A Parallel Acceleration Method for Multimodal Graph Matching

A pattern diagram and multi-pattern technology, applied in other database retrieval, other database indexing, etc., can solve the problem that there is no parallel processing method for structural correlation pattern diagrams, and achieve the effects of optimal performance, improved efficiency, and improved performance

Active Publication Date: 2021-06-04
INST OF INFORMATION ENG CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing multi-pattern graph matching technology is not mature enough, and there is no efficient parallel processing method for schema graphs with weak structural correlations, and the performance of multi-pattern graph matching technology needs to be improved.

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
  • A Parallel Acceleration Method for Multimodal Graph Matching
  • A Parallel Acceleration Method for Multimodal Graph Matching
  • A Parallel Acceleration Method for Multimodal Graph Matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, and to make the purpose, features and advantages of the present invention more obvious and understandable, the technical core of the present invention will be further described in detail below in conjunction with the accompanying drawings . It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0046] The parallel matching algorithm proposed by the present invention mainly includes four key processes: multi-pattern graph index construction, schema graph heuristic grouping, schema graph parallel matching, and "parallel+serial" matching optimization strategy. The algorithm will be analyzed from these four parts below for details.

[0047] Process 1: Multi-mode graph index construction

[0048] A tree-type index structure Pattern Tree based ...

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 discloses a parallel acceleration method for multi-mode graph matching. The method is as follows: 1) generating a multi-pattern map index of the pattern atlas in the target field; 2) adopting a layer-by-layer grouping strategy for the multi-pattern map index, that is, for the pattern maps appearing in each layer of the multi-pattern map index Carry out evaluation to obtain the matching cost of each pattern graph in this layer, and then group the pattern graphs of this layer according to the matching cost; 3) assign a thread to different groups to perform matching calculation at the same time. The invention uses the PatternTree index construction algorithm to mine the structural correlation between the pattern graphs, and designs a parallel matching strategy for the pattern graphs with weak structural correlation to further improve the matching performance.

Description

technical field [0001] The invention proposes a parallel acceleration method for multi-mode graph matching, which belongs to the technical field of computer software. Background technique [0002] In the era of big data, the scale of data continues to expand, the structure of data is increasingly complex, and the correlation between data is closer. These characteristics bring great challenges to big data analysis. As a widely used data structure, graphs can effectively describe closely related data. Practical problems in many fields can be transformed into computational problems on graphs, such as image analysis, biological data analysis, social network analysis, privacy protection, etc. Graph Pattern Matching Technology (Graph Pattern Matching Technology) is an important means to solve the above complex graph data analysis and mining problems through the efficient query of large-scale graph data. It has become a problem that has been widely concerned by academia and industr...

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 Patents(China)
IPC IPC(8): G06F16/901
Inventor 于静郭晶晶刘小梅刘燕兵曹聪谭建龙郭莉
Owner INST OF INFORMATION ENG CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap