AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis
Patents provide inventors exclusive rights to their inventions by protecting their intellectual property rights. However, analyzing patent documents generally requires knowledge of various fields, considerable human labor, and expertise. Recent studies to alleviate this problem on patent analysis de...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9779775/ |
| _version_ | 1811257220186243072 |
|---|---|
| author | Junyoung Son Hyeonseok Moon Jeongwoo Lee Seolhwa Lee Chanjun Park Wonkyung Jung Heuiseok Lim |
| author_facet | Junyoung Son Hyeonseok Moon Jeongwoo Lee Seolhwa Lee Chanjun Park Wonkyung Jung Heuiseok Lim |
| author_sort | Junyoung Son |
| collection | DOAJ |
| description | Patents provide inventors exclusive rights to their inventions by protecting their intellectual property rights. However, analyzing patent documents generally requires knowledge of various fields, considerable human labor, and expertise. Recent studies to alleviate this problem on patent analysis deal only with the analysis of claims and abstract parts, neglecting the descriptions that contain essential technical cores. Moreover, few studies use a deep learning approach to handle the entire patent analysis process, including preprocessing, summarization, and key-phrase generation. Therefore, we propose a novel multi-stage framework that can aid in analyzing patent documents by using the description part of the patent rather than abstracts or claims with deep learning. The framework comprises two stages: key-sentence extraction and key-phrase generation tasks. These stages are based on the T5 model structure, transformer-based architecture that uses a text-to-text approach. To further improve the framework’s performance, we employed two key factors: i) post-training the model with a patent-related raw corpus for encouraging the model’s comprehension of the patent domain, and ii) utilizing a text rank algorithm for efficient training based on the priority score of each sentence. We verified that our key-phrase generation method of the framework shows higher performance in both superficial and semantic evaluation than other extraction methods. In addition, we provided the validity and effectiveness of our methods through quantitative and qualitative analysis, demonstrating the practical functionality of our methods. We also provided a practical contribution to the patent analysis by releasing the framework as a demo system. |
| first_indexed | 2024-04-12T17:54:06Z |
| format | Article |
| id | doaj.art-ce0e409118194391bf56e3898832c15d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T17:54:06Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ce0e409118194391bf56e3898832c15d2022-12-22T03:22:25ZengIEEEIEEE Access2169-35362022-01-0110592055921810.1109/ACCESS.2022.31768779779775AI for Patents: A Novel Yet Effective and Efficient Framework for Patent AnalysisJunyoung Son0https://orcid.org/0000-0002-4142-6927Hyeonseok Moon1https://orcid.org/0000-0002-0841-4262Jeongwoo Lee2Seolhwa Lee3https://orcid.org/0000-0002-8109-8497Chanjun Park4https://orcid.org/0000-0002-7200-9632Wonkyung Jung5Heuiseok Lim6https://orcid.org/0000-0002-9269-1157Department of Computer Science and Engineering, Korea University, Seoul, Republic of KoreaDepartment of Computer Science and Engineering, Korea University, Seoul, Republic of KoreaHuman-Inspired AI Research Institute, Seoul, Republic of KoreaDepartment of Computer Science, University of Copenhagen, Copenhagen, DenmarkDepartment of Computer Science and Engineering, Korea University, Seoul, Republic of KoreaLG Innotek, Seoul, Republic of KoreaDepartment of Computer Science and Engineering, Korea University, Seoul, Republic of KoreaPatents provide inventors exclusive rights to their inventions by protecting their intellectual property rights. However, analyzing patent documents generally requires knowledge of various fields, considerable human labor, and expertise. Recent studies to alleviate this problem on patent analysis deal only with the analysis of claims and abstract parts, neglecting the descriptions that contain essential technical cores. Moreover, few studies use a deep learning approach to handle the entire patent analysis process, including preprocessing, summarization, and key-phrase generation. Therefore, we propose a novel multi-stage framework that can aid in analyzing patent documents by using the description part of the patent rather than abstracts or claims with deep learning. The framework comprises two stages: key-sentence extraction and key-phrase generation tasks. These stages are based on the T5 model structure, transformer-based architecture that uses a text-to-text approach. To further improve the framework’s performance, we employed two key factors: i) post-training the model with a patent-related raw corpus for encouraging the model’s comprehension of the patent domain, and ii) utilizing a text rank algorithm for efficient training based on the priority score of each sentence. We verified that our key-phrase generation method of the framework shows higher performance in both superficial and semantic evaluation than other extraction methods. In addition, we provided the validity and effectiveness of our methods through quantitative and qualitative analysis, demonstrating the practical functionality of our methods. We also provided a practical contribution to the patent analysis by releasing the framework as a demo system.https://ieeexplore.ieee.org/document/9779775/Deep learningkey-sentence extractionkeyword extractionpatentpatent analysispost training |
| spellingShingle | Junyoung Son Hyeonseok Moon Jeongwoo Lee Seolhwa Lee Chanjun Park Wonkyung Jung Heuiseok Lim AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis IEEE Access Deep learning key-sentence extraction keyword extraction patent patent analysis post training |
| title | AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis |
| title_full | AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis |
| title_fullStr | AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis |
| title_full_unstemmed | AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis |
| title_short | AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis |
| title_sort | ai for patents a novel yet effective and efficient framework for patent analysis |
| topic | Deep learning key-sentence extraction keyword extraction patent patent analysis post training |
| url | https://ieeexplore.ieee.org/document/9779775/ |
| work_keys_str_mv | AT junyoungson aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis AT hyeonseokmoon aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis AT jeongwoolee aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis AT seolhwalee aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis AT chanjunpark aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis AT wonkyungjung aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis AT heuiseoklim aiforpatentsanovelyeteffectiveandefficientframeworkforpatentanalysis |