EconBase
← All papers

BERT based freedom to operate patent analysis

Michael Freunek, André Bodmer

arXiv 12 Apr 2021 · cs.CL

arXiv:2105.00817 · PDF · DOI · OpenAlex · Extracted main text

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.

Citation extraction

12
references
18
in-text mentions
12
distinct cited
0
self-citations
4,074
main-text words

appendix boundary found by appendix_command · 30% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Freunek \ Bodmer (2021) `BERT based patent novelty search by training claims to their own description', arXiv preprint:2103.011261.00073100%
2Aristodemou \ Tietze (2018) `The state-of-the-art on intellectual property analytics (ipa): A literature review on artificial intelligence, machine learning…0.40511100%
3Chikkamath, Endres, Bayyapu \ Hewel (2020) `An empirical study on patent novelty detection: A novel approach using machine learning and natural language processing', 2020…0.40511100%
4Choi, Lee, Park \ Choi (2019) `Deep patent landscaping model using transformer and graph embedding', arXiv preprint:1903.058230.40511100%
5Devlin, Chang, Lee \ Toutanova (2018) `Bert: Pre-training of deep bidirectional transformers for language understanding', arXiv preprint:1810.048050.40511100%
6Krestel, Chikkamath, Hewel \ Risch (2021) `A survey on deep learning for patent analysis', World Patent Information 65, 1020350.40511100%
7Lee \ Hsiang (2020) `Patent classification by fine-tuning BERT language model', World Patent Information 61, 40.40511100%
8Lee \ Hsiang (2020) `Prior art search and reranking for generated patent text', arXiv preprint:2009.091320.40511100%
9Risch, Alder, Hewel \ Krestel (2020) `PatentMatch: data for matching patent claims & prior art', arXiv preprint:2012.139190.40511100%
10Setchi, Spasić, Morgan, Harrison \ Corken (2021) `Artificial intelligence for patent prior art searching', World Patent Information 64, 1020210.40511100%

Showing the top 10 of 12 scored citations.