The Promise of Machine Learning for Patent Landscaping

9 Pages Posted: 17 Mar 2020

See all articles by Andrew A. Toole

Andrew A. Toole

US Patent and Trademark Office

Nicholas A. Pairolero

United States Patent and Trademark Office

James Forman

Google

Alexander V. Giczy

United States Patent and Trademark Office

Date Written: March 2020

Abstract

Patent landscaping involves the identification of patents in a specific technology area to understand the business, economic, and policy implications of technological change. Traditionally, patent landscapes were constructed using keyword and classification queries, a labor-intensive process that produced results limited to the scope of the query. In this paper, we discuss the advantages and disadvantages of using machine learning to produce patent landscapes. Machine learning leverages traditional queries to construct the data necessary to train the machine learning models, and the models allow the resultant landscapes to extend more broadly into areas of technology not expected a priori. The models, however, are “black boxes” that limit transparency into their underlying reasoning. To illustrate these points, we summarize two landscapes we recently conducted, one in mineral mining and another in artificial intelligence.

Keywords: patent landscape, machine learning, keyword and classification search

JEL Classification: O3, C01

Suggested Citation

Toole, Andrew A. and Pairolero, Nicholas and Forman, James and Giczy, Alexander, The Promise of Machine Learning for Patent Landscaping (March 2020). USPTO Economic Working Paper No. 2020-1, Available at SSRN: https://ssrn.com/abstract=3555834 or http://dx.doi.org/10.2139/ssrn.3555834

Andrew A. Toole (Contact Author)

US Patent and Trademark Office ( email )

Alexandria
VA 22313-1451
United States

Nicholas Pairolero

United States Patent and Trademark Office ( email )

James Forman

Google ( email )

Alexander Giczy

United States Patent and Trademark Office ( email )

Alexandria
VA 22313-1451
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
129
Abstract Views
522
rank
238,833
PlumX Metrics