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

A Method of Automatic Construction of RDF Structured Query Based on Vector Space

A technology of structured query and vector space, applied in the field of automatic construction of RDF structured query based on vector space, can solve problems such as low efficiency

Active Publication Date: 2020-12-01
GUANGDONG XIAN JIAOTONG UNIV ACADEMY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 2) The above patent is based on the traditional graph theory method to search subgraphs and generate SPARQL queries. If it is applied to a large-scale RDF graph, its efficiency will become very low

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 Method of Automatic Construction of RDF Structured Query Based on Vector Space
  • A Method of Automatic Construction of RDF Structured Query Based on Vector Space
  • A Method of Automatic Construction of RDF Structured Query Based on Vector Space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The present invention provides a method for automatically constructing RDF structured query based on vector space. Firstly, the RDF graph is mapped to a continuous vector space by using generalized local subgraphs, and the vector representation of each node and edge in the RDF graph is learned; and then given After expressing the query intent through the natural language question, firstly extract the entities and relational phrases in the question, and match them in the RDF graph to obtain candidate matching nodes and edges; Express it as a vector and calculate the optimal query structure; finally, use the translation mechanism to select the optimal matching nodes and edges in each candidate set and generate the target structured query.

[0076] see figure 1 , the present invention a kind of RDF structured query based on vector space automatic construction method, comprises the following steps:

[0077] S1. Define the local subgraph of nodes and edges in the RDF 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 an RDF structured query automatic construction method based on vector space. The RDF graph is mapped into a continuous vector space by using a generalized local subgraph, and vector representations of each node and edge in the RDF graph are learned. Given the query intention expressed by the natural language problem, the entities and relational phrases in the problem are extracted and matched in the RDF graph to obtain candidate matching nodes and edges. Then, the set of candidate matching nodes and edges is represented as vectors by vector representation of RDF graph and the optimal query structure is calculated. Finally, the optimal matching nodes in each candidate set are selected by translation mechanism, and the target structured query is generated. By using the vector representation of RDF graph, the efficiency of query construction is greatly improved. At that same time, the accurate match of the entity and the relation phrase can be avoided in the process of determining the structure, and the matching recall rate is improved; in the final query generation process, the translation mechanism also ensures the consistency between the generated query andthe RDF graph.

Description

technical field [0001] The invention belongs to the technical field of automatically answering natural language questions based on RDF data, and in particular relates to an automatic construction method of RDF structured query based on vector space. Background technique [0002] The full name of RDF is Resource Description Framework (Resource Description Framework), which is a standard specification for publishing, sharing and connecting various data resources on the Internet recommended by the Internet Society (W3C). In recent years, more and more large-scale RDF graph data, such as DBpedia and Wikidata, have been published on the Internet. Large-scale RDF graphs contain rich information. Currently, the main way to query RDF graphs is to use structured query languages ​​such as SPARQL and GraphQL. However, the grammatical rules of Structured Query Language are relatively complex, and users are required to have a precise understanding of the structure and schema of RDF gra...

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): G06F16/242G06F16/2453G06F16/36
Inventor 王瑞杰刘均王萌
Owner GUANGDONG XIAN JIAOTONG UNIV ACADEMY
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