Introduction

International Standard Serial Number:

ISSN 1001-4551

Sponsor:

Zhejiang University;

Zhejiang Machinery and Electrical Group

Edited by:

Editorial of Journal of Mechanical & Electrical Engineering

Chief Editor:

ZHAO Qun

Vice Chief Editor:

TANG ren-zhong,

LUO Xiang-yang

Tel:

86-571-87041360,87239525

Fax:

86-571-87239571

Add:

No.9 Gaoguannong,Daxue Road,Hangzhou,China

P.C:

310009

E-mail:

meem_contribute@163.com

Design knowledge recommendation method based on ontology-matching bi-directional extension model
Published:2024-10-30 author:DONG Jinjin, GU Hairui, LU Jiawei, et al. Browse: 114 Check PDF documents
Design knowledge recommendation method based on ontology-matching 
bi-directional extension model


DONG Jinjin1, GU Hairui1, LU Jiawei1, WANG Qibing1, JIANG Xueming2, XIAO Gang1

(1.College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018,China; 
2.Zhejiang Supcon Information Co., Ltd., Hangzhou 310018, China)


Abstract: To address the lack of effective summarization and organization of knowledge on escalator truss design, which led to poor reusability and sharing of knowledge, an ontology-matching bi-directional extension model based on escalator truss design knowledge recommendation method was proposed. First, the escalator truss name entity recognition (ETNER) model was proposed, and the knowledge features in this domain were extracted effectively, which provided the data basis for the construction of knowledge ontology. Then, the domain knowledge ontology was constructed, the design knowledge was represented normally, and the correlation between the ontology knowledge was used for reasoning. Finally, the ontology-matching bidirectional extended knowledge recommendation model was designed, and in the scenario where the ontology reasoning was empty, the improved knowledge similarity calculation method and document extension matching method were used to improve the understanding of the user's knowledge requirements and to supplement the knowledge recommendation results of escalator truss design, and at the same time promote the updating of the knowledge ontology of escalator truss design. The research results show that the F1 index of the proposed entity recognition model can reach 0.863, which can effectively extract the design knowledge features of the escalator truss. The mean reciprocal rank (MRR), hit ratio (HR) and normalized discounted cumulative gain (NDCG) indexes of the proposed knowledge recommendation method are 0.79, 0.85 and 0.80, respectively. Comparing with the traditional Doc2query method, it can fully understand the design knowledge requirements and improve the effectiveness of knowledge recommendation results. The research results can provide a method support for knowledge sharing and reuse in escalator truss design and other similar engineering applications.

Key words: escalator truss design; escalator truss name entity recognition (ETNER) model; knowledge recommendation; knowledge reusability; knowledge sharing; ontology-matching bidirectional extension model
Advanced Search
Online Office System
  • Chinese Core Periodicals
  • Chinese Sci-tech Core Periodicals
  • SA, INSPEC Indexed
  • CSA: T Indexed
  • UPD:Indexed


2010 Zhejiang Information Institute of Mechinery Industry

Technical Support：Hangzhou Bory science and technology

You are 1895221 visit this site