Natural Language based On-demand Service Composition

Florin-Claudiu Pop (1) , Marcel Cremene (1) , Jean-Yves Tigli (2) , Stéphane Lavirotte (2) , Michel Riveill (2) , Mircea Vaida (1)

1 LCI - Computer Science Research Laboratory [Cluj-Napoca]
2 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe RAINBOW

The widespread of Web services in the ubiquitous computing era and the impossibility to predict a priori all possible user needs generates the necessity for on-demand service composition. Natural language is one of the the easiest ways for a user to express what he expects regarding a service. Two main problems need to be solved in order to create a composite service to sat- isfy the user: a)retrieval of relevant services and b) orchestration/composition of the selected services in order to fulfill the user request. We solve the first problem by using semantic concepts associated with the services and we define a conceptual distance to measure the similarity between the user request and a service configuration. Retrieved services are composed, based on aspect ori- ented templates called Aspects of Assembly. We have tested our application in an environment for pervasive computing called Ubiquarium, where our system composes a service according to the user request described by a sentence. The implementation is based on the WComp middleware that enables us to use regular Web services but also Web services for devices.

Domaines: Génie logiciel [cs.SE]

Florin-Claudiu Pop, Marcel Cremene, Jean-Yves Tigli, Stéphane Lavirotte, Michel Riveill, et al.. Natural Language based On-demand Service Composition. International Journal of Computers, Communications and Control, 2010, pp.871-883. ⟨hal-00564613⟩