Parks and waterfronts quality assessment lacks systematic methodologies that integrate empirical research findings into practical evaluation frameworks. Current approaches remain fragmented, limiting comprehensive evaluation and evidence-based decision-making for these critical urban spaces. This study develops an AI-driven framework for parks and waterfronts quality assessment through algorithmic integration of empirical research findings. Using a 5-phase methodology, we transform quality factors extracted from peer-reviewed studies focused specifically on parks and waterfronts into a validated hierarchical taxonomy. The methodology combines semantic analysis, algorithmic clustering, and domain knowledge integration to address terminological variations and functional relationships. The resulting framework organizes unique quality factors across main categories and subcategories, providing systematic consistency in factor organization and theoretical alignment with established parks and waterfronts research. This research demonstrates how AI algorithms can transform fragmented empirical research into practical assessment frameworks, supporting evidence-based policy development, design quality evaluation, and systematic understanding of what creates successful parks and waterfronts.