Self-learning Predictor Aggregation for the Evolution of People-Driven Ad-Hoc Processes
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.
Keywordsdocument analysis process recommendation people-driven ad-hoc processes document and process evolution
Unable to display preview. Download preview PDF.
- 1.Adams, M., Edmond, D., ter Hofstede, A.H.M.: The application of activity theory to dynamic workflow adaptation issues. In: 7th Pacific Asia Conference on Information Systems. pp. 1836–1852 (2003)Google Scholar
- 2.Adams, M., Hofstede, A., Edmond, D., van der Aalst, W.: Facilitating flexibility and dynamic exception handling in workflows through worklets. In: Proceedings of the CAiSE 2005 Forum, FEUP. pp. 45–50 (2005)Google Scholar
- 3.Berry, M.W., Drmac, Z., Jessup, E.R.: Matrices, vector spaces, and information retrieval. Society for Industrial and Applied Mathematics Review 41(2) (1999)Google Scholar
- 4.Dorn, C., Burkhart, T., Werth, D., Dustdar, S.: Self-adjusting recommendations for people-driven ad-hoc processes. In: Proceedings of International Conference on Business Process Modelling. Springer, Heidelberg (September 2010)Google Scholar
- 7.Joseph, D., Marín, C.A.: A study on aligning documents using the circle of interest technique. In: 5th International Conference on Software and Data Technologies, pp. 374–383. SciTe Press (2010)Google Scholar
- 10.Laclavík, M., Dlugolinký, S., Šeleng, M., Kvassay, M., Hluchý, L.: Email analysis and information extraction for enterprise benefit. Computing and Informatics 30(1) (2011)Google Scholar
- 11.Lakshmanan, G.T., Duan, S., Keyser, P.T., Khalaf, R., Curbera, F.: A heuristic approach for making predictions for semi- structured case oriented business processes. In: First Workshop on Traceability and Compliance of Semi-structured Processes @BPM 2010. Springer, Heidelberg (2010)Google Scholar
- 12.Marín, C.A., Carpenter, M., Wajid, U., Mehandjiev, N.: Devolved ontology in practice for a seamless semantic alignment within dynamic collaboration networks of smes. Computing and Informatics 30(1) (2011)Google Scholar
- 13.OASIS: ebXML technical architecture specification. Tech. rep., ebXML (2001)Google Scholar
- 16.Scerri, S., Davis, B., Handschuh, S.: Improving Email Conversation Efficiency through Semantically Enhanced Email. In: Proceedings of the 18th International Conference on Database and Expert Systems Applications, pp. 490–494. IEEE Computer Society, Washington (2007)Google Scholar
- 20.UN/CEFACT: Core components technical specification – part 8 of the ebXML framework. Tech. rep., UN/CEFACT (2003)Google Scholar