With the rapid development of e-commerce and the intensification of market competition, intelligent logistics system plays a key role in improving logistics efficiency, reducing costs and enhancing service experience. This paper studies the intelligent logistics path planning and real-time scheduling optimization based on ant colony optimization algorithm (ACO). ACO algorithm simulates the foraging behavior of ants in nature, and shows great potential in solving complex optimization problems with its global search ability, distributed computing characteristics and good adaptability. In this paper, an ACO algorithm model which conforms to the characteristics of intelligent logistics is constructed, and the path planning and resource scheduling in the logistics system are dynamically optimized by combining real-time data and information. Through simulation research, the effectiveness of dynamic pheromone updating, adaptive volatile factor adjustment and multi-ant colony collaborative optimization strategy in improving the efficiency and accuracy of path planning and reducing the total transportation cost is verified. The experimental results show that ACO algorithm can effectively adapt to environmental changes and find an approximate optimal solution in intelligent logistics path planning. Compared with other algorithms such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), ACO algorithm shows lower transportation cost and higher time efficiency. The research in this paper provides an effective solution tool for complex logistics problems, especially for large-scale and dynamic logistics network environment.