Knowledge graph question and answer method based on deep learning

A knowledge graph and deep learning technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of inability to take into account character-level matching and semantic relevance, low accuracy, etc., to improve the performance of knowledge graph question answering, Reduce noise issues and improve accuracy

Pending Publication Date: 2022-01-14
积至(海南)信息技术有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a knowledge map question answering method based on deep learning, which solves the problem that the existing deep learning knowledge map question answering method usually cannot take into account character-level matching and semantic relevance, and the accuracy is not high

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 question and answer method based on deep learning
  • Knowledge graph question and answer method based on deep learning
  • Knowledge graph question and answer method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

no. 2 example

[0040] Based on the knowledge graph question answering method based on deep learning in the first embodiment of the present invention, the second embodiment of the present invention provides another knowledge graph question answering method based on deep learning, wherein the second embodiment does not hinder the first embodiment Independent implementation of technical solutions.

[0041] Specifically, the present invention provides another deep learning-based knowledge map question answering method that is different in that:

[0042] It also includes a graph question answering system for completing knowledge graph question answering. The graph graph question answering system includes a knowledge graph acquisition module for obtaining knowledge graph question answering data sets, an entity recognition module for identifying entities in natural language questions, and a system for constructing Candidate relationship building blocks for candidate relationship sets, matching rela...

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 question and answer method based on deep learning. The knowledge graph question and answer method based on deep learning comprises the following operation steps: S1, obtaining a knowledge graph question and answer data set: obtaining the knowledge graph question and answer data set, carrying out modeling by using a CNN and Transform model, and inputting data into the model to train the model. The provided knowledge graph question and answer method based on deep learning mainly utilizes the characteristics of knowledge graph question and answer to construct a deep learning model based on CNN and Transform, and utilizes the characteristics of CNN and Transform to realize character-level matching between natural language questions and relationships and matching of context semantics, so that the matching accuracy is effectively improved; and meanwhile, the entity in the natural language question is effectively identified by using a Bi-LSTM neural network, so that the noise problem generated by the traditional character string matching can be effectively reduced, and the knowledge graph question and answer performance is further improved.

Description

technical field [0001] The present invention relates to the field of knowledge graphs, in particular to a knowledge graph question answering method based on deep learning. Background technique [0002] Knowledge map, known as knowledge domain visualization or knowledge domain mapping map in the library and information industry, is a series of different graphics showing the relationship between knowledge development process and structure, using visualization technology to describe knowledge resources and their carriers, mining, analyzing and constructing , Mapping and displaying knowledge and their interconnections. [0003] In recent years, several large-scale general-purpose knowledge graphs such as YAGO, Freebase, NELL, and DBpedia have emerged. People are looking for effective ways to obtain the rich knowledge in them. There are several languages ​​​​designed for querying knowledge graphs, but they are not very user-friendly. It is friendly and requires users to be famil...

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 & AuthorityApplications(China)
IPC IPC(8): G06F16/332G06F16/33G06F16/338G06F16/36G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06F16/338G06F16/367G06N3/049G06N3/08G06N3/045
Inventor黄园园苏俊龙绍楠杨世宇
Owner积至(海南)信息技术有限公司