Personalised federated patent Search - PerFedPat

Patent search is an economically important problem, central to the R&D operations of many industries including pharmaceuticals, biotechnology, automotive and many more. Besides the economic interest, from a technological perspective, patent search reveals important challenges for the field of information access. This is because it has important differences (lengthy search sessions, demand for high recall, high value documents) despite it shares a number of important characteristics with web search.

The PerFedPat project aims to research into a new generation of advanced patent search systems for the patent related industries and the whole spectrum of patent users by designing a new exciting framework for integrating multiple patent data sources, patent search tools and UIs. The iPerFedPat system, which will be the main result of the project, will have a pluggable architecture, providing core services and operations being able to integrate multiple patent data sources and patent related data streams, thus providing multiple patent search tools and UIs while hiding complexity from the end user. At the core of the system’s architecture lies the idea of Personalised Federated Search. In iPerFedPat federated search is used as a method for retrieving information from distributed data sets into user’s workbench, possibly operate and/or integrate, and finally deliver to the patent users for using them in a parallel, coordinated way. As a result the iPerFedPat system will be able to provide a rich, personalised information seeking experience for different types of patent search types, potentially exploiting techniques from diverse areas such as distributed information retrieval, machine learning  and human-computer interaction.