The design of a product requires to satisfy a large number of design rules so as to avoid design errors. [Problem] Although there are numerous technological alternatives for managing knowledge, design departments continue to store design rules in nearly unusable documents. Indeed, existing propositions based on basic information retrieval techniques applied to unstructured engineering documents do not provide good results. Conversely, the development and management of structured ontologies are too laborious. [Proposition] We propose a property graph data model that paves the way to a context-aware design assistant. The property graph data model is a graph-oriented data structure that enables us to formally define a design context as a consolidated set of five sub-contexts: social, semantic, engineering, operational IT, and traceability. [Future work] Connected to or embedded in a Computer Aided Design (CAD) environment, our context-aware design assistant will extend traditional CAD capabilities as it could, for instance, ease: 1) the retrieval of rules according to a particular design context, 2) the recommendation of design rules while a design activity is being performed, 3) the verification of design solutions, 4) the automation of design routines, etc.