OAK -- Onboarding with Actionable Knowledge

TL;DR

This paper introduces a novel method combining knowledge graph embeddings, multi-modal interfaces, and large language models to capture, retrieve, and make operational expertise actionable, supporting decision-making in manufacturing environments.

Contribution

It presents a new integrated approach for knowledge collection and retrieval that enhances decision-making on the shop floor, especially in high-precision manufacturing.

Findings

Effective knowledge retrieval for manufacturing quality control

Improved query understanding with LLMs

Prototype demonstrates practical application in industry

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.