Chatbots enhanced by VR can deliver rich social cues through both verbal and non-verbal communication. While existing research emphasizes verbal factors and visual anthropomorphism, systematic exploration of body movements remains limited. This study proposes the Interactive-Cheerful-Empathic (ICE) Movements Framework, mapping body movements to three psychological needs: autonomy, competence, and relatedness. We developed a VR chatbot (Hilie) with four movement modes (interactive, cheerful, empathic, and no movement) and conducted a single-factor within-subjects experiment involving 56 university students. Quantitative and qualitative results revealed that chatbots with body movements—particularly cheerful movements—significantly enhanced users’ self-disclosure willingness, satisfaction, trust, and intention to use compared to static counterparts. The ICE framework effectively addresses multi-level psychological needs through coordinated movements. This work pioneers the operationalization of self-determination theory in chatbot design, providing theoretical models and practical guidelines for developing highly anthropomorphic chatbots, while advancing optimization strategies for online mental health services.

Federated learning is a distributed machine -learning technique that allows multiple clients to collaboratively train a model without sharing their local raw data. In existing federated learning solutions, one-shot federated learning is a promising yet challenging direction. It involves model training with just one round of communication between clients and the server, reducing communication overheads and security risks. However, most existing methods still face several challenges. First, generating additional data for training prolongs the model training time. Second, the traditional single model cannot handle data heterogeneity in real world scenarios. To address these issues, this paper proposes a personalized federated learning method called FedOM under the one -communication premise. Considering the high data heterogeneity, FedOM abandons the traditional single global model architecture and generates multiple group models to overcome the generalization limitations of a single model. Additionally, based on FedOM, this study proposes FedOMF, a personalized method with a fine-tuning module. Experiments on public datasets show that in highly heterogeneous data scenarios, the proposed methods outperform baseline methods, demonstrating superior performance and great practical potential.

Based on the three-dimensional viscous, steady, incompressible NS equation and the standard k-ε two-equation turbulence model, this paper establishes a three-dimensional static fluid calculation model for the vacuum pipeline ultra-high-speed train, and the flow field analysis software ANASYS/Fluent was used to simulate the aerodynamic performance of the vacuum piping system under different operating speeds, pipe block ratios and pipe pressure conditions. The calculation results show that when the pipeline pressure and the operating speed is constant, the larger the blocking ratio is, the greater the aerodynamic resistance experienced by the train, the greater the blockage ratio of the vacuum pipeline, the more drastic the change in the aerodynamic resistance of the car body; When the train runs under the same pipeline blocking ratio, the aerodynamic resistance experienced by the train increases with the increase of running speed and pipeline pressure.