An integrated approach of knowledge extraction and ontology-based reasoning for green building evaluation and electricity efficiency

Introduction Promoting green building practices is essential in addressing climate change and achieving sustainable development goals. Green building evaluation plays a critical role in assessing building performance across multiple criteria, including electricity efficiency, environmental protection, and occupant wellbeing. However, existing evaluation methods are often manual, subjective, and heavily reliant on expert judgment. Methods This study proposes an intelligent and automated approach to green building evaluation by integrating knowledge extraction and ontology development. Using advanced natural language processing (NLP) and machine learning techniques, relevant knowledge is extracted from diverse sources, including regulatory documents, building standards, and academic literature. The structured knowledge is then formalized into an ontology using Protégé, enabling the application of Semantic Web Rule Language (SWRL) rules for comprehensive evaluation. Results The proposed method enables the systematic and automated assessment of green building performance with a focus on electricity efficiency. It significantly improves the objectivity, accuracy, and scalability of the evaluation process compared to traditional expert-driven methods. Discussion This research demonstrates the potential of combining semantic technologies and machine learning for sustainable building assessment. The framework supports more consistent and efficient evaluations, providing a scalable tool for policymakers, developers, and sustainability assessors. Future work may extend the ontology to include dynamic sensor data and real-time monitoring.