Knowledge graph embedding method

The invention belongs to the technical field of computer storage, and particularly relates to a knowledge graph embedding method which comprises the following steps: calculating the value of an importance evaluation index of each node in a triple set, and calculating the information entropy of the e...

Full description

Saved in:
Bibliographic Details
Main Authors YAN RAN, SHI ZHAN, ZUO PENGWEI, WU YUTONG, WANG FANG, TIAN ZHIPENG, FENG DAN
Format Patent
LanguageChinese
English
Published 22.03.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention belongs to the technical field of computer storage, and particularly relates to a knowledge graph embedding method which comprises the following steps: calculating the value of an importance evaluation index of each node in a triple set, and calculating the information entropy of the evaluation index based on the value of each evaluation index on each node so as to calculate the weight of the evaluation index; respectively performing inner product on each evaluation index value of each node and the corresponding weight, and calculating the sum of the inner products corresponding to the node as the importance score of the node; traversing the nodes in a descending order according to the importance scores, and determining a preset number of anchor points according to the anchor point distribution density; coding parameters are initialized, multi-dimensional marking information of each node is coded, and the multi-dimensional marking information comprises a nearest anchor point sequence, an anchor
Bibliography:Application Number: CN202311744192