Open Access
ARTICLE
Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design
Yuexin Huang1,2, Suihuai Yu1, Jianjie Chu1,*, Zhaojing Su1,3, Yangfan Cong1, Hanyu Wang1, Hao Fan4
1
Key Laboratory of Industrial Design and Ergonomics, Ministry of Industry and Information Technology, Northwestern
Polytechnical University, Xi’an, 710072, China
2
School of Industrial Design Engineering, Delft University of Technology, Delft, 2628 CE, The Netherlands
3
Department of Industrial Design, College of Arts, Shandong University of Science and Technology, Tsingtao, 266590, China
4
College of Computer Science and Technology, Zhejiang University, Hangzhou, 310027, China
* Corresponding Author: Jianjie Chu. Email:
Computer Modeling in Engineering & Sciences 2024, 138(1), 167-200. https://doi.org/10.32604/cmes.2023.028268
Received 08 December 2022; Accepted 31 March 2023; Issue published 22 September 2023
Abstract
The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in
conceptual product design. This study proposes a novel method for acquiring design knowledge by combining
deep learning with knowledge graph. Specifically, the design knowledge acquisition method utilises the knowledge
extraction model to extract design-related entities and relations from fragmentary data, and further constructs
the knowledge graph to support design knowledge acquisition for conceptual product design. Moreover, the
knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the
entity extraction module, and uses multi-granularity information to overcome segmentation errors and polysemy
ambiguity in the relation extraction module. Experimental comparison verified the effectiveness and accuracy
of the proposed knowledge extraction model. The case study demonstrated the feasibility of the knowledge
graph construction with real fragmentary porcelain data and showed the capability to provide designers with
interconnected and visualised design knowledge.
Keywords
Cite This Article
APA Style
Huang, Y., Yu, S., Chu, J., Su, Z., Cong, Y. et al. (2024). Combining deep learning with knowledge graph for design knowledge acquisition in conceptual product design. Computer Modeling in Engineering & Sciences, 138(1), 167-200. https://doi.org/10.32604/cmes.2023.028268
Vancouver Style
Huang Y, Yu S, Chu J, Su Z, Cong Y, Wang H, et al. Combining deep learning with knowledge graph for design knowledge acquisition in conceptual product design. Comput Model Eng Sci. 2024;138(1):167-200 https://doi.org/10.32604/cmes.2023.028268
IEEE Style
Y. Huang et al., "Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design," Comput. Model. Eng. Sci., vol. 138, no. 1, pp. 167-200. 2024. https://doi.org/10.32604/cmes.2023.028268