Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents

Patents, i.e., the output of research and development (R&D) activities, are regarded as a concentration of Problem–Solution information. Despite various patent analysis studies aimed at solving problems, large language model (LLM)-based studies are scarce. LLMs, which are effective for natural l...

Full description

Saved in:
Bibliographic Details
Main Authors: Seunghyun Lee, Jiho Lee, Seoin Park, Jae-Min Lee, Hong-Woo Chun, Janghyeok Yoon
Format: Article
Language:English
Published: Korea Institute of Intellectual Property 2024-09-01
Series:Journal of Intellectual Property
Subjects:
Online Access:https://jip.or.kr/1903-08/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312978366627840
author Seunghyun Lee
Jiho Lee
Seoin Park
Jae-Min Lee
Hong-Woo Chun
Janghyeok Yoon
author_facet Seunghyun Lee
Jiho Lee
Seoin Park
Jae-Min Lee
Hong-Woo Chun
Janghyeok Yoon
author_sort Seunghyun Lee
collection DOAJ
description Patents, i.e., the output of research and development (R&D) activities, are regarded as a concentration of Problem–Solution information. Despite various patent analysis studies aimed at solving problems, large language model (LLM)-based studies are scarce. LLMs, which are effective for natural language processing tasks, such as text summarization and generation, have been applied in numerous fields, including healthcare, finance, and law. By learning the Problem-Solution information of patents as an LLM instead of merely examining existing R&D solutions, one can generate new solutions applicable to a specified problem. Therefore, this study proposes an approach to generate and analyze new R&D solutions using LLMs. Our systematic approach involves 1) collecting numerous patents and constructing a database; 2) extracting Problem-Solution information from the Common Application Form section of patents and constructing a Problem-Solution dataset; 3) fine-tuning an LLM using the problem-solution dataset and generating R&D solutions; and 4) analyzing R&D solutions to present a technology concept portfolio map. This study extends beyond the existing R&D solution exploration, presents a new approach for generating solutions, and suggests technology concepts using LLMs. Therefore, this study contributes to the expansion of the available options and fosters innovation in R&D field.
format Article
id doaj-art-cc2b52bc8cf840ca9bf35381e0e50494
institution Kabale University
issn 1975-5945
2733-8487
language English
publishDate 2024-09-01
publisher Korea Institute of Intellectual Property
record_format Article
series Journal of Intellectual Property
spelling doaj-art-cc2b52bc8cf840ca9bf35381e0e504942025-08-20T03:52:52ZengKorea Institute of Intellectual PropertyJournal of Intellectual Property1975-59452733-84872024-09-0119315518010.34122/jip.2024.19.3.155Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of PatentsSeunghyun Lee0Jiho Lee1Seoin Park2Jae-Min Lee3Hong-Woo Chun4Janghyeok Yoon5https://orcid.org/0000-0002-8701-0695PhD Candidate, Department of Industrial Engineering, Konkuk University, Republic of KoreaDirector, AI Lab, Neopons Inc., Republic of KoreaMaster’s Student, Department of Industrial Engineering, Konkuk University, Republic of KoreaPrincipal Researcher, Future Technology Analysis Center, Korea Institute of Science and Technology Information, Republic of KoreaDirector, Future Technology Analysis Center, Korea Institute of Science and Technology Information, Republic of KoreaProfessor, Department of Industrial Engineering, Konkuk University, Republic of KoreaPatents, i.e., the output of research and development (R&D) activities, are regarded as a concentration of Problem–Solution information. Despite various patent analysis studies aimed at solving problems, large language model (LLM)-based studies are scarce. LLMs, which are effective for natural language processing tasks, such as text summarization and generation, have been applied in numerous fields, including healthcare, finance, and law. By learning the Problem-Solution information of patents as an LLM instead of merely examining existing R&D solutions, one can generate new solutions applicable to a specified problem. Therefore, this study proposes an approach to generate and analyze new R&D solutions using LLMs. Our systematic approach involves 1) collecting numerous patents and constructing a database; 2) extracting Problem-Solution information from the Common Application Form section of patents and constructing a Problem-Solution dataset; 3) fine-tuning an LLM using the problem-solution dataset and generating R&D solutions; and 4) analyzing R&D solutions to present a technology concept portfolio map. This study extends beyond the existing R&D solution exploration, presents a new approach for generating solutions, and suggests technology concepts using LLMs. Therefore, this study contributes to the expansion of the available options and fosters innovation in R&D field.https://jip.or.kr/1903-08/patent analysisproblem-solution informationr&d solutionlarge language modelfine-tuning
spellingShingle Seunghyun Lee
Jiho Lee
Seoin Park
Jae-Min Lee
Hong-Woo Chun
Janghyeok Yoon
Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents
Journal of Intellectual Property
patent analysis
problem-solution information
r&d solution
large language model
fine-tuning
title Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents
title_full Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents
title_fullStr Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents
title_full_unstemmed Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents
title_short Large Language Model-based R&D Solution Analysis Approach Using Problem-Solution Information of Patents
title_sort large language model based r d solution analysis approach using problem solution information of patents
topic patent analysis
problem-solution information
r&d solution
large language model
fine-tuning
url https://jip.or.kr/1903-08/
work_keys_str_mv AT seunghyunlee largelanguagemodelbasedrdsolutionanalysisapproachusingproblemsolutioninformationofpatents
AT jiholee largelanguagemodelbasedrdsolutionanalysisapproachusingproblemsolutioninformationofpatents
AT seoinpark largelanguagemodelbasedrdsolutionanalysisapproachusingproblemsolutioninformationofpatents
AT jaeminlee largelanguagemodelbasedrdsolutionanalysisapproachusingproblemsolutioninformationofpatents
AT hongwoochun largelanguagemodelbasedrdsolutionanalysisapproachusingproblemsolutioninformationofpatents
AT janghyeokyoon largelanguagemodelbasedrdsolutionanalysisapproachusingproblemsolutioninformationofpatents