Automated Recognition and Control of Human Interaction by Video Image

   The purpose of research is to increase the efficiency of recognition and control of interaction between buyers and sellers of stores by developing a model of automated recognition and control of human interaction by video image.   Methods. The research is aimed at solving the fundamental scientific problem of developing models and methods for monitoring and recognizing human interaction by video image. At the moment, the sphere of trade is  rapidly developing, there are more and more online resources that take over a significant part of the flow of customers, and therefore, ordinary stores and shopping centers need to introduce new ways and methods of interacting with customers, and therefore provide a better service. Modern companies are trying to solve this problem in different ways: counting visitors, monitoring devices, various neural network solutions, and so on. However, none of the currently available offers on the market is able to automatically classify a person as a buyer or seller by video image, as well as to assess the degree of customer satisfaction with the service provided. To remedy this situation, methods and models have been developed that make it possible to develop software based on them, with the help of which it will be possible to determine the satisfaction of visitors and customers, recognize customers and sellers among people and determine the quality of employees' work.   Results. Models and methods for classifying customers and sellers by uniform, methods for determining the level of interaction between sellers and customers based on algorithms for determining the satisfaction of visitors andcustomers by voice and face, and algorithms for determining the quality of employees' work have been developed.   Conclusion. As a result, models have been developed that allow improving the quality of interaction between sellers and customers by video image.