A method includes, through a server, determining a context of interaction between a user of a data processing device communicatively coupled to the server through a computer network and the server, fetching a set of queries from a database associated with the server in accordance with determining the context of interaction, and loading the set of queries one by one on a first media device configured to render the set of queries in an audio, a video and/or a gesture format. The method also includes, through the server, receiving a response to a query of the set of queries from the user via the first media device and/or the data processing device, and refining the set of queries based on the response received to the query from the user in accordance with an Artificial Intelligence (AI) and/or a Machine Learning (ML) engine executing on the server.