Title:
WORK LEARNING SYSTEM, WORK DETERMINATION SYSTEM, LEARNING DEVICE, DETERMINATION DEVICE, WORK LEARNING METHOD, WORK DETERMINATION METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2023/085208
Kind Code:
A1
Abstract:
A work learning system (100) comprises: a learning device (1); a location information generation device (2) that generates location information indicating the location of a worker; a stationary/movement information generation device (3) that generates stationary/movement information indicating movement of the worker; an object information generation device (4) that generates object information indicating an object being handled by the worker; and a work information generation device (5) that generates work information indicating a work classification with respect to work being performed by the worker. The learning device (1) includes: a data acquisition unit (11) that acquires the location information, the stationary/movement information, the object information, and the work information from the location information generation device (2), the stationary/movement information generation device (3), the object information generation device (4), and the work information generation device (5), respectively; and a model generation unit (12) that learns, on the basis of the location information, the stationary/movement information, the object information, and the work information, the work classification of the work being performed by the worker to generate a learned model.
Inventors:
TAMAKI TETSUYA (JP)
HATTA TOSHIYUKI (JP)
HATTA TOSHIYUKI (JP)
Application Number:
PCT/JP2022/041162
Publication Date:
May 19, 2023
Filing Date:
November 04, 2022
Export Citation:
Assignee:
MITSUBISHI ELECTRIC CORP (JP)
International Classes:
G06N20/00; G06T7/00; G06T7/20
Foreign References:
| JP2019101516A | 2019-06-24 | |||
| JP2017010186A | 2017-01-12 |
Other References:
MATSUMURA, YUKI ET AL.: "Intention Estimation of Workers Based on Tracking of Implementation Process Using Objects and Their Positions as Clues", IEICE TECHNICAL REPORT, vol. 117, no. 483, 1 March 2018 (2018-03-01), pages 41 - 46, XP009545610
Attorney, Agent or Firm:
KIMURA Mitsuru (JP)
Download PDF: