A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems

TL;DR

This paper presents a human-centered, modular architecture for integrating Large Language Model-based cognitive assistants into manufacturing quality management systems, enhancing process improvement and knowledge sharing.

Contribution

It introduces a novel component-based architecture tailored for QMS that enables effective integration of LLM-CAs, addressing a significant gap in current literature.

Findings

Architecture ensures flexibility, scalability, and modularity.

Validation through iterative expert focus groups.

Demonstrates potential for industrial implementation.

Abstract

Large Language Models-Cognitive Assistants (LLM-CAs) can enhance Quality Management Systems (QMS) in manufacturing, fostering continuous process improvement and knowledge management. However, there is no human-centred software architecture focused on QMS that enables the integration of LLM-CAs into manufacturing in the current literature. This study addresses this gap by designing a component-based architecture considering requirement analysis and software development process. Validation was conducted via iterative expert focus groups. The proposed architecture ensures flexibility, scalability, modularity, and work augmentation within QMS. Moreover, it paves the way for its operationalization with industrial partners, showcasing its potential for advancing manufacturing processes.