The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning

The operation scenario of human-robot collaboration assembly involves multiple channels to acquire assembly domain knowledge data. In order to equip collaborative robots with certain general knowledge of assembly work and logical reasoning ability, this paper proposes a Chinese-character-based names...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Qu, Yanmei Li, Huilong Du, Wen Wang, Weiping Fu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11021648/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850161456871374848
author Jing Qu
Yanmei Li
Huilong Du
Wen Wang
Weiping Fu
author_facet Jing Qu
Yanmei Li
Huilong Du
Wen Wang
Weiping Fu
author_sort Jing Qu
collection DOAJ
description The operation scenario of human-robot collaboration assembly involves multiple channels to acquire assembly domain knowledge data. In order to equip collaborative robots with certain general knowledge of assembly work and logical reasoning ability, this paper proposes a Chinese-character-based names entity recognition model Bert-BiLSTM-CRF and a relational extraction model Bert-BiGRU-ATT, based on the multiple heterogeneous data in the assembly domain, to construct an assembly domain knowledge graph centered on <operator> and <assembly object> for human-robot collaboration. Among them, the Chinese-character-based names entity recognition model avoids the error bias caused by Chinese word segmentation in traditional methods, while the relation extraction model fully extracts the association information between entities and relations. The proposed entity recognition model and relation extraction model are validated in a real scenario of mechanical product assembly. The experimental results show that the proposed models exhibit excellent performance in the human-machine collaborative assembly domain, with overall average F1-score of 84.02% and 94.92% for entities and relations, respectively. The constructed knowledge graph of the assembly domain contains 2724 triples, and the knowledge graph is presented through a visual interactive interface.
format Article
id doaj-art-05a2c23fec014d618bc06650274b36e2
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-05a2c23fec014d618bc06650274b36e22025-08-20T02:22:50ZengIEEEIEEE Access2169-35362025-01-011310095710096910.1109/ACCESS.2025.357616811021648The Construction of Knowledge Graphs in the Assembly Domain Based on Deep LearningJing Qu0https://orcid.org/0009-0009-1433-8225Yanmei Li1Huilong Du2Wen Wang3https://orcid.org/0000-0001-9914-5311Weiping Fu4https://orcid.org/0000-0001-9803-3908School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, Shaanxi, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, Shaanxi, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, Shaanxi, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, Shaanxi, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an, Shaanxi, ChinaThe operation scenario of human-robot collaboration assembly involves multiple channels to acquire assembly domain knowledge data. In order to equip collaborative robots with certain general knowledge of assembly work and logical reasoning ability, this paper proposes a Chinese-character-based names entity recognition model Bert-BiLSTM-CRF and a relational extraction model Bert-BiGRU-ATT, based on the multiple heterogeneous data in the assembly domain, to construct an assembly domain knowledge graph centered on <operator> and <assembly object> for human-robot collaboration. Among them, the Chinese-character-based names entity recognition model avoids the error bias caused by Chinese word segmentation in traditional methods, while the relation extraction model fully extracts the association information between entities and relations. The proposed entity recognition model and relation extraction model are validated in a real scenario of mechanical product assembly. The experimental results show that the proposed models exhibit excellent performance in the human-machine collaborative assembly domain, with overall average F1-score of 84.02% and 94.92% for entities and relations, respectively. The constructed knowledge graph of the assembly domain contains 2724 triples, and the knowledge graph is presented through a visual interactive interface.https://ieeexplore.ieee.org/document/11021648/Human-robot collaboration assemblyknowledge graphknowledge extractionknowledge visualization
spellingShingle Jing Qu
Yanmei Li
Huilong Du
Wen Wang
Weiping Fu
The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
IEEE Access
Human-robot collaboration assembly
knowledge graph
knowledge extraction
knowledge visualization
title The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
title_full The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
title_fullStr The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
title_full_unstemmed The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
title_short The Construction of Knowledge Graphs in the Assembly Domain Based on Deep Learning
title_sort construction of knowledge graphs in the assembly domain based on deep learning
topic Human-robot collaboration assembly
knowledge graph
knowledge extraction
knowledge visualization
url https://ieeexplore.ieee.org/document/11021648/
work_keys_str_mv AT jingqu theconstructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT yanmeili theconstructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT huilongdu theconstructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT wenwang theconstructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT weipingfu theconstructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT jingqu constructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT yanmeili constructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT huilongdu constructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT wenwang constructionofknowledgegraphsintheassemblydomainbasedondeeplearning
AT weipingfu constructionofknowledgegraphsintheassemblydomainbasedondeeplearning