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.
@article{arxiv.2507.02914,
title = {OAK -- Onboarding with Actionable Knowledge},
author = {Steve Devènes and Marine Capallera and Robin Cherix and Elena Mugellini and Omar Abou Khaled and Francesco Carrino},
journal= {arXiv preprint arXiv:2507.02914},
year = {2025}
}
Comments
This paper is an extended version of the work originally presented at the AI-Days 2024 conference in Lausanne, Switzerland. It builds upon the findings shared during the conference and includes additional results and analysis