This study aims to develop a dedicated dengue fever prediction and monitoring system for the Tainan City Government to predict dengue fever outbreaks using advanced AI technologies. We compared statistical models, linear models, machine learning (ML), and deep learning (DL) models to construct the system. We found that the Graph WaveNet (Gwinnet) model which is based on graph neural networks, performed best for predicting the total egg count. In contrast, the gradient boosting machine learning algorithm (XGBoost) was most effective for predicting the positivity rate. Using these optimal models, we successfully forecasted the total egg count and positivity rate in all regions of Tainan. The system provides a clear and user-friendly interface for the government to quickly view the relationship between the risk areas and spatially influenced factors of dengue. Using the developed real-time risk warning and monitoring system, the efficiency and effectiveness of dengue fever prevention are improved. The potential of AI technology in public health is confirmed, and the system provides a reference for future epidemic prevention efforts.