Question analyzing method and system for interactive question answering

An interactive question-and-answer and analysis method technology, which is applied in neural learning methods, special data processing applications, instruments, etc., can solve problems such as low accuracy of semantic restoration and cannot better meet the needs of industrial applications, and improve the accuracy of semantic restoration Effect

Inactive Publication Date: 2018-01-26
HUAZHONG UNIV OF SCI & TECH
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problem that the accuracy of semantic recovery is low when parsing existing problems and cannot better meet the needs of industrial applications

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
  • Question analyzing method and system for interactive question answering
  • Question analyzing method and system for interactive question answering
  • Question analyzing method and system for interactive question answering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0040] In a possible interactive question and answer scenario, imagine that when the user conducts the following rounds of questions:

[0041] Q1: "What is the monthly rent for the cheapest package?";

[0042] Q2: "How much traffic is there?";

[0043] Q3: "What about the more expensive one?";

[0044] Existing automatic question answering systems can correctly understand question Q1, but quest...

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 question analyzing method and system for interactive question answering. The method includes the steps of S1, determining question information, preprocessing the question information and extracting multiple pieces of feature information in the question information; S2, extracting a plurality of keywords in the question information according to the feature information, anddetermining a plurality of properties corresponding to the keywords; S3, determining whether the semantic meaning of the question information is complete or not in combination with the properties, ifnot, executing the step S4, otherwise executing the step S5; S4, restoring the semantic meaning of the question information in combination with a historical conversation and based on a deep learningenhancing method, using the restored question information as new question information and executing the step S1 to S3; S5, conducting template matching on the question information according to the properties and dividing the question information according to types. The deep Q-Learning method based on deep learning enhancing is added, and therefore the semantic meaning restoration accuracy is improved, and the industrial application requirements are well met.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and more specifically, relates to a question analysis method and system for interactive question answering. Background technique [0002] In recent years, the rise of artificial intelligence has made a major breakthrough in interactive question answering systems. However, the existing interactive question-answering system is still not "intelligent" enough in the process of communicating with users. This is because in the process of asking questions, users often retain the language habits of talking with people, use pronouns to refer to the content mentioned above, or even omit it, which will cause the problem of missing key semantics. If the semantic recovery of the current question is not performed, it will be difficult for the machine to understand the user's question, so that it cannot retrieve an accurate answer. Especially in complex customer service systems, a prob...

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): G06F17/27G06F17/30G06N3/04G06N3/08
Inventor 路松峰李翔黄炎徐科王同洋
Owner HUAZHONG UNIV OF SCI & TECH
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