Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model

The global competition for technological supremacy is intensifying, prompting every country to focus on securing technological advantages through patent acquisition. In this environment, efficient and accurate patent searching is a key factor for establishing national technological sovereignty and s...

Full description

Saved in:
Bibliographic Details
Main Authors: Jaeok Min, Hansung Noh, Minhak Kwak, Solbin Hwang, Taehoon Kim
Format: Article
Language:English
Published: Korea Institute of Intellectual Property 2025-03-01
Series:Journal of Intellectual Property
Subjects:
Online Access:https://jip.or.kr/2001-04/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850143582870044672
author Jaeok Min
Hansung Noh
Minhak Kwak
Solbin Hwang
Taehoon Kim
author_facet Jaeok Min
Hansung Noh
Minhak Kwak
Solbin Hwang
Taehoon Kim
author_sort Jaeok Min
collection DOAJ
description The global competition for technological supremacy is intensifying, prompting every country to focus on securing technological advantages through patent acquisition. In this environment, efficient and accurate patent searching is a key factor for establishing national technological sovereignty and strengthening global competitiveness. However, identifying prior art patents accurately and effectively within vast patent data remains a challenging task. To address this challenge, this study proposes an advanced patent search model that leverages artificial intelligence technology. This study presents a method for creating models according to the CPC classification model based on the KorPatBERT(Korean Patent BERT) that can deeply understand the detailed technical context of patent documents through pre-training involving vast patent data. Furthermore, this study presents a method for generating high-dimensional document embedding vectors that can effectively reflect the technical subject and context of patent documents and a method for building a search system capable of processing large volumes of patent data in real time. By integrating the proposed patent search model into this system, the study successfully demonstrated improved search performance compared with existing methods in objective performance evaluations. This study can contribute toward enhancing industrial applicability and practical usability by applying the processes of currently operational patent search data and systems. The current study’s findings are expected to provide a foundation for nations and companies to continuously lead innovation and efficiently manage and utilize patents.
format Article
id doaj-art-7ebf3725b87f4048ac4343f367deec7c
institution OA Journals
issn 1975-5945
2733-8487
language English
publishDate 2025-03-01
publisher Korea Institute of Intellectual Property
record_format Article
series Journal of Intellectual Property
spelling doaj-art-7ebf3725b87f4048ac4343f367deec7c2025-08-20T02:28:40ZengKorea Institute of Intellectual PropertyJournal of Intellectual Property1975-59452733-84872025-03-012018911710.34122/jip.2025.20.1.89Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification ModelJaeok Min0https://orcid.org/0000-0003-0436-164XHansung Noh1Minhak Kwak2Solbin Hwang3Taehoon Kim4Ph.D. Candidate, Dept. of Intellectual Property Convergence, Chungnam National University, Republic of Korea; Intelligent Information Strategy Dept., Korea Institute of Patent Information, Republic of KoreaPh.D. Candidate, Dept. of Intellectual Property Convergence, Chungnam National University, Republic of Korea; Intelligent Information Strategy Dept., Korea Institute of Patent Information, Republic of KoreaIntelligent Information Strategy Dept., Korea Institute of Patent Information, Republic of KoreaIntelligent Information Strategy Dept., Korea Institute of Patent Information, Republic of KoreaProfessor, Dept. of Electric, Electronic & Communication Engineering Education, College of Education, Chungnam National University, Republic of KoreaThe global competition for technological supremacy is intensifying, prompting every country to focus on securing technological advantages through patent acquisition. In this environment, efficient and accurate patent searching is a key factor for establishing national technological sovereignty and strengthening global competitiveness. However, identifying prior art patents accurately and effectively within vast patent data remains a challenging task. To address this challenge, this study proposes an advanced patent search model that leverages artificial intelligence technology. This study presents a method for creating models according to the CPC classification model based on the KorPatBERT(Korean Patent BERT) that can deeply understand the detailed technical context of patent documents through pre-training involving vast patent data. Furthermore, this study presents a method for generating high-dimensional document embedding vectors that can effectively reflect the technical subject and context of patent documents and a method for building a search system capable of processing large volumes of patent data in real time. By integrating the proposed patent search model into this system, the study successfully demonstrated improved search performance compared with existing methods in objective performance evaluations. This study can contribute toward enhancing industrial applicability and practical usability by applying the processes of currently operational patent search data and systems. The current study’s findings are expected to provide a foundation for nations and companies to continuously lead innovation and efficiently manage and utilize patents.https://jip.or.kr/2001-04/intellectual property rightspatentkorpatbertartificial intelligenceprior-art patentcpcpatent classificationpatent searchembedding vector
spellingShingle Jaeok Min
Hansung Noh
Minhak Kwak
Solbin Hwang
Taehoon Kim
Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model
Journal of Intellectual Property
intellectual property rights
patent
korpatbert
artificial intelligence
prior-art patent
cpc
patent classification
patent search
embedding vector
title Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model
title_full Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model
title_fullStr Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model
title_full_unstemmed Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model
title_short Improving the Performance of a Korean Patent Document Search Model using KorPatBERT-based CPC Classification Model
title_sort improving the performance of a korean patent document search model using korpatbert based cpc classification model
topic intellectual property rights
patent
korpatbert
artificial intelligence
prior-art patent
cpc
patent classification
patent search
embedding vector
url https://jip.or.kr/2001-04/
work_keys_str_mv AT jaeokmin improvingtheperformanceofakoreanpatentdocumentsearchmodelusingkorpatbertbasedcpcclassificationmodel
AT hansungnoh improvingtheperformanceofakoreanpatentdocumentsearchmodelusingkorpatbertbasedcpcclassificationmodel
AT minhakkwak improvingtheperformanceofakoreanpatentdocumentsearchmodelusingkorpatbertbasedcpcclassificationmodel
AT solbinhwang improvingtheperformanceofakoreanpatentdocumentsearchmodelusingkorpatbertbasedcpcclassificationmodel
AT taehoonkim improvingtheperformanceofakoreanpatentdocumentsearchmodelusingkorpatbertbasedcpcclassificationmodel