Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Computer system to constitute natural language base and automatic dialogue retrieve

A computer system and natural language technology, applied in the field of computer systems, can solve unfavorable, cumbersome and complex problems, and achieve the effect of enhancing depth and breadth, and good scalability.

Inactive Publication Date: 2007-04-25
梁威
View PDF0 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing natural language processing technology marks out the linguistic role of each part in the sentence. The annotation of this sentence and sentence group still retains the dependence on the form of natural language and the cumbersome and complicated form of natural language for the representation of knowledge. , so it is not conducive to building an efficient and unified knowledge processing model

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
  • Computer system to constitute natural language base and automatic dialogue retrieve
  • Computer system to constitute natural language base and automatic dialogue retrieve
  • Computer system to constitute natural language base and automatic dialogue retrieve

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0019] The technical solution disclosed by the present invention is based on the establishment of a knowledge base for HNC natural language understanding and an automatic question-and-answer retrieval computer system. Natural language is an unstructured information form. By using HNC technology to perform natural language processing on it, the sentence structure of the sentence is obtained. Annotation information such as group, sentence class, semantic block, semantic block structure, etc. The present invention uses ERE expressions to express semantic knowledge on the basis of this natural language processing. Based on the analysis results of HNC sentences, ERE knowledge is extracted, and then the ERE knowledge base is constructed, and the framework knowledge base is defined and filled.

[0020] The ERE knowledge expression and framework knowledge base are d...

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

This invention relates to a knowledge database establishing and automatically answer index system based on HNC natural language, which extracts ERE knowledge to establish ERE knowledge database and to define and establish knowledge frame to describe frame knowledge data. The two database receives user inquires by natural language through analysis on question sentences and aim ERE structure extraction.

Description

technical field [0001] The invention relates to a computer system, in particular to a computer system for establishing a natural language knowledge base and its automatic question-and-answer retrieval. Based on the HNC natural language processing technology, the knowledge base is established through natural language processing and accepts query requests in natural language. , the answer is given automatically. Background technique [0002] At present, the tools that people use to query information, such as query software and search engines such as Google, mainly use keyword matching, web page link analysis, statistical analysis and other technologies to find what users want in the vast ocean of information. However, it is difficult for people to accurately define their own search intentions through simple keyword combinations, and the search process of keyword matching does not deal with semantic factors such as word meaning combinations and semantic relationships within sen...

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 梁威
Owner 梁威
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products