Assessing Patent Value through Advanced Text Analytics

Patent, as an intellectual property, got tremendous attention lately from the technological companies, who are filing more and more patents, evidently to realize a rich portfolio. It serves both the defensive and the license revenue generating purposes. But, along with that, the portfolio management is also becoming difficult. One of the major challenges in this regard is to identify a small set of patents that are highly innovative and hence, are valuable in the technology market in terms of licensability. Again, a large fraction of recent patents are software or business method kinds, for which the novelty or the innovation is difficult to assess. Hence, an automated or semi-automated software system is required that can employ a ranking mechanism for patents. Unfortunately, no such system exists. The existing patent software systems, mostly web-based, provide the following services: patent data feeds, structured or unstructured search platform on patents, portfolio analysis, like, comparison among different assignees patent strength, or patent visualization, like patent citation graph, etc. These services are helpful for prior search or analyzing assignees market strength; yet, not capable to provide any insight to compare the novelty among a set of patents. Therefore, identifying patents that have high license potential, is still, predominately, a manual, laborious and time-consuming process. In this research, we proposed a patent ranking method that is very suitable for ranking software or business-method kind of patents. It adopts information retrieval methodologies that use text from the patent claim sections to rank the patents based on their novelty. Moreover, it provides user interaction provisions in all critical steps of the ranking to fine tune the rank results. This method also employs innovative visualization tools to assist the users in understanding the salient features of a patent. We implemented the proposed method to build a patent ranking tool, named COA (Claim Originality Analysis) and subsequently, used it in analyzing IBM’s patent portfolio. Our experiments and analyses show that COA is very effective in identifying innovative patents in a very short time and effort.

By: Mohammad Hasan, W. Scott Spangler

Published in: Proceedings of the 11th International Conference on Artificial Intelligence and Law. , ACM, p.191-2 in 2007


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to .