Enhancing Knowledge Sharing Workshops with Natural Language Processing in Maintenance Work

In maintenance and inspection work, sharing and leveraging latent and tacit knowledge possessed by field inspectors are crucial for efficient maintenance and skill enhancement. We have developed the smart voice messaging system, which was designed to accumulate and utilize this latent and tacit knowledge, known as "Gen-Ba knowledge," which is difficult to describe as explicit knowledge (e.g. manuals). An effective approach for knowledge sharing is conducting workshops by inspectors using voice messages containing "Gen-Ba knowledge" recorded in the field by smart voice messaging system. Here, it is important that workshops are conducted efficiently and effectively. This study proposes a method to enhance workshop activation using natural language processing technologies. We applied the proposed method to electrical maintenance work and evaluated its effectiveness. A technical contribution elucidates how various large language models can enhance knowledge sharing workshops.