{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:07:27Z","timestamp":1785434847545,"version":"3.56.0"},"reference-count":34,"publisher":"ASME International","issue":"8","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In the assembly process design, knowledge question\u2013answering is a crucial scenario for promoting the sharing of knowledge resources and enhancing the process design accuracy and efficiency. Simultaneously, knowledge graph technology enables efficient semantic modeling of knowledge, allowing for more accurate capture of user semantics and intentions. This, in turn, enhances the accuracy and flexibility of knowledge question\u2013answering. However, due to the high complexity and specialization of assembly processes, current knowledge graph question\u2013answering for assembly processes still faces challenges, such as difficulty in understanding complex queries. In response to this, this article proposes a large language model (LLM)-enhanced knowledge graph multi-hop reasoning method for assembly process question\u2013answering. This method decomposes the multi-hop knowledge graph question\u2013answering task into three subtasks: LLM-tuning-based question\u2013answering chain generation task, which transforms the question into one or more question\u2013answering chains, multi-hop question\u2013answering chain reasoning task, and LLM-based natural language answer generation task. Among them, a graph path-based multi-hop reasoning model for assembly processes is constructed for question\u2013answering chain generation. This model employs a \u201ccore reasoning + attribute constraints\u201d strategy and a task-oriented negative sample setting method to enable rapid and precise reasoning between the knowledge graph and question\u2013answering chains. The effectiveness of the proposed method is validated through the comparative experiments with existing mature knowledge graph question\u2013answering models. In the comparative experiments, three datasets were constructed for LLM fine-tuning and question\u2013answering chain reasoning of multi-hop questions, and the performance index HITS@5 of 0.913 surpassed the existing mature Hete-MF model and could fully meet the process designer needs.<\/jats:p>","DOI":"10.1115\/1.4071611","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:28:16Z","timestamp":1775579296000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":0,"title":["A Large Language Model-Enhanced Knowledge Graph Multi-Hop Reasoning Method for Assembly Process Question\u2013Answering"],"prefix":"10.1115","volume":"26","author":[{"given":"Peilin","family":"Shao","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03s8xc553","id-type":"ROR","asserted-by":"publisher"}],"name":"Shanxi Datong University School of Mechanical and Electrical Engineering, , , \u00a0 ,","place":["Datong, Shanxi, China, 037009"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicheng","family":"Huang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00wk2mp56","id-type":"ROR","asserted-by":"publisher"}],"name":"Beihang University School of Mechanical Engineering and Automation, , Haidian District, \u00a0 ,","place":["Beijing, China, 100191"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Qiao","sequence":"additional","affiliation":[{"name":"Beihang University School of Mechanical Engineering and Automation, , Haidian District, \u00a0 ,","place":["Beijing, China, 100191"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinzheng","family":"Xu","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00wk2mp56","id-type":"ROR","asserted-by":"publisher"}],"name":"Beihang University School of Mechanical Engineering and Automation, , Haidian District, \u00a0 ,","place":["Beijing, China, 100191"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqiang","family":"Wan","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00wk2mp56","id-type":"ROR","asserted-by":"publisher"}],"name":"Beihang University School of Mechanical Engineering and Automation, , Haidian District, \u00a0 ,","place":["Beijing, China, 100191"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Chen","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00wk2mp56","id-type":"ROR","asserted-by":"publisher"}],"name":"Beihang University School of Mechanical Engineering and Automation, , Haidian District, \u00a0 ,","place":["Beijing, China, 100191"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhujia","family":"Li","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00wk2mp56","id-type":"ROR","asserted-by":"publisher"}],"name":"Beihang University School of Mechanical Engineering and Automation, , Haidian District, \u00a0 ,","place":["Beijing, China, 100191"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nabil","family":"Anwer","sequence":"additional","affiliation":[{"name":"Paris-Saclay University ENS Paris-Saclay, LURPA, , \u00a0 ,","place":["Gif-sur-Yvette, France, 91190"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Qie","sequence":"additional","affiliation":[{"name":"Paris-Saclay University ENS Paris-Saclay, LURPA, , \u00a0 , ;","place":["Gif-sur-Yvette, France, 91190"]},{"id":[{"id":"https:\/\/ror.org\/01skt4w74","id-type":"ROR","asserted-by":"publisher"}],"name":"Beijing Institute of Technology School of Mechanical Engineering, , Haidian District, \u00a0 ,","place":["Beijing, China, 100081"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"2026061612150177100_CIT0001","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-981-97-0827-7_28","article-title":"An Assembly Instruction Question Answering System Based on Knowledge Graph","author":"Zhang","year":"2023"},{"key":"2026061612150177100_CIT0002","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/EDUCON60312.2024.10578654","article-title":"Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations","author":"Abu-Rasheed","year":"2024"},{"issue":"8","key":"2026061612150177100_CIT0003","doi-asserted-by":"publisher","first-page":"081001","DOI":"10.1115\/1.4065166","article-title":"CarbonKG: Industrial Carbon Emission Knowledge Graph-Based Modeling and Application for Carbon Traceability of Complex Manufacturing Process","volume":"24","author":"Wu","year":"2024","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026061612150177100_CIT0004","doi-asserted-by":"publisher","first-page":"102403","DOI":"10.1016\/j.aei.2024.102403","article-title":"AKGNN-PC: An Assembly Knowledge Graph Neural Network Model With Predictive Value Calibration Module for Refrigeration Compressor Performance Prediction With Assembly Error Propagation and Data Imbalance Scenarios","volume":"60","author":"Xu","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"2026061612150177100_CIT0005","doi-asserted-by":"publisher","first-page":"102172","DOI":"10.1016\/j.aei.2023.102172","article-title":"Systematic Knowledge Modeling and Extraction Methods for Manufacturing Process Planning Based on Knowledge Graph","volume":"58","author":"Wen","year":"2023","journal-title":"Adv. Eng. Inform."},{"key":"2026061612150177100_CIT0006","doi-asserted-by":"publisher","first-page":"103449","DOI":"10.1016\/j.compind.2021.103449","article-title":"Exploiting Knowledge Graphs in Industrial Products and Services: A Survey of Key Aspects, Challenges, and Future Perspectives","volume":"129","author":"Li","year":"2021","journal-title":"Comput. Ind."},{"key":"2026061612150177100_CIT0007","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-031-52649-7_20","article-title":"Knowledge Graph-Driven Manufacturing Resources Recommendation Method for Ship Pipe Manufacturing Workshop","author":"Zhang","year":"2023"},{"key":"2026061612150177100_CIT0008","doi-asserted-by":"publisher","first-page":"106722","DOI":"10.1016\/j.engappai.2023.106722","article-title":"A Patent Recommendation Method Based on KG Representation Learning","volume":"126","author":"Xiao","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"2026061612150177100_CIT0009","doi-asserted-by":"publisher","first-page":"6627114","DOI":"10.1155\/2021\/6627114","article-title":"Knowledge Graph Question and Answer System for Mechanical Intelligent Manufacturing Based on Deep Learning","volume":"1","author":"Shi","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"2026061612150177100_CIT0010","doi-asserted-by":"publisher","first-page":"117737","DOI":"10.1016\/j.eswa.2022.117737","article-title":"Categorization of Knowledge Graph Based Recommendation Methods and Benchmark Datasets From the Perspectives of Application Scenarios: A Comprehensive Survey","volume":"206","author":"Khan","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"4","key":"2026061612150177100_CIT0011","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641288","article-title":"Knowledge Graph Enhanced Contextualized Attention-Based Network for Responsible User-Specific Recommendation","volume":"15","author":"Elahi","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"2026061612150177100_CIT0012","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1109\/ICSECS58457.2023.10256354","article-title":"A Review of Knowledge Graph Embedding Methods of TransE, TransH and TransR for Missing Links","author":"Asmara","year":"2023"},{"key":"2026061612150177100_CIT0013","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1145\/3308558.3313705","article-title":"Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences","author":"Cao","year":"2019"},{"key":"2026061612150177100_CIT0014","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1109\/BigData59044.2023.10386186","article-title":"TransGNN: Towards Knowledge Enhanced Top-K Recommendation Via Transformed Heterogeneous Graph Neural Network","author":"Wang","year":"2023"},{"key":"2026061612150177100_CIT0015","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1145\/2939672.2939673","article-title":"Collaborative Knowledge Base Embedding for Recommender Systems","author":"Zhang","year":"2016"},{"key":"2026061612150177100_CIT0016","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1145\/3209978.3210017","article-title":"Improving Sequential Recommendation With Knowledge-Enhanced Memory Networks","author":"Huang","year":"2018"},{"issue":"9","key":"2026061612150177100_CIT0017","doi-asserted-by":"publisher","first-page":"137","DOI":"10.3390\/a11090137","article-title":"Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation","volume":"11","author":"Ai","year":"2018","journal-title":"Algorithms"},{"key":"2026061612150177100_CIT0018","doi-asserted-by":"publisher","first-page":"102339","DOI":"10.1016\/j.aei.2023.102339","article-title":"XMKR: Explainable Manufacturing Knowledge Recommendation for Collaborative Design With Graph Embedding Learning","volume":"59","author":"Jing","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"2026061612150177100_CIT0019","first-page":"1","article-title":"Collaborative Filtering With Entity Similarity Regularization in Heterogeneous Information Networks","volume":"27","author":"Yu","year":"2013","journal-title":"IJCAI HINA"},{"key":"2026061612150177100_CIT0020","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1145\/3097983.3098063","article-title":"Meta-Graph Based Recommendation Fusion Over Heterogeneous Information Networks","author":"Zhao","year":"2017"},{"key":"2026061612150177100_CIT0021","first-page":"285","article-title":"Reinforcement Knowledge Graph Reasoning for Explainable Recommendation","author":"Xian","year":"2019"},{"issue":"3","key":"2026061612150177100_CIT0022","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/s10115-016-0925-0","article-title":"Integrating Heterogeneous Information Via Flexible Regularization Framework for Recommendation","volume":"49","author":"Shi","year":"2016","journal-title":"Knowl. Inf. Syst."},{"key":"2026061612150177100_CIT0023","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.18653\/v1\/2021.findings-acl.90","article-title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-Hop Science Question Answering","author":"Zong","year":"2021"},{"key":"2026061612150177100_CIT0024","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1109\/ICDM.2014.64","article-title":"Hete-CF: Social-Based Collaborative Filtering Recommendation Using Heterogeneous Relations","author":"Luo","year":"2014"},{"key":"2026061612150177100_CIT0025","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1145\/3269206.3271739","article-title":"RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems","author":"Wang","year":"2018"},{"key":"2026061612150177100_CIT0026","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1145\/3292500.3330989","article-title":"KGAT: Knowledge Graph Attention Network for Recommendation","author":"Wang","year":"2019"},{"issue":"2","key":"2026061612150177100_CIT0027","doi-asserted-by":"publisher","first-page":"024501","DOI":"10.1115\/1.4067332","article-title":"Do Large Language Models Produce Diverse Design Concepts? A Comparative Study With Human-Crowdsourced Solutions","volume":"25","author":"Ma","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026061612150177100_CIT0028","doi-asserted-by":"publisher","first-page":"giae082","DOI":"10.1093\/gigascience\/giae082","article-title":"Knowledge Graph-Based Thought: A Knowledge Graph-Enhanced LLM Framework for Pan-Cancer Question Answering","volume":"14","author":"Feng","year":"2025","journal-title":"GigaScience"},{"key":"2026061612150177100_CIT0029","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1007\/978-3-031-70371-3_32","article-title":"FinQA: A Training-Free Dynamic Knowledge Graph Question Answering System in Finance With LLM-Based Revision","author":"Tao","year":"2024"},{"key":"2026061612150177100_CIT0030","first-page":"300","article-title":"ForensIQ: A Knowledge Graph Question Answering System for IoT Forensics","author":"Zhang","year":"2023"},{"issue":"2","key":"2026061612150177100_CIT0031","doi-asserted-by":"publisher","first-page":"021010","DOI":"10.1115\/1.4067389","article-title":"Integrating Graph Retrieval-Augmented Generation With Large Language Models for Supplier Discovery","volume":"25","author":"Li","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"7\u20139","key":"2026061612150177100_CIT0032","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1080\/09544828.2023.2272555","article-title":"A Question Answering System for Assembly Process of Wind Turbines Based on Multi-Modal Knowledge Graph and Large Language Model","volume":"36","author":"Hu","year":"2025","journal-title":"J. Eng. Des."},{"key":"2026061612150177100_CIT0033","unstructured":"Liu, Z.\n          , 2025, \u201cIntelligent Industrial Maintenance: Using Natural Language Processing Technology and Domain Knowledge for Decision Support,\u201d Ph.D. thesis, University of Auckland, Auckland, New Zealand."},{"key":"2026061612150177100_CIT0034","doi-asserted-by":"publisher","first-page":"55537","DOI":"10.1109\/ACCESS.2021.3070395","article-title":"Knowledge Graphs in Manufacturing and Production: A Systematic Literature Review","volume":"9","author":"Buchgeher","year":"2021","journal-title":"IEEE Access"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/8\/081003\/7605662\/jcise-25-1145.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/8\/081003\/7605662\/jcise-25-1145.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:15:10Z","timestamp":1781626510000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/26\/8\/081003\/1232369\/A-Large-Language-Model-Enhanced-Knowledge-Graph"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":34,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4071611","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]},"article-number":"081003"}}