This study introduces an innovative approach to sustainable tourist trip planning that aligns tourists’ preferences with vital sustainability factors. Traditional methods often prioritize singular objectives, such as minimizing travel time or cost, thereby overlooking the broader sustainability implications associated with travel. To bridge this gap, we propose a multi-objective sustainability tourist trip design model that optimizes travel itineraries across various dimensions, including CO2 emissions, environmental impacts, and socio-economic benefits. To address this problem, we developed a mixed-integer programming model. Subsequently, a novel Artificial Multiple Intelligence System (AMIS) was employed. The AMIS integrates multiple intelligence systems and employs meticulously designed and effective improvement methods facilitated by adaptive heuristic learning selection procedures. We subjected the model to rigorous testing using real-world data, and our analysis underscored the superiority of our approach. It resulted in a noteworthy 22.46%–27.95% reduction in CO2 costs and a substantial 14.20% reduction in waste generation, along with a noteworthy 6.46% increase in community ownership and a 7.07% increase in cultural heritage value, compared to existing models and methods based on differential evolution algorithms, ant colony optimization, and genetic algorithms. This study contributes significantly to enhancing our understanding of the challenges and prospects inherent in integrating sustainability considerations into the design of travel itineraries.