Fig. 3: Overview of a human-centric knowledge system.
From: MetalMind: A knowledge graph-driven human-centric knowledge system for metal additive manufacturing
The system operates in two phases: a Knowledge graph (KG) construction using large language models (LLMs), incorporating expert feedback for quality assurance. b Multi-modal knowledge acquisition through mixed reality (MR) (i) direct interaction for retrieving explicit knowledge with associated images and documentation, including video analysis for operational knowledge, and (ii) expert interaction and hands-on experience for developing implicit knowledge, with the system capturing operational patterns to enhance the KG's practical expertise representation.
