With the rapid development of low Earth orbit (LEO) satellite communication technology, its applications in mobile communication and data transmission are becoming increasingly widespread. To improve the user experience for video services and reduce communication interruptions and network congestion during link switching, this study proposes a LEO satellite switching recovery method based on an enhanced congestion control algorithm. The method includes a neural network-based attitude control strategy, a handover detection mechanism incorporating the satellite’s remaining service time, and a rate recovery algorithm combining congestion control with time series prediction. Simulation results show that the proposed method reduces the communication interruption rate from 6.48 to 2.13%, increases the minimum throughput from 257 kbps to 2017 kbps, and shortens the average recovery time from 3200 ms to 1800 ms. Moreover, the false detection rate decreases by 71.6%, and the detection accuracy improves to 96.32%. Under conditions of system stability exceeding 95%, the method maintains good real-time performance, with average processing times of 5.23 s (training) and 4.58 s (validation). These results demonstrate the effectiveness of the proposed method in improving switching and recovery performance in LEO satellite networks and provide theoretical and technical support for stable and efficient satellite system operations.
With the widespread adoption of large language models such as ChatGPT, distinguishing AI-generated text from human-written content has become increasingly challenging. Existing detection methods often rely solely on semantic representations and exhibit limited robustness, particularly when texts are paraphrased or rewritten. This study proposes an integrated detection framework that combines contextual semantic embeddings with auxiliary surface-level features, including pronunciation-related textual cues and handcrafted statistical descriptors. Specifically, a RoBERTa encoder is employed to capture deep contextual semantics, while a convolutional neural network aggregates multi-scale representations. In parallel, a set of text-derived structural, lexical, and readability features—serving as proxies for phonetic and stylistic regularities—are incorporated to enrich the representation space. Rather than introducing a fundamentally new detection paradigm, the proposed approach emphasizes feature-level fusion and systematic empirical evaluation. Experiments on the HAGTC dataset and a ChatGPT-written abstract dataset show that the proposed RoBERTa–CNN framework consistently outperforms several strong baselines in terms of accuracy and F1 score. Notably, the model demonstrates improved robustness in detecting rewritten AI-generated texts. Ablation studies further confirm that integrating multiple feature types significantly enhances detection performance. These results indicate that combining contextual representations with auxiliary surface features offers a practical and effective direction for AI-generated text detection.