AI 中文总结
该研究提出带偏好对齐的混合专家框架UrbanShare-MoE-PA，通过智能体级流动性建模连接政策、行为与流行病模拟，评估了不同封锁政策的流行病-活动权衡，为NPI情景分析提供了可解释工具。
AI 中文摘要
非药物干预（NPIs）通过行为重新分配而非单纯的总流动性减少来改变流行病风险。因此，基于情景的NPI分析需要一个行为层，在模拟下游结果之前，将替代政策时间表转化为合理的活动和流动性轨迹。我们引入UrbanShare-MoE-PA，这是一个数据驱动的智能体级框架，可将实际和替代NPI时间表映射到每日时间分配轨迹，并通过校准的行为驱动型SEIR模拟器传播这些轨迹。行为引擎将每个智能体-日分解为出行份额、停留时的兴趣点（POI）类别分配以及出行时的出行方式分配。它结合了结构化的UrbanShare基线、用于异构POI和方式响应的混合专家头，以及用于时间表条件展开的阶段感知偏好对齐。使用2020年3月至8月期间新加坡911个智能体的数据，我们评估了实际重建、四个替代封锁时间表以及流行病-活动权衡。UrbanShare-MoE在POI重建方面优于基线，而UrbanShare-MoE-PA实现了最低的出行方式误差和最清晰的替代时间表轨迹。在校准的SEIR模拟中，早期封锁降低了感染负担，晚期封锁增加了感染负担，而短期封锁在相对于原始政策仅适度增加流行病负担的情况下，保留了最高的加权活动。这些结果表明，流行病-活动结论取决于政策时间表如何转化为行为，而智能体级流动性份额建模为政策时机、行为和下游模拟之间提供了可解释的桥梁。
英文摘要
Non-pharmaceutical interventions (NPIs) alter epidemic risk through behavioral reallocations, not simply aggregate mobility reductions. Scenario-based NPI analysis therefore requires a behavioral layer that translates alternative policy calendars into plausible activity and mobility trajectories before downstream outcomes are simulated. We introduce UrbanShare-MoE-PA, a data-driven agent-level framework that maps factual and alternative NPI calendars to daily time-allocation trajectories and propagates them through a calibrated behavior-driven SEIR simulator. The behavioral engine decomposes each agent-day into travel share, POI-category allocation conditional on staying, and travel-mode allocation conditional on traveling. It combines a structured UrbanShare baseline, mixture-of-experts heads for heterogeneous POI and mode responses, and phase-aware preference alignment for calendar-conditioned rollouts. Using data from 911 agents in Singapore observed from March to August 2020, we evaluate factual reconstruction, four alternative lockdown calendars, and epidemic-activity trade-offs. UrbanShare-MoE improves POI reconstruction over the baseline, while UrbanShare-MoE-PA achieves the lowest travel-mode errors and the clearest alternative-calendar trajectories. In the calibrated SEIR simulation, early lockdown lowers infectious burden, late lockdown increases it, and short lockdown preserves the highest weighted activity with only a modest increase in epidemic burden relative to the original policy. These results show that epidemic-activity conclusions depend on how policy calendars are translated into behavior, and that agent-level mobility-share modeling provides an interpretable bridge between policy timing, behavior, and downstream simulation.
