Mining user intents to compose services for end-users

Yu Zhao, Shaohua Wang, Ying Zou, Joanna Ng, Tinny Ng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

End-users repetitively perform various on-line tasks and invoke multiple web services for their re-occurring activities, such as planning a trip. Usually, end-users have to complete different tasks in order to achieve a goal, and look through large volumes of services to find the best ones that satisfy their constraints, such as a budget limit. Current approaches on service composition require programming skills and domain knowledge to accomplish goals. Moreover, existing approaches lack an automatic way to analyze end-users' goals and extract relevant tasks for achieving goals. In this paper, we provide a lightweight service composition framework for end-users with limited technical background. Our framework analyzes end-users' goals expressed in natural languages to mine tasks (e.g., plan a trip) and non-functional constraints (e.g., budget).

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE International Conference on Web Services, ICWS 2016
EditorsStephan Reiff-Marganiec
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages348-355
Number of pages8
ISBN (Electronic)9781509026753
DOIs
StatePublished - Aug 31 2016
Externally publishedYes
Event23rd IEEE International Conference on Web Services, ICWS 2016 - San Francisco, United States
Duration: Jun 27 2016Jul 2 2016

Publication series

NameProceedings - 2016 IEEE International Conference on Web Services, ICWS 2016

Other

Other23rd IEEE International Conference on Web Services, ICWS 2016
Country/TerritoryUnited States
CitySan Francisco
Period6/27/167/2/16

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Networks and Communications

Keywords

  • End-user goals and constraints
  • Natural language processing
  • Service composition
  • Web tasks

Fingerprint

Dive into the research topics of 'Mining user intents to compose services for end-users'. Together they form a unique fingerprint.

Cite this