Abstract: Provided is a manpower management system comprising a data communication unit configured to receive motion signals from a wearable unit worn by a specific employee to sense motions of the specific employee; a data processing unit configured to label the motion signals with behavior data to generate a labeled training dataset for the specific employee; a deep learning model for the specific employee configured to be trained through machine learning using the labeled training dataset, a recognition unit configured to recognize behavior of the specific employee in response to an input of a motion signal of the specific employee received by the data communication unit, using the trained deep learning model, and output a behavior data of the specific employee; and a simulation unit configured to evaluate employee's work efficiency using the output behavior data.