Natural language query interface achievement method oriented to big data

A technology of natural language and query interface, applied in electronic digital data processing, special data processing applications, unstructured text data retrieval, etc.

Active Publication Date: 2018-04-06
DONGHUA UNIV
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing natural language-based query interface technology still has obvious limitations in the big data environment, mainly including the limited portability of the interface, that is, the current technology is mainly responsible for the conversion of natural language to relational database SQL language, to NoSQL database The query conversion is not supported; the language is limited, that is, English natural language is mainly supported; the pertinence to the field is not strong, that is, the current interface technology is aimed at the general field, which makes it difficult to convert to the underlying database language, and the usability is not strong

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
  • Natural language query interface achievement method oriented to big data
  • Natural language query interface achievement method oriented to big data
  • Natural language query interface achievement method oriented to big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] In order to make the present invention more comprehensible, preferred embodiments are described in detail as follows.

[0077] The invention provides a conversion strategy for converting Chinese natural language query into SQL or BSON. Aiming at the limitations of current natural language query interfaces, such as the lack of adaptability to specific fields and the difficulty in realizing query conversion to NoSQL databases, the invention performs domain-based semantic extension on the used corpus during the conversion process, and provides a query tree orientation The conversion method of NoSQL database query languages ​​such as BSON improves the accuracy and scope of query conversion. Specific steps are as follows:

[0078] Step 1. Obtain the natural language query statement from the front end, call the corresponding JAR package of Stanford Parser to parse the natural language query, and obtain the corresponding semantic dependency tree. Take the following query sta...

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 provides a natural language query interface achievement method oriented to big data. Chinese natural language query is converted into an SQL or BSON transformation strategy, semantic depending trees are generated according to natural languages, then the semantic depending trees are converted into query trees according to established rules, and BSO sentences of SQL and NoBSON corresponding to the natural languages are obtained by parsing the query trees. The method supports corpus extension and improves the conversion accuracy in the given field. In addition, NoSQL conversion nodes are increased, and the application range of the method is widened.

Description

technical field [0001] The invention relates to an interface implementation method that supports Chinese natural language as an input and converts it into a relational or non-relational database query language. Background technique [0002] With the rapid development of information technology, global data resources are growing and accumulating at an unprecedented rate, how to mine the required knowledge from big data has become a widely concerned issue. In traditional relational databases, people use the SQL standard query language to query. At this time, users need to master a large number of grammatical structures and be familiar with the table structure in the database before they can write corresponding queries according to their own query intentions. statement. The introduction of the interactive visual query interface has reduced the user's learning costs to a certain extent, but it still cannot avoid the need for users to have a certain programming foundation and SQL...

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): G06F17/30
CPCG06F16/243G06F16/3329G06F16/36
Inventor 王梅乐嘉锦朱扬勇陈德华潘乔郑晓东
Owner DONGHUA 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