There has recently been some interest in applying machine learning techniques to support the acquisition and adaptation of workflow models. The different learning algorithms, that have been proposed, share some restrictions, which may prevent them from being used in practice. Approaches applying techniques from grammatical inference are restricted to sequential workflows. Other algorithms allowing concurrency require unique activity nodes. This contribution shows how the basic principle of our previous approach to sequential workflow induction can be generalized, so that it is able to deal with concurrency. It does not require unique activity nodes. The presented approach uses a log-likelihood guided search in the space of workflow models, that starts with a most general workflow model containing unique activity nodes.

Understanding the dynamic behavior of a workflow is crucial for being able to modify, maintain, and improve it. A particularly difficult aspect of some behavior is concurrency. Automated techniques which seek to mine workflow data logs to discover information about the workflows must be able to handle the concurrency that manifests itself in the workflow executions. This paper presents techniques to discover patterns of concurrent behavior from traces of workflow events. The techniques are based on a probabilistic analysis of the event traces. Using metrics for the number, frequency, and regularity of event occurrences, a determination is made of the likely concurrent behavior being manifested by the system. Discovering this behavior can help a workflow designer better understand and improve the work processes they are managing.

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 an approach, that induces workflow models from workflow instances. In this contribution we focus on the induction of the workflow structure and report about ongoing research in this area. We define four problem classes in terms of characteristics of the target model. For three of these classes solutions are presented. These solutions have been implemented in a research prototype, which we have validated using artificially generated workflow instances. The induced workflow models can be imported by the commercial business process management system ADONIS 1 . We also outline a solution of the fourth and most general problem class. 1 Introduction Acquisition of Workflow Models One of the most time consuming tasks within a workflow project is the acquisition of the workflow model. In v...

The online version of this article can be found at:

WPDL (Workflow Process Definition Language) is a file format for exchanging process definitions between workflow management systems (WMS) and process modeling tools. It is a standard defined by the WfMC (Workflow Management Coalition) and was published in November 1998. Unfor-tunately, WPDL in its current status (V.1.1) lacks a formal definition. This is seen as one of the main reasons why WPDL is not yet widely supported by modeling tools and WMS. This paper makes a proposal how WPDL can be formalized using graph theory. It is explained how this formal model can be used in defining the flow semantics of WPDL and transformation algorithms between the different WPDL conformance classes.

Citation for published version (APA): Maruster, L., Weijters, A., van der Aalst, W. M. P., & van den Bosch, A. (2006). A rule-based approach for

Abstract. Effective information systems require the existence of explicit process models. A completely specified process design needs to be developed in order to enact a given business process. This development is time consuming and often subjective and incomplete. We propose a method that constructs the process model from process log data, by determining the relations between process tasks. To predict these relations, we employ machine learning technique to induce rule sets. These rule sets are induced from simulated process log data generated by varying process characteristics such as noise and log size. Tests reveal that the induced rule sets have a high predictive accuracy on new data. The effects of noise and imbalance of execution priorities during the discovery of the relations between process tasks are also discussed. Knowing the causal, exclusive, and parallel relations, a process model expressed in the Petri net formalism can be built. We illustrate our approach with real world data in a case study. Keywords: rule induction, process mining, knowledge discovery, Petri nets

AND DUMITRU RĂDOIU Abstract. This paper presents a novel data mining technique, known as Post Sequential Patterns Mining. The technique can be used to discover structural patterns that are composed of sequential patterns, branch patterns or iterative patterns. The concurrent branch pattern is one of the main forms of structural patterns and plays an important role in event-based data modelling. To discover concurrent branch patterns efficiently, a concurrent group is defined and this is used roughly to discover candidate branch patterns. Our technique accomplishes this by using an algorithm to determine concurrent branch patterns given a customer database. The computation of the support for such patterns is also discussed.

A rule-based approach for process discovery Dealing with noise and imbalance in process logs