The capacity to create innovative Business Models (BM) has become the foundation for numerous businesses. Business Model Innovation (BMI) grows more significant as digitalization influences our everyday lives and prompts the development of better approaches for working, imparting and collaborating in this computerized universe of Industry 4.0. In this paper we present a conceptual architecture which can be applied in the modern video-conference systems with the help of semantic segmentation. The scene represents an environment, intended for discussion of ideas in business modeling. The semantic segmentation allows each pixel of an image (or video) from the scene to be related or classified to a specific type of object. In this way it is possible to interpret the description of a scene by the machine. Thus, with the help of the proposed architecture, the processes taking place between objects and people in the surrounding environment can be analyzed for the purpose of digitization of BMI by modelling human behavior and cognitive processes into logical expressions that can be digitized and automated. The semantic segmentation is considered as a basic element in this type of interaction. We demonstrate the effectiveness of our algorithm in with real data examples.