Models and algorithms for managing the emotional state of customers in commercial banks using deep convolutional neural networks

In this research, a model for managing the emotional state of customers in commercial bank has been developed using deep convolutional neural network (DCNN) and algorithms distributing conflicting along routes to certain operator, depending on state. order route customer it was necessary develop mathematical target routing based Newton interpolation polynomial. The four classes [angry, happy, neutral, sad], trained tested well-known FER2013 dataset machine learning computer vision. Finally, validation accuracy 70.35% achieved.