Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Adaptive knowledge graph technology based on machine learning

A technology of knowledge graph and machine learning, which is applied in the field of knowledge graph construction through machine learning technology, can solve problems such as the influence of automation associations, and achieve the effect of accurate and convenient knowledge graph support and efficient technology platform

Active Publication Date: 2020-03-13
上海孚典智能科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, as the content and method of associated information are manually modified, it will also have an impact on the automatic association between the subsequently added information monomers

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
  • Adaptive knowledge graph technology based on machine learning
  • Adaptive knowledge graph technology based on machine learning
  • Adaptive knowledge graph technology based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] According to the construction of an analysis technology framework for unstructured data information association described in the summary of the invention, its specific implementation is described in the following sections: the knowledge graph system of this invention is composed of graph database Neo4J (see attached Figure 4 ), Neo4J is a widely used and stable graph data engine that supports both structured and unstructured information. The construction of adaptive knowledge graph needs to expand Neo4J in the following aspects (see attached Figure 6 ):

[0033] a. The eigenvector generation system of unstructured information (see appendix Figure 6 );

[0034] b. The feature vector data table that manages various unstructured information (see appendix Figure 7 ), the corresponding relationship from each kind of unstructured information to the corresponding feature vector data table is stored by the feature vector management table;

[0035] Build a feature extrac...

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 implementation technology for establishing indexes and correlations for various kinds of information by using a machine learning technology. The knowledge graph implementation technology focuses on feature discrimination of information mainly including unstructured data and generation of a graph database system based on information association in combination with information association. The method is different from a graph database system for structured information. The invention aims at challenges formed by extraction and association (see attached drawings) of unstructured data (such as images, audios, videos and the like) widely appearing in commercial application at present. Machine learning feature extraction is used as a technical basis. A graph database index system which combines structured data and unstructured data and takes feature association as a basis is constructed through a self-adaptive data feature correction technology which is realized along with data change, and a knowledge graph is realized, so that automatic knowledge graph construction of large-scale data is realized. The technology can be widely applied to various data analysis and query scenes in an intelligent application environment.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to the technology of constructing knowledge map through machine learning technology. This technology uses a deep neural network to extract features from different types of unstructured data, and on this basis, performs adaptive information association on the continuously updated knowledge base records in an adaptive manner, thus simplifying the process of information collection and knowledge map construction , which can automate the construction of knowledge graphs for large-scale data. This technology can be widely used in various data analysis and query scenarios in intelligent application environments. This technology can be widely used in scenarios such as business intelligence, intelligent information retrieval, and automatic information association involving smart cities. Background technique [0002] The knowledge map expresses information in the form of as...

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): G06F16/43G06F16/41G06F16/36G06F16/901
CPCG06F16/367G06F16/41G06F16/43G06F16/9024
Inventor 赵继胜吴宇
Owner 上海孚典智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com