To fully realise the potential of web services it is necessary to develop viable dynamic discovery and composition techniques. Matchmaking is considered as one of the crucial factors to ensure dynamic discovery and composition of web services. Current matchmaking methods are inadequate given their inability to abstract and classify the underlying data of web services. Instead, they classify web services based on the capability of services, software signatures, and so on. This paper proposes a novel framework which exploits fuzzy logic in order to abstract and classify the underlying data of web services as fuzzy terms and rules. The aim is to increase the efficiency of the discovery of web services and to allow imprecise or vague terms in the search query.