Knowledge graph optimization method based on a fuzzy theory

A technology of knowledge graph and optimization method, applied in fuzzy logic-based systems, unstructured text data retrieval, electrical components, etc., can solve problems such as multiple training times, and achieve the effect of comprehensive, accurate and high-accuracy knowledge graphs

Inactive Publication Date: 2019-06-04
NORTHEASTERN UNIV
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, most of the existing knowledge map technologies are based on deep learning algorithms, and the data of each dimension in each vector is treated in isolation, which makes the process of building a better knowledge map often require more training time and a larger training set

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 optimization method based on a fuzzy theory
  • Knowledge graph optimization method based on a fuzzy theory
  • Knowledge graph optimization method based on a fuzzy theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The invention will be further described below in conjunction with the accompanying drawings and specific implementation examples. For the knowledge map optimization method, the starting point of the present invention is to consider that each entity has multiple different attributes, and different attributes correspond to different relationships. The emphases of the corresponding attributes are also different, and the fuzzy theory is used to blur the stage of deep learning to start modeling. Based on this, a knowledge map optimization method based on fuzzy theory is proposed, such as figure 1 and figure 2 As shown, the specific steps are as follows:

[0037] Step 1: Obtain triplet data in the training set and preprocess all triplet data. The main purpose of this step is to prepare data for the construction of triplet fuzzy projections in the fuzzy space, including steps 1.1 to 1.2:

[0038] Step 1.1: Obtain the triplet data in the training set, initialize all triplet...

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 optimization method based on the fuzzy theory, and the method comprises the steps: obtaining the triple data of a training set, and carrying out the preprocessing of all the triple data;constructing a knowledge graph based on fuzzy relation synthesis to obtain a fuzzy relation of the knowledge graph; and based on the loss function, minimizing a target optimization function, and obtaining an optimized triple vector which is the triple set of the optimized knowledge map. According to the invention, a fuzzy vector operation method is used for carrying outoperation on training data of each dimension; According to the knowledge graph optimization method based on the fuzzy theory, semantic information given to data in fuzzy logic is combined with the deep learning theory, experiments show that the knowledge graph obtained through the knowledge graph optimization method based on the fuzzy theory is more comprehensive and accurate, and the optimized knowledge graph has higher accuracy in the aspects of link prediction and triple classification.

Description

technical field [0001] The invention belongs to the field of knowledge management and information retrieval, and in particular relates to a method for optimizing a knowledge map based on fuzzy theory. Background technique [0002] The original intention of the knowledge map is to illustrate the relationship between various entities, relationships, and attributes of entities and relationships in the real world. It uses the relationship in the triplet to describe the "head entity" and "tail entity". It has a specific connection, and its main goal is to improve the search engine, improve the accuracy of its search results and improve the user's search experience, which involves a variety of specific applications such as classification and prediction. [0003] Most of the current knowledge graph algorithms are based on triples (head entity, relationship, tail entity). Entities are the most basic elements in knowledge graphs, and different entities have different relationships. ...

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 Applications(China)
IPC IPC(8): G06F16/36G06N7/02
Inventor 王大玲王楚冯时张一飞
Owner NORTHEASTERN UNIV
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