Method for answering with natural language

A natural language and question technology, applied in the field of natural language question answering, can solve problems such as unable to satisfy users, unable to retrieve results, keywords unable to clearly express user needs, etc.

Inactive Publication Date: 2012-08-15
TSINGHUA UNIV
View PDF4 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the increase of information, this way of information acquisition gradually fails to meet the needs of users
This information acquisition method based on keyword retrieval mainly has the following two shortcomings: (1) too much information is returned, and the user needs to further click on the returned link to obtain the information he needs; Words sometimes cannot clearly express the user's needs, resulting in the inability to retrieve the desired results
However, since this type of question-and-answer community relies on other users to answer, it is difficult to answer users' questions in a timely and effective manner, especially compared with the speed at which search engines return results.

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 for answering with natural language
  • Method for answering with natural language
  • Method for answering with natural language

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The technical solution of the present invention will be further described in detail below.

[0017] Such as figure 1 As shown, this natural language question answering method includes the following steps:

[0018] (1) Carry out problem analysis for the problem input by the user;

[0019] (2) Use the results of question analysis and the corpus of community question-and-answer to answer questions;

[0020] (3) Use the results of question analysis and encyclopedia corpus to answer questions;

[0021] (4) For the answers returned from steps (2) and (3), perform answer verification and selection, and finally return the best answer to the user.

[0022] Due to the use of community Q&A and encyclopedia data to answer users' natural language questions, and to verify and select answers, it can answer user questions in a timely and effective manner.

[0023] Preferably, as figure 2 As shown, step (1) includes the following sub-steps:

[0024] (1.1) Use the Chinese word seg...

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 method for answering with natural language, which is used for instantly and effectively answering the questions of users. The method comprises the following steps of: (1) performing question analysis on a question input by a user; (2) answering the question by use of the question analysis result and the corpus of community questions and answers; (3) answering the question by use of the question analysis result and the encyclopedia corpus; and (4) verifying and selecting the answers returned by the steps (2) and (3), and finally returning the best answer to the user.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a natural language question answering method. Background technique [0002] With the explosive growth of Internet information, users have more ways to obtain information. But it also poses more challenges to users' ability to retrieve information. Keyword retrieval technology is adopted by many search engines, and has achieved good results in many fields, and has achieved great success in the industry. However, with the increase of information, this way of obtaining information gradually fails to meet the needs of users. This information acquisition method based on keyword retrieval mainly has the following two shortcomings: (1) too much information is returned, and the user needs to further click on the returned link to obtain the information he needs; Words sometimes cannot clearly express the needs of users, resulting in the inability to retrieve the desired...

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): G06F17/30G06F17/27
Inventor 郝宇黄民烈朱小燕
Owner TSINGHUA 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