Overview and download

Process Discovery consists of analyzing a set of traces registering the sequence of tasks performed along several enactments of a transactional system, in order to build a process model that can explain all the episodes recorded over them. The implemented approach can accomplish this task by exploiting the background knowledge that, in many cases, is available to the analysts taking care of the process (re-)design. Indeed, it is based on encoding the information gathered from the log and the (possibly) given background knowledge in terms of precedence constraints, i.e., of constraints over the topology of the resulting process models. Mining algorithms are eventually formulated in terms of reasoning problems over precedence constraints.

The algorithm has been implemented as a plug-in for the well-known process mining suite ProM. The plug-in, named CNMining, receives as input a log file in the (standard) MXML or XES format plus the constraints that users can define by using an intuitive XML-based specification language (see the section Constraints).

As output, it produces a (possibly extended) causal net that, according to the philosophy of ProM, is made available and can be re-used in the suite for subsequent elaborations. Actually, ProM deals with causal nets only (i.e., multisets of bindings are flattened), while true mined models are always exported into a file encoding dependencies and bindings (again) via an XML-based specification language. The file (ExtendedCausalNet.xml) is available in the directory where the plug-in is installed.

Furhter details are in the paper "Process Discovery under Precedence Constraints".