CN109857758A - A kind of association analysis method and system based on neighbours' window - Google Patents
A kind of association analysis method and system based on neighbours' window Download PDFInfo
- Publication number
- CN109857758A CN109857758A CN201811647923.0A CN201811647923A CN109857758A CN 109857758 A CN109857758 A CN 109857758A CN 201811647923 A CN201811647923 A CN 201811647923A CN 109857758 A CN109857758 A CN 109857758A
- Authority
- CN
- China
- Prior art keywords
- data
- window
- neighbours
- association
- association analysis
- 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
- 238000012097 association analysis method Methods 0.000 title claims abstract description 8
- 238000012098 association analyses Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 19
- 238000012216 screening Methods 0.000 claims description 8
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of association analysis method and system based on neighbours' window, in association analysis, is analyzed by solving the joint association analysis of data and itself association window and neighbours' window across the associated data on association window boundary；The correlation rule in association window between all data item is excavated in real time using limited space resources.The present invention can be with existing all correlation rules between the real-time mining data item of limited space cost, and efficiency with higher and excellent scalability.
Description
Technical field
The invention belongs to data analysis field, especially relates to a kind of association analysis method based on neighbours' window and be
System.
Background technique
In the information age of data explosion, data flow is widely used in the every field of social life.Accumulate in data flow
Contain existing incidence relation under information abundant, especially mass data, is all important in prediction and on-line analysis system
Decision-making foundation.
One emphasis of data correlation analysis is exactly to determine association window, still, in the cured method in current side, static window
Mouth can not handle the association individual across window edge, and there are association analysis omissions.
Summary of the invention
In view of this, the present invention proposes the side for carrying out association analysis in data flow under a kind of mode using neighbours' window
Method and system, can be and with higher with existing all correlation rules between the real-time mining data item of limited space cost
Efficiency and excellent scalability.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of association analysis method based on neighbours' window, comprising:
S1, data and itself association window and neighbours' window are subjected to joint association analysis；
S2, the real-time correlation rule excavated in association window between all data item.
Further, joint association analysis described in step S1 includes:
S11, the period that time shaft is divided into fixed intervals；
S12, the different periods is labeled serial number as starting point by some period；
All data in S13, traversal time axis take out all data associated with detection data.
Further, step S2 includes:
S21, all data identical with detection data serial number are selected；
S22, data in two periods adjacent with detection data, the relevance of judgement and detection data, row are selected
Except ineligible data, qualified data are filtered out；
S23, the screening for completing all data, generate final associated data set.
Another aspect of the present invention additionally provides a kind of correlation analysis system based on neighbours' window, comprising:
Relating module: data and itself association window and neighbours' window are subjected to joint association analysis；
It excavates module: excavating the correlation rule in association window between all data item in real time.
Further, relating module includes:
Cutting unit: time shaft is divided into the period of fixed intervals；
Serial number unit: the different periods is labeled serial number as starting point by some period；
Traversal Unit: all data in traversal time axis take out all data associated with detection data.
Further, excavating module includes:
First screening unit: all data identical with the period serial number of detection data are selected；
Second screening unit: the data in two periods adjacent with detection data, judgement and detection data are selected
Relevance excludes ineligible data, filters out qualified data；
Data set unit: completing the screening of all data, generates final associated data set.
Compared with prior art, the present invention have it is following the utility model has the advantages that
The present invention proposes to carry out association analysis in data flow under a kind of mode using neighbours' window, can be with limited sky
Between existing all correlation rules between the real-time mining data item of cost, and efficiency with higher and excellent scalability.
Detailed description of the invention
Fig. 1 is neighbours' window schematic diagram of the embodiment of the present invention；
Fig. 2 is neighbours' windows associate analysis operating process schematic diagram of the embodiment of the present invention.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
Technical solution of the present invention is described in further detail with reference to the accompanying drawing:
When being associated analysis, it is thus necessary to determine that the position of the association window of analyzed entity.Often such window
Position is uncertain, is dynamic change, it is necessary to which we constantly adjust the position of sliding window, promote operational standard
True property.Such as: in the association analysis of vehicle detection, have before and after often being carried out in 2 minutes windows by the user of detection mouth
Association suspicion, we can be divided into entire time bracket multiple windows that basket size is 2 minutes and in each window
User or individual carry out correlation analysis.
As shown in Figure 1, the time is divided into the 2 minutes time shafts in interval, it may be assumed that
[0,2],[2,4],[4,6],[6,8],[8,10]
It may insure to fall in the above section in 2 minutes by the vehicle sections detected in this way, such as p2 and p3.But across
Two points of more two adjacent time intervals also meet sometimes to be spaced in 2 minutes, such as p1 and p2, and this patent is specially for such quiet
The insurmountable problem of state window situation proposes a solution.
1, different time intervals is labeled serial number by some start time first, as shown in Fig. 2, next
All users on time shaft are once traversed, user associated there is searched, below to find p2 user as showing
Example；
2, select with the identical all users of detection user's serial number, p3 is taken out into alternately result in this step.
3, two periods adjacent with p2 are found, i.e. user in 1 and 3 two period judges the relevance with p2,
By judgement, ineligible data item is excluded, filters out qualified data, such as p1 meets condition, takes out conduct
As a result.
4, by all users in traversal time axis, all associated individuals and user can be taken out.
5, the filtering that conditional filtering carries out all data is finally carried out, final associated data set is generated.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of association analysis method based on neighbours' window characterized by comprising
S1, data and itself association window and neighbours' window are subjected to joint association analysis；
S2, the real-time correlation rule excavated in association window between all data item.
2. a kind of association analysis method based on neighbours' window according to claim 1, which is characterized in that described in step S1
Joint association analysis includes:
S11, the period that time shaft is divided into fixed intervals；
S12, the different periods is labeled serial number as starting point by some period；
All data in S13, traversal time axis take out all data associated with detection data.
3. a kind of association analysis method based on neighbours' window according to claim 1, which is characterized in that step S2 packet
It includes:
S21, all data identical with detection data serial number are selected；
S22, data in two periods adjacent with detection data are selected, the relevance of judgement and detection data excludes not
Qualified data filter out qualified data；
S23, the screening for completing all data, generate final associated data set.
4. a kind of correlation analysis system based on neighbours' window characterized by comprising
Relating module: data and itself association window and neighbours' window are subjected to joint association analysis；
It excavates module: excavating the correlation rule in association window between all data item in real time.
5. a kind of correlation analysis system based on neighbours' window according to claim 4, which is characterized in that relating module packet
It includes:
Cutting unit: time shaft is divided into the period of fixed intervals；
Serial number unit: the different periods is labeled serial number as starting point by some period；
Traversal Unit: all data in traversal time axis take out all data associated with detection data.
6. a kind of correlation analysis system based on neighbours' window according to claim 4, which is characterized in that excavate module packet
It includes:
First screening unit: all data identical with the period serial number of detection data are selected；
Second screening unit: selecting the data in two periods adjacent with detection data, and judgement is associated with detection data
Property, ineligible data are excluded, qualified data are filtered out；
Data set unit: completing the screening of all data, generates final associated data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811647923.0A CN109857758A (en) | 2018-12-29 | 2018-12-29 | A kind of association analysis method and system based on neighbours' window |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811647923.0A CN109857758A (en) | 2018-12-29 | 2018-12-29 | A kind of association analysis method and system based on neighbours' window |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109857758A true CN109857758A (en) | 2019-06-07 |
Family
ID=66893667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811647923.0A Pending CN109857758A (en) | 2018-12-29 | 2018-12-29 | A kind of association analysis method and system based on neighbours' window |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109857758A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289507A (en) * | 2011-08-30 | 2011-12-21 | 王洁 | Method for mining data flow weighted frequent mode based on sliding window |
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| CN108964995A (en) * | 2018-07-03 | 2018-12-07 | 上海新炬网络信息技术股份有限公司 | Log correlation analysis method based on time shaft event |
| CN109101530A (en) * | 2018-06-22 | 2018-12-28 | 哈尔滨工业大学（深圳） | Effective sequence of events pattern mining algorithm |
-
2018
- 2018-12-29 CN CN201811647923.0A patent/CN109857758A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289507A (en) * | 2011-08-30 | 2011-12-21 | 王洁 | Method for mining data flow weighted frequent mode based on sliding window |
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| CN109101530A (en) * | 2018-06-22 | 2018-12-28 | 哈尔滨工业大学（深圳） | Effective sequence of events pattern mining algorithm |
| CN108964995A (en) * | 2018-07-03 | 2018-12-07 | 上海新炬网络信息技术股份有限公司 | Log correlation analysis method based on time shaft event |
Non-Patent Citations (5)
| Title |
|---|
| 李娜等: "时间滑动窗口内基于密度的数据流聚类算法", 《计算机应用》 * |
| 王振飞等: "面向时间序列的微博话题演化模型研究", 《计算机科学》 * |
| 赵纪刚等: "民航旅客服务信息***告警关联规则挖掘", 《计算机应用与软件》 * |
| 逯晓鹏等: "基于关联规则挖掘算法的规则发现***的设计和实现", 《铁路计算机应用》 * |
| 郑金芳等: "基于模糊频繁模式的数据流关联规则挖掘方法", 《湘潭大学自然科学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107667370B (en) | Method and system for abnormal process detection | |
| Accorsi et al. | Discovering workflow changes with time-based trace clustering | |
| CN103455515A (en) | User recommendation method and system in SNS (social networking services) community | |
| CN110020178A (en) | Point of interest recognition methods, device, equipment and storage medium | |
| CN106886417A (en) | A kind of universal parallel method for digging of linear temporal specification | |
| CN105827422A (en) | Method and device for determining network element alarm correlation relation | |
| CN106777060A (en) | Node type seismic detector data file management system and method | |
| Harb et al. | A suffix-based enhanced technique for data aggregation in periodic sensor networks | |
| CN105447079A (en) | Data cleaning method based on functional dependency | |
| Wang et al. | Investigative visual analysis of global terrorism | |
| CN109857758A (en) | A kind of association analysis method and system based on neighbours' window | |
| CN106970791A (en) | A kind of universal parallel digging system of linear temporal specification | |
| Sim | Consolidation of success factors in data mining projects | |
| CN110968570A (en) | Distributed big data mining system facing E-commerce platform | |
| CN107330724A (en) | A kind of traffic flow analysis new method of the user behavior similarity based on Web daily records | |
| Sanchez-Pi et al. | An information fusion framework for context-based accidents prevention | |
| Pena et al. | Detecting Changes in User Behavior to Understand Interaction Provenance during Visual Data Analysis. | |
| Abd-Allah et al. | DyadChurn: customer churn prediction using strong social ties | |
| Bahi et al. | Frequency filtering approach for data aggregation in periodic sensor networks | |
| Fahed et al. | Episode rules mining algorithm for distant event prediction | |
| Sachpenderis et al. | Determining interesting communities in evolving social networks | |
| Rudolphi et al. | Visitor management and ecological integrity: one example of an integrated management approach using Decision Analysis | |
| Kim et al. | CTAR: Classification based on temporal class-association rules for intrusion detection | |
| Chen et al. | A Study on Security Trend based on News Analysis | |
| Ramanan et al. | A Novel Clustering & Machine Learning Algorithm for Crime Rate Prediction and Analysis |
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: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |