In modern metropolitan areas, there has always been a problem of low efficiency and resource utilization in the transportation scheduling of the transportation network, especially the frequent traffic congestion during peak hours and transportation delays caused by improper scheduling, resulting in an unreasonable scheduling system. This study establishes an intelligent scheduling system based on data analysis technology to improve the transportation efficiency of the transportation network and solve the above-mentioned problems. By collecting and integrating data from various traffic information sources such as real-time traffic flow, vehicle location, and scheduling history, and then using big data analysis methods to conduct more comprehensive data mining of traffic characteristics. Especially in the development of traffic flow prediction and optimization scheduling methods, this study also uses support vector machines. The research results are validated through simulations and practical applications. The research results show that the scheduling system significantly improves scheduling efficiency in multiple traffic scenarios, reduces average transportation time by 25%, and increases vehicle resource utilization by 30%. The scheduling system designed in this article can change the scheduling plan in real time, thereby reducing congestion levels during peak hours.