In recent years, the rapid advancement of computing power networks and computing-network integration has made the coordinated scheduling of network and computing resources a critical component of next-generation information infrastructure. Resource scheduling in cloud-edge-end collaborative environments exhibits high heterogeneity, strong coupling, and dynamic complexity. This challenges traditional optimization methods, such as mathematical programming and heuristic algorithms, by introducing modeling difficulties and real-time limitations in large-scale, complex scenarios. However, the introduction of reinforcement learning, graph neural networks, and large models into computing network resource scheduling has successfully advanced scheduling mechanisms toward intelligence, adaptability, and cross-scenario generalization. This paper systematically reviews optimal allocation methods for computing network resources, categorizes and summarizes research progress in traditional optimization methods, reinforcement learning approaches, graph neural network methods, and large-model techniques, and compares the capability boundaries of these methods. Finally, it discusses current research challenges and future development trends.