Skip to content
View Woo-Chul's full-sized avatar
  • 슈퍼웬즈데이, 한국특허정보원
  • 대전

Block or report Woo-Chul

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Woo-Chul/README.md

Sim WooChul

AI Research Engineer focused on NLP, Patent Search, and Deep Learning.
7+ years of experience in research and applied machine learning.


Research Interests

  • Patent Retrieval & Semantic Search
  • Korean NLP & Tokenization
  • Transformer-based Models and LLMs
  • Name Disambiguation / Entity Resolution

Selected Work

  • (2019) Research on an Automated IPC Classification Recommendation System for Korean Patents
  • (2020) Research on Korean Patent Language Models and NER for Composition and Physical Properties in Chemical Patents
  • (2021) Research and Development of an Automated CPC Classification Recommendation System for Korean Patents
  • (2022) Research on a Weak Signal Detection System for Automatically Identifying High-Value Patents
  • (2023) Research and Development of an AI-based Trademark Name Similarity Search System
  • (2024) Research on Performance Enhancement of an Automated CPC Classification Recommendation System
  • (2025) Research on Constructing Korean Search Training Datasets to Improve AI-based Patent Search Systems

→ Details: Research Archive


Publications & Papers

  • An Automatic Patent Classification Method Considering the Hierarchical Feature of CPC
  • An automatic patent classification method using a CPC generation filter
  • A Study on Judging Phonetic Similarities for Trademark Searches by Focusing on Enhancing the Search Precision of Korean and English Character Trademarks
  • A Study on the Automatic Classification of CPC Considering the Characteristics of Korean Patent Documents and Deep Learning-based Classification Model
  • A Study on Automatic CPC Classification based on Korean Patent Sentence ―A Deep Learning Approach using Artificial Intelligence Language Model KorPatBERT
  • Patent Tokenizer: a research on the optimization of tokenize for the Patent sentence using the Morphemes and SentencePiece
  • Hybrid Approach Combining Deep Learning and Rule-Based Model for Automatic IPC Classification of Patent Documents

Technical Stack

  • Languages: Python
  • ML/DL: PyTorch, HuggingFace, JAX
  • NLP: Custom Korean Tokenizer, BERT-based Models
  • Search: FAISS, Dense Retrieval
  • Infra: Linux, Docker

Background

  • M.S. in Artificial Intelligence
  • Research & Development (2019–Present)
  • Development (2015–2019)

Contact

Popular repositories Loading

  1. RnD-Patent RnD-Patent Public

    인공지능 연구 - 특허 정보 분야

    1

  2. Woo-Chul Woo-Chul Public

    심우철