2.Assuming that minimal confidence threshold
It is 70%, then the corresponding confidence level of AB type is all larger than minimal confidence threshold, shows that type-A and B type have relevance.
Step s209: the corresponding fault message group of various fault types with relevance is chosen out of first frequent item set
At the second frequent item set, the second frequent item set is relevant fault collection.
Preferably, after obtaining the second frequent item set in step s209 further include:
Step s210: being determined as first database for the second frequent item set, updates minimum support threshold according to preset rules
Value, minimal confidence threshold and preset time difference repeat step s202, until obtained the second frequent item set satisfaction terminates
Condition, then using the second frequent item set obtained at this time as relevant fault collection.
It is understood that there are many quantity of fault type in practical application, an above-mentioned steps s202- step is only carried out
The operation of s209 obtains result and is not enough to accurately show fault correlation relationship, thus need constantly adjustment minimum support threshold value,
The numerical value of minimal confidence threshold and preset time difference, and repeat aforesaid operations, until obtained result is smart enough
Until really.It is understood that in order to improve the accuracy of each circulate operation, minimum support threshold value and most in preset rules
The size of small confidence threshold value should be gradually increased, and preset time difference should be gradually reduced, such as minimum in first time circulate operation
Support threshold is 1, minimal confidence threshold 70%, and preset time difference is 1s；It is minimum in second of circulate operation to support
Spending threshold value is 3, minimal confidence threshold 80%, and preset time difference is 30s.Certainly, the present invention does not limit each circulation behaviour
The specific value of minimum support threshold value, minimal confidence threshold and preset time difference in work, staff can be according to realities
Border situation sets itself.
Preferably, termination condition here specifically:
The obtained fault type quantity in the second frequent item set is less than preset quantity threshold value.
It is understood that when the fault type quantity in the second frequent item set is sufficiently small, it can be to a certain extent
The accuracy of the relevance prediction of reflection at this time is more accurate.
Preferably, in another embodiment, termination condition here specifically:
Obtain use when the second frequent item set one group of minimum support threshold value, minimal confidence threshold and preset time
The size of difference meets default correlation threshold group.
It is understood that as the above analysis, minimum support threshold value, minimal confidence threshold and preset time
The numerical value of difference is constantly adjusted with the increase of cycle-index, therefore works as the number of minimum support threshold value and minimal confidence threshold
Be worth sufficiently large and preset time difference it is sufficiently small when, the relevance of various fault types is accurate in obtained the second frequent item set
Degree i.e. can be relatively high, i.e., the numerical value of minimum support threshold value, minimal confidence threshold and preset time difference can be from side
Reflect the association accuracy of the second obtained frequent item set, therefore can judge whether that end loop is answered to operate accordingly.
Certainly, both the above termination condition is only preferred embodiment, and any condition may be selected in staff, or uses it
His termination condition, this is not limited by the present invention.
The present invention provides a kind of server relevant fault prediction technique, the preparatory Apriori algorithm of this method obtains one
Relevant fault collection can concentrate the relevance of fault type, prediction is subsequent can after server breaks down according to relevant fault
The fault type that can occur avoids consequent malfunction so that staff be enable to make certain compensating operation ahead of time in time
Occur and reduce as far as possible after consequent malfunction generation the influence to server, improves the reliability, availability, processor of server.
The present invention also provides a kind of server relevant fault forecasting systems, and shown in Figure 3, Fig. 3 provides for the present invention
A kind of server relevant fault forecasting system structural schematic diagram.The system includes:
Fault determination module 11, for determining the type of failure after server fail；
Consequent malfunction prediction module 12, for concentrated from the relevant fault that is obtained previously according to Apriori algorithm obtain with
The associated failure of failure, as subsequent prediction failure；Corresponding compensation behaviour is taken according to subsequent prediction failure for staff
Make.
The present invention provides a kind of server relevant fault forecasting system, the preparatory Apriori algorithm of the system obtains one
Relevant fault collection can concentrate the relevance of fault type, prediction is subsequent can after server breaks down according to relevant fault
The fault type that can occur avoids consequent malfunction so that staff be enable to make certain compensating operation ahead of time in time
Occur and reduce as far as possible after consequent malfunction generation the influence to server, improves the reliability, availability, processor of server.
It should be noted that in the present specification, relational terms such as first and second and the like are used merely to one
A entity or operation with another entity or operate distinguish, without necessarily requiring or implying these entities or operation it
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to
Cover non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or setting
Standby intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in the process, method, article or apparatus that includes the element.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (5)
1. a kind of server relevant fault prediction technique characterized by comprising
After the server fail, the type of the failure is determined；
It is concentrated from the relevant fault obtained previously according to Apriori algorithm and obtains failure associated with the failure, as rear
Continuous prediction failure；Corresponding compensating operation is taken according to the subsequent prediction failure for staff；
The acquisition process of the relevant fault collection specifically:
Step s201: collecting the fault message of the server, obtain fault information database, by the fault information database
As first database；Wherein, every fault message includes fault type and the time that failure occurs；
Step s202: traversing the first database, searches frequency and is greater than the minimum set according to the Apriori algorithm
The fault type of support threshold extracts the corresponding whole fault message groups of the fault type out of described first database
At the first frequent item set；
Step s203: traversal first frequent item set obtains the time of origin section of every kind of fault type；
Step s204: related fault type combination is determined, wherein include two generations in each fault type combination
Time interval has the fault type of intersection；
Step s205: determine that each fault type in first frequent item set combines the event of corresponding two kinds of fault types
Hinder simultaneous number；Wherein, if the time of origin difference of the failure of two kinds of fault types is less than preset time difference, sentence
The failure of fixed described two fault types occurs simultaneously；
Step s206: it chooses frequency simultaneously and is greater than the fault type of the minimum support threshold value and combine, determine described the
The number that two kinds of fault types in one frequent item set in each fault type combination occur respectively；
Step s207: by each fault type combine while frequency respectively with self-contained two kinds of fault types
The number occurred respectively makees ratio, one group of confidence level for combining obtain two comparison results as the fault type；
Step s208: judge whether two in confidence level described in each group comparison results are all larger than according to the Apriori algorithm
The minimal confidence threshold of setting, if so, two kinds of fault types in the corresponding fault type combination of the confidence level have
Relevance；
Step s209: the corresponding fault message group of various fault types with relevance is chosen out of described first frequent item set
At the second frequent item set, second frequent item set is the relevant fault collection.
2. the method according to claim 1, wherein obtained in the step s209 second frequent item set it
Afterwards further include:
Second frequent item set is determined as the first database, updates the minimum support threshold according to preset rules
Value, the minimal confidence threshold and the preset time difference, repeating said steps s202, until second obtained is frequent
Item collection meets termination condition, then using the second frequent item set obtained at this time as the relevant fault collection.
3. according to the method described in claim 2, it is characterized in that, the termination condition specifically:
The obtained fault type quantity in the second frequent item set is less than preset quantity threshold value.
4. according to the method described in claim 2, it is characterized in that, the termination condition specifically:
Obtain use when the second frequent item set one group of minimum support threshold value, minimal confidence threshold and preset time difference
Size meet default correlation threshold group.
5. a kind of server relevant fault forecasting system characterized by comprising
Fault determination module, for determining the type of the failure after the server fail；
Consequent malfunction prediction module obtains and the event for concentrating from the relevant fault obtained previously according to Apriori algorithm
Hinder associated failure, as subsequent prediction failure；Corresponding compensation is taken according to the subsequent prediction failure for staff
Operation；
The acquisition process of the relevant fault Ji Guanlianguzhangji specifically: the fault message for collecting the server obtains event
Hinder information database, using the fault information database as first database；Wherein, every fault message includes failure
The time that type and failure occur；The first database is traversed, frequency is searched and is greater than according to the Apriori algorithm
The fault type of the minimum support threshold value of setting extracts the corresponding whole of the fault type out of described first database
Fault message forms the first frequent item set；First frequent item set is traversed, the time of origin section of every kind of fault type is obtained；
Determine related fault type combination, wherein include that two time of origin sections have friendship in each fault type combination
The fault type of collection；Determine that each fault type in first frequent item set combines the event of corresponding two kinds of fault types
Hinder simultaneous number；Wherein, if the time of origin difference of the failure of two kinds of fault types is less than preset time difference, sentence
The failure of fixed described two fault types occurs simultaneously；Choose the failure that frequency simultaneously is greater than the minimum support threshold value
Type combination determines what two kinds of fault types in first frequent item set in each fault type combination occurred respectively
Number；The frequency while combination of each fault type is occurred with self-contained two kinds of fault types respectively respectively
Number make ratio, one group of confidence level for combining obtain two comparison results as the fault type；Judge described in each group
Whether two comparison results in confidence level are all larger than the minimal confidence threshold according to Apriori algorithm setting, if
It is that two kinds of fault types in the corresponding fault type combination of the confidence level have relevance；From first frequent item set
There is interior choose the corresponding fault message of the various fault types of relevance to form the second frequent item set, second frequent item set
The as described relevant fault collection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610719771.5A CN106294076B (en) | 2016-08-24 | 2016-08-24 | A kind of server relevant fault prediction technique and its system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610719771.5A CN106294076B (en) | 2016-08-24 | 2016-08-24 | A kind of server relevant fault prediction technique and its system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106294076A CN106294076A (en) | 2017-01-04 |
| CN106294076B true CN106294076B (en) | 2019-03-15 |
Family
ID=57616329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610719771.5A Active CN106294076B (en) | 2016-08-24 | 2016-08-24 | A kind of server relevant fault prediction technique and its system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106294076B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844582A (en) * | 2017-01-10 | 2017-06-13 | 北京市地铁运营有限公司地铁运营技术研发中心 | A kind of subway train failure emergent treatment system and method |
| CN108362957B (en) * | 2017-12-19 | 2020-09-11 | 东软集团股份有限公司 | Equipment fault diagnosis method and device, storage medium and electronic equipment |
| DE112018006856T5 (en) * | 2018-01-15 | 2020-10-01 | Mitsubishi Electric Corporation | Fault detection device, supervisory control system and fault detection method |
| CN109814526B (en) * | 2018-12-29 | 2021-06-08 | 卡斯柯信号有限公司 | Maintenance diagnosis method for trackside safety signal system |
| CN110474799B (en) * | 2019-07-31 | 2022-03-25 | 中国联合网络通信集团有限公司 | Fault positioning method and device |
| CN110502398B (en) * | 2019-08-21 | 2022-03-29 | 吉林吉大通信设计院股份有限公司 | Switch fault prediction system and method based on artificial intelligence |
| CN111143134A (en) * | 2019-12-30 | 2020-05-12 | 深圳Tcl新技术有限公司 | Fault processing method, equipment and computer storage medium |
| CN112801426B (en) * | 2021-04-06 | 2021-06-22 | 浙江浙能技术研究院有限公司 | Industrial process fault fusion prediction method based on correlation parameter mining |
| CN113515560A (en) * | 2021-07-19 | 2021-10-19 | 彩虹无线（北京）新技术有限公司 | Vehicle fault analysis method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010198410A (en) * | 2009-02-26 | 2010-09-09 | Nec Computertechno Ltd | Server failure prediction system |
| CN102006198A (en) * | 2010-12-16 | 2011-04-06 | 中国电子科技集团公司第三十研究所 | Method and device for acquiring network failure association rule |
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN104463706A (en) * | 2014-12-10 | 2015-03-25 | 深圳供电局有限公司 | Method and system for power grid to detect reasons of voltage sag incident |
| CN104734871A (en) * | 2013-12-20 | 2015-06-24 | 中兴通讯股份有限公司 | Method and device for positioning failures |
| CN105224616A (en) * | 2015-09-18 | 2016-01-06 | 浪潮软件股份有限公司 | A kind of based on seasonal effect in time series APRIORI algorithm improvement method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3981349B2 (en) * | 2003-10-09 | 2007-09-26 | 株式会社森精機製作所 | Remote control system |
-
2016
- 2016-08-24 CN CN201610719771.5A patent/CN106294076B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010198410A (en) * | 2009-02-26 | 2010-09-09 | Nec Computertechno Ltd | Server failure prediction system |
| CN102006198A (en) * | 2010-12-16 | 2011-04-06 | 中国电子科技集团公司第三十研究所 | Method and device for acquiring network failure association rule |
| CN104734871A (en) * | 2013-12-20 | 2015-06-24 | 中兴通讯股份有限公司 | Method and device for positioning failures |
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN104463706A (en) * | 2014-12-10 | 2015-03-25 | 深圳供电局有限公司 | Method and system for power grid to detect reasons of voltage sag incident |
| CN105224616A (en) * | 2015-09-18 | 2016-01-06 | 浪潮软件股份有限公司 | A kind of based on seasonal effect in time series APRIORI algorithm improvement method |
Non-Patent Citations (1)
| Title |
|---|
| "基于时序关联规则的设备故障预测方法研究";甘超等;《机床与液压》;20140630;第42卷(第11期);第167-171页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106294076A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106294076B (en) | A kind of server relevant fault prediction technique and its system | |
| US11176015B2 (en) | Log message analysis and machine-learning based systems and methods for predicting computer software process failures | |
| JP6293642B2 (en) | General-purpose graphs, rules and spatial structure based on recommendation engine | |
| US8806330B2 (en) | Automatic detection of item lists within a web page | |
| CN102915314A (en) | Automatic error correction pair generation method and system | |
| CN102959542A (en) | Method and apparatus for managing video content | |
| JP5521807B2 (en) | Failure cause estimation apparatus, failure cause estimation program, and failure cause estimation method | |
| US20210014102A1 (en) | Reinforced machine learning tool for anomaly detection | |
| CN101706812B (en) | Method and device for searching documents | |
| CN111368241B (en) | Webpage element identification method based on XPath | |
| CN106294535A (en) | The recognition methods of website and device | |
| CN106649413A (en) | Grouping method and device for webpage tabs | |
| CN104572999B (en) | Heterogeneous data-based error data detection method and device | |
| CN106528409A (en) | Application crash problem finding method and device | |
| CN103984757A (en) | Method and system for inserting news information articles in search result page | |
| CN113568940A (en) | Data query method, device, equipment and storage medium | |
| US20110113006A1 (en) | Business process control apparatus, businesses process control method and business process control program | |
| US11295039B2 (en) | Support system and method | |
| US8005775B2 (en) | System and method for detecting human judgment drift and variation control | |
| CN105119961A (en) | Semantic Web service automatic combination method based on body | |
| EP4131090A1 (en) | Machine learning device, learning model generation method, and program | |
| US20170344628A1 (en) | Methods and systems for identifying local search queries | |
| KR101691083B1 (en) | System and Method for Bug Fixing Developers Recommendation and Bug Severity Prediction based on Topic Model and Multi-Feature | |
| CN104063394B (en) | Method, device and equipment for determining target webpage | |
| CN112802603A (en) | Method and device for predicting influenza degree |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |