The complexity of current software systems obliges software engineers to learn about the good practices employed in previous projects. The use of design patterns is not an exception, as they can provide developers with a tool to improve the reusability and modularisation of their code. In this context, this talk will introduce a three-step prototypical model aimed at supporting software engineers to implement design patterns based on previous examples and successful experiences. This model makes use of machine learning techniques like frequent pattern mining. A suitable representation of this knowledge will allow us to identify potential code chunks which might become a design pattern.