A knowledge map acquisition method based on deep learning

A knowledge map and deep learning technology, applied in relational databases, database models, semantic analysis, etc., can solve problems such as inflexibility and incomplete relational networks of knowledge maps, and achieve the goal of improving the accuracy of results, improving the quality of results, and reducing costs Effect

Active Publication Date: 2021-04-02
浙江万维空间信息技术有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method for acquiring knowledge graphs based on deep learning, which aims to solve the problem in the prior art that the creation of knowledge graphs needs to add artificial knowledge and experience, which leads to the incomplete and inflexible problem of the acquired knowledge graph relationship network

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
  • A knowledge map acquisition method based on deep learning
  • A knowledge map acquisition method based on deep learning
  • A knowledge map acquisition method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Such as figure 1 As shown, a knowledge map acquisition method based on deep learning includes the following steps:

[0063] S110. Acquire heterogeneous data, and divide the heterogeneous data into N structural data, where N is an integer greater than 1;

[0064] S120. Perform corresponding processing on the N structural data according to natural language processing technology to obtain word vectors;

[0065] S130. Input the word vector into the graph neural network model to obtain a first knowledge graph;

[0066] S140. Process the first knowledge graph according to the clustering method and the bag-of-words model to obtain a second knowledge graph.

[0067] In Embodiment 1, multi-source heterogeneous data such as plain text, relational database, XML, picture, video, etc. are obtained, and are divided into structured data, Semi-structured data and unstructured data, wherein structured data and semi-structured data are used to build a knowledge base, which is used to ...

Embodiment 2

[0069] Such as figure 2 As shown, a knowledge map acquisition method based on deep learning, including:

[0070] S210. Obtain heterogeneous data, where the heterogeneous data includes structured data, semi-structured data and unstructured data;

[0071] S220. Construct a knowledge base according to the structured data and the semi-structured data;

[0072] S230. Identify candidate entities in the unstructured data according to entity linking technology, and disambiguate the candidate entities to obtain entities in the knowledge base, where the knowledge base also includes entity relationships and entity attributes;

[0073] S240. Establish a connection between the entity and the knowledge base based on the entity relationship, and vectorize the entity in the knowledge base to obtain a word vector.

[0074] S250. Input the word vector into the graph neural network model to obtain a first knowledge graph;

[0075] S260. Process the first knowledge graph according to the clus...

Embodiment 3

[0078] Such as image 3 As shown, a knowledge map acquisition method based on deep learning, including:

[0079] S310. Acquire heterogeneous data, and divide the heterogeneous data into N structural data, where N is an integer greater than 1;

[0080] S320. Perform corresponding processing on the N structural data according to natural language processing technology to obtain word vectors;

[0081] S330. Obtain target industry information, where the target industry information includes M nodes and message features, where M is an integer greater than 2;

[0082] S340. Transmit the message feature from the first node to an adjacent node, process the message feature at the adjacent node, and transmit the processed message feature to the next node for iterative learning, Obtain the graph neural network model;

[0083] S350. Input the word vector into the graph neural network model to obtain a first knowledge graph;

[0084] S360. Process the first knowledge graph according to t...

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 acquiring knowledge graphs based on deep learning, including acquiring heterogeneous data, dividing the heterogeneous data into structured data, semi-structured data and unstructured data; The heterogeneous data is processed accordingly to obtain a word vector; the word vector is input into the graph neural network model to obtain the first knowledge graph; the first knowledge graph is processed according to the clustering method and the bag-of-words model to obtain The second knowledge map, compared with the traditional self-supervision mode, the present invention is more flexible, different data sources can use different methods, and can also be selected according to different demand biases and scene characteristics, maximizing the advantages of each method , better reduce costs and improve the accuracy of results.

Description

technical field [0001] The present invention relates to the field of deep learning, in particular to a method for acquiring knowledge graphs based on deep learning. Background technique [0002] The knowledge map is essentially a semantic network that reveals the relationship between entities. It can be divided into two levels, the schema layer and the data layer, in terms of logical structure. The data layer is mainly composed of a series of facts, and the knowledge will be based on facts. If you use triples such as (entity 1, relationship, entity 2) and (entity, attribute, attribute value) to express facts, you can choose a graph database as the storage medium, such as open source Neo4j, Twitter's FlockDB, JanusGraph, etc., the schema layer is built on the data layer, mainly through the ontology library to standardize a series of fact expressions in the data layer. Ontology is the conceptual template of the structured knowledge base. , and the degree of redundancy is smal...

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 Patents(China)
IPC IPC(8): G06F40/30G06F16/28G06F16/36G06F16/81
CPCG06F16/288G06F16/367G06F16/81G06F40/30
Inventor 汪晖陆建波王恩茂钱微夏
Owner 浙江万维空间信息技术有限公司
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