Emergency medical services (EMS) are emergency services that provide urgent pre-hospital treatment for serious illness and injuries. However, in most countries, EMS is faced with the problem of untimely emergency response. In this paper, we develop an Optimized Regularization based framework (OpRe-RRS) by optimizing the Rescue Route Selection problem to increase the rescue speed. Specifically, through the analysis of spatio-temporal data, we predict the ranking of road priority and select the rescue route for ambulances to lift speed. Along this line, we match the GPS data of ambulances to the correct road section through a map matching algorithm. Then, we extract different features from three perspectives: (i) basic features, (ii) POI features and (iii) traffic features. To effectively exploit the roads similarity, we develop a loss function with regularization to solve this prediction problem. Finally, experiments on real-world data demonstrate that our method can effectively reduce rescue time.

紧急医疗服务 (EMS) 是为严重疾病和伤害提供紧急院前治疗的紧急服务。然而，在大多数国家，EMS都面临着应急响应不及时的问题。在本文中，我们通过优化救援路线选择问题来开发基于优化正则化的框架（OpRe-RRS）以提高救援速度。具体来说，通过对时空数据的分析，预测道路优先级排序，选择救护车的救援路线以提升速度。沿着这条路线，我们通过地图匹配算法将救护车的 GPS 数据与正确的路段进行匹配。然后，我们从三个角度提取不同的特征：（i）基本特征，（ii）POI 特征和（iii）交通特征。为了有效地利用道路相似性，我们开发了一个带有正则化的损失函数来解决这个预测问题。最后，对真实世界数据的实验表明，我们的方法可以有效地减少救援时间。