Method and device for mining related questions in question answering system

A question answering system and question sentence technology, applied in relational databases, special data processing applications, instruments, etc., can solve problems such as low accuracy of returned answers, low accuracy and recall of question answering systems, and improve the ability to understand user intentions , reduce the amount of calculation, improve the effect of efficiency

Active Publication Date: 2018-05-18
SHANGHAI XIAOI ROBOT TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When the association rules obtained by the method of the prior art are used in the question answering system to calculate the answer returned to the user, the accuracy rate of the returned answer is low, in other words, the precision rate and recall rate of the question answering system are 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
  • Method and device for mining related questions in question answering system
  • Method and device for mining related questions in question answering system
  • Method and device for mining related questions in question answering system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] As stated in the background technology, when the association rules obtained by the methods of the prior art are used in the question answering system to calculate the answers returned to the user, the accuracy of the returned answers is low, which makes the accuracy and recall of the question answering system relatively low. Low.

[0041] The inventors of the present application have found through research that in the prior art, the core words of user input questions are mostly determined by statistical features, such as word frequency, part of speech, positional relationship between words, and some artificially set grammatical rules. The extracted core words are associated question sequences mined by association rules, and the accuracy of the returned answers after participating in the calculation of the returned answers of the question answering system is low, which in turn affects the accuracy and recall of the question answering system.

[0042] In the technical sol...

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

A method and device for mining associated questions in a question answering system, the method comprising: performing word segmentation on each question sentence in a target question answering interactive transaction in a knowledge base; Extract the core words by dependency analysis; save the core words of each question sentence of each of the target question-and-answer interactive transactions in the knowledge base to obtain the target question sentence transaction set of the knowledge base; The associated question sequence corresponding to the core word strong association rule of the target question sentence transaction set. Using the associated question sequence provided by the above scheme can improve the accuracy rate and recall rate of the question answering system.

Description

technical field [0001] The invention relates to the technical field of intelligent question answering, in particular to a method and device for mining associated question sentences in a question answering system. Background technique [0002] Association rule mining (Association rule mining) is one of the most active research methods in data mining, which can be used to discover the relationship between things. It was originally used to discover the relationship between different commodities in the supermarket transaction database. [0003] At present, association rule mining is also applied in natural language-based question-and-answer interactive systems, in order to obtain the association relationship between questions, and then use the obtained association relationship between questions to calculate the answer returned to the user by the question-answering system. Accuracy and recall are technical indicators for evaluating automatic question answering systems. The accur...

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): G06F17/27G06F17/30
CPCG06F16/284G06F40/216G06F40/211
Inventor 张昊朱频频
Owner SHANGHAI XIAOI ROBOT TECH CO LTD
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