BERT based freedom to operate patent analysis
Computation and Language
2021-05-05 v2 Machine Learning
Econometrics
Abstract
In this paper we present a method to apply BERT to freedom to operate patent analysis and patent searches. According to the method, BERT is fine-tuned by training patent descriptions to the independent claims. Each description represents an invention which is protected by the corresponding claims. Such a trained BERT could be able to identify or order freedom to operate relevant patents based on a short description of an invention or product. We tested the method by training BERT on the patent class G06T1/00 and applied the trained BERT on five inventions classified in G06T1/60, described via DOCDB abstracts. The DOCDB abstract are available on ESPACENET of the European Patent Office.
Cite
@article{arxiv.2105.00817,
title = {BERT based freedom to operate patent analysis},
author = {Michael Freunek and André Bodmer},
journal= {arXiv preprint arXiv:2105.00817},
year = {2021}
}