A method for implementing a question answering system based on a question-answer pair

A question answering and question answering system technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems such as complex models, time-consuming parameter adjustment, etc.

Active Publication Date: 2019-01-25
深圳智能思创科技有限公司
View PDF4 Cites 84 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] 1) The model is more complicated than the traditional retrieval mo

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 method for implementing a question answering system based on a question-answer pair
  • A method for implementing a question answering system based on a question-answer pair
  • A method for implementing a question answering system based on a question-answer pair

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0043] Such as figure 1 As shown, the present invention is a method for implementing a question answering system based on question answer pairs, including: question analysis, question retrieval and answer selection.

[0044] Each part will be described in detail below.

[0045] S1. Problem Analysis

[0046] The main goal of question analysis is to understand the user's query intent. It mainly includes three tasks: 1) Question vectorization: the text representation of the question can be convenient for people to read, and the vector representation of the question can be convenient for computer use. After the question is converted into a vector, the obtained question vector can provide help for other steps of question analysis; 2) question keyword extraction: the question keyword can well reflect the user's query intention, and these keywords...

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 for implementing a question answering system based on a question-answer pair comprises the following steps: question analysis, question retrieval and answer selection. After a user submits aquestion expressed in natural language to the question answering system, the question answering system uses question vectorization, keyword extraction, keyword extension and other natural language processing techniques to understand the questioning intent of a user, and then uses the engine searching method in the question-answer pair database to obtain the question-related candidate question-answer pair set, and uses a matching algorithm and sorting algorithm to accurately select the best answer from the candidate sets. The invention obtains the function of the matching degree score between the question and the answer by learning by synthesizing different algorithms and models, the method of choosing the best answer from the candidate question-answer pairs is realized, and an answer selection method based on convolution neural network and Xgboost feature fusion is completed, which provides a better method for the answer selection of the question answering system.

Description

technical field [0001] The invention relates to a method for implementing a question answering system based on question answer pairs, and belongs to the technical field of natural language processing. Background technique [0002] Search engine technology can meet the information needs of users in terms of information retrieval, but there are many imperfections in search engines, which are mainly reflected in two aspects: First, the search engine returns a series of relevant webpages after searching the query input by the user, and the webpage contains There are too many contents, and users often need to read these web pages to locate their own needs; second, search engines use keyword matching pairs for information retrieval, and keyword matching technology only performs grammatical analysis on sentences without semantic analysis. For complex requirements that are difficult to express with keywords, search cannot give satisfactory query results. In order to improve the use...

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): G06F16/332G06F16/33
Inventor 李舟军肖武魁兰忻怡
Owner 深圳智能思创科技有限公司
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