Urban flood prevention faces challenges in real-time monitoring, data integration, and decision-making support, particularly under constraints of sensitive data security and efficient emergency response. This study proposes an artificial intelligence-assisted decision-making framework for urban flood prevention, integrating multi-dimensional data fusion via an intranet. A city-level digital twin platform is developed, combining real-time sensor data, meteorological information, and social media data using a geographic information system, the Internet of Things, and artificial intelligence algorithms. The framework ensures secure data processing through intranet-based operations, enhancing flood prediction accuracy and emergency response efficiency. The system was successfully implemented in Hebi City, Henan Province, demonstrating significant improvements in flood risk management. This research advances urban resilience and provides a scientific basis for flood management in smart cities.

Based on the data from the 2013-2014 school year of the China Education Panel Survey (CEPS), this study addresses the issue of insufficient learning capacity among left-behind children by designing and proposing a data-driven dynamic monitoring and early intervention system. The system collects and analyzes key data indicators in real-time, such as learning attitudes, teacher emotional support, and parental educational expectations, to dynamically assess the learning capacity of left-behind children. The system employs a multi-layer architecture, including infrastructure, data exchange, logical analysis, and service application layers, to facilitate easy access for rural teachers using basic internet infrastructure. The study identifies the main factors affecting the learning capacity of left-behind children and develops corresponding monitoring algorithms and models. Additionally, early intervention strategies are formulated, including learning support, psychological counseling, and family involvement, aimed at timely identification and response to learning difficulties, enhancing the learning motivation, capability, and academic performance of left-behind children. The system design considers user-friendliness, data privacy, and ethics, and ensures effectiveness and safety through integrated testing, user acceptance evaluation, and intervention effectiveness assessment. This research provides personalized educational support for left-behind children, promoting educational equity and quality improvement.