Integrating machine learning and workflow management to support acquisition and adaptation of workflow models

Current workflow management systems (WFMS) offer little aid for the acquisition of workflow models and their adaptation to changing requirements. To support these activities we propose to apply techniques from machine learning, which enable an inductive approach to workflow acquisition and adaptation. We present a machine learning component that combines two different machine learning algorithms: the first induces the structure of sequential workflows and the second is responsible for the induction of transition conditions. The second task can be solved by applying standard decision rule induction algorithms. In this contribution we focus mainly on the algorithms for the first task. For this purpose we describe two algorithms based on the induction of hidden Markov models. The first algorithm is a bottom-up, specific-to-general algorithm and the other applies a top-down, general-to-specific strategy. Both algorithms have been implemented in a research prototype. In six scenarios we evaluate and compare the two algorithms experimentally. The induced workflow models can be imported by the business process management system ADONIS.