基于不完备出行数据的多天活动-出行链需求建模  

A multi⁃day activity⁃travel chain demand model using incomplete travel data

作　　者：安东 黄东浩 戴琦 李大韦[2,3,4] AN Dong;HUANG Donghao;DAI Qi;LI Dawei(Xi’an City Planning Design and Research Institute,Xi’an 710082,China;School of Transportation,Southeast University,Nanjing 211189,China;Jiangsu Key Laboratory of Urban ITs,Southeast University,Nanjing 211189,China;Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies,Nanjing 211189,China)

机构地区：[1]西安市城市规划设计研究院,陕西西安710082 [2]东南大学交通学院,江苏南京211189 [3]江苏省城市智能交通重点实验室,江苏南京211189 [4]江苏省现代城市交通技术协同创新中心,江苏南京211189

出　　处：《现代交通与冶金材料》2025年第2期75-83,共9页Modern Transportation and Metallurgical Materials

基　　金：国家自然科学基金资助项目(52432010,52202399)。

摘　　要：本文利用小样本的单日出行调查数据为多天的不完备手机信令出行链补全出行目的及个人属性信息,并基于补全后的数据建立了多天活动-出行需求模型。然后利用补全后的数据,搭建多日活动-出行链模型框架,在考虑了相邻多天中活动安排相关性的情况下,模拟了个体的活动参与决策过程,分析了影响居民活动和出行需求的特征因素。模拟仿真居民一周内各天的活动-出行安排。实验结果表明,本文提出的方法能较为准确地预测个体一周内的出行行为,有效反映出城市居民出行行为在工作日与周末的差异化特征。In this paper,we use the small-sample single-day travel survey data to complement the travel purpose and personal attribute information for a multi-day incomplete cell phone signaling travel chain,and establish a multi-day activity-travel demand model based on the complemented data.Then,using the supplemented data,the multi-day activity-travel chain model framework is constructed to simulate the individual's activity participation decision-making process and analyze the characteristic factors affecting residents'activity and travel demand,taking into account the correlation of activity sched-ules in the adjacent multi-days.The simulation of the activity-travel arrangements of residents on each day of the week is performed.The experimental results show that the method proposed in this paper can more accurately predict the travel behavior of individuals within a week,effectively reflecting the differentiated characteristics of urban residents'travel behavior on weekdays and weekends.

关 键 词：交通需求模型 活动-出行链建模 不完备数据 生成对抗网络 

分 类 号：U491[交通运输工程—交通运输规划与管理]