CN107864050A - Server failure Effective Association Rules analysis method based on lattice structure - Google Patents
Server failure Effective Association Rules analysis method based on lattice structure Download PDFInfo
- Publication number
- CN107864050A CN107864050A CN201710983382.8A CN201710983382A CN107864050A CN 107864050 A CN107864050 A CN 107864050A CN 201710983382 A CN201710983382 A CN 201710983382A CN 107864050 A CN107864050 A CN 107864050A
- Authority
- CN
- China
- Prior art keywords
- item
- effectiveness
- association rules
- item collection
- collection
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- 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
- G06F11/0766—Error or fault reporting or storing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of server failure Effective Association Rules analysis method based on lattice structure provided by the invention, extract the log information in server system event log storehouse, fault log data storehouse is formed, using lattice structure, each item collection in item collection lattice is made up of following three attribute:Item collection X, support s, effectiveness u (X), deletion is poorly efficient to use item collection, generates effective item collection lattice HUIL, utilizes HUIL to carry out the efficient rule association of server failure and analyzes;Enable to established correlation rule that there is stronger failure prediction capability, so as to realize the accurate detection to server failure and analysis, provided safeguard for the continual and steady operation of server, and whole method is simple, effectively improves the efficiency of whole analysis process.
Description
Technical field
The present invention relates to a kind of failure analysis methods, more particularly to a kind of server failure efficient correlation based on lattice structure
Rule analysis method.
Background technology
At present, server is widely used in all trades and professions, penetrates into the every aspect of society, and it stores mass data letter
Breath, is one of most basic, most important equipment in network.Most industries require server can it is round-the-clock provide safety,
Stable, efficient network service, if the failure occurred cannot be properly settled in time, can not just ensure the smooth of network service
It is logical, or even can also trigger bigger failure, so the accident analysis of server just seems most important.
Association analysis method is one kind in server failure analysis, assigns the certain failure predication of server system and place
Ability is put, a knowledge base is established using the conventional fault log of server, is got according to real-time monitoring server running status
Data matched with the information in knowledge base, so as to predict potential failure and risk and respond in time.So
The safe operation time of server, efficient offer network service can be provided;In the prior art, for server event
The association analysis method of barrier mainly has following several:Apriori algorithm and FP-growth algorithms;Wherein, Apriori algorithm makes
With a kind of alternative manner for being referred to as and successively searching for, k- item collections are used to explore (k+1)-item collection.First, the collection of frequent 1- item collections is found out
Close.It is denoted as L1, L1For finding out the set L of frequent 2- item collections2, it is used further to find out L3, so on, until that can not find frequently
K- item collections;Look for each LkRun-down database is needed, so that processing speed is slow, efficiency is low.FP-growth algorithms
By twice sweep transaction database, the frequent item that each office includes is arrived FP- by the compression storage of its support descending
In tree.During finding frequent mode afterwards, it is not necessary to scan transaction database again, and carried out only in FP-Tree
Lookup, and frequent mode is directly produced by recursive call FP-growth method, in whole discovery procedure also not
Candidate pattern need to be produced, therefore, FP-growth algorithms improve efficiency to a certain extent compared to Apriori algorithm, but
It is that its efficiency is still very low, this is due to that the log information of server is complicated, and there is substantial amounts of redundancy, and
FP-growth algorithms effectively can not carry out rationalization processing to redundancy, so that final efficiency is low, application
Effect is poor, and its failure prediction capability is poor.
It is, therefore, desirable to provide a kind of new server failure Association Rule Analysis method, enables to established association
Rule has stronger failure prediction capability, so as to realize the accurate detection to server failure and analysis, for holding for server
Continuous stable operation provides safeguard, and whole method is simple, effectively improves the efficiency of whole analysis process.
The content of the invention
In view of this, it is an object of the invention to provide a kind of server failure Effective Association Rules analysis based on lattice structure
Method, enable to established correlation rule that there is stronger failure prediction capability, so as to realize the essence to server failure
Really detection and analysis, provide safeguard for the continual and steady operation of server, and whole method is simple, effectively improves whole analysis
The efficiency of process.
A kind of server failure Effective Association Rules analysis method based on lattice structure provided by the invention, including following step
Suddenly:
S2. the log information in the fault log data storehouse of server is pre-processed to obtain the set i=of data item
{i1,i2,…,im, wherein, m is the number of data item;
S3. setting time T is divided into n period, in d-th of period TdThe data item i of interior event of failurep(q
(ip,td)) one affairs t of compositiond, and d by n transaction sets into affairs set D={ t1,t2,…,td,…,tn, wherein, 1≤d
≤ n, q (ip,td) it is in period TdThe data item i of internal fault eventpThe number of appearance, ipFor the set i={ i of data item1,
i2,…,imIn pth item, 1≤p≤m;
S4. all item collections occurred in the set of data item are enumerated using lattice structure, each item collection in item collection lattice
It is made up of following three attribute:Item collection X, support s and effectiveness u (X);
S5. by the effectiveness u (X) of item collection and the minimum value of utility u of settingminIt is compared, deletes effectiveness and be less than minimum effectiveness
The item collection of value, remaining item collection is formed into effective item collection lattice HUIL;
S6., Effective Association Rules set Rulesset is set, and is by efficient regular collection Rulesset initializing sets
Empty set, and the minimum effectiveness confidence value of Effective Association Rules is set as min-uconf;
S7. all 1- item collections searched in effective item collection lattice HUIL, and the 1- item collections of no child node are deleted, and obtain
1- item collection set H;
S8. the Effective Association Rules set for guide service device accident analysis is determined according to 1- item collection set H
Ruleset。
Further, comprise the following steps in step S8:
S801. to the data item i of the event of failure in any 1- item collections set Hp, searched in effective item collection lattice HUIL
Rope includes data item ipAll item collections, and effective item collection lattice HUIL is included into data item ipAll item collections composition item collection collection
Close H*;
S802. according to effective item collection lattice HUIL lattice structure direction top down, item collection set H is set*In have son
One of k- item collections of node are Xk, item collection set H is set*In one of them (k+j)-item collection be Xk, whereinIt is X so as to obtain candidate rule Rk.Itemset →Xk+j.Itemset\Xk.Itesmset, candidate is calculated
The R of rule effectiveness confidence level uconf (R);
S803. such as effectiveness confidence level uconf (R) >=min-uconf of current candidate rule, then an efficient correlation is obtained
Regular R, and Effective Association Rules R is added to Effective Association Rules set Rulesset;
S804. item collection set H is traveled through according to step 801 to step 803*In all item collections, generation Effective Association Rules simultaneously
It is added in Effective Association Rules set Ruleset.
S805. step S801 to step S804 is performed to remaining all 1- item collections in 1- item collection set H, obtained final
Effective Association Rules set Ruleset for guide service device accident analysis.
Further, in step S4, item collection X effectiveness u (X) is calculated according to equation below:
Wherein, u (X, td) for item collection X in affairs tdIn
Effectiveness.
Further, effectiveness u (X, t are calculated according to equation belowd):
Wherein, u (ip,td) be any event of failure data item ipIn thing
Be engaged in tdIn effectiveness.
Further, effectiveness u (i are calculated according to equation belowp,td):
u(ip,td)=p (ip)×q(ip,td), wherein, p (ip) be event of failure data item ipImportant level value.
Further, effectiveness confidence level uconf (R) is calculated according to equation below in step S802:
Wherein, luv (xk,Xk+j) it is k- item collections XkIn k+j- item collections
Xk+jLocal effectiveness, u (Xk) it is k- item collections XkEffectiveness.
Further, local effectiveness luv (x are calculated according to equation belowk,Xk+j):
Wherein, luv (xi,Xk) it is k-
Item collection XkAny one of xkLocal effectiveness.
Further, k- item collections X is calculated according to equation belowkAny one of xkLocal effectiveness be luv (xi,Xk):
Further, in addition to step S1:Pre-processed as follows:
Log information is extracted from server event daily record storehouse and forms fault log data storehouse;
Log information in fault log data storehouse is mapped to the set i={ i to form data item1,i2,…,im, and press
According to data item significance level to data item ipSetting important level value p (ip)。
Further, log information is mapped as by data item according to following method:
The attribute of log information is represented using English alphabet, the value of log information is represented with Arabic numerals.
Beneficial effects of the present invention:By means of the invention it is possible to so that the correlation rule established has stronger failure pre-
Survey ability, so as to realize the accurate detection to server failure and analysis, provided safeguard for the continual and steady operation of server, and
And entirely method is simple, the efficiency of whole analysis process is effectively improved.
Embodiment
The present invention is further described in detail below:
A kind of server failure Effective Association Rules analysis method based on lattice structure provided by the invention, including following step
Suddenly:
S1:Pre-processed as follows:
Log information is extracted from server event daily record storehouse and forms fault log data storehouse;By in fault log data storehouse
Log information map the set i={ i to form data item1,i2,…,im, and according to data item significance level to data item
ipSetting important level value p (ip), log information is mapped as by data item, 1≤p≤m according to following method;
The attribute of log information is represented using English alphabet, the value of log information is represented with Arabic numerals.
S2. the log information in the fault log data storehouse of server is pre-processed to obtain the set i=of data item
{i1,i2,…,im, wherein, m is the number of data item;
S3. setting time T is divided into n period, in d-th of period TdThe data item i of interior event of failurep(q
(ip,td)) one affairs t of compositiond, and d by n transaction sets into affairs set D={ t1,t2,…,td,…,tn, wherein, 1≤d
≤ n, q (ip,td) it is in period TdThe data item i of internal fault eventpThe number of appearance, ipFor the set i={ i of data item1,
i2,…,imIn pth item, 1≤p≤m;
S4. all item collections occurred in the set of data item are enumerated using lattice structure, each item collection in item collection lattice
It is made up of following three attribute:Item collection X, support s and effectiveness u (X);
S5. by the effectiveness u (X) of item collection compared with the minimum value of utility umin set, effectiveness is deleted less than most poorly efficient
With the item collection of value, remaining item collection is formed into effective item collection lattice HUIL;
S6., Effective Association Rules set Rulesset is set, and is by efficient regular collection Rulesset initializing sets
Empty set, and the minimum effectiveness confidence value of Effective Association Rules is set as min-uconf;
S7. all 1- item collections searched in effective item collection lattice HUIL, and the 1- item collections of no child node are deleted, and obtain
1- item collection set H;
S8. the Effective Association Rules set for guide service device accident analysis is determined according to 1- item collection set H
Ruleset.By the method for the present invention, the difference of item collection effectiveness is taken into full account in processing procedure, so as to effectively pick
Except the influence to processing procedure such as redundancy, enable to established correlation rule that there is stronger failure predication energy
Power, so as to realize the accurate detection to server failure and analysis, provided safeguard for the continual and steady operation of server, and it is whole
Individual method is simple, effectively improves the efficiency of whole analysis process
In the present embodiment, comprise the following steps in step S8:
S801. to the data item i of the event of failure in any 1- item collections set Hp, searched in effective item collection lattice HUIL
Rope includes data item ipAll item collections, and effective item collection lattice HUIL is included into data item ipAll item collections composition item collection collection
Close H*;
S802. according to effective item collection lattice HUIL (for the Lattice of High Utility Itemsets, HUIL
Abbreviation) lattice structure direction top down, item collection set H is set*In have child node one of k- item collections be XkIf
Put item collection set H*In one of them (k+j)-item collection be Xk, whereinIt is so as to obtain candidate rule R
Xk.Itemset→Xk+j.Itemset\ Xk.Itesmset, the R of candidate rule effectiveness confidence level uconf (R) is calculated;
S803. such as effectiveness confidence level uconf (R) >=min-uconf of current candidate rule, then an efficient correlation is obtained
Regular R, and Effective Association Rules R is added to Effective Association Rules set Rulesset;
S804. item collection set H is traveled through according to step 801 to step 803*In all item collections, generation Effective Association Rules simultaneously
It is added in Effective Association Rules set Ruleset.
S805. step S801 to step S804 is performed to remaining all 1- item collections in 1- item collection set H, obtained final
For the Effective Association Rules set Ruleset of guide service device accident analysis, by the above method, can select accurately
Effective Association Rules, so that last Effective Association Rules have stronger failure prediction capability, and then ensure server
The accurate detection of failure and analysis.
In the present embodiment, in step S4, item collection X effectiveness u (X) is calculated according to equation below:
Wherein, u (X, td) for item collection X in affairs tdIn
Effectiveness.
Wherein:Effectiveness u (X, t are calculated according to equation belowd):
Wherein, u (ip,td) be any event of failure data item ipIn thing
Be engaged in tdIn effectiveness.
Effectiveness u (i are calculated according to equation belowp,td):
u(ip,td)=p (ip)×q(ip,td), wherein, p (ip) be event of failure data item ipImportant level value, lead to
Cross the above method, can accurately at evaluation item collection value of utility, and then embody the utilization variance of item collection, be follow-up processing
Provide safeguard, and improve the efficiency of whole process.
In the present embodiment, effectiveness confidence level uconf (R) is calculated according to equation below in step S802:
Wherein, luv (xk,Xk+j) it is k- item collections XkIn k+j- item collections
Xk+jLocal effectiveness, u (Xk) it is k- item collections XkEffectiveness.
Wherein, local effectiveness luv (x are calculated according to equation belowk,Xk+j):
Wherein, luv (xi,Xk) it is k-
Item collection XkAny one of xkLocal effectiveness.
K- item collections X is calculated according to equation belowkAny one of xkLocal effectiveness be luv (xi,Xk):
By the above method, on the basis of item collection effectiveness, provided safeguard for final accurate determination Effective Association Rules,
Beneficial to the efficiency for improving whole processing procedure.
Below by way of an instantiation to the detailed description of the invention:
It is below the log information in the fault log data storehouse of certain server, as illustrated in chart 1:
Table 1
Table 2
Table 2 is to map the log information in table 1 in the log database to be formed according to the mapping method in step S1
Data item, by taking temperature as an example:A represents attribute information, as temperature event, and 0,1 and 2 expression is that the attribute of log information takes
Value, three different property values of temperature event are finally represented by A0, A1 and A2, and important level value is carried out according to significance level
Setting.
Also, it will averagely be divided into n=9 period, a period T in 2016 4,5, JunedIn (1≤d≤n)
All event of failures in item ip(q(ip,td)) one affairs t of compositiond(1≤d≤n), wherein q (ip,td) represent in the time
Section TdMean terms ipThe number of appearance, obtain affairs set D={ t1,t2,...,tn};After the method in above-mentioned, draw as follows
Rule:
1. temperature exceeds danger threshold → CPU overtemperature protections, restarted (uconf=86%);
2. temperature is in fence coverage → CPU overtemperature protections (uconf=61%);
3. internal memory ECC error → blue screen (uconf=90%)
4. software NMI → machine of delaying (uconf=75%)
5. there is exception → cpu fan high-speed cruising (uconf=63%) in backboard fan
6. battery electric quantity is low → OS starts and closes (uconf=78%)
7. power supply supply power mismatch → case fan rotating speed is low and temperature exceeds secure threshold (uconf=
73%)
8. power supply supply voltage mismatch → CPU voltages are less than secure threshold and machine of delaying (uconf=76%);Therefore,
Pass through above-mentioned method, you can the failure of server is detected and predicted, so that the temperature of server is too high as an example, if
Know that temperature exceeds danger threshold, then it may determine that the failure that server is likely to occur either is restarted for CPU overtemperature protections, its
Effectiveness confidence level reaches 86%, whereas if Server Restart or generation overtemperature protection, then the failure that can be determined that is temperature
Degree did danger threshold, and temperature is in fence coverage in other words, and effectiveness confidence level has respectively reached 86% or 61%, therefore,
Pass through the method for the present invention so that there is stronger forecast analysis ability for the failure of server, and there is stronger inspection
Analysis ability is surveyed, so as to Accurate Prediction or the failure of server is detected, effectively improves the O&M efficiency of server, protect
Card server can continually and steadily be run, and whole process is more succinct reliable, efficiency high.
Finally illustrate, the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although with reference to compared with
The present invention is described in detail good embodiment, it will be understood by those within the art that, can be to the skill of the present invention
Art scheme is modified or equivalent substitution, and without departing from the objective and scope of technical solution of the present invention, it all should cover at this
Among the right of invention.
Claims (10)
- A kind of 1. server failure Effective Association Rules analysis method based on lattice structure, it is characterised in that:Comprise the following steps:S2. the log information in the fault log data storehouse of server is pre-processed to obtain the set i={ i of data item1, i2,…,im, wherein, m is the number of data item;S3. setting time T is divided into n period, in d-th of period TdThe data item i of interior event of failurep(q(ip, td)) one affairs t of compositiond, and d by n transaction sets into affairs set D={ t1,t2,…,td,…,tn, wherein t, d (1≤d≤ N) q (ip,td) it is in period TdThe data item i of internal fault eventpThe number of appearance, ipFor the set i={ i of data item1, i2,…,imIn pth item, 1≤p≤m;S4. all item collections occurred in the set of data item are enumerated using lattice structure, each item collection in item collection lattice is by such as Lower three attributes composition:Item collection X, support s and effectiveness u (X);S5. by the effectiveness u (X) of item collection and the minimum value of utility u of settingminIt is compared, deletes effectiveness less than minimum value of utility Item collection, remaining item collection is formed into effective item collection lattice HUIL;S6., Effective Association Rules set Rulesset is set, and is empty set by efficient regular collection Rulesset initializing sets, And the minimum effectiveness confidence value of Effective Association Rules is set as min-uconf;S7. all 1- item collections searched in effective item collection lattice HUIL, and the 1- item collections of no child node are deleted, and obtain 1- items Collect set H;S8. the Effective Association Rules set Ruleset for guide service device accident analysis is determined according to 1- item collection set H.
- 2. the server failure Effective Association Rules analysis method based on lattice structure according to claim 1, it is characterised in that: Comprise the following steps in step S8:S801. to the data item i of the event of failure in any 1- item collections set Hp, search for and include in effective item collection lattice HUIL Data item ipAll item collections, and effective item collection lattice HUIL is included into data item ipAll item collections composition item collection set H*;S802. according to effective item collection lattice HUIL lattice structure direction top down, item collection set H is set*In have child node One of k- item collections are Xk, item collection set H is set*In one of them (k+j)-item collection be Xk, wherein It is X so as to obtain candidate rule Rk.Itemset→Xk+j.Itemset\Xk.Itesmset, the effectiveness for calculating the R of candidate rule is put Reliability uconf (R);S803. such as effectiveness confidence level uconf (R) >=min-uconf of current candidate rule, then an Effective Association Rules are obtained R, and Effective Association Rules R is added to Effective Association Rules set Rulesset;S804. item collection set H is traveled through according to step 801 to step 803*In all item collections, generation Effective Association Rules simultaneously be added to In Effective Association Rules set Ruleset.S805. step S801 to step S804 is performed to remaining all 1- item collections in 1- item collection set H, obtains final be used for The Effective Association Rules set Ruleset of guide service device accident analysis.
- 3. the server failure Effective Association Rules analysis method based on lattice structure according to claim 2, it is characterised in that: In step S4, item collection X effectiveness u (X) is calculated according to equation below:Wherein, u (X, td) for item collection X in affairs tdIn effectiveness.
- 4. the server failure Effective Association Rules analysis method based on lattice structure according to claim 3, it is characterised in that: Effectiveness u (X, t are calculated according to equation belowd):Wherein, u (ip,td) be any event of failure data item ipIn affairs tdIn Effectiveness.
- 5. the server failure Effective Association Rules analysis method based on lattice structure according to claim 4, it is characterised in that: Effectiveness u (i are calculated according to equation belowp,td):u(ip,td)=p (ip)×q(ip,td), wherein, p (ip) be event of failure data item ipImportant level value.
- 6. the server failure Effective Association Rules analysis method based on lattice structure according to claim 5, it is characterised in that: Effectiveness confidence level uconf (R) is calculated according to equation below in step S802:Wherein, luv (xk,Xk+j) it is k- item collections XkIn k+j- item collections Xk+j's Local effectiveness, u (Xk) it is k- item collections XkEffectiveness.
- 7. the server failure Effective Association Rules analysis method based on lattice structure according to claim 6, it is characterised in that: Local effectiveness luv (x are calculated according to equation belowk,Xk+j):Wherein, luv (xi,Xk) it is k- item collections Xk Any one of xkLocal effectiveness.
- 8. the server failure Effective Association Rules analysis method based on lattice structure according to claim 7, it is characterised in that: K- item collections X is calculated according to equation belowkAny one of xkLocal effectiveness be luv (xi,Xk):<mrow> <mi>l</mi> <mi>u</mi> <mi>v</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>,</mo> <msub> <mi>X</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <munder> <mo>&Sigma;</mo> <mrow> <msub> <mi>X</mi> <mi>k</mi> </msub> <mo>&SubsetEqual;</mo> <msub> <mi>t</mi> <mi>d</mi> </msub> <mo>&cap;</mo> <msub> <mi>t</mi> <mi>d</mi> </msub> <mo>&Element;</mo> <mi>D</mi> </mrow> </munder> <mi>u</mi> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>,</mo> <msub> <mi>t</mi> <mi>d</mi> </msub> <mo>)</mo> </mrow> <mo>.</mo> </mrow>
- 9. the server failure Effective Association Rules analysis method based on lattice structure according to claim 1, it is characterised in that: Also include step S1:Pre-processed as follows:Log information is extracted from server event daily record storehouse and forms fault log data storehouse;Log information in fault log data storehouse is mapped to the set i={ i to form data item1,i2,…,im, and according to number According to the significance level of item to data item ipSetting important level value p (ip)。
- 10. the server failure Effective Association Rules analysis method based on lattice structure, its feature exist according to claim 9 In:Log information is mapped as by data item according to following method:The attribute of log information is represented using English alphabet, the value of log information is represented with Arabic numerals.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710983382.8A CN107864050A (en) | 2017-10-20 | 2017-10-20 | Server failure Effective Association Rules analysis method based on lattice structure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710983382.8A CN107864050A (en) | 2017-10-20 | 2017-10-20 | Server failure Effective Association Rules analysis method based on lattice structure |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107864050A true CN107864050A (en) | 2018-03-30 |
Family
ID=61696760
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710983382.8A Pending CN107864050A (en) | 2017-10-20 | 2017-10-20 | Server failure Effective Association Rules analysis method based on lattice structure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107864050A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110349678A (en) * | 2019-07-19 | 2019-10-18 | 齐鲁工业大学 | A kind of Chinese medicine marketing system and its working method based on the positive and negative sequence rule digging of effective |
CN112488181A (en) * | 2020-11-26 | 2021-03-12 | 哈尔滨工程大学 | Service fault high-response matching method based on MIDS-Tree |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120130964A1 (en) * | 2010-11-18 | 2012-05-24 | Yen Show-Jane | Fast algorithm for mining high utility itemsets |
CN105608182A (en) * | 2015-12-23 | 2016-05-25 | 一兰云联科技股份有限公司 | Uncertain data model oriented utility item set mining method |
CN105975608A (en) * | 2016-05-17 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Data mining method and device |
CN106033447A (en) * | 2015-03-16 | 2016-10-19 | 哈尔滨工业大学深圳研究生院 | Method and device for item-sets mining |
-
2017
- 2017-10-20 CN CN201710983382.8A patent/CN107864050A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120130964A1 (en) * | 2010-11-18 | 2012-05-24 | Yen Show-Jane | Fast algorithm for mining high utility itemsets |
CN106033447A (en) * | 2015-03-16 | 2016-10-19 | 哈尔滨工业大学深圳研究生院 | Method and device for item-sets mining |
CN105608182A (en) * | 2015-12-23 | 2016-05-25 | 一兰云联科技股份有限公司 | Uncertain data model oriented utility item set mining method |
CN105975608A (en) * | 2016-05-17 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Data mining method and device |
Non-Patent Citations (1)
Title |
---|
THANG MAI等: "A lattice-based approach for mining high utility association rules", 《INFORMATION SCIENCES》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110349678A (en) * | 2019-07-19 | 2019-10-18 | 齐鲁工业大学 | A kind of Chinese medicine marketing system and its working method based on the positive and negative sequence rule digging of effective |
CN112488181A (en) * | 2020-11-26 | 2021-03-12 | 哈尔滨工程大学 | Service fault high-response matching method based on MIDS-Tree |
CN112488181B (en) * | 2020-11-26 | 2022-10-18 | 哈尔滨工程大学 | Service fault high-response matching method based on MIDS-Tree |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hu et al. | No free lunch theorem for concept drift detection in streaming data classification: A review | |
US9292688B2 (en) | System and method for automated machine-learning, zero-day malware detection | |
Liu et al. | Event detection and evolution in multi-lingual social streams | |
CN107404473A (en) | Based on Mshield machine learning multi-mode Web application means of defences | |
Lima et al. | A comparative study of use of Shannon, Rényi and Tsallis entropy for attribute selecting in network intrusion detection | |
CN107864050A (en) | Server failure Effective Association Rules analysis method based on lattice structure | |
CN106874951A (en) | A kind of passenger's attention rate ranking method and device | |
Lu et al. | Discovering event evolution chain in microblog | |
CN117473571B (en) | Data information security processing method and system | |
CN114448657A (en) | Power distribution communication network security situation perception and abnormal intrusion detection method | |
CN110334508A (en) | A kind of host sequence intrusion detection method | |
Rezvani et al. | Enhancing accuracy of topic sensitive PageRank using jaccard index and cosine similarity | |
CN116628554B (en) | Industrial Internet data anomaly detection method, system and equipment | |
Pohl et al. | Active online learning for social media analysis to support crisis management | |
Xia et al. | Source Code Vulnerability Detection Based On SAR-GIN | |
CN110472416A (en) | A kind of web virus detection method and relevant apparatus | |
Lighari | Hybrid model of rule based and clustering analysis for big data security | |
Gao et al. | Informative scene graph generation via debiasing | |
Kexin et al. | GA-iForest: An Efficient Isolated Forest Framework Based on Genetic Algorithm for Numerical Data Outlier Detection. | |
Portela et al. | The search of conditional outliers | |
CN114329287A (en) | Abnormal link processing method and device, computer equipment and storage medium | |
Rabanser et al. | Intrinsic Anomaly Detection for Multi-Variate Time Series | |
Nasrin et al. | How many users are enough? Exploring semi-supervision and stylometric features to uncover a russian troll farm | |
Dauber et al. | Supervised Authorship Segmentation of Open Source Code Projects | |
Ju et al. | Detection of malicious code using the direct hashing and pruning and support vector machine |
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: 20180330 |
|
RJ01 | Rejection of invention patent application after publication |