What to search on, What to search for, and How to search for patents

Abstract:

Patent Information Retrieval is an economically important activity. Today's economy is becoming increasingly knowledge-based and intellectual property in the form of patents plays a vital role in this growth. According to the WIPO IP Statistics Data Centre, between 2004 and 2014, the number of patent applications filed worldwide grew by more than 70%. With the exception of 2009, the year immediately after the economic collapse, every year has shown an increase in the number of filed applications. In this talk I will present the results of our latest research project, SelfOptimizer, in the area of patent search. I have divided the work in three areas: what to search on (i.e. how to focus the search process on a subset of patents); what to search for (i.e. how to generate meaningful queries); and How to search (i.e. how to adapt the search methods to the domain).

Biography:

Mihai Lupu is the operative Data Science Studio Leader within the Research Studios Austria, and a Senior Researcher at the TU Wien. His expertise spans over 10 years and covers both academic and industry practice. He has recently been invited to talk about artificial intelligence and semantic search at the EPO Conference in Madrid in 2016 and at the International Information Conference on Search, Data Mining and Visualisation and is the Deputy Project Coordinator of the Austrian Lighthouse project Data Market Austria, funded by the Austrian Federal Ministry for Transport, Innovation and Technology. Mihai has received his PhD degree from the Singapore-MIT Alliance at the National University of Singapore, where he has worked mostly on Information Retrieval on Peer-to-Peer Networks, but also on Semantic Web techniques, as well as programming languages. Since then, he has published over 80 peer-reviewed publications, among which two editions of the Curr ent Challenges in Patent Information Retrieval book. Now, his research interests continue in the area of information retrieval, with emphasis on professional search in general intellectual property in particular.