Check patentability & draft patents in minutes with Patsnap Eureka AI!

Intelligent question and answer method

An intelligent question answering and question sentence technology, applied in special data processing applications, instruments, semantic tool creation, etc., can solve problems such as lack of semantic information, poor algorithm portability, and high degree of domain customization

Active Publication Date: 2019-04-26
北京北大软件工程股份有限公司
View PDF8 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1. Based on document retrieval, lack of semantic information;
[0006] 2. The degree of domain customization is too high, and the algorithm portability is poor;
[0007] 3. The type of answering questions is limited to factual and simple questions, and it is impossible to answer more complex questions

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
  • Intelligent question and answer method
  • Intelligent question and answer method
  • Intelligent question and answer method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be described in detail below. Apparently, the described embodiments are only some of the embodiments of this application, not all of them. Based on the embodiments in the present application, all other implementation manners obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0062] figure 1 A schematic flow diagram of an intelligent question answering method provided for an embodiment of the present application, such as figure 1 As shown, the intelligent question answering method includes the following steps:

[0063] S1. Acquiring natural language questions input by the user;

[0064] S2. According to the combination template in the preset index database, judge whether the natural language question has complex semantics;

[0065...

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 intelligent question and answer method, and belongs to the technical field of natural language processing. The method comprises the steps of obtaining a natural language question input by a user; judging whether the question has complex semantics or not through a preset combination template; if the complex semanteme exists, judging that the complex semanteme exists; analyzing the content of the complex semantic part by using the combined template to obtain first analysis information; analyzing the content of the simple semantic part by utilizing the natural languagemodel to obtain second analysis information, then integrating the first analysis information and the second analysis information to obtain a graph query language capable of expressing complete semantics of the natural language question, and then performing query to obtain an answer. According to the method, the complex semantic content of the question is processed by using the combined template;According to the method and the device, the knowledge graph is established, questions and answers are made on the basis of the knowledge graph, a great deal of high-quality question and answer corporadoes not need to be used in specific application by utilizing the very good description capability of the knowledge graph on the data, and thus the accuracy of answering natural language questions containing complex semantics is improved.

Description

technical field [0001] This application belongs to the technical field of natural language processing, and specifically relates to an intelligent question answering method. Background technique [0002] With the development of the Internet, the representation of knowledge is no longer web page links, but individual things or concepts in the real world. These things are connected to each other and convey semantic relationships to each other, forming a knowledge graph. An important application based on knowledge graph is to do search. Unlike traditional search engines based on keyword search, knowledge graph can be used to better query complex related information, understand user intent from the semantic level, and improve search quality. [0003] A typical application scenario of knowledge graph plus search is automatic question answering. Q&A can be divided into open domain and limited domain according to the domain. The Q&A in the open domain is still in its infancy, and r...

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): G06F16/332G06F16/36
Inventor 高留杰张君福段俊峰赵文
Owner 北京北大软件工程股份有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com