A Semantic Segmentation based POI Coordinates Generating Framework for On-demand Food Delivery Service

Nowadays, on-demand food delivery service has become fashionable in China. The efficiency of food delivery relies heavily on accurate coordinates of destination Points of Interest (POI). However, the coordinates of the destination POIs from the existing geospatial data warehouses still have many problems that perplex couriers severely. The major problems can be concluded in two categories: 1) the deviation of POI coordinates; 2) the lack of POI coordinates. To address these problems, we propose a POI-coordinate-generating framework based on couriers' and users' behavioral data of historical waybills. In particular, we start with a combinatorial strategy to assign waybills to Areas of Interest (AOI). Second, we generate a destination POI name by processing the user address for each waybill, and all waybills are grouped by the corresponding POI name. Then, a data density image of the behavioral data is generated for each group, with the ground-truth location of the POI labeled. Finally, a U-Net is trained by using the images generated in the previous step to infer locations of the POIs. We evaluated this framework by launching experiments and case studies on large-scale datasets, and the result shows our framework can predict coordinates of POIs accurately. These predicted coordinates can be used to calibrate deviated coordinates of many POIs and complement the geospatial data warehouse.