Method for answering questions in petrochemical field based on knowledge map

A knowledge graph and domain technology, applied in the field of artificial intelligence, can solve the problems of inability to meet business knowledge acquisition needs, inability to fully understand user semantics, and high business barriers, achieve good scalability, provide work efficiency, and reduce manual intervention.

Active Publication Date: 2019-03-19
北京智通云联科技有限公司
View PDF5 Cites 85 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the field of petrochemicals, due to high business barriers and special user groups, neither search engines nor existing question answering systems can meet the needs of this group of people for acquiring business knowledge
For example, if a user queries "How many oil wells are there in Dongzhuang Oil and Gas Field?" on a search engine, traditional search engines cannot provide you with the an

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 questions in petrochemical field based on knowledge map
  • Method for answering questions in petrochemical field based on knowledge map
  • Method for answering questions in petrochemical field based on knowledge map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0052] It should be understood that terms such as "having", "comprising" and "including" as used herein do not entail the presence or addition of one or more other elements or combinations thereof.

[0053] It should be noted that the experimental methods described in the following embodiments, unless otherwise specified, are conventional methods, and the reagents and materials, unless otherwise specified, can be obtained from commercial sources.

[0054] Such as figure 2 As shown, the present invention provides a question-and-answer method in the field of petrochemicals based on knowledge graphs. Users input voice or text to frequently asked questions in the field of petrochemicals, such as "How many wells are there in Pinghu Oil and Gas Field" or "What is the longitude and...

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 questions in the petrochemical field based on a knowledge map, which comprises the following steps: constructing conceptual knowledge map and entity knowledge map; receiving the question input by user, segmenting the question, extracting entity, attribute, relation and restriction condition, abstracting the entity into concept, matching the question template and transforming it into structured query statement; query conceptual knowledge map and entity knowledge map, generate answers, match answers to answer sentences template, and transform them into natural language answers. The invention also discloses a petrochemical field question answering system based on knowledge map. The invention can store and express the knowledge in the petrochemical field in the form of knowledge map, establish the connection between the business requirement and the development and production data, provide convenience for the user to obtain the professional knowledge in the form of natural language interactive question answering, improve the user experience, and help to provide the work efficiency of the user.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence. More specifically, the present invention relates to a method and system for question answering in the field of petrochemicals based on knowledge graphs. Background technique [0002] The development of search engine technology makes it convenient for people to obtain information. However, mainstream search engines are based on words or words to build inverted indexes. In the query, word or word matching is the main method. There are some problems that cannot understand the semantics of user input, return a large amount of information, and return content that is not targeted. , Users need to search for many times and other issues. As an advanced form of information retrieval system, question answering system can answer the questions raised by users in natural language with accurate and concise natural language. Therefore, its research has also received more and more attention. A...

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): G06F16/332
Inventor 王智超谭培波肖波柳晶晶茹海燕侯志强
Owner 北京智通云联科技有限公司
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