CN103473458B - Method for comparatively analyzing similarities of fold lines - Google Patents
Method for comparatively analyzing similarities of fold lines Download PDFInfo
- Publication number
- CN103473458B CN103473458B CN201310420053.4A CN201310420053A CN103473458B CN 103473458 B CN103473458 B CN 103473458B CN 201310420053 A CN201310420053 A CN 201310420053A CN 103473458 B CN103473458 B CN 103473458B
- Authority
- CN
- China
- Prior art keywords
- axis
- interval
- value
- lineb
- linea
- 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
Landscapes
- Complex Calculations (AREA)
Abstract
The invention relates to a method for comparatively analyzing similarities of fold lines. Deviation and coupling degrees are indicated through quantitative indexes, and the similarities of a plurality of fold lines can be compared through the quantitative indexes. The method is mainly characterized in that direct deviation and square deviation can be accumulated through summarized fold lines obtained by sectional summarizing for X axes of the fold lines and are compared with reference values of direct deviation and square deviation to obtain percent quantitative indexes, so that the similarities of the fold lines are indicated through the quantitative indexes.
Description
Technical field
The present invention relates to a kind of computer software, especially relate to similar with regard to two broken lines in a kind of computer software
The control methods of degree.
Background technology
During some are to the excavation of data, analysis, the plane coordinates constituting some discrete data is needed to click through
Row analysis, thus draw the mutual relation between these plane coordinates points.If it is flat that the two groups of data that there is precedence relationship are constituted
Areal coordinate point constitutes two two broken lines having precedence relationship, to analyze the similarity of this two broken lines by computer,
It is the important and effective step of the degree of association cracking this two groups of data.But it is in existing software, similar to two broken lines
The judgement of degree is very rough, and its reliability is not high.
Content of the invention
The similarity that the present invention is mainly two broken lines of judgement existing for solution prior art is very rough, and reliability is not
High technical problem, provide one kind can digitization, and accurately, reliably judge two broken lines degree of accuracy broken line to score
The method of analysis similarity.
1. the above-mentioned technical problem of the present invention is mainly addressed by following technical proposals：A kind of broken line is to score
The method of analysis similarity, it includes initial A coordinate memory module, initial B coordinate memory module, merges index module, calculates mould
Block is it is characterised in that it comprises the steps：
1st, store broken line LineA coordinate in initial A coordinate memory module, store folding in initial B coordinate memory module
The coordinate of line LineB, AXmin, BXmin respectively interval minima of the interval X-axis with LineB of the X-axis of LineA, AXmax,
BXma x is respectively the maximum in the interval X-axis interval with LineB of X-axis of LineA, by interval for the X-axis of the LineA X with LineB
Axle interval all inputs merging index module, obtains X-axis combine interval [Xmin, Xmax], and wherein Xmin is AXmin, in BXmin
Minima, wherein Xmax be AXmax, the maximum in BXmax；
2nd, on the time period that LineA is not had sampled point on combine interval, it is that LineA generates new sampled point, will
LineB does not have the time period of sampled point on combine interval（X-axis unit）On, it is that LineB generates new sampled point；
3rd, it is provided with two positions in computing module and is used for preserving irrelevance, respectively directly deviate aggregate-value position
AmpAcc, variance deviate aggregate-value position SqrAcc and AmpAcc and SqrAcc are initialized as 0, are additionally provided with computing module
Two positions are used for preserving deviates radix, and respectively directly deviation aggregate-value benchmark position AmpAccBase, variance deviation are accumulative
Value benchmark position SqrAccBase, AmpAccBase and SqrAccBase is also initialized as 0；
4th, to combine interval [Xmin, Xmax] located at section length SegLen, the length of SegLen is 1 X-axis time period
Multiple, LineA, all sampled points of LineB carry out collecting segmentation according to SegLen, if N be natural number, n-th
The X-axis time period of the corresponding X-axis combine interval of segmentation SegN is that [N, N+SegLen] is interval, when the Y-axis value of SegN is corresponding
Between section the Y-axis value of sampled point cumulative and, finally give two and new collect broken line LineSA, LineSB；
5th, according to segmentation, from first segmentation Seg1 to last segmentation, traveled through：
(1) for current fragment SegC, LineSA and LineSB is subtracted each other and then taken in the Y-axis value of current fragment
Absolute value obtains and directly deviates AmpC, AmpC is carried out with power and obtains variance deviation AmpS；
(2) AmpC is added on AmpAcc, realizes AmpAcc accumulative for the direct deviation of all segmentations；
(3) AmpS is added on SqrAcc, realizes SqrAcc accumulative for the variance deviation of all segmentations；
(4) absolute value of the current value of LineSA is added on AmpAccBase, by the current value of LineSA
The power of absolute value is added on SqrAccBase, obtains two divergence indicator benchmark；
The AmpAcc that traversal obtains after terminating represents the accumulative of the direct bias of all segmentations, and SqrAcc represents
The deviation power of all segmentations accumulative；
6th, two irrelevance indexs are obtained：
Directly deviate percentage ratio（AmpPer）：AmpPer = AmpAcc / AmpAccBase * 100%；
Variance deviates percentage ratio（SqrPer）：SqrPer = SqrAcc / SqrAccBase * 100%；
7th, two overlapping indexes are obtained：
Direct-coupling percentage ratio（AmpFitPer）：AmpFitPer = 100% - AmpPer；
Variance coupling percentage（SqrFitPer）：SqrFitPer = 100% - SqrPer.
The present invention is the value of the X-axis of each sampled point, Y-axis in a kind of broken line, in conjunction with the permission distribution of the X-axis setting
Deviate window, obtain the degree of coupling, the irrelevance index quantifying, and then can be the broken line specified, from specified broken line set, seek
Find coupling degree of coupling highest, the broken line of irrelevance minimum, thus obtaining the data analysis system of best match broken line pair.
Assume：There are two clear and definite broken line LineA, LineB first sending out, sending out afterwards relation, wherein LineA is first to send out folding
Line, LineB is rear broken line, and the X-axis of the sampled point of LineA is interval to be [AXmin, AXmax], the X-axis area of the sampled point of LineB
Between be [BXmin, BXmax].
Broken line：X-axis has unit, and each unit has a sampled point, and each sampled point has value in Y-axis.One
As common application scenarios be：（1）X-axis is the time, and unit is the second；（2）Y-axis is quantity, and unit is secondary；（3）One sampled point
（x,y）Represent in time period second time x（More than or equal to x second time point, less than x+1 second time point）Interior, there is certain event altogether
Meter y time；
First send out broken line, send out broken line afterwards：First send out broken line, represent the corresponding event of this broken line it should occur front.After send out folding
Line, represents the corresponding event of this broken line it should occur rear.
Coupling：For first sending out certain event of broken line, from all events of rear broken line, deviate window according to allowing distribution
Rule, finds an event and is matched；First send out certain particular event of broken line, at most can only be with one of rear broken line thing
Part is matched；After send out one of broken line event, at most can only first be sent out one of broken line event and be matched.
Distribution is allowed to deviate window：It is assumed that it is N that distribution deviates window size, between two broken lines LineA, LineB,
Carry out during Coupling Degrees it is allowed to first send out certain sampled point of broken line（Ax,Ay）Corresponding Ay event, in LineB（N+
1）Individual sampled point carries out coupling association, and in LineB, corresponding time segment limit is x, x+1, x+2 ..., x+N.
The degree of coupling：Between two broken lines LineA, LineB, if two broken lines are completely superposed（The value phase of sampled point
With）, the degree of coupling of this kind of situation is necessarily unity couping；If the corresponding each event of each sampled point in LineA, can
Allowing distribution to deviate the corresponding event several times of sampled point in the range of the time period of the corresponding LineB of window, obtaining unique
The corresponding event of coupling, and each event in each sampled point in final LineB, have all been matched correspondence, then two
The degree of coupling between bar broken line is unity couping；During unity couping, overlapping index should reach highest.
Irrelevance：The order of severity being the failure to enough acquisition pairings of irrelevance explanation, during unity couping, irrelevance index should
For 0 it is impossible to mate is more, irrelevance index should be higher.
Directly deviate：Correspondence collects the same time period of broken line, the absolute value of the difference of Y-axis value of two sampled points.
Variance deviates：Correspondence collects the same time period of broken line, its power directly deviateing.
This method be intended to by broken line between relative analyses, obtain quantify broken line between the degree of coupling, irrelevance index,
Thus for different broken lines between similarity system design comparative approach is provided, and then for the broken line specified from several broken lines,
Search out the broken line of best match.Irrelevance refers to that target value is bigger, illustrates that the similarity between broken line is poorer；Overlapping index
Value（It may be negative）Less, illustrate that the similarity of this part of broken line is poorer；When two irrelevance indexs are all 0%, two degrees of coupling
Index is all 100%, illustrates that the similarity between broken line is 100%.
Preferably, the length of described SegLen can 1 X-axis time period to 20% X-axis combine interval [Xmin,
Xmax] length range in selected.The program can ensure that SegLen has suitable length, can ensure that suitably many again
Sampled point.
The beneficial effect brought of the present invention is, the similarity solving two broken lines of judgement existing for prior art is non-
Often rough, the not high technical problem of reliability it is achieved that one kind can digitization, and accurately, reliably judge two broken lines
The method of the broken line relative analyses similarity of degree of accuracy.
Brief description
Accompanying drawing 1 is the schematic diagram of LineA, LineB of the present invention；
Accompanying drawing 2 is the schematic diagram of LineSA, LineSB of the present invention；
Accompanying drawing 3 is according to the segmentation statistics schematic diagram that directly deviation, variance deviate to LineSA, LineSB.
Specific embodiment
Below by embodiment, and combine accompanying drawing, technical scheme is described in further detail.
Embodiment：
As shown in Figure 1, Figure 2, Figure 3 shows, the present invention is a kind of method of broken line relative analyses similarity, and it includes initially
A coordinate memory module, initial B coordinate memory module, merging index module, computing module, it comprises the steps：
1st, store broken line LineA coordinate in initial A coordinate memory module, store folding in initial B coordinate memory module
The coordinate of line LineB, AXmin, BXmin respectively interval minima of the interval X-axis with LineB of the X-axis of LineA, AXmax,
BXma x is respectively the maximum in the interval X-axis interval with LineB of X-axis of LineA, by interval for the X-axis of the LineA X with LineB
Axle interval all inputs merging index module, obtains X-axis combine interval [Xmin, Xmax], and wherein Xmin is AXmin, in BXmin
Minima, wherein Xmax be AXmax, the maximum in BXmax；
2nd, on the time period that LineA is not had sampled point on combine interval, it is that LineA generates new sampled point, will
LineB does not have the time period of sampled point on combine interval（X-axis unit）On, it is that LineB generates new sampled point；
3rd, it is provided with two positions in computing module and is used for preserving irrelevance, respectively directly deviate aggregate-value position
AmpAcc, variance deviate aggregate-value position SqrAcc and AmpAcc and SqrAcc are initialized as 0, are additionally provided with computing module
Two positions are used for preserving deviates radix, and respectively directly deviation aggregate-value benchmark position AmpAccBase, variance deviation are accumulative
Value benchmark position SqrAccBase, AmpAccBase and SqrAccBase is also initialized as 0；
4th, to combine interval [Xmin, Xmax] located at section length SegLen, the length of SegLen can be 1 X-axis time
Section is selected, by LineA, all samplings of LineB in the length range of 20% X-axis combine interval [Xmin, Xmax]
Point, carries out collecting segmentation according to SegLen, if N is natural number, the X-axis time of the corresponding X-axis combine interval of n-th segmentation SegN
Section is interval for [N, N+SegLen], the Y-axis value of SegN be the cumulative of the Y-axis value of the sampled point of corresponding time period and,
Obtain two eventually and new collect broken line LineSA, LineSB；
5th, according to segmentation, from first segmentation Seg1 to last segmentation, traveled through：
(1) for current fragment SegC, LineSA and LineSB is subtracted each other and then taken in the Y-axis value of current fragment
Absolute value obtains and directly deviates AmpC, AmpC is carried out with power and obtains variance deviation AmpS；
(2) AmpC is added on AmpAcc, realizes AmpAcc accumulative for the direct deviation of all segmentations；
(3) AmpS is added on SqrAcc, realizes SqrAcc accumulative for the variance deviation of all segmentations；
(4) absolute value of the current value of LineSA is added on AmpAccBase, by the current value of LineSA
The power of absolute value is added on SqrAccBase, obtains two divergence indicator benchmark；
The AmpAcc that traversal obtains after terminating represents the accumulative of the direct bias of all segmentations, and SqrAcc represents
The deviation power of all segmentations accumulative；
6th, two irrelevance indexs are obtained：
Directly deviate percentage ratio AmpPer：AmpPer = AmpAcc / AmpAccBase * 100%；
Variance deviates percentage ratio SqrPer：SqrPer = SqrAcc / SqrAccBase * 100%；
7th, two overlapping indexes are obtained：
Direct-coupling percentage ratio AmpFitPer：AmpFitPer = 100% - AmpPer；
Variance coupling percentage SqrFitPer：SqrFitPer = 100% - SqrPer.
Claims (2)
1. a kind of method of broken line relative analyses similarity, it include initial A coordinate memory module, initial B coordinate memory module,
Merge index module, computing module it is characterised in that it comprises the steps：
（1）Store broken line LineA coordinate in initial A coordinate memory module, store broken line in initial B coordinate memory module
The coordinate of LineB, AXmin, BXmin respectively interval minima of the interval X-axis with LineB of the X-axis of LineA, AXmax,
BXma x is respectively the maximum in the interval X-axis interval with LineB of X-axis of LineA, by interval for the X-axis of the LineA X with LineB
Axle interval all inputs merging index module, obtains X-axis combine interval [Xmin, Xmax], and wherein Xmin is AXmin, in BXmin
Minima, wherein Xmax be AXmax, the maximum in BXmax；
（2）On the time period that LineA is not had sampled point on combine interval, it is that LineA generates new sampled point, by LineB
On the time period not having sampled point on combine interval, it is that LineB generates new sampled point；
（3）Be provided with two positions and be used for preserving irrelevance in computing module, respectively directly deviate aggregate-value position AmpAcc,
Variance deviates aggregate-value position SqrAcc and AmpAcc and SqrAcc is initialized as 0, is additionally provided with two positions in computing module
Deviate radix for preserving, respectively directly deviate aggregate-value benchmark position AmpAccBase, variance deviates aggregate-value reference region
Position SqrAccBase, AmpAccBase and SqrAccBase is also initialized as 0；
（4）Combine interval [Xmin, Xmax] is provided with section length SegLen, the length of SegLen be 1 X-axis time period times
Number, LineA, all sampled points of LineB carry out collecting segmentation according to SegLen, if N is natural number, n-th segmentation
The X-axis time period of the corresponding X-axis combine interval of SegN is that [N, N+SegLen] is interval, and the Y-axis value of SegN is the corresponding time period
The Y-axis value of sampled point cumulative and, finally give two and new collect broken line LineSA, LineSB；
（5）According to segmentation, from first segmentation Seg1 to last segmentation, traveled through：
1）For current fragment SegC, LineSA and LineSB is subtracted each other and then taken definitely in the Y-axis value of current fragment
Value obtains and directly deviates AmpC, AmpC is carried out with power and obtains variance deviation AmpS；
2）AmpC is added on AmpAcc, realizes AmpAcc accumulative for the direct deviation of all segmentations；
3）AmpS is added on SqrAcc, realizes SqrAcc accumulative for the variance deviation of all segmentations；
4）The absolute value of the current value of LineSA is added on AmpAccBase, by the absolute value of the current value of LineSA
Power be added on SqrAccBase, obtain two divergence indicator benchmark；
Traversal terminate after the AmpAcc that obtains represent all segmentations direct bias accumulative, and SqrAcc represent all
The deviation power of segmentation accumulative；
（6）Obtain two irrelevance indexs：
Directly deviate percentage ratio AmpPer：AmpPer = AmpAcc / AmpAccBase * 100%；
Variance deviates percentage ratio SqrPer：SqrPer = SqrAcc / SqrAccBase * 100%；
（7）Obtain two overlapping indexes：
Direct-coupling percentage ratio AmpFitPer：AmpFitPer = 100% - AmpPer；
Variance coupling percentage SqrFitPer：SqrFitPer = 100% - SqrPer.
2. a kind of method of broken line relative analyses similarity according to claim 1 is it is characterised in that described SegLen
Length can be selected in the length range of the X-axis combine interval [Xmin, Xmax] of 1 X-axis time period to 20%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310420053.4A CN103473458B (en) | 2013-09-13 | 2013-09-13 | Method for comparatively analyzing similarities of fold lines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310420053.4A CN103473458B (en) | 2013-09-13 | 2013-09-13 | Method for comparatively analyzing similarities of fold lines |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103473458A CN103473458A (en) | 2013-12-25 |
| CN103473458B true CN103473458B (en) | 2017-02-08 |
Family
ID=49798305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310420053.4A Active CN103473458B (en) | 2013-09-13 | 2013-09-13 | Method for comparatively analyzing similarities of fold lines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473458B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740399B (en) * | 2016-01-28 | 2019-05-07 | 北京航空航天大学 | Time series data curve processing method and apparatus |
| CN110853720A (en) * | 2019-10-10 | 2020-02-28 | 重庆金融资产交易所有限责任公司 | Service data processing method, device, equipment and storage medium |
| CN111753084B (en) * | 2020-06-04 | 2024-04-30 | 江南大学 | Short text feature extraction and classification method |
-
2013
- 2013-09-13 CN CN201310420053.4A patent/CN103473458B/en active Active
Non-Patent Citations (5)
| Title |
|---|
| "Computing the frechet distance between two polygonal curves";Helmut Alt等;《International Journal of Computational Geometry & Applications》;19951231;第5卷(第1&2期);第75-91页 * |
| "Curve Matching，Time Warping，and Light Fields：New Algorithms for Computing Similarity between Curves";Alon Efrat等;《J Math Image》;20071231;第27卷(第3期);第203-216页 * |
| "基于形态的时间序列相似性度量研究";董晓莉等;《电子与信息学报》;20070531;第29卷(第5期);第1228-1231页 * |
| "形状匹配方法研究与展望";周瑜等;《自动化学报》;20120630;第38卷(第6期);第889-910页 * |
| "曲线形态相似性的定义与度量";江浩等;《云南民族大学学报（自然科学版）》;20091031;第18卷(第4期);第316-318页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103473458A (en) | 2013-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8819038B1 (en) | System and method for performing set operations with defined sketch accuracy distribution | |
| CN109143291B (en) | Vehicle-mounted GPS track space index accurate matching method | |
| CN103473458B (en) | Method for comparatively analyzing similarities of fold lines | |
| CN109634941B (en) | Medical data processing method and device, electronic equipment and storage medium | |
| CN105468907A (en) | Accelerated degradation data validity testing and model selection method | |
| CN101887478A (en) | Sequence radial basis function agent model-based high-efficiency global optimization method | |
| JP2021119507A (en) | Traffic lane determination method, traffic lane positioning accuracy evaluation method, traffic lane determination apparatus, traffic lane positioning accuracy evaluation apparatus, electronic device, computer readable storage medium, and program | |
| CN104133994A (en) | Reliability evaluation method fusing multi-source success or failure data | |
| CN104657613A (en) | Estimation method for service life of complex electromechanical system | |
| WO2021233231A1 (en) | Method and system for evaluating reliability of gathering and transportation combination station and key device | |
| CN103247062A (en) | Method for surveying and mapping map by collecting farmland key points | |
| CN104809246A (en) | Method and device for processing charging data | |
| CN103514233B (en) | A kind of track data check method and device | |
| CN103902798B (en) | Data preprocessing method | |
| CN104166756A (en) | Computation method for mass distribution of aircraft | |
| CN102567536A (en) | Key performance target analyzing method based on data statistics | |
| CN106650964A (en) | Fault analysis system, method and device for charging equipment | |
| CN108957397A (en) | The localization method and device of crusing robot | |
| CN103984617A (en) | Active monitoring data pushing method of server | |
| CN105069574A (en) | New method for analyzing business flow behavior similarity | |
| CN110969900B (en) | All-lane horizontal offset calculation method based on lane management | |
| CN107895235A (en) | Financial modeling system based on decision tree | |
| CN104536879A (en) | Fuzzy clustering based multi-error positioning method | |
| CN105095981A (en) | Oil-gas reservoir scale sequence resource evaluation method based on human-computer interaction | |
| CN104462139A (en) | User behavior clustering method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Zhejiang Zhongcai Building No. 68 Binjiang District road Hangzhou City, Zhejiang Province, the 310051 and 15 layer Patentee after: Hangzhou Annan information technology Limited by Share Ltd Address before: Zhejiang Zhongcai Building No. 68 Binjiang District road Hangzhou City, Zhejiang Province, the 310051 and 15 Floor Patentee before: Dbappsecurity Co.,ltd. |
|
| CP03 | Change of name, title or address | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201026 Address after: 310000 floor 5, building 1, 188 Lianhui street, Xixing street, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou Anheng Information Security Technology Co., Ltd Address before: Zhejiang Zhongcai Building No. 68 Binjiang District road Hangzhou City, Zhejiang Province, the 310051 and 15 layer Patentee before: Hangzhou Anheng Information Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |