[Back]

C. Dorn, C. Marin, N. Mehandjiev, S. Dustdar:
"Self-learning Predictor Aggregation for the Evolution of People-Driven Ad-Hoc Processes";
Talk: Business Process Management 9th International Conference (BPM 2011), Clermont-Ferrand, France; 2011-08-30 - 2011-09-02; in: "Business Process Management Proceedings of the 9th International Conference (BPM 2011)", S. Rinderle-Ma, F. Toumani, K. Wolf (ed.); Springer, LNCS 6896 (2011), ISBN: 978-3-642-23058-5; 215 - 230.

Contemporary organisational processes evolve with people´s
skills and changing business environments. For instance, process documents
vary with respect to their structure and occurrence in the process.
Supporting users in such settings requires sophisticated learning mechanisms
using a range of inputs overlooked by current dynamic process
systems. We argue that analysing a document´s semantics is of uttermost
importance to identify the most appropriate activity which should
be carried out next. For a system to reliably recommend the next steps
suitable for its user, it should consider both the process structure and the
involved documents´ semantics. Here we propose a self-learning mechanism
which dynamically aggregates a process-based document prediction
with a semantic analysis of documents. We present a set of experiments
testing the prediction accuracy of the approaches individually then compare
them with the aggregated mechanism showing a better accuracy.

document analysis, process recommendation, people-driven ad-hoc processes, document and process evolution.

Project Head Schahram Dustdar:
Commius