多周期强化学习的人机混合物资供应任务分派模型数据集

研究物资物流供应保障感知预警问题，设计基于时空图卷积神经网络的多阶段动态供给能力预测模型，实现多阶段细粒度应急物资供需精准预警。本数据集包含处理好的物资物流配送订单数据；用户收件订单数据；以及用户表数据。共包含620,000条订单数据取自京东物流真实配送场景，采集自2022年1月-9月，采集地点为北京无人配送营业部，数据量72MB。This research investigates the perception and early warning issues related to material logistics supply support. A multi-stage dynamic supply capacity prediction model based on spatio-temporal graph convolutional neural networks is proposed to achieve accurate, multi-stage and fine-grained early warning of emergency material supply and demand. This dataset includes three types of processed data: material logistics distribution order data, user recipient order data, and user table data. A total of 620,000 order records are collected from real JD Logistics distribution scenarios, covering the period from January to September 2022 at the Beijing Unmanned Delivery Business Department, with a total data volume of 72 MB.

搜集汇总

背景与挑战

背景概述

该数据集聚焦于物资物流供应保障的感知预警问题，基于京东物流2022年在北京无人配送营业部的真实场景，提供了包含62万条订单、总量72MB的配送订单、收件订单及用户表数据。它旨在支持开发基于时空图卷积神经网络的多阶段动态供给能力预测模型，以实现应急物资供需的精准预警和任务分派优化。