Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Approximate order-preserving sequence pattern mining method

A sequential pattern mining and pattern technology, applied in visual data mining, instrumentation, database indexing, etc., to ensure continuity, wide application, and avoid repeated scanning.

Inactive Publication Date: 2021-05-11
HEBEI UNIV OF TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The mining process ensures the continuity of the time series, overcomes the problem that the existing methods can only mine the order-preserving patterns with the same relative order, and can mine the order-preserving patterns more flexibly, adapting to more application fields

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Approximate order-preserving sequence pattern mining method
  • Approximate order-preserving sequence pattern mining method
  • Approximate order-preserving sequence pattern mining method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment D

[0075] Time series S=(22,4,74,53,94,41,20,92,51,94,86,91,12,5,44,31,97), δ=0, γ=0, minsup= 3.

[0076] Step 1: Input time series S, local constraint δ, global constraint γ and minimum support threshold minsup:

[0077] Input time series S=(22,4,74,53,94,41,20,92,51,94,86,91,12,5,44,31,97), δ=0, γ=0, minsup =3.

[0078] Step 2: Obtain a frequent (δ-γ) order-preserving pattern set fre of length 2 2 :

[0079] First, create an index table for the time series S. 2-length (δ-γ) candidate pattern set cand 2 ={(1,2),(2,1)}, calculate cand sequentially according to the method of calculating (δ-γ) order-preserving mode support as described below 2 The support of each (δ-γ) order-preserving pattern in , if the number of (δ-γ) order-preserving occurrences of a certain 2-length (δ-γ) candidate pattern P in the time series S is greater than or equal to the user-defined minimum The support threshold minsup, then the 2-length (δ-γ) order-preserving pattern P is a frequent (δ-γ) order-...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an approximate order-preserving sequence pattern mining method, the current order-preserving sequence pattern mining only digs sub-sequences which meet the support degree threshold and have completely same (most accurate) relative sequences in time sequences, but some important information is often missed when only the most accurate order-preserving pattern is mined. According to the mining method, the most accurate order-preserving mode can be mined, and the order-preserving modes with different approximation degrees can be mined according to different input parameter values. And more meaningful order-preserving modes can be mined, so that the method is suitable for more application fields and can better help people to carry out analysis and prediction. In the aspect of candidate mode generation, a mode fusion strategy based on prefix and suffix splicing is adopted, and the number of meaningless candidate modes is reduced. In the aspect of mode support degree calculation, candidate sequences are obtained on the left and right sides of the frequent mode appearing position, repeated scanning of a database is avoided, the mode matching frequency is greatly reduced, and the mining performance is remarkably improved.

Description

technical field [0001] The technical solution of the present invention relates to the technical field of electrical digital data processing, in particular to an approximate order-preserving sequence pattern mining method. Background technique [0002] As a common and important data, time series data widely exists in human production and life, such as passenger flow analysis, marketing, river flow, stock price, and heart / EEG analysis. Different from character sequences, time series data is a numerical sequence arranged in chronological order, which contains a large amount of regular information. In order to quickly and effectively obtain valuable information, researchers have proposed many time series analysis methods, such as sequence Pattern mining method, discrete short-time Fourier transform method and logistic regression method, etc. Due to the high efficiency and strong interpretability of sequential pattern mining, it has received extensive attention and has been wide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/26G06F16/2458G06F16/22
CPCG06F16/26G06F16/2465G06F16/2228G06F16/2282
Inventor 武优西刘锦耿萌孟玉飞王珍杨鸿茜杨仕琦
Owner HEBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com