OAK -- Onboarding with Actionable Knowledge

2025/06/25 by Devènes, Steve, Capallera, Marine, Cherix, Robin +3
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2507.02914

Abstract

The loss of knowledge when skilled operators leave poses a critical issue for companies. This know-how is diverse and unstructured. We propose a novel method that combines knowledge graph embeddings and multi-modal interfaces to collect and retrieve expertise, making it actionable. Our approach supports decision-making on the shop floor. Additionally, we leverage LLMs to improve query understanding and provide adapted answers. As application case studies, we developed a proof-of-concept for quality control in high precision manufacturing.

Citations

• Psychometric Evaluation of the F-SUS: Creation and Validation of the French Version of the System Usability Scale
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Xception: Deep Learning with Depthwise Separable Convolutions
• Data mining: an overview from a database perspective

Related

• Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solving
• LLM-Powered Knowledge Graphs for Enterprise Intelligence and Analytics
• Knowledge Modelling and Active Learning in Manufacturing
• Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planning
• Knowledge Sharing in Manufacturing using Large Language Models: User Evaluation and Model Benchmarking