In order to solve the impractical problem of path optimization in open-pit mines adoping equivalent haulage distance as weight coefficient, we establish an optimization modeling with the aim of minimizing transport work path to describe the stochastic fluctuation in real open-pit road network. Firstly, a calculation model of transport work is established, and then a probability optimization model based on stochastic process is proposed. Finally, the convergence speed of solution is further improved from the aspect of modifying genetic algorithm. Compared with other algorithms, the experimental results show that this algorithm can not only quickly obtain low energy consumption optimization path, but also greatly improve the convergence speed of solution. Thus the cost of the whole transport network can be reduced. The algorithm is more efficient in the process of actual scheduling.