🤖 AI Summary
Existing ERP systems struggle to respond agilely to evolving business requirements, heavily relying on manual modeling and consultant intervention—resulting in high customization costs, prolonged development cycles, and low alignment accuracy. To address this, we propose an adaptive ERP framework that pioneers the deep integration of natural language processing (NLP) into the entire Petri net modeling and matching pipeline: it semantically parses natural-language requirements to automatically generate evolvable Petri net process models and enables dynamic structural–functional matching between business processes and system capabilities. Our approach combines design science research (DSR) with a systematic literature review (SLR), validated through enterprise process model analysis. Experiments demonstrate that the framework significantly reduces dependence on human consultants, improves model generation efficiency and semantic matching accuracy, and supports real-time, automated system adaptation to business changes—thereby overcoming key bottlenecks in conventional ERP customization paradigms.
📝 Abstract
Enterprise Resource Planning (ERP) consultants play a vital role in customizing systems to meet specific business needs by processing large amounts of data and adapting functionalities. However, the process is resource-intensive, time-consuming, and requires continuous adjustments as business demands evolve. This research introduces a Self-Adaptive ERP Framework that automates customization using enterprise process models and system usage analysis. It leverages Artificial Intelligence (AI)&Natural Language Processing (NLP) for Petri nets to transform business processes into adaptable models, addressing both structural and functional matching. The framework, built using Design Science Research (DSR) and a Systematic Literature Review (SLR), reduces reliance on manual adjustments, improving ERP customization efficiency and accuracy while minimizing the need for consultants.