Business organizations achieve their mission by performing a number of processes. These span from simple sequences of actions to complex structured sets of activities with complex interrelation among them. The field of Business Processes Management studies how to describe, analyze, preserve and improve processes. In particular the subfield of Process Mining aims at inferring a model of the processes from logs (i.e. the collected records of performed activities). Moreover, processes can change over time to reflect mutated conditions, therefore it is often necessary to update the model. We call this activity Incremental Process Mining. To solve this problem, we modify the process mining system DPML to obtain IPM (Incremental Process Miner), which employs a subset of the SCIFF language to represent models and adopts techniques developed in Inductive Logic Programming to perform theory revision. The experimental results show that is more convenient to revise a theory rather than learning a new one from scratch.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
|Titolo:||Incremental Declarative Process Mining|
|Autori interni:||CATTAFI, Massimiliano|
|Data di pubblicazione:||2010|
|Serie:||STUDIES IN COMPUTATIONAL INTELLIGENCE|
|Appare nelle tipologie:||02.1 Contributo in volume (Capitolo, articolo)|