CausalTemporalCraft: A Computational Analytics Framework for Manufacturing Craftsmanship Spirit Cultivation via Lewin’s Field Dynamics and Multi-Dimensional Collaboration

Abstract

This research propose CausalTemporalCraft, a computational analytics framework that models the cultivation of craftsmanship spirit in manufacturing enterprises through multi-dimensional collaboration, grounded in Lewin’s field dynamics theory. The framework addresses the limitations of conventional approaches by constructing a temporal causal graph to capture dynamic interactions among collaborators, where driving, restraining, and supporting forces shape the evolution of craftsmanship spirit over time. At its core, the system employs a transformer-based Causalformer architecture to infer causal relationships from longitudinal collaboration data, enabling the identification of delayed effects and critical dependencies. The proposed method integrates symbolic AI to translate causal edges into interpretable rules, thereby bridging the gap between data-driven insights and actionable interventions. Moreover, the framework supports adaptive data fusion with existing enterprise systems, such as quality control modules, to refine force dynamics and trigger targeted improvements. For practical deployment, the Causalformer leverages a GPT-3.5-inspired architecture with causal masking, while neural-guided inductive logic programming generates human-readable rules compatible with enterprise knowledge graphs. Visual analytics powered by force-directed layouts further enhance interpretability, allowing stakeholders to trace collaboration impacts and force imbalances dynamically. The novelty of this work lies in its unified treatment of temporal causality and field theory, offering a principled approach to craftsmanship spirit cultivation that is both theoretically grounded and empirically actionable. Experimental validation on real-world manufacturing datasets demonstrates the framework’s ability to uncover latent collaboration patterns and predict craftsmanship outcomes with high fidelity. This research contributes to the broader discourse on organizational analytics by introducing a scalable, interpretable, and adaptive solution for fostering craftsmanship in industrial settings.