Multilayer Collection Selection and Search of Topically Organized Patents
Michail Salampasis, Anastasia Giachanou, George Paltoglou · 2013
We present a patent search system that explores three issues: (a) topical organization of patents based on their IPC, (b) collection selection of topically organised patent collections and (c) integration of collection selection tools to patent search systems. Patent documents produced worldwide have manually-assigned classification codes which in our work are used to cluster, distribute and index patents through hundreds or thousands of sub-collections. We propose a new collection selection method suitable for search systems having documents organized using hierarchical classification schemes such as IPC/CPC. The new method uses multiple evidence utilising, for each collection, the ranking of ancestors collections in higher level of the classification hierarchy. We tested our method on CLEF-IP 2011 and compared its performance to state-of-the-art collection selection algorithms. We also integrated this method as a component suggesting patent collections in the iPerFedPat patent search system. 1