Space-Air-Ground Integrated Networks (SAGINs) are a cornerstone of future 6 G systems, promising ubiquitous connectivity by amalgamating satellite, aerial, and terrestrial communication resources. However, these networks traditionally operate in isolated silos, leading to inefficient resource utilization and limited adaptability. To address these challenges, this paper proposes a collaborative access framework that allows cross-layer communication, enabling user equipment from one domain to access network infrastructure in another. The key innovations of this work lie in three aspects: first, it breaks the fixed hierarchy of traditional SAGINs and integrates access selection into the optimization problem, allowing dynamic adjustment of useraccess point associations; second, it establishes a holistic mathematical model that simultaneously considers access selection, frequency resource block allocation, and power control, capturing the complex interference interactions between different layers; third, it provides a theoretical benchmark for evaluating the performance of practical algorithms by formulating the problem as a unified MINLP model.

We present a novel deep reinforcement learning framework for optimizing telecom product portfolios. Our proposed Telecom Product Portfolio Optimization (TPPO) algorithm formulates portfolio consolidation as a sequential decision-making problem, integrating multi-dimensional product feature representation and a specially designed multi-objective reward function. The framework employs deep Q-learning to balance portfolio reduction with revenue preservation and user experience. Experimental results demonstrate that TPPO achieves a 33.8% portfolio reduction while increasing revenue by 5.47%, significantly outperforming traditional rule-based and clustering approaches. The framework demonstrates strong practical value for telecom operators seeking to streamline their product portfolios while enhancing business performance.

The huge amount of video data produced by ubiqui tous cameras imposes significant challenges for users to efficiently obtain useful video information. Multi-view video summarization (MVS) aggregates multi-view videos into information-rich video summaries by considering content correlations within each view and between multiple views. Existing MVS methods fail to concentrate on performance across scenarios and usually achieve satisfactory performance on specific training datasets. However, when faced with unseen video scenarios, the quality of the summaries generated by existing methods may degrade. Moreover, they usually only use cameras for data acquisition, which require a large amount of network bandwidth to transfer the data to the server for processing. To bridge this gap, we propose a context-adaptive online reinforcement learning multi-view video summarization framework (COORS) that meets the low response latency performance requirements of context adaptation while ensuring camera hardware compatibility. Specifically, COORS enables retraining in new contexts by extracting contextindependent rewards, while improving model convergence speed based on representation learning and replica playback. Extensive experiments show that COORS has better performance compared to the state-of-the-art baselines.