An ontology-based retrieval augmented generation procedure for a voice-controlled maintenance assistant

IF 8.2 1区 计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Heiner Ludwig, Thorsten Schmidt, Mathias Kühn
{"title":"An ontology-based retrieval augmented generation procedure for a voice-controlled maintenance assistant","authors":"Heiner Ludwig,&nbsp;Thorsten Schmidt,&nbsp;Mathias Kühn","doi":"10.1016/j.compind.2025.104289","DOIUrl":null,"url":null,"abstract":"<div><div>This paper presents a novel approach to support complex maintenance procedures through a dialogue-driven digital assistant using an ontology-based retrieval augmented generation method. The core of the proposed system relies on the strong formalisation capabilities of the graph-based Web Ontology Language (OWL), combined with various retrieval algorithms and different Large Language Models (LLMs) to determine the most useful context for answering user queries. To do this, we use the popular principle of Retrieval Augmented Generation (RAG). Graph traversal enriches the contextual knowledge, enabling more accurate and context-aware responses. An evaluation using an OWL example ontology and an extensive Q&amp;A dataset demonstrates the improved retrieval quality achieved by combining classical and vector-based semantic matching methods. The community-driven analysis of generation quality illustrates the usability of an OWL-based assistant for maintenance procedures on the basis of contexts and LLMs of varying configurations.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"169 ","pages":"Article 104289"},"PeriodicalIF":8.2000,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers in Industry","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0166361525000545","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents a novel approach to support complex maintenance procedures through a dialogue-driven digital assistant using an ontology-based retrieval augmented generation method. The core of the proposed system relies on the strong formalisation capabilities of the graph-based Web Ontology Language (OWL), combined with various retrieval algorithms and different Large Language Models (LLMs) to determine the most useful context for answering user queries. To do this, we use the popular principle of Retrieval Augmented Generation (RAG). Graph traversal enriches the contextual knowledge, enabling more accurate and context-aware responses. An evaluation using an OWL example ontology and an extensive Q&A dataset demonstrates the improved retrieval quality achieved by combining classical and vector-based semantic matching methods. The community-driven analysis of generation quality illustrates the usability of an OWL-based assistant for maintenance procedures on the basis of contexts and LLMs of varying configurations.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Computers in Industry
Computers in Industry 工程技术-计算机:跨学科应用
CiteScore
18.90
自引率
8.00%
发文量
152
审稿时长
22 days
期刊介绍: The objective of Computers in Industry is to present original, high-quality, application-oriented research papers that: • Illuminate emerging trends and possibilities in the utilization of Information and Communication Technology in industry; • Establish connections or integrations across various technology domains within the expansive realm of computer applications for industry; • Foster connections or integrations across diverse application areas of ICT in industry.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信