FAQ based Chinese natural language ask and answer method

A technology of natural language and question-and-answer database, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as limited types of questions and unrealizable applications, and achieve the effect of easy wide application and regular format

Inactive Publication Date: 2008-09-03
ZHEJIANG UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are shortcomings in this way of presenting results: although the user obtains the filtered results through the search tool, if the user wants to get the information they really need, they need to further manually click on the link and relocate
However, the current question-answering system still has solvability However, the current question-answering system still has shortcomings such as limited types of questions that can be solved, and cannot be applied in a general sense.

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
  • FAQ based Chinese natural language ask and answer method
  • FAQ based Chinese natural language ask and answer method
  • FAQ based Chinese natural language ask and answer method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The processing flow of the present invention is as figure 2 shown. Firstly, through the existing search engines such as Google, Baidu, Yahoo, etc., using the resources on the Internet, the question-and-answer database is established by the steps of establishing the question-and-answer database. The question text in the question-and-answer database obtains the stem words through the question sentence analysis based on the dependency system, and uses these stem words as index items to establish an inverted index from word to question sentence. For the query conditions entered by the user, firstly, the main words of the query conditions are obtained through question analysis; using the common method based on keyword matching, the result of the main word hits is obtained from the index through question retrieval, and then the number of hits in the results is calculated. The similarity between the sentence and the user's query sentence is sorted according to the similarity...

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 disclosed database-based Chinese natural language question-answering method comprises mainly analyzing Web structure to extract internet FAQ and question-answering from opening community to build database. Unlike to prior art, this invention can accept natural language query and return the answer directly without user screening, and overcomes defects in a certain extent.

Description

technical field [0001] The invention relates to information retrieval, a natural language question answering system, and the field of Chinese natural language processing, in particular to a Chinese natural language question answering method based on a question answer database. Background technique [0002] With the continuous growth of Internet information, the Internet is filled with more and more redundant information; for Internet users who search for the information they need on the Internet, the whole behavior is undoubtedly similar to "finding a needle in a haystack". Although the emergence of the second-generation search engines represented by Google has greatly reduced the difficulty for users to find information, there are certain defects in such search engines: [0003] First of all, since its search mode is based on the exact matching of keywords to find relevant information, any keyword entered by the user may become the basis for hitting a certain webpage (excep...

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): G06F17/30
Inventor 陈纯卜佳俊仇光黄鹏蔡柯柯
Owner ZHEJIANG 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