Master Thesis - Discovery of Object-Centric Local Process Models

Kontakt

Name

Viki Peeva

Wissenschaftliche Mitarbeiterin

E-Mail

E-Mail
 

Description

In the process mining community, the term event log is well-known. An event log is a multiset of traces, where each trace is a sequence of events. The popular way of thinking is that each event contains at the least three types of information: case, activity, and timestamp, as described by the XES standard (https://xes-standard.org/). However, in recent years, a new more-intuitive idea has appeared. Instead of assuming that each event is executed for a unique case, events refer to multiple objects that are intertwined. This led to the new object-centric event log standard (http://www.ocel-standard.org/), and therefore to a new type of Petri nets, object-centric Petri nets, that can model the process, together with the interaction between the different objects.

The discovery algorithms we use are orthogonal to OCELs. One branch of process discovery is local process model discovery. In contrast to process discovery, where the goal is to find one process model that explains all traces in the event log from start to end, local process model discovery aims to find a set of smaller models that describe what happens locally in the event log. The primary purpose of local process models was to give insights on event logs for which the traditional process discovery techniques failed to return a well-structured model. However, with time, the importance and application of local process models grew and became multi-fold. Now they are used for event abstraction, trace clustering, outcome prediction, etc.There exist multiple approaches for discovering local process models. One approach builds local process models by combining place nets. The place nets are accepted as input of the algorithm and are generated by an oracle. The built local process models can be filtered and sorted based on different attributes or evaluation metrics.

The goal of the thesis is to discover object-centric local process models. One direction is to use the already existing discovery algorithm but discover place nets for each object separately. The approach should be implemented as a plugin in ProM (https://www.promtools.org) and the resulting object-centric local process models should be visualized as object-centric Petri nets. This means any object-centric extensions not already implemented in ProM will have to be added. The student should evaluate the method on various real and artificial event logs.

Prerequisites

The thesis includes implementation as well as formal reasoning. Java programming skills and an interest in theoretical and practical aspects of process mining is required.

Pointers

Supervisor

Prof.dr.ir. Wil van der Aalst

Advisor

Viki Peeva

For more Information

Send an e-mail to . Make sure to include detailed information about your background and scores for completed courses.