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

Natural language question and answer method and device

A natural language and phrase technology, applied in natural language data processing, semantic tool creation, instruments, etc., can solve problems such as cost, large amount of calculation, and correctness of interference results.

Active Publication Date: 2019-09-10
PEKING UNIV +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And disambiguation is not a simple task, not only requires a lot of calculation, but also if the disambiguation fails, it will interfere with the correctness of the result

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 question and answer method and device
  • Natural language question and answer method and device
  • Natural language question and answer method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0116] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0117] The embodiment of the present invention provides a brand new natural language question answering mechanism. Unlike the background technology that uses SPARQLs query statements and SPARQLs search engines to obtain answers to natural language questions N, the embodiment of the present invention uses query semantic graph Q s and RDF graph G to obtain answers to natural language questions N. details as follows:

[0118] Please refer to Figure 2A , which shows a method flowchart of a natural language question answering method provided by an embodiment of the present invention. The natural language question answering method is applied in the server, and the method includes:

[0119] Step 202, obtaining natural language questions ...

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 embodiment of the invention discloses a natural language question answering method and device, belonging to the field of information retrieval and processing. The method includes: obtaining a natural language question N; converting the natural language question N into a query semantic graph Q s , the query semantic graph Q s Each edge in represents a semantic relationship in the natural language question sentence N; in the RDF graph G, search and query semantic graph Q s A matched subgraph; the answer to the natural language question N is obtained according to the subgraph. The embodiment of the present invention solves the problem that a large amount of calculation is required to disambiguate in the question understanding stage; it provides a brand-new natural language question answering mechanism, which converts natural language question sentences N into query semantic graph Q s No need for disambiguation, the disambiguation process is in the search and query semantic graph Q s The effect is done naturally in the process of matching subgraphs.

Description

technical field [0001] The embodiments of the present invention relate to the field of information retrieval and processing, and in particular to a natural language question answering method and device. Background technique [0002] Question answering systems are an advanced form of information retrieval systems. It can answer questions raised by users in natural language in accurate and concise natural language. [0003] RDF (Resource Description Framework, resource description framework) resource library is a basis for realizing the question answering system. RDF resource base, also known as knowledge base, usually includes a large number of triples that are easy for computers to recognize and understand. Each triple is represented as a subject, a predicate, and an object, such as the subject "The Actor's Self-cultivation", the predicate "category" and the object "books". Current question answering systems mainly consist of two phases: question understanding phase and q...

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): G06F16/332G06F17/27
CPCG06F16/3334G06F16/322G06F16/36G06F40/242
Inventor 邹磊刘婷婷路彦雄刘怀军黄睿哲
Owner PEKING UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com