Visual retrieval method for multivariate graph database based on attribute enhanced representation learning

An attribute enhancement, database technology, applied in the field of information, can solve problems such as difficulty in learning and use

Pending Publication Date: 2022-01-14
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to learn and use, especially for non-expert users

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
  • Visual retrieval method for multivariate graph database based on attribute enhanced representation learning
  • Visual retrieval method for multivariate graph database based on attribute enhanced representation learning
  • Visual retrieval method for multivariate graph database based on attribute enhanced representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] like figure 1 As shown, the multivariate graph database visual retrieval method based on attribute-enhanced representation learning, the specific steps are:

[0033] Step (1) Use the graph representation model and mathematical statistics method to extract the structure and attribute features of multivariate graphs, and combine the feature extraction results, use canonical correlation analysis to establish a graph representation learning model based on attribute enhancement, and combine the learned structure vector and The attribute vectors are fused into a comprehensive embedding space to obtain high-dimensional structure-attribute fusion vectors. specifically is:

[0034] (1-1) Use the graph representation learning model graph2vec to convert all multivariate graph data in the large-scale graph database into a high-dimensional structure vector set S={S 1 ,S 2 ,…,S M}, S m is the high-dimensional structure vector of the mth multivariate graph in the large-scale graph ...

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 multivariate graph database visual retrieval method based on attribute enhanced representation learning. The method comprises the following steps of: firstly, extracting structure and attribute characteristics of a multivariate graph by utilizing a graph representation learning model and a mathematical statistical method, establishing a graph representation learning model based on attribute enhancement by utilizing canonical correlation analysis in combination with a characteristic extraction result of the multivariate graph, and fusing a structure vector and an attribute vector into a comprehensive embedding space; and then projecting the high-dimensional structure-attribute fusion vector into a two-dimensional space and clustering to construct a distance-based graph retrieval model. Visual evaluation is conducted on retrieval results from the structural similarity and the attribute similarity through a node link graph and a parallel coordinate view, interaction is designed to help a user to construct a target graph to achieve retrieval, and the retrieval results are compared. According to the method disclosed by the invention, a multivariate graph database visual retrieval tool based on attribute enhancement representation learning is realized, so that a user can easily construct graph retrieval and visually evaluate and compare graph retrieval results.

Description

technical field [0001] The invention belongs to the field of information technology, in particular to the technical field of graph retrieval, and in particular relates to a visual retrieval method of a multivariate graph database based on attribute-enhanced representation learning. Background technique [0002] With the development of graph data management techniques, massive graph datasets are widely collected to satisfy data-related research and applications in many fields, such as natural sciences, business relations, and knowledge derivation. Graph retrieval is an exploratory approach to retrieve desired graphs from massive graph datasets based on various similarity measures. [0003] Structure has always been the primary consideration in graph retrieval, and structural similarity is measured in terms of topological features or embedding vectors. For example, in compound databases, biochemists typically search and match desired compounds based on structural similarity. ...

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
IPC IPC(8): G06F16/903G06F16/904G06F16/901G06F16/906
CPCG06F16/903G06F16/9024G06F16/904G06F16/906
Inventor 周志光孙玲王浩轩刘玉华苏为华王毅刚
Owner HANGZHOU DIANZI UNIV
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