An intelligent assistant for interactive workflow composition

ABSTRACT

Complex applications in many areas, including scientific computations and business-related web services, are created from collections of components to form computational workflows. In many cases end users have requirements and preferences that depend on how the workflow unfolds, and that cannot be specified beforehand. Workflow editors enable users to formulate workflows, but the editors need to be augmented with intelligent assistance in order to help users in several key aspects of the task, namely: 1) keeping track of detailed constraints across selected components and their connections; 2) specifying the workflow flexibly, e.g., top-down, bottom-up, from requirements, or from available data; and 3) taking partial or incomplete descriptions of workflows and understanding the steps needed for their completion. We present an approach that combines knowledge bases (that have rich representations of components) together with planning techniques (that can track the relations and constraints among individual steps). We illustrate the approach with an implemented system called CAT (Composition Analysis Tool) that analyzes workflows and generates error messages and suggestions in order to help users compose complete and consistent workflows.

REFERENCES

• 1: George Chin, Jr. , L. Ruby Leung , Karen Schuchardt , Debbie Gracio, New paradigms in problem solving environments for scientific computing, Proceedings of the 7th international conference on Intelligent user interfaces, January 13-16, 2002, San Francisco, California, USA [doi>10.1145/502716.502726]
• 2: Edge Diagrammer. http://www.pacestar.com/edge/.
• 3: KHOROS PRO 2001. http://www.khoral.com/.
• 4: GriPhyN. http://www.griphyn.org/.
• 5: Kim, J. et al. A Knowledge-Based Approach to Interactive Workflow Composition. ISI Internal Project Report, 2003.
• 6: Jihie Kim , Yolanda Gil, User studies of an interdependency-based interface for acquiring problem-solving knowledge, Proceedings of the 5th international conference on Intelligent user interfaces, p.165-168, January 09-12, 2000, New Orleans, Louisiana, United States [doi>10.1145/325737.325817]
• 7: McIlraith, S. and Son, T. Adapting Golog for programming in the semantic web. Fifth International Symposium on Logical Formalizations of Commonsense Reasoning, 2001.
• 8: McDermott, D. and Burstein, M. Extending an estimated-regression planner for multi-agent planning. AAAI Workshop on Planning by and for Multi-Agent Systems, 2002.
• 9: Myers, K., et al. A Mixed-Initiative Framework for Robust Plan Sketching. Proceedings of Int'l Conf. on Automatic Planning and Scheduling, 2003.
• 10: NVO (US National Virtual Observatory). http://www.us-vo.org/.
• 11: SCEC (Southern California Earthquake Center). http://www.scec.org/.
• 12: Smith, S., et al. Configurable mixed initiative systems for planning and scheduling. In A. Tate, editor, Advanced Planning Technology. AAAI Press, 1996.
• 13: W3C: WSDL specification. http://www.w3c.org/TR/WSDL/.
• 14: Weld, D. Recent Advances in AI Planning. AI Magazine,1999.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: User interface management systems (UIMS)

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.0 General

General Terms:
Algorithms, Human Factors, Verification

Keywords:
interactive planning, knowledge acquisition, web service composition, workflow composition, workflow editors