This research introduces a novel modelling approach based on methods from feature-oriented software development, aimed at enhancing accessibility and diversity in interactive systems. The method integrates user requirements, particularly accessibility and sensitivity to diversity, into software family development. Utilizing a user model subtree, it allows for customization based on users' needs, constraints, and preferences. A prototypical demonstration is shown through a voice user interface of an assistance robot. Despite an overall satisfying success rate of 96%, results suggest the quality of configuration slightly decreases with an increasing number of user constraints. This innovative approach offers significant potential, especially given the growing need for personalized human-computer interaction in our ageing society. However, it also prompts further research questions, such as its adaptability to non-software family systems and quality of configuration via smart AI models.