Intelligent Scheduling Enhancement Technology for Optimizing Tobacco Production Supply Chain Based on AI

In order to improve the scheduling optimization capability of the tobacco production supply chain, a data-driven intelligent scheduling approach is adopted to construct an optimization model, and dynamic scheduling optimization is carried out based on deep reinforcement learning and genetic algorithm. The study analyzes the performance of the scheduling system on indicators such as order fulfillment rate, inventory turnover, transportation cost and production energy consumption. The results show that the method can improve supply chain operation efficiency, reduce resource consumption, optimize logistics scheduling, and provide scientific and effective scheduling strategies for supply chain management in the tobacco industry.