Claim Breadth Model
contributors: Google Patents, Otto Stegmaier, Vihang Mehta, Darío Hereñú
tags: machine learning, claim breadth, classification
terms of_use: http://www.apache.org/licenses/LICENSE-2.0
description: We demonstrate a machine learning (ML) based approach to estimating claim breadth, which has the ability to capture more nuance than a simple word count model. While our approach may be an improvement over simpler methods, it is still imperfect and does not account for any semantic meaning within the text of the claim. This is not intended to be a recommendation on how to measure claim breadth, but instead we aim to spark academic and corporate interest in using the large amounts of public patent data in BigQuery to further the state of the art in patent research.
last edit: Fri, 01 Dec 2023 12:21:25 GMT