Recognizing emotions on human faces has always received attention and attraction from researchers. Along with the development of artificial intelligence, facial emotion recognition cameras are increasingly being introduced into various fields such as healthcare, education, and commerce. Thanks to the effective support of cameras integrated with artificial intelligence technology, the above fields are growing strongly. Therefore, this study will present an effective and simple facial emotion recognition model based on deep learning technology. Facial emotion recognition is performed automatically and accurately, thereby shortening implementation time and increasing work efficiency. In this study, the VGG-Face model is trained using the FER-2013 data set and applied to evaluate customer service quality. The input data are videos of human faces to perform emotion recognition and 7 different facial expressions have been performed recognition. Experimental results have shown the effectiveness of the model.