Federated Learning （FL） is a distributed machine learning method that utilizes distributed data for model training while ensuring data privacy. However， it performs poorly in scenarios with highly heterogeneous data distributions. Personalized Federated Learning （PFL） addresses this challenge by providing personalized models for each client. However， the previous PFL algorithms primarily focus on optimizing client local models， while ignoring optimization of server global model. Consequently， server computational resources are not utilized fully. To overcome these limitations，FedPASD， a PFL method based on model pre-assignment and self-distillation， was proposed. FedPASD was operated in both server-side and client-side aspects. On server-side， client models for the next round were pre-assigned targetedly， which not only enhanced model personalization performance， but also utilized server computational resources effectively. On client-side， models were trained hierarchically and fine-tuned using self-distillation to better adapt to local data distribution characteristics. Experimental results on three datasets， CIFAR-10，Fashion-MNIST， and CIFAR-100 of comparing FedPASD with classic algorithms such as FedCP （Federated Conditional Policy），FedPAC （Personalization with feature Alignment and classifier Collaboration）， and FedALA （Federated learning with Adaptive Local Aggregation） as baselines demonstrate that FedPASD achieves higher test accuracy than those of baseline algorithms under various data heterogeneity settings. Specifically，FedPASD achieves a test accuracy improvement of 29.05 to 29.22 percentage points over traditional FL algorithms and outperforms the PFL algorithms by 1.11 to 20.99 percentage points on CIFAR-100 dataset； on CIFAR-10 dataset，FedPASD achieves a maximum accuracy of 88.54%.