16 124 818 livres à l’intérieur 175 langues
2 047 051 livres numériques à l’intérieur 101 langues
Cela ne vous convient pas ? Aucun souci à se faire ! Vous pouvez renvoyer le produit dans les 30 jours
Impossible de faire fausse route avec un bon d’achat. Le destinataire du cadeau peut choisir ce qu'il veut parmi notre sélection.
Politique de retour sous 30 jours
Internet helps us to get all the required information; but the question is that whether the retrieved information is relevant or not. Query recommendation system helps user in finding the accurate information from the Web corpus efficiently. Search engine is used when user know their actual query. User prefers to use recommendation system when they don't know what query must be fired to search engine. Thus query recommendation assists the learner to satisfy the information need at very initial stage. Many researchers have presented different methods for recommendation based on history of user, navigational patters, query flow graph, query similarity, user previous query, click behaviors, history of snippets for information retrieval. But sometimes these methods fail to retrieve the proper recommendation for low frequency queries. The presented method for URL recommendation uses snippets, user preference, location and the synonyms to recommend better results. The performances of the systems are measured on the basis of precision and recall. The method works better and effective for all high and low frequency queries.