Inducing Workflow Models from Workflow Instances

One of the main barriers to achieving a high degree of concurrency in product development processes is the efficiency of communication and coordination. Workflow management systems (WFMS) support the coordination of repetitive routine processes within the product development process by enacting them according to a defined workflow model. Current WFMS offer little aid for many management activities such as the acquisition of the initial workflow model and its adaptation to changing requirements. To support these activities we propose to integrate techniques from machine learning into a WFMS. This enables an inductive approach to workflow acquisition and adaptation by processing traces of manually enacted workflow instances. We present a machine learning component that combines two different machine learning algorithms. In this contribution we focus mainly on the first one, which induces the structure of the workflow, based on the induction of hidden markov models. The second algorithm, a standard decision rule induction algorithm, induces transition conditions. The main concepts have been implemented in a prototype, which we have validated using artificial process traces. We demonstrate the application of our prototype using a simplified version of the release process within the product development process for the Mercedes Benz passenger cars. The workflow model induced by the prototype can be imported by the commercial business process management system ADONIS 1.

[1]  Dimitris Karagiannis,et al.  Integrating machine learning and workflow management to support acquisition and adaptation of workflow models , 2000, Intell. Syst. Account. Finance Manag..

[2]  Ludwig Nastansky,et al.  The GroupFlow Framework: Enterprise Model and Architecture of the Workflow System , 1996 .

[3]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[4]  Dimitrios Gunopulos,et al.  Mining Process Models from Workflow Logs , 1998, EDBT.

[5]  Alberto L. Sangiovanni-Vincentelli,et al.  Design management based on design traces , 1991, DAC '90.

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  Grzegorz Rozenberg,et al.  Dynamic change within workflow systems , 1995, COCS '95.

[8]  Andreas Stolcke,et al.  Best-first Model Merging for Hidden Markov Model Induction , 1994, ArXiv.

[9]  Dimitris Karagiannis,et al.  Introduction to Business Process Management Systems Concepts , 1996 .

[10]  Christoph Wargitsch,et al.  An organizational-memory-based approach for an evolutionary workflow management system-concepts and implementation , 1998, Proceedings of the Thirty-First Hawaii International Conference on System Sciences.

[11]  Fabio Casati,et al.  Workflow Evolution , 1996, ER.

[12]  Manfred Reichert,et al.  A framework for dynamic changes in workflow management systems , 1997, Database and Expert Systems Applications. 8th International Conference, DEXA '97. Proceedings.