Human Work Support Technology Utilizing Sensor Data

In response to problems associated with the shortage of factory workers, the demand for efficiency maximization by eliminating wasted work has recently become stronger. Moreover, to ensure compliance with product quality, the demand for reliable work execution is also increasing. Conventionally, productivity has fallen because workers must manually enter a system to start and finish work. To circumvent this, we have developed advanced human work techniques, “automatic switching of work instruction screen” and “real-time work deviation detection”, by utilizing deep learning technology. Compared to conventional approaches, we achieved a 15% reduction in product assembly time and a deviation detection leak of almost zero (more than 95% work identification accuracy).