LLM-based Business Process Adaptation Method to Respond Long-tailed Changes

Business process adaptation is one of fundamental and enduring tasks in business process management,aimed at enhancing flexibility and achieving business objectives by adjusting process models and instances in response to everchanging environment.Long-tailed changes(LTCs),stemming from residual uncertainty during modeling,are inevitable and pose a significant challenge to business resilience.The most effective approach available now is a tripartite collaboration framework,consisting of a frontend business operators perceiving LTCs and fulfilling adaptation using domain specific languages(DSL),a technical backend and managerial team providing service repository and compliance requirements,and an enabling tool assisting the adaptation.However,the diversity,complexity,and urgency of LTCs in varying spatiotemporal scenarios may exceed the frontend’s ability to grasp the situations,formulate appropriate solutions,and express them in DSL.To address the limitation and further expand the effective framework,LLM-Adapt,a long-tailed changes adaptation method based on large language models(LLMs),is proposed.By leveraging the generalization ability,content generation power,and embedded knowledge of events and countermeasures in LLMs,LLM-Adapt provides a more efficient and applicable adaptation mechanism.Firstly,a prompt engineering strategy tailored to the characteristics of LTCs is developed to enable frontend to interact with LLMs in natural language and obtain adaptation solutions.Secondly,in alignment with the business baseline constraints set by the back-end process owners,functional validation of the adaptation solutions is conducted.Furthermore,a new algorithm SSDT-Lane based on process structural similarity is proposed to filter out adaptation candidates that strike current organizational and resource configurations.Case studies and experiments conducted using both synthetic and real-world datasets demonstrate that LLM-Adapt outperforms existing methods in terms of accuracy,efficiency and applicability.