Abstract: A system for searching and discovering information where a first server is provided with a digital catalogue of products and is connected to a communication network. The first server communicates with a front-end client associated to an user and connected to said communication network, and with a back-end server connected to said communication network. The back-end server has in turn an indexing section for processing the data of said digital catalogue in order to extract and save relevant data of said digital catalogue in an index, and a runtime section adapted to interpret the user query on the front-end client, compare the search information and/or the user behavior with said index and send to said front-end client suggestions to the user on how to refine said query.

Abstract: A method and system for ranking search results is disclosed. Search sessions are tracked to determined accessed search results. For each accessed search result occurring across the plurality of search sessions, the accessed search result is associated with each search query having been executed within a given search session, prior to the user accessing the accessed search result. A preselection is made among the query elements forming each search query, for indexing the selected query elements. For each pairing of a query element from the preselection and an associated accessed search result, a result score is calculated. A ranking model is then generated. The ranking model contains the result score in association with the corresponding pairing, for ranking subsequent search results from subsequent search queries according to the result scores.

Abstract: A method and system for ranking search results is disclosed. Search sessions are tracked to determined accessed search results. For each accessed search result occurring across the plurality of search sessions, the accessed search result is associated with each search query having been executed within a given search session, prior to the user accessing the accessed search result. A preselection is made among the query elements forming each search query, for indexing the selected query elements. For each pairing of a query element from the preselection and an associated accessed search result, a result score is calculated. A ranking model is then generated. The ranking model contains the result score in association with the corresponding pairing, for ranking subsequent search results from subsequent search queries according to the result scores.

Abstract: A method and a related system to index voicemail documents by training a language model for a speaker or group of speakers by using existing emails and contact information on available repositories.

Abstract: A method and a related system to index audio and video documents and to automatically train the language model of a speech recognition system according to the context of the documents being indexed.