返回全部动态
TAGR：跨异构城市配送任务的任务自适应地理语义检索
原标题：TAGR: Task-Adaptive Geo-Semantic Retrieval across Heterogeneous Urban Delivery Tasks
AI 摘要
该论文提出 TAGR，一个面向城市即时配送中需求预测、ETA 预测和下一站预测三类异构任务的统一检索框架。TAGR 利用冻结的 LLM 编码器构建地理语义共享先验，并结合任务特定适配器与检索库，以在共享区域知识的同时保留各任务特有的证据结构。实验在三个城市数据集上显示，TAGR 在多个任务上持续优于现有最优基线。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
TAGR: Task-Adaptive Geo-Semantic Retrieval across Heterogeneous Urban Delivery Tasks Abstract As urban residents demand higher-quality instant delivery services, demand forecasting, estimated time of arrival prediction, and next-stop prediction have become critical tasks in urban delivery systems. However, the three tasks rely on historical evidence with substantially different structures and granularities. Meanwhile, their prediction targets differ in output form, making it difficult to integra
发布时间：2026-10-22 12:00
抓取时间：2026-10-22 12:27
来源机构：arXiv