Intelligent route scheduling method for non-full-loaded vehicle based on unbalanced data mining

Aiming at the problems of long vehicle routing distance and time-consuming, high cost and low user satisfaction, an intelligent route scheduling method for non-full-loaded vehicle based on unbalanced data mining is proposed. Unbalanced data mining method is used to acquire the data information needed for the non-full-load vehicle route scheduling, and relevant data information is collected and processed through knowledge generalization. According to the mining results, the constraints and optimization objective functions of intelligent scheduling for non-full-load vehicle route scheduling are briefly analyzed. The scheduling problem is divided into single-source non-full-load time-limited scheduling and multi-source non-full-load time-limited scheduling, and the objective functions are constructed respectively. Tabu search method is designed to solve the objective function, and the optimal solution satisfying the objective function and constraints is output by constantly updating the current optimal solution, that is, the optimal solution satisfying the objective function for intelligent vehicle routing scheduling. The experimental results show that the vehicle routing mileage and travel time of the proposed scheduling method are less than the current research results, and it has the advantages of low cost and high user satisfaction.