Filling Delivery Time Automatically Based on Couriers' Trajectories

Sijie Ruan, Xi Fu, Cheng Long, Zi Xiong, Jie Bao, Ruiyuan Li, Yiheng Chen, Shengnan Wu, Yu Zheng

Abstract: Nowadays, couriers are still the main solution to address the “last mile” problem in logistics. They are usually required to record the delivery time of each parcel manually, which is essential for delivery insurances, delivery performance evaluations, and customer available time discovery. Stay points extracted from couriers’ trajectories provide a chance to fill the delivery time automatically to ease their burdens. However, it is challenging due to inaccurate delivery locations and various stay scenarios. To this end, we propose the improved <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</u> elivery <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</u> ime <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Inf</u> erence (DTInf <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">+</sup> ), to infer the delivery time of waybills based on their trajectories. DTInf <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">+</sup> is composed of three steps: 1) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Data Pre-processing</i> , which organizes waybills and stay points by delivery trips, 2) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Delivery Location Mining</i> , which obtains the delivery location for each address and each Geocoded waybill location by mining historical delivery caused stay points, and 3) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Delivery Event-based Matching</i> , which infers the delivery caused stay point for waybills at the same delivery location based on a pointer network-like model SPSelector to obtain the delivery time. Extensive experiments and case studies based on real-world datasets from JD Logistics confirm the effectiveness of our approach. Finally, a system is deployed in JD Logistics.