Presentation 2020-12-11
How to collect teacher data for machine learning models to classify internal document know-how
Takahiro Shimura, Kohei Yabuki, Takumi Hasegawa, Shiva Krishna Maheshuni, Takeshi Mizuma,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Not many companies seem to be able to utilize the product design know-how in their internal documents across the board. The purpose of this study is to establish a method of constructing a machine learning model to classify design know-how from internal documents and to prepare the groundwork for application implementation to support cross-sectional utilization of know-how. In this paper, we describe the philosophy and implementation method of the tool we have implemented to collect teacher data for the machine learning model, and propose a formula for calculating the usefulness of know-how that allows to easily compare the quality of know-how.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Know-how / Knowledge Management / Machine Learning / Teacher Data
Paper # DC2020-62
Date of Issue 2020-12-04 (DC)

Conference Information
Committee DC
Conference Date 2020/12/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hiroshi Takahashi(Ehime Univ.)
Vice Chair Tatsuhiro Tsuchiya(Osaka Univ.)
Secretary Tatsuhiro Tsuchiya(Nihon Univ.)
Assistant

Paper Information
Registration To Technical Committee on Dependable Computing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) How to collect teacher data for machine learning models to classify internal document know-how
Sub Title (in English)
Keyword(1) Know-how
Keyword(2) Knowledge Management
Keyword(3) Machine Learning
Keyword(4) Teacher Data
1st Author's Name Takahiro Shimura
1st Author's Affiliation Kyosan Electric Manufacturing Co., Ltd.(Kyosan Electric Mfg)
2nd Author's Name Kohei Yabuki
2nd Author's Affiliation Kyosan Electric Manufacturing Co., Ltd.(Kyosan Electric Mfg)
3rd Author's Name Takumi Hasegawa
3rd Author's Affiliation Kyosan Electric Manufacturing Co., Ltd.(Kyosan Electric Mfg)
4th Author's Name Shiva Krishna Maheshuni
4th Author's Affiliation The University of Tokyo(Univ.Tokyo)
5th Author's Name Takeshi Mizuma
5th Author's Affiliation The University of Tokyo(Univ.Tokyo)
Date 2020-12-11
Paper # DC2020-62
Volume (vol) vol.120
Number (no) DC-288
Page pp.pp.18-22(DC),
#Pages 5
Date of Issue 2020-12-04 (DC)