<p>With the widespread popularity of family cars, traffic management problems are becoming increasingly complex, and a large number of real-time processing tasks have emerged in intelligent traffic management systems. To solve the task offloading decision problem in the multi-user and multi-server scenarios of intelligent transportation system, the communication model, cache model, delay model, energy consumption model, load model and multi-objective optimization task offloading model were designed, and an offloading decision scheme based on NSGA-III algorithm was proposed in this paper. The experimental results show that the proposed scheme can reduce the vehicle task offloading delay and system energy consumption of the intelligent transportation system, and has a good application prospect.</p>