Adaptive composition of conversational services through graph planning encoding

  • Authors:
  • Pascal Poizat;Yuhong Yan

  • Affiliations:
  • University of Evry Val d'Essonne, Evry, France and LRI, UMR, CNRS, Orsay, France;University of Evry Val d'Essonne, Evry, France and LRI, UMR, CNRS, Orsay, France

  • Venue:
  • ISoLA'10 Proceedings of the 4th international conference on Leveraging applications of formal methods, verification, and validation - Volume Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Service-Oriented Computing supports description, publication, discovery and composition of services to fulfil end-user needs. Yet, service composition processes commonly assume that service descriptions and user needs share the same abstraction level, and that services have been pre-designed to integrate. To release these strong assumptions and to augment the possibilities of composition, we add adaptation features into the service composition process using semantic structures for exchanged data, for service functionalities, and for user needs. Graph planning encodings enable us to retrieve service compositions efficiently. Our composition technique supports conversations for both services and user needs, and it is fully automated thanks to a tool, pycompose, which can interact with state-of-the-art graph planning tools.