CLLGEMApr 12, 2021

BERT based freedom to operate patent analysis

arXiv:2105.00817v21 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental application of an existing method to a domain-specific problem in patent analysis.

The paper tackled the problem of automating freedom to operate patent analysis by fine-tuning BERT on patent descriptions to match independent claims, and tested it on a specific patent class with five inventions, but did not report concrete performance numbers.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes