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

Multilayer flowchart dialogue organizing linguistic data-based natural language question-answering method

A flow chart and corpus technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of high implementation cost

Inactive Publication Date: 2010-06-16
张曦
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] From the above code, we can see that the contextual coherence of the question answering system can be achieved through labels and variables. This method can accurately define the context logic relationship. The disadvantage is that the implementation cost is high, and the context is defined when the knowledge base is large. Relationships require a lot of work from the designer

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
  • Multilayer flowchart dialogue organizing linguistic data-based natural language question-answering method
  • Multilayer flowchart dialogue organizing linguistic data-based natural language question-answering method
  • Multilayer flowchart dialogue organizing linguistic data-based natural language question-answering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the purpose, technical solutions and advantages of the present invention more clearly expressed, the following describes the present invention in detail with reference to the accompanying drawings and a specific example. Example content: The user asks the question and answer system "what do you like", and the question and answer system gives different answers in different contexts.

[0030] Step 1: Corpus collection

[0031] Attached figure 2 , Attached image 3 , Attached Figure 4 It is the data entered through the corpus collection system, and its storage format is as follows.

[0032] Node ID Parent Node ID Classification ID Data

[0033] 140 1 112 what do you like

[0034] 141 140 112 Eat snacks and watch TV

[0035] 142 140 112 Watching TV while eating snacks.

[0036] 404 1 101 Eight Major Chinese Local Cuisine

[0037] 405 404 101 Sichuan, Guangdong, Shandong, Fujian, Zhejiang, Huixiang.

[0038] 419 1 103 Shandong cuisine

[0039] 427 405 101 What do you l...

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 relates to an information retrieval and natural language question-answering system and the field of natural language processing, in particular to a question-answer library-based natural language question-answering system. The invention aims to provide a method for making a context of a dialogue of the question-answering system have coherence, which is named a multilayer flowchart dialogue organizing linguistic data-based natural language question-answering method. The method is characterized in that: a multilayer flowchart is used for saving logical relationships among the linguistic data. Two nodes having shorter distance in the flowchart have larger correlation degree, which is taken as a basis to select the node having larger correlation degree in the dialogue. The method can effectively improve contextual coherence of the dialogue of the question-answering system.

Description

Technical field [0001] The invention relates to information retrieval, natural language question answering systems, and natural language processing fields, in particular to a natural language question answering system based on question answering libraries. The present invention is an improvement to the usual question answering system to improve the context correlation effect. Background technique [0002] Question Answering System (QuestionAnswering System) refers to a computer program that can answer questions entered by a computer user in natural language. Question answering systems integrate natural language processing, information retrieval, and knowledge representation, and are increasingly becoming a hot topic in international research. It not only allows users to ask questions in natural language, but also returns a concise and accurate answer for users. The human-machine interface, accuracy and real-time nature of the natural language question answering system are the t...

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): G06F17/30
Inventor 张曦
Owner 张曦
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com