Knowledge graph-based question and answer template automatic generation method and device

A knowledge graph and automatic generation technology, applied in the field of artificial intelligence and automatic machine learning, which can solve the problems of no solution, high time cost, energy consumption, etc.

Pending Publication Date: 2021-04-09
厦门渊亭信息科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, a template-based knowledge graph question answering system has been realized technically. The advantages of this system are: fast query response speed, high accuracy, and can answer complex queries. The process of building a huge template library is very energy-intensive. At this time, it is ine...

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
  • Knowledge graph-based question and answer template automatic generation method and device
  • Knowledge graph-based question and answer template automatic generation method and device
  • Knowledge graph-based question and answer template automatic generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0051] figure 1 is a block diagram of an example computing device 100 arranged to implement a knowledge graph-based question-and-answer template automatic generation method according to the present invention. In a basic configuration 102 , computing device 100 typically includes system memory 106 and one or more processors 104 . A memory bus 108 may be used for communication between the processor 104 and the system memory 106 .

[0052]Depend...

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 provides a knowledge graph-based question and answer template automatic generation method and device, a readable storage medium and a computing device. By automatically generating the question and answer template, a natural language can be split into a plurality of clauses, answers are searched for respectively, and finally answers are merged, so the retrieval process is simplified, the retrieval difficulty is reduced, and the efficiency is greatly improved. The method comprises the steps of obtaining a plurality of user questions and answer pairs used for generating a question and answer template; generating a plurality of question and answer templates according to the plurality of user questions and answer pairs, wherein the question and answer template comprises an utterance template, a query graph template and alignment information of the utterance template and the query graph template; when a question input by a user is received, instantiating the query graph template according to the alignment information and a dictionary if it is determined that the question input by the user is matched with an analytic tree of the utterance template to obtain candidate answers; ranking the plurality of candidate answers, and returning one or more candidate answers ranked before to the user.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence and automatic machine learning, and in particular to a method, device, readable storage medium and computing device for automatically generating question and answer templates based on knowledge graphs. Background technique [0002] With the explosive growth of information on the Internet, people's demand for information retrieval is increasing. How to quickly, accurately and reliably search for the information users need from a large amount of information with diverse modes has become an urgent and urgent task. issues that need resolving. [0003] At present, a template-based knowledge graph question answering system has been realized technically. The advantages of this system are: fast query response speed, high accuracy, and can answer complex queries. The process of building a huge template library is very energy-intensive. At this time, it is inevitable to design an au...

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): G06F16/332G06F16/36G06F16/33
CPCG06F16/3329G06F16/367G06F16/3331
Inventor 洪万福钱智毅熊朝阳
Owner 厦门渊亭信息科技有限公司
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