Kunpeng Xu

Yanyan Wang, Yingying Wang, Junli Liang et al.

The rapid advancement of large language models (LLMs) has significantly propelled progress in artificial intelligence, demonstrating substantial application potential across multiple specialized domains. Telecommunications operation scheduling (OS) is a critical aspect of the telecommunications industry, involving the coordinated management of networks, services, risks, and human resources to optimize production scheduling and ensure unified service control. However, the inherent complexity and domain-specific nature of OS tasks, coupled with the absence of comprehensive evaluation benchmarks, have hindered thorough exploration of LLMs' application potential in this critical field. To address this research gap, we propose the first Telecommunications Operation Scheduling Evaluation Benchmark (TeleEval-OS). Specifically, this benchmark comprises 15 datasets across 13 subtasks, comprehensively simulating four key operational stages: intelligent ticket creation, intelligent ticket handling, intelligent ticket closure, and intelligent evaluation. To systematically assess the performance of LLMs on tasks of varying complexity, we categorize their capabilities in telecommunications operation scheduling into four hierarchical levels, arranged in ascending order of difficulty: basic NLP, knowledge Q&A, report generation, and report analysis. On TeleEval-OS, we leverage zero-shot and few-shot evaluation methods to comprehensively assess 10 open-source LLMs (e.g., DeepSeek-V3) and 4 closed-source LLMs (e.g., GPT-4o) across diverse scenarios. Experimental results demonstrate that open-source LLMs can outperform closed-source LLMs in specific scenarios, highlighting their significant potential and value in the field of telecommunications operation scheduling.

Jorden Lam, Kunpeng Xu

The paper investigates the escalating concerns surrounding the surge in diabetes cases, exacerbated by the COVID-19 pandemic, and the subsequent strain on medical resources. The research aims to construct a predictive model quantifying factors influencing inpatient hospital stay durations for diabetes patients, offering insights to hospital administrators for improved patient management strategies. The literature review highlights the increasing prevalence of diabetes, emphasizing the need for continued attention and analysis of urban-rural disparities in healthcare access. International studies underscore the financial implications and healthcare burden associated with diabetes-related hospitalizations and complications, emphasizing the significance of effective management strategies. The methodology involves a quantitative approach, utilizing a dataset comprising 10,000 observations of diabetic inpatient encounters in U.S. hospitals from 1999 to 2008. Predictive modeling techniques, particularly Generalized Linear Models (GLM), are employed to develop a model predicting hospital stay durations based on patient demographics, admission types, medical history, and treatment regimen. The results highlight the influence of age, medical history, and treatment regimen on hospital stay durations for diabetes patients. Despite model limitations, such as heteroscedasticity and deviations from normality in residual analysis, the findings offer valuable insights for hospital administrators in patient management. The paper concludes with recommendations for future research to address model limitations and explore the implications of predictive models on healthcare management strategies, ensuring equitable patient care and resource allocation.