A natural language query method and system oriented to a software project knowledge map

A natural language and knowledge graph technology, applied in the field of natural language query methods and systems, can solve problems such as difficulty in using automatic extraction templates, insufficient number of questions, and frequent use of the system

Inactive Publication Date: 2018-12-18
PEKING UNIV
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with this type of method is that the words in the natural language query input by the user need to be clearly corresponding to a certain information (table name, attribute name, record, etc.) in the database table, otherwise the syntax tree is incomplete and the correct answer cannot be obtained
The problem with this type of method is that the number of questions answered by th

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 natural language query method and system oriented to a software project knowledge map
  • A natural language query method and system oriented to a software project knowledge map
  • A natural language query method and system oriented to a software project knowledge map

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0086] In order to make the above-mentioned features and advantages of the present invention more obvious and understandable, the following specific examples are given in conjunction with the accompanying drawings to describe in detail as follows:

[0087] The invention provides a natural language query system oriented to the knowledge graph of software projects, such as figure 1 As shown, the system includes an index structure and data storage layer, a natural language parsing layer, a reasoning and measurement layer, and a subgraph display and query layer.

[0088] The index structure and data storage layer traverses and analyzes the neo4j-based software project knowledge graph, and extracts the data element model therein. The implementation steps are as follows:

[0089] 1) Completely traverse the knowledge graph, store all the entities in it, and record all entity types as the node set of the metamodel;

[0090] 2) Traverse all the relationships in the knowledge graph, and establ...

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 natural language inquiry method and system oriented to a software project knowledge map. This method is: 1) extracting the metamodel of software project knowledge map; 2) transforming the natural language query sentence into a series of sub-graphs on the knowledge map meta-model, which are called inference sub-graphs, and measuring the inference sub-graphs; 3) constructing a Cypher query sentence based on that inference sub-graph, executing the Cypher query sentence on the knowledge map of the software project, and returning the query result. The invention can automatically extract the metamodel of the knowledge map of the software project, accurately understand the natural language problem of the user and construct the inquiry, has the characteristics of strong universality and expansibility, and improves the inquiry efficiency of the knowledge map of the software.

Description

technical field [0001] The invention relates to the fields of information retrieval and database query, in particular to a natural language query method and system for software project knowledge graphs. Background technique [0002] Database Natural Language Interface [0003] Database natural language interface mainly refers to the interface that supports natural language query for relational database construction. The existing research work on the natural language interface of databases is mainly carried out around natural language understanding, and mainly adopts the method of converting natural language query into formal query based on syntactic analysis, the method based on constructing natural language template, and the method based on interactive algorithm improvement. Method to query the effect. [0004] In terms of query transformation based on syntactic analysis, typical work is [Li F 2016]. The basic process is: first parse the natural language query and constru...

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): G06F17/30
Inventor 邹艳珍王敏倪际楠谢冰赵俊峰
Owner PEKING 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