The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centric blending of organic and advertising content. Prevailing ranking models often rely on fragmented modules and hand-crafted features, limiting their ability to interpret complex user intent. This challenge is further amplified in location-based services such as food delivery, where user decisions are shaped by dynamic spatial, temporal, and individual contexts. To address these limitations, we propose a novel generative framework that reframes ranking as a context comprehension task, modeling heterogeneous signals in a unified architecture. Our architecture consists of two core components: the Generative Contextual Encoder (GCE) and the Generative Contextual Fusion (GCF). The GCE comprises three specialized modules: a Personalized Context Enhancer (PCE) for user-specific modeling, a Collective Context Enhancer (CCE) for group-level patterns, and a Dynamic Context Enhancer (DCE) for real-time situational adaptation. The GCF module then seamlessly integrates these contextual representations through low-rank adaptation. Extensive experiments confirm that our method achieves significant gains in critical business metrics, including click-through rate and platform revenue. We have successfully deployed our method on a large-scale food delivery advertising platform, demonstrating its substantial practical impact. This work pioneers a new perspective on generative recommendation and highlights its practical potential in industrial advertising systems.

We propose a novel hypocenter localization model based on machine learning in the hope of providing a feasible solution for earthquake early warning system (EEWs). The model predicts the hypocenter location using the time series of trigger stations. We compare the test results of three machine learning models: 1) random forest (RF); 2) eXtreme gradient boosting (XGBoost); and 3) light gradient boosting machine (LightGBM). LightGBM is found the most efficient and thus is applied for further testing. Moreover, considering the difference in station trigger between ocean and land earthquakes, ocean and land earthquake hypocenter prediction models are determined separately. When triggered by five stations, the mean absolute errors (MAEs) for predicting the hypocenter location in land and ocean earthquakes is 2.10 and 12.66 km, respectively. With fewer stations (three stations), the predicted MAEs for distance reaches 17.80 and 2.34 km for ocean and land earthquakes, respectively. In addition, a classification model for rapid discrimination of ocean and land earthquakes using information from three trigger stations is constructed. The proposed method in this letter can provide a more reliable solution to EEWs.