•  
  •  
 

Journal of System Simulation

Abstract

Abstract: Aiming at the disadvantages of high redundancy and weakness between knowledge and data in intelligent production system, and the difficulty to perform knowledge reasoning, a process knowledge reasoning method for knowledge maps is proposed. The input information is semantically labeled and classified, the characteristics of the information match are extracted, the extracted local feature and global feature are associated through graph convolution method, and the feature of the difference value information is integrated and mapped with the constructed knowledge graph. Different reasoning rules are used according to different reasoning types, and the association and topology information between instances are deduced, and the properties and values of input information are generated. Compared with the recommended system algorithm and fusion knowledge map, the algorithm has higher predictive rates on Movielens-1M, Book-Crossing, Last.FM data set. The feasibility of the reasoning model is verified by the process instance knowledge.

First Page

773

Revised Date

2022-02-15

Last Page

785

CLC

TP391.9

Recommended Citation

Weikai Yang, Yan Wang, Zhicheng Ji. Knowledge Graph-based Process Knowledge Reasoning Method for Intelligent Production System[J]. Journal of System Simulation, 2023, 35(4): 773-785.

DOI

10.16182/j.issn1004731x.joss.21-1305

Share

COinS