How to Kill a Patent with Python

Open Data
Location: F150
Tags: patents, nlp, graphs
Average rating: ****.
(4.00, 2 ratings)

When faced with a patent case, it is essential to find “prior art” – patents and publications that describe a technology before a certain date. The problem is that the indexing mechanisms for patents and publications are not as good as they could be, making good prior art searching more of an art than a science. We can apply some of our natural language processing and “big data” techniques to the US patent database, getting us better results more quickly.

  • Part I: The USPTO as a data source. The full-text of each patent is available from the USPTO (and now from Google.) What does this data look like? How can it be harvested and normalized to create data structures that we can work with?
  • Part II: Once the patents have been cleaned and normalized, they can be turned into data structures that we can use to evaluate their relationship to other documents. This is done in two ways – by modeling each patent as a document vector and a graph node.
  • Part IIA: Patents as document vectors. Once we have a patent as a data structure, we can treat the patent as a vector in an n-dimensional space. In moving from a document into a vector space, we will touch on normalization, stemming, TF/IDF, Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA).
  • Part IIB: Patents as technology graphs. This will show building graph structures using the connections between patents – both the built-in connections in the patents themselves as well as the connections discovered while working with the patents as vectors. We apply some social network analysis to partition the patent graph and find other documents in the same technology space.
  • Part III: What have we built? Now that we have done all this analysis, we can see some interesting things about the patent database as a whole. How does the patent database act as a map to the world of technology? And how has this helped with the original problem – finding better prior art?
Photo of Van Lindberg

Van Lindberg


Van Lindberg is a member at Dykema, where he focuses on intellectual property matters. Van specializes in the intersection of technology and law, with particular expertise in the area of open source. Over his career, he has helped businesses with everything from open source compliance to business strategy and represents companies in high-stakes IP litigation and inter partes review proceedings before the Patent Trial and Appeal Board. Van has represented companies on Capitol Hill, before Congress, and in industry associations; has led teams through successful mergers and acquisitions and restructurings; and has organized employee agreements to create greater employee satisfaction and promote higher compliance with internal policies. Previously, he was vice president and associate general counsel for Rackspace, where he set the strategy and policy around patent, copyright, trademark, trade secret, and open source matters. Van is a regular speaker on everything from community dynamics to graph theory and has testified in Congressional proceedings as an expert on both copyright and encryption policy. In 2012, he was named one of “America’s top 12 techiest attorneys” by the American Bar Association Journal. He is the author of Intellectual Property and Open Source.

Comments on this page are now closed.


Bryan Davis
07/28/2011 4:27pm PDT

Van was able to touch on some great material, but unfortunately he had about 2 hours worth of topics compressed into his 40 minute time slot.