- Sensor data recognition
- Status estimation
- Numerical analysis
- Indexing
Technology for comparing the work of skilled workers and beginners
Automatically identifies skilled workers and beginners.
- Extracts elemental tasks from work data measured using acceleration sensors, etc.
- Determines whether data input using neural networks with attention mechanisms are from skilled workers or beginners. Also extracts elemental tasks with high dependency on skills at the time.
- Joint research with Osaka University
Applications
- Analyze tasks in the front lines of production.
Benchmarks, strengths, and track record
- By using neural networks equipped with attention mechanisms, this technology can extract elemental tasks with high dependency on worker skills.
- Attained outstanding results through verification using data from actual manufacturing workplaces.
Inquiries
Inquiries to the Corporate Manufacturing Engineering Center of Toshiba Corporation
Please include the title “Toshiba AI Technology Catalog: Technology for comparing the work of skilled workers and beginners” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
References:
- Qingxin Xia, Atsushi Wada, Takanori Yoshii, Yasuo Namioka, and Takuya Maekawa: Comparative Analysis of High- and Low-Performing Factory Workers with Attention-based Neural Networks, Proceedings of 18th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Nov,. 2021.