Article(id=1149776964589936945, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149776900194791454, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2403271, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1714838400000, receivedDateStr=2024-05-05, revisedDate=1722441600000, revisedDateStr=2024-08-01, acceptedDate=null, acceptedDateStr=null, onlineDate=1752057790181, onlineDateStr=2025-07-09, pubDate=1744905600000, pubDateStr=2025-04-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752057790181, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752057790181, creator=13701087609, updateTime=1752057790181, updator=13701087609, issue=Issue{id=1149776900194791454, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='11', pageStart='4397', pageEnd='4826', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752057774827, creator=13701087609, updateTime=1768456666677, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218558837930512931, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149776900194791454, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218558837930512932, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149776900194791454, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=4761, endPage=4768, ext={EN=ArticleExt(id=1149776964841595186, articleId=1149776964589936945, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Vehicle Travel Destination Prediction Considering Spatiotemporal Correlation Degree: A Case of Futian Central District in Shenzhen, columnId=1156262728772735295, journalTitle=Science Technology and Engineering, columnName=Papers·Traffics and Transportations, runingTitle=null, highlight=null, articleAbstract=

To meet the increasingly refined individual-level traffic management and travel service needs in the new era, a vehicle travel destination prediction method that comprehensively considers temporal and spatial correlation was proposed based on the traditional prediction method based on historical trajectories. Using data from video AI recognition and vehicle satellite positioning, the vehicle stopping points were identified to segment the vehicle's full-day travel trajectories and establish a historical vehicle travel trajectory database. By studying the temporal and spatial characteristics of vehicle travel, a calculation method for the temporal and spatial correlation of vehicle travel trajectories was proposed, and a vehicle travel destination prediction model was constructed using temporal and spatial correlation as weights. Taking the vehicle travel in Futian Central District of Shenzhen as an example, four typical vehicle travel trajectories including private cars and taxis were selected to establish a model prediction accuracy evaluation function. The prediction accuracy of travel destinations for different types of travel and different degrees of trajectory completion was analyzed and compared with the historical trajectory-based prediction method. The results show that the prediction accuracy of travel destinations for different types of vehicles is basically positively correlated with the degree of trajectory completion. When the trajectory completion rate reaches 80%, the accuracy of travel prediction basically reaches over 80%. Compared with the traditional prediction method based on historical trajectories, the prediction method considering temporal and spatial correlation has higher prediction accuracy, especially for taxis services with no fixed commuting travel characteristics. The prediction accuracy of travel destinations has been improved by more than 16%. The research results can better meet the needs of global traffic management.

, correspAuthors=Shi-kun LIU, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Yi TANG, Shi-kun LIU, Jian-dong QIU), CN=ArticleExt(id=1149776970977861978, articleId=1149776964589936945, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=考虑时空关联度的车辆出行目的地预测——以深圳市福田中心区为例, columnId=1156262730664366426, journalTitle=科学技术与工程, columnName=论文·交通运输, runingTitle=null, highlight=null, articleAbstract=

为满足新时期愈加精细化的个体级交通管理与出行服务需求,在传统基于历史轨迹的出行目的地预测方法基础上,提出一种综合考虑时空关联度的车辆出行目的地预测方法。基于视频AI识别与车辆卫星定位等数据,识别车辆停留点,以此切分车辆全天出行轨迹,建立历史车辆出行轨迹库;研究车辆出行时空特征,提出车辆出行轨迹时间关联度与空间关联度的计算方法,以时空关联度为权重构建车辆出行目的地预测模型;以深圳市福田中心区的车辆出行为例,选取包含私家车、出租汽车等4个典型特征的车辆出行轨迹,建立模型预测准确度评价函数,分析不同类型出行、不同轨迹完成度的出行目的地预测准确度,并与基于历史轨迹预测方法进行对比。结果表明:不同类型车辆出行目的地预测准确度与轨迹完成度基本呈正相关,当轨迹完成度达到80%时,出行预测准确度基本达到80%以上;相比传统基于历史轨迹的预测方法,考虑时空关联度的预测方法预测准确度更高,特别是针对无固定通勤出行特征的出租车,出行目的地预测准确度提高了16%以上,研究成果能够更好适应全局的交通管理需要。

, correspAuthors=刘诗昆, authorNote=null, correspAuthorsNote=
* 刘诗昆(1997—),女,汉族,湖南衡阳人,博士研究生。研究方向:智能交通,交通环境。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=we+qccEPvhDy+EeRLFpdrA==, magXml=kWP6e9PwyVVO1UIoTojF3Q==, pdfUrl=null, pdf=sXBcfh24W7cUFoyZya2YSg==, pdfFileSize=6131752, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=G+9INJxEVzc1YMSzsJoV8A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=OdIdBpAGYjOaxOVomTgPLQ==, mapNumber=null, authorCompany=null, fund=null, authors=

唐易(1992—),男,汉族,江西南昌人,硕士,工程师。研究方向:交通大数据,交通模型仿真。E-mail:

, authorsList=唐易, 刘诗昆, 丘建栋)}, authors=[Author(id=1218843912844792093, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tangyi@sutpc.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1218843912966426923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, authorId=1218843912844792093, language=EN, stringName=Yi TANG, firstName=Yi, middleName=null, lastName=TANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Urban Transport Planning Center Co., Ltd, Shenzhen 518057, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843913104838964, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, authorId=1218843912844792093, language=CN, stringName=唐易, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057, bio={"content":"

唐易(1992—),男,汉族,江西南昌人,硕士,工程师。研究方向:交通大数据,交通模型仿真。E-mail:

"}, bioImg=null, bioContent=

唐易(1992—),男,汉族,江西南昌人,硕士,工程师。研究方向:交通大数据,交通模型仿真。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843912471498993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=1, ext=[AuthorCompanyExt(id=1218843912479887602, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912471498993, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Urban Transport Planning Center Co., Ltd, Shenzhen 518057, China), AuthorCompanyExt(id=1218843912488276211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912471498993, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057)])]), Author(id=1218843913213890877, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liushk27@mail2.sysu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1218843913356497224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, authorId=1218843913213890877, language=EN, stringName=Shi-kun LIU, firstName=Shi-kun, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, *, address=2 School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, China
3 Guangdong Provincial Key Laboratory of Intelligent Transportation System, Shenzhen 518107, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843913482326355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, authorId=1218843913213890877, language=CN, stringName=刘诗昆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, *, address=2 中山大学智能工程学院, 深圳 518107
3 广东省智能交通系统重点实验室, 深圳 518107, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843912605716735, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=2, ext=[AuthorCompanyExt(id=1218843912614105344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912605716735, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, China), AuthorCompanyExt(id=1218843912622493953, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912605716735, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中山大学智能工程学院, 深圳 518107)]), AuthorCompany(id=1218843912710574349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=3, ext=[AuthorCompanyExt(id=1218843912718962958, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912710574349, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Guangdong Provincial Key Laboratory of Intelligent Transportation System, Shenzhen 518107, China), AuthorCompanyExt(id=1218843912723157264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912710574349, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 广东省智能交通系统重点实验室, 深圳 518107)])]), Author(id=1218843913599766878, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1218843913733984617, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, authorId=1218843913599766878, language=EN, stringName=Jian-dong QIU, firstName=Jian-dong, middleName=null, lastName=QIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Urban Transport Planning Center Co., Ltd, Shenzhen 518057, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843913834647920, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, authorId=1218843913599766878, language=CN, stringName=丘建栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843912471498993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=1, ext=[AuthorCompanyExt(id=1218843912479887602, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912471498993, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Urban Transport Planning Center Co., Ltd, Shenzhen 518057, China), AuthorCompanyExt(id=1218843912488276211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912471498993, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057)])])], keywords=[Keyword(id=1218843914035974530, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, orderNo=1, keyword=travel destination prediction), Keyword(id=1218843914157609354, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, orderNo=2, keyword=spatiotemporal correlation degree), Keyword(id=1218843914241495441, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, orderNo=3, keyword=travel trajectory), Keyword(id=1218843914350547353, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, orderNo=4, keyword=trajectory completion degree), Keyword(id=1218843914434433443, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, orderNo=5, keyword=video AI recognition data), Keyword(id=1218843914585428391, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, orderNo=1, keyword=出行目的地预测), Keyword(id=1218843914690286000, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, orderNo=2, keyword=时空关联度), Keyword(id=1218843914795143612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, orderNo=3, keyword=出行轨迹), Keyword(id=1218843914891612611, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, orderNo=4, keyword=轨迹完成度), Keyword(id=1218843915000664521, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, orderNo=5, keyword=视频AI识别数据)], refs=[Reference(id=1218843917307531859, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=3, pageStart=98, pageEnd=105, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=殷韫, 廖璟瑒, 吴克寒, journalName=城市交通, refType=null, unstructuredReference=殷韫, 廖璟瑒, 吴克寒. 智慧出行服务新模式构建和出行需求优化系统设计[J]. 城市交通, 2023, 21(3): 98-105, 118., articleTitle=智慧出行服务新模式构建和出行需求优化系统设计, refAbstract=null), Reference(id=1218843917416583769, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=3, pageStart=98, pageEnd=105, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Yin Yun, Liao Jingyang, Wu Kehan, journalName=Urban Transport of China, refType=null, unstructuredReference=Yin Yun, Liao Jingyang, Wu Kehan. Smart travel service new mode construction and travel demand optimization system design[J]. Urban Transport of China, 2023, 21(3): 98-105, 118., articleTitle=Smart travel service new mode construction and travel demand optimization system design, refAbstract=null), Reference(id=1218843917534024287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=28, pageStart=11921, pageEnd=11931, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=梁泉, 翁剑成, 胡娟娟, journalName=科学技术与工程, refType=null, unstructuredReference=梁泉, 翁剑成, 胡娟娟, 等. 多源数据驱动下公共交通出行行为特征挖掘与预测[J]. 科学技术与工程, 2021, 21(28): 11921-11931., articleTitle=多源数据驱动下公共交通出行行为特征挖掘与预测, refAbstract=null), Reference(id=1218843917630493285, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=28, pageStart=11921, pageEnd=11931, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Liang Quan, Weng Jiancheng, Hu Juanjuan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Liang Quan, Weng Jiancheng, Hu Juanjuan, et al. Feature mining and prediction for the trip behavior of public transport driven by multi-source data[J]. Science Technology and Engineering, 2021, 21(28): 11921-11931., articleTitle=Feature mining and prediction for the trip behavior of public transport driven by multi-source data, refAbstract=null), Reference(id=1218843917735350893, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=2, pageStart=210, pageEnd=217, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=孔德学, 敖谷昌, 张惠玲, journalName=深圳大学学报(理工版), refType=null, unstructuredReference=孔德学, 敖谷昌, 张惠玲, 等. 差异化收费下货车出行选择偏好分析及建模[J]. 深圳大学学报(理工版), 2023, 40(2): 210-217., articleTitle=差异化收费下货车出行选择偏好分析及建模, refAbstract=null), Reference(id=1218843917856985718, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=2, pageStart=210, pageEnd=217, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Kong Dexue, Ao Guchang, Zhang Huiling, journalName=Journal of Shenzhen University Science and Engineering, refType=null, unstructuredReference=Kong Dexue, Ao Guchang, Zhang Huiling, et al. Analysis and modeling of trucks travel choice preference under differentiated charging[J]. Journal of Shenzhen University Science and Engineering, 2023, 40(2): 210-217., articleTitle=Analysis and modeling of trucks travel choice preference under differentiated charging, refAbstract=null), Reference(id=1218843917982814843, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2022, volume=3, issue=null, pageStart=15, pageEnd=24, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=杨亚璪, 唐浩冬, 彭勇, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=杨亚璪, 唐浩冬, 彭勇. 考虑偏好差异的后疫情时代居民出行方式选择行为研究[J]. 交通运输系统工程与信息, 2022, 3: 15-24., articleTitle=考虑偏好差异的后疫情时代居民出行方式选择行为研究, refAbstract=null), Reference(id=1218843918108643972, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2022, volume=3, issue=null, pageStart=15, pageEnd=24, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Yang Yazao, Tang Haodong, Peng Yong, journalName=Journal of Transportation Engineering and Information, refType=null, unstructuredReference=Yang Yazao, Tang Haodong, Peng Yong. Residents' travel mode choice behavior in post-COVID-19 era considering preference differences[J]. Journal of Transportation Engineering and Information, 2022, 3: 15-24., articleTitle=Residents' travel mode choice behavior in post-COVID-19 era considering preference differences, refAbstract=null), Reference(id=1218843918234473097, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2021, volume=5, issue=null, pageStart=91, pageEnd=101, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=甘蜜, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=甘蜜. 货车轨迹数据在公路货运系统中应用研究综述[J]. 交通运输系统工程与信息, 2021, 5: 91-101, 113., articleTitle=货车轨迹数据在公路货运系统中应用研究综述, refAbstract=null), Reference(id=1218843918347719312, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2021, volume=5, issue=null, pageStart=91, pageEnd=101, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Gan Mi, journalName=Journal of Transportation Engineering and Information, refType=null, unstructuredReference=Gan Mi. Review on application of truck trajectory data in highway freight system[J]. Journal of Transportation Engineering and Information, 2021, 5: 91-101, 113., articleTitle=Review on application of truck trajectory data in highway freight system, refAbstract=null), Reference(id=1218843918465159829, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2014, volume=5, issue=1, pageStart=1, pageEnd=33, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Ying J C, Lee W C, Tseng V S, journalName=ACM Transactions on Intelligent Systems & Technology, refType=null, unstructuredReference=Ying J C, Lee W C, Tseng V S. Mining geographic-temporal-semantic patterns in trajectories for location prediction[J]. ACM Transactions on Intelligent Systems & Technology, 2014, 5(1): 1-33., articleTitle=Mining geographic-temporal-semantic patterns in trajectories for location prediction, refAbstract=null), Reference(id=1218843918582600349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=2, pageStart=494, pageEnd=506, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Jiang F, Lu Z N, Gao M, journalName=Journal of Central South University, refType=null, unstructuredReference=Jiang F, Lu Z N, Gao M, et al. DP-BPR: destination prediction based on Bayesian personalized ranking[J]. Journal of Central South University, 2021, 28(2): 494-506., articleTitle=DP-BPR: destination prediction based on Bayesian personalized ranking, refAbstract=null), Reference(id=1218843918687457959, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=6, pageStart=143, pageEnd=149, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=张国兴, 李亚东, 张磊, journalName=计算机工程与应用, refType=null, unstructuredReference=张国兴, 李亚东, 张磊, 等. 基于SDZ-RNN的出租车出行目的地预测方法[J]. 计算机工程与应用, 2018, 54(6): 143-149., articleTitle=基于SDZ-RNN的出租车出行目的地预测方法, refAbstract=null), Reference(id=1218843918796509872, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=6, pageStart=143, pageEnd=149, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Zhang Guoxing, Li Yadong, Zhang Lei, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Zhang Guoxing, Li Yadong, Zhang Lei, et al. Taxi travel destination prediction based on SDZ-RNN[J]. Computer Engineering and Applications, 2018, 54(6): 143-149., articleTitle=Taxi travel destination prediction based on SDZ-RNN, refAbstract=null), Reference(id=1218843918892978867, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=7, pageStart=2100, pageEnd=2106, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=魏远, 林彦, 郭晟楠, journalName=计算机应用, refType=null, unstructuredReference=魏远, 林彦, 郭晟楠, 等. 融合出发地与目的地时空相关性的城市区域间出租车需求预测[J]. 计算机应用, 2023, 43(7): 2100-2106., articleTitle=融合出发地与目的地时空相关性的城市区域间出租车需求预测, refAbstract=null), Reference(id=1218843919006225081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=7, pageStart=2100, pageEnd=2106, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Wei Yuan, Lin Yan, Guo Shengnan, journalName=Journal of Computer Applications, refType=null, unstructuredReference=Wei Yuan, Lin Yan, Guo Shengnan, et al. Prediction of taxi demands between urban regions by fusing origin-destination spatial-temporal correlation[J]. Journal of Computer Applications, 2023, 43(7): 2100-2106., articleTitle=Prediction of taxi demands between urban regions by fusing origin-destination spatial-temporal correlation, refAbstract=null), Reference(id=1218843919148831423, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2019, volume=2, issue=null, pageStart=66, pageEnd=72, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=龙小强, 苏跃江, 余畅, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=龙小强, 苏跃江, 余畅, 等. 基于卡口车牌识别数据的车辆出行分析[J]. 交通运输系统工程与信息, 2019, 2: 66-72., articleTitle=基于卡口车牌识别数据的车辆出行分析, refAbstract=null), Reference(id=1218843919241106116, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2019, volume=2, issue=null, pageStart=66, pageEnd=72, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Long Xiaoqiang, Su Yuejiang, Yu Chang, journalName=Journal of Transportation Engineering and Information, refType=null, unstructuredReference=Long Xiaoqiang, Su Yuejiang, Yu Chang, et al. Analyzing methods of vehicle' travel using plate recognition data[J]. Journal of Transportation Engineering and Information, 2019, 2: 66-72., articleTitle=Analyzing methods of vehicle' travel using plate recognition data, refAbstract=null), Reference(id=1218843919366935239, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=5, pageStart=40, pageEnd=46, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=程琳, 张晨皓, 于新莲, journalName=武汉理工大学学报, refType=null, unstructuredReference=程琳, 张晨皓, 于新莲, 等. 基于马尔可夫决策过程的出租车寻客路径优化[J]. 武汉理工大学学报, 2022(5): 40-46., articleTitle=基于马尔可夫决策过程的出租车寻客路径优化, refAbstract=null), Reference(id=1218843919480181452, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=5, pageStart=40, pageEnd=46, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Cheng Lin, Zhang Chenhao, Yu Xinlian, journalName=Journal of Wuhan University of Technology, refType=null, unstructuredReference=Cheng Lin, Zhang Chenhao, Yu Xinlian, et al. Route optimization of taxicab based on Markov decision process[J]. Journal of Wuhan University of Technology, 2022(5): 40-46., articleTitle=Route optimization of taxicab based on Markov decision process, refAbstract=null), Reference(id=1218843919606010578, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=2, pageStart=111, pageEnd=120, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=胡明伟, 王守峰, 黄文柯, journalName=深圳大学学报(理工版), refType=null, unstructuredReference=胡明伟, 王守峰, 黄文柯, 等. 基于车牌识别数据的行驶轨迹重构和排放测算[J]. 深圳大学学报(理工版), 2020, 37(2): 111-120., articleTitle=基于车牌识别数据的行驶轨迹重构和排放测算, refAbstract=null), Reference(id=1218843919715062485, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=2, pageStart=111, pageEnd=120, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=Hu Mingwei, Wang Shoufeng, Huang Wenke, journalName=Journal of Shenzhen University Science and Engineering, refType=null, unstructuredReference=Hu Mingwei, Wang Shoufeng, Huang Wenke, et al. Vehicle trajectory reconstruction and emission estimation based on license plate recognition data[J]. Journal of Shenzhen University Science and Engineering, 2020, 37(2): 111-120., articleTitle=Vehicle trajectory reconstruction and emission estimation based on license plate recognition data, refAbstract=null)], funds=[Fund(id=1218843917076845126, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, awardId=2022B1212020005, language=CN, fundingSource=广东省城市交通数字孪生企业重点实验室项目(2022B1212020005), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1218843912471498993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=1, ext=[AuthorCompanyExt(id=1218843912479887602, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912471498993, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Urban Transport Planning Center Co., Ltd, Shenzhen 518057, China), AuthorCompanyExt(id=1218843912488276211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912471498993, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057)]), AuthorCompany(id=1218843912605716735, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=2, ext=[AuthorCompanyExt(id=1218843912614105344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912605716735, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, China), AuthorCompanyExt(id=1218843912622493953, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912605716735, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中山大学智能工程学院, 深圳 518107)]), AuthorCompany(id=1218843912710574349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, xref=3, ext=[AuthorCompanyExt(id=1218843912718962958, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912710574349, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Guangdong Provincial Key Laboratory of Intelligent Transportation System, Shenzhen 518107, China), AuthorCompanyExt(id=1218843912723157264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, companyId=1218843912710574349, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 广东省智能交通系统重点实验室, 深圳 518107)])], figs=[ArticleFig(id=1218843915311043041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Fig.1, caption=Research idea, figureFileSmall=QQRPtpPutrCuuh54oeZ3nQ==, figureFileBig=Dck8dydSKOzDpFIeG0Gm0w==, tableContent=null), ArticleFig(id=1218843915449455077, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=图1, caption=研究思路, figureFileSmall=QQRPtpPutrCuuh54oeZ3nQ==, figureFileBig=Dck8dydSKOzDpFIeG0Gm0w==, tableContent=null), ArticleFig(id=1218843915579478512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Fig.2, caption=Vehicle travel trajectory segmentation process, figureFileSmall=/OWMp5J1hi1Q0yacnM1D8w==, figureFileBig=ujXEvb7Nt+ZAlIppfLBQQw==, tableContent=null), ArticleFig(id=1218843915705307638, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=图2, caption=车辆出行轨迹切分流程, figureFileSmall=/OWMp5J1hi1Q0yacnM1D8w==, figureFileBig=ujXEvb7Nt+ZAlIppfLBQQw==, tableContent=null), ArticleFig(id=1218843915831136763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Fig.3, caption=Desire line of travel for four drivers, figureFileSmall=JlihK9cUztGXlY3rdB6KzQ==, figureFileBig=VVFbhefl8FNVIximn1ueiA==, tableContent=null), ArticleFig(id=1218843915961160196, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=图3, caption=选取4名驾驶员的出行期望线, figureFileSmall=JlihK9cUztGXlY3rdB6KzQ==, figureFileBig=VVFbhefl8FNVIximn1ueiA==, tableContent=null), ArticleFig(id=1218843916074406409, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Fig.4, caption=Travel prediction accuracy in scenarios with similar trajectory modeling, figureFileSmall=X9CWe6klwH0DPCpehE+9qw==, figureFileBig=dVSWXwJFt7BTHHSIUML5SQ==, tableContent=null), ArticleFig(id=1218843916170875409, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=图4, caption=不同轨迹完成度的出行目的地预测准确度, figureFileSmall=X9CWe6klwH0DPCpehE+9qw==, figureFileBig=dVSWXwJFt7BTHHSIUML5SQ==, tableContent=null), ArticleFig(id=1218843916284121622, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Fig.5, caption=Comparison of accuracy of travel prediction models, figureFileSmall=fSR8+NwB1krk0sb+MSAI3Q==, figureFileBig=EDJLRoVqtPBNWfrAzzdl2w==, tableContent=null), ArticleFig(id=1218843916435116575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=图5, caption=出行预测模型准确度对比, figureFileSmall=fSR8+NwB1krk0sb+MSAI3Q==, figureFileBig=EDJLRoVqtPBNWfrAzzdl2w==, tableContent=null), ArticleFig(id=1218843916535779878, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Table 1, caption=

Historical travel trajectory data structure

, figureFileSmall=null, figureFileBig=null, tableContent=
字段 类型 示例 说明
车辆编号 文本型 092425580865357 车辆唯一标识,根据车牌加密处理
出发日期 整型 20230725 2023年7月25日
出发日期类型 整型 1/2 1表示工作日,2表示周末节假日
出发时间 整型 822 00:08:22
出发时段类型 整型 1/2 1表示高峰时段,2表示平峰时段
轨迹节点序列 文本型 {11235,11587,12987} 各轨迹节点对应的视频AI识别设备编号
轨迹时间序列 文本型 {822,836,853} 各轨迹节点的检测时间
), ArticleFig(id=1218843916649026090, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=表1, caption=

历史出行轨迹数据字段结构

, figureFileSmall=null, figureFileBig=null, tableContent=
字段 类型 示例 说明
车辆编号 文本型 092425580865357 车辆唯一标识,根据车牌加密处理
出发日期 整型 20230725 2023年7月25日
出发日期类型 整型 1/2 1表示工作日,2表示周末节假日
出发时间 整型 822 00:08:22
出发时段类型 整型 1/2 1表示高峰时段,2表示平峰时段
轨迹节点序列 文本型 {11235,11587,12987} 各轨迹节点对应的视频AI识别设备编号
轨迹时间序列 文本型 {822,836,853} 各轨迹节点的检测时间
), ArticleFig(id=1218843916758078002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=EN, label=Table 2, caption=

Statistics of travel characteristic indicators for four drivers

, figureFileSmall=null, figureFileBig=null, tableContent=
驾驶员 总出行距离/km 平均出行距离/km 轨迹数量
1 120.0 2.3 52
2 89.6 3.2 28
3 1 169.1 2.9 397
4 1 236.4 2.9 424
), ArticleFig(id=1218843916879712825, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776964589936945, language=CN, label=表2, caption=

选取4名驾驶员的出行特征指标统计

, figureFileSmall=null, figureFileBig=null, tableContent=
驾驶员 总出行距离/km 平均出行距离/km 轨迹数量
1 120.0 2.3 52
2 89.6 3.2 28
3 1 169.1 2.9 397
4 1 236.4 2.9 424
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403271, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2403271, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2403271, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2403271, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
考虑时空关联度的车辆出行目的地预测——以深圳市福田中心区为例
收藏切换
PDF下载
唐易 1 , 刘诗昆 2, 3, * , 丘建栋 1
科学技术与工程 | 论文·交通运输 2025,25(11): 4761-4768
收起
收藏切换
科学技术与工程 | 论文·交通运输 2025, 25(11): 4761-4768
考虑时空关联度的车辆出行目的地预测——以深圳市福田中心区为例
全屏
唐易1 , 刘诗昆2, 3, * , 丘建栋1
作者信息
  • 1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057
  • 2 中山大学智能工程学院, 深圳 518107
  • 3 广东省智能交通系统重点实验室, 深圳 518107
  • 唐易(1992—),男,汉族,江西南昌人,硕士,工程师。研究方向:交通大数据,交通模型仿真。E-mail:

通讯作者:

* 刘诗昆(1997—),女,汉族,湖南衡阳人,博士研究生。研究方向:智能交通,交通环境。E-mail:
Vehicle Travel Destination Prediction Considering Spatiotemporal Correlation Degree: A Case of Futian Central District in Shenzhen
Yi TANG1 , Shi-kun LIU2, 3, * , Jian-dong QIU1
Affiliations
  • 1 Shenzhen Urban Transport Planning Center Co., Ltd, Shenzhen 518057, China
  • 2 School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, China
  • 3 Guangdong Provincial Key Laboratory of Intelligent Transportation System, Shenzhen 518107, China
出版时间: 2025-04-18 doi: 10.12404/j.issn.1671-1815.2403271
文章导航
收藏切换

为满足新时期愈加精细化的个体级交通管理与出行服务需求,在传统基于历史轨迹的出行目的地预测方法基础上,提出一种综合考虑时空关联度的车辆出行目的地预测方法。基于视频AI识别与车辆卫星定位等数据,识别车辆停留点,以此切分车辆全天出行轨迹,建立历史车辆出行轨迹库;研究车辆出行时空特征,提出车辆出行轨迹时间关联度与空间关联度的计算方法,以时空关联度为权重构建车辆出行目的地预测模型;以深圳市福田中心区的车辆出行为例,选取包含私家车、出租汽车等4个典型特征的车辆出行轨迹,建立模型预测准确度评价函数,分析不同类型出行、不同轨迹完成度的出行目的地预测准确度,并与基于历史轨迹预测方法进行对比。结果表明:不同类型车辆出行目的地预测准确度与轨迹完成度基本呈正相关,当轨迹完成度达到80%时,出行预测准确度基本达到80%以上;相比传统基于历史轨迹的预测方法,考虑时空关联度的预测方法预测准确度更高,特别是针对无固定通勤出行特征的出租车,出行目的地预测准确度提高了16%以上,研究成果能够更好适应全局的交通管理需要。

出行目的地预测  /  时空关联度  /  出行轨迹  /  轨迹完成度  /  视频AI识别数据

To meet the increasingly refined individual-level traffic management and travel service needs in the new era, a vehicle travel destination prediction method that comprehensively considers temporal and spatial correlation was proposed based on the traditional prediction method based on historical trajectories. Using data from video AI recognition and vehicle satellite positioning, the vehicle stopping points were identified to segment the vehicle's full-day travel trajectories and establish a historical vehicle travel trajectory database. By studying the temporal and spatial characteristics of vehicle travel, a calculation method for the temporal and spatial correlation of vehicle travel trajectories was proposed, and a vehicle travel destination prediction model was constructed using temporal and spatial correlation as weights. Taking the vehicle travel in Futian Central District of Shenzhen as an example, four typical vehicle travel trajectories including private cars and taxis were selected to establish a model prediction accuracy evaluation function. The prediction accuracy of travel destinations for different types of travel and different degrees of trajectory completion was analyzed and compared with the historical trajectory-based prediction method. The results show that the prediction accuracy of travel destinations for different types of vehicles is basically positively correlated with the degree of trajectory completion. When the trajectory completion rate reaches 80%, the accuracy of travel prediction basically reaches over 80%. Compared with the traditional prediction method based on historical trajectories, the prediction method considering temporal and spatial correlation has higher prediction accuracy, especially for taxis services with no fixed commuting travel characteristics. The prediction accuracy of travel destinations has been improved by more than 16%. The research results can better meet the needs of global traffic management.

travel destination prediction  /  spatiotemporal correlation degree  /  travel trajectory  /  trajectory completion degree  /  video AI recognition data
唐易, 刘诗昆, 丘建栋. 考虑时空关联度的车辆出行目的地预测——以深圳市福田中心区为例. 科学技术与工程, 2025 , 25 (11) : 4761 -4768 . DOI: 10.12404/j.issn.1671-1815.2403271
Yi TANG, Shi-kun LIU, Jian-dong QIU. Vehicle Travel Destination Prediction Considering Spatiotemporal Correlation Degree: A Case of Futian Central District in Shenzhen[J]. Science Technology and Engineering, 2025 , 25 (11) : 4761 -4768 . DOI: 10.12404/j.issn.1671-1815.2403271
随着交通信息感知技术的不断演进,越来越丰富的车辆出行数据被获取,为深入研究车辆出行模式提供了强有力的数据支撑[1]。车辆出行目的地预测作为该领域的重要内容,备受学术界和业界的瞩目。相比于传统基于四阶段法的集计交通出行预测,基于个体级交通数据的车辆出行目的地预测聚焦个体车辆的出行行为决策机理[2],能更好地满足交通数字孪生、出行链模型、自动驾驶等新兴技术对个体行为分析的需求,同时也有助于提供更贴合个体出行需求的定制化服务,如出行导航路径推送、车辆巡航速度推荐、车载广告精准投放等,对于新时期城市交通高质量发展与出行服务品质提升具有重要意义。
文献[3-4]表明出行者的出行决策习惯存在一定的规律性,通过挖掘一段时间内的车辆出行轨迹,可以较准确地分析预测出行者的出行决策习惯,包括出行目的地、出行方式、出行路径等,车辆出行行为具有可预测性。基于此理论,许多学者研究了基于历史出行轨迹对不同类型的车辆出行目的地进行预测。例如,甘蜜[5]论证了基于货车轨迹数据预测货运特征规律的可行性,包含了货运路径选择、出行目的地、货车交通流量等,但预测时空范围的局限性较大;Ying等[6]通过挖掘车辆的轨迹信息数据,进行轨迹序列与目的地预测。Jiang等[7]从历史轨迹数据中学习出行目的地偏好,构建出行预测模型。张国兴等[8]针对出租车轨迹具有长期依赖关系,采用一种改进的循环神经网络进行出租车目的地预测,并且缩短预测模型训练时间。魏远等[9]同样以出租车为研究对象,提出一种面向城市区域间的出租车出行起终点预测模型,该模型从区域和区域对两个维度出发,采用图卷积来分析区域之间的时空相关性,实现对区域间出行起终点与出行需求量的预测。
上述研究大多以个体车辆出行全球定位系统(global positioning system,GPS)数据为基础构建预测模型,但GPS数据覆盖样本较低,且多为出租车、货车等特殊营运车辆,数据具有明显的异构性和稀疏性,难以融合表征所有个体车辆的出行特征,很大程度上限制了预测模型精度。此外,上述研究主要是根据历史轨迹空间相似度预测未来即将发生的同类出行轨迹,但忽略了考虑对历史轨迹区分出行时段,或仅考虑了历史与预测相同出行时段的轨迹,不同时段的轨迹同样具有关联性。假定一种场景,因为加班调休的原因,原定工作日高峰时段的通勤出行,调整至工作日平峰出行,若完全基于历史工作日平峰时段的轨迹数据对该轨迹出行目的地进行预测,而忽视工作日高峰时段的轨迹数据,其预测结果准确度将受到极大影响。因此在建立出行目的地预测模型时,需综合考虑出行时间与轨迹空间双重因素的影响。
现提出一种考虑时空关联度的车辆出行目的地预测方法。选取深圳市福田中心区进行实例研究,以大量实测视频AI识别、车辆卫星定位等数据为基础,对全天车辆出行轨迹进行切分,并分时段建立车辆历史出行轨迹库,分析车辆出行时空特征,在时间上考虑不同出行时段对出行目的地预测的影响程度,在空间上考虑不同轨迹子区间对出行目的地预测的影响程度,提出车辆出行目的地预测时空关联度计算方法,并以时空关联度为权重构建出行目的地预测模型。
本文的研究思路如图1所示,包括数据准备、模型构建、实例分析3个步骤。首先,基于视频AI识别、车辆卫星定位等数据,识别全天车辆出行停留点,以此切分车辆出行轨迹,建立车辆历史出行轨迹库;然后,研究车辆出行轨迹时间与空间相关性,分别计算出行轨迹时间关联度与空间关联度,并以时间关联度与空间关联度为权重建立出行目的地预测模型;最后,选取深圳市福田中心区作为实例,计算不同轨迹完成度的出行预测准确度,并与常规基于历史轨迹的出行目的地预测方法进行对比,验证本文提出方法的实用性与有效性。
采用深圳市福田中心区视频AI识别数据以及出租车卫星定位数据作为研究基础。视频AI识别数据描述了所有经过视频卡口的过车明细情况,包含检测日期、车辆编号、设备编号、通过时间、车道编号等,视频AI识别的设备与地理信息系统(geographic information system,GIS)网络关联匹配,由此可以完整记录所有经过视频AI识别点位的车辆信息[10];出租车卫星定位数据描述了出租车实时定位及运行状况,包含定位时间、车辆编号、所属公司代码、经纬度坐标位置、车辆速度、方向角、运营状态等,基于出租车卫星定位数据可以准确计算每条路段的平均运行速度、行驶时间等运行指标[11]
已有研究成果主要是利用视频AI识别数据,捕捉车辆在全天范围内的有序出行位置信息,重构还原车辆全天完整的出行轨迹[12]。在此基础上,定义这些有序出行位置为轨迹节点,通过识别轨迹节点是否为车辆停留点,进一步将车辆全天出行轨迹切分为若干次出行。车辆全天出行轨迹切分的具体流程(图2)如下。
(1)最佳路径提取。从全天视频AI识别数据中筛选特定车辆数据,构建车辆全天出行轨迹数据集。采用GIS路网的拓扑结构作为参考,对相邻两个轨迹节点之间是否存在有效路径进行判断。若在这两个轨迹节点之间未发现有效的路径,则可推断前一个轨迹节点为停留点,表明车辆可能在该点位持续停车一段时间;若在这两个点位之间存在多条有效路径,选取距离最短路径作为最佳路径,用于后续的分析。
(2)行驶时间计算。基于出租车卫星定位数据,除了可以分析经过路段的平均行驶时间,还可以分析经过路段的最大行驶时间与最小行驶时间,进而计算由若干路段组成最佳路径的最大行驶时间与最小行驶时间。假定两个点位之间的最佳路径 L l 1 , l 2 , , l nn条路段有序组成,每条路段的出租车数量分别为 m 1 , m 2 , , m n,经过最佳路径 L的行驶时间最大值 T m a x与最小值 T m i n计算公式为
T m a x = k = 1 n m a x 1 i m k t i l k T m i n = k = 1 n m i n 1 i m k t i l k
式(1)中: T m a x T m i n分别为最佳路径行驶时间的最大值与最小值; l k为最佳路径 L的第 k条路段, 1 k n,最佳路径 L共有 n条路段; t i l k为在路段 l k的第 i辆车行驶时间, 1 i m k
(3)时间符合指数计算。定义时间符合指数TD,用来描述两个轨迹节点时间间隔与最佳路径行驶时间相符合的程度。时间符合指数TD越大,两个轨迹节点时间间隔与最佳路径行驶时间特征越符合;反之,两个轨迹节点时间间隔与最佳路径行驶时间特征越不相符。时间符合指数TD计算公式为
T D = 1 , T m i n T a b T m a x 1 - T a b - T m a x T a b , T m a x T a b 1 - ( T m i n - T a b ) T m i n , T a b T m i n
式(2)中:TD表示两个轨迹节点 a b的时间符合指数; T a b表示两个轨迹节点 a b的时间间隔; T m a x T m i n分别表示两个轨迹节点 a b之间最佳路径的行驶时间最大值与最小值。
(4)停留点识别。根据时间符合指数TD识别轨迹节点是否为停留点。定义阈值P,作为两个轨迹节点时间间隔与最佳路径行驶时间相符合的最小容忍值。若时间符合指数TD>P,两个轨迹节点时间间隔与最佳路径行驶时间相符合,两个轨迹节点为一次出行轨迹的连续节点,前一个轨迹节点为行程的出发点或中间点;反之,两个轨迹节点不连续,前一个轨迹节点为行程的停留点,后一个轨迹节点为行程的出发点。
(5)轨迹切分。识别车辆全天轨迹节点中的停留点,根据停留点对车辆全天出行轨迹进行划分,停留点作为前一次出行终点,停留点下一点作为后一次出行起点,其余轨迹节点作为为出行中间点。
基于车辆全天出行轨迹切分结果,以单次出行轨迹为记录粒度,建立车辆历史出行轨迹库。历史出行轨迹数据的字段结构包含车辆编号、出发日期、出发日期类型、出发时间、出发时段类型、轨迹节点序列、轨迹时间序列等,具体如表1所示。
基于历史出行轨迹库,可以实现多条件出行轨迹数量的查询与统计,而出行轨迹数量是后续构建出行目的地预测模型的重要基础。指定车辆在工作日高峰时段 T、经过轨迹 G、最终到达目的地 D的轨迹数量,可以通过历史出行轨迹数据的出发日期、出发时间、轨迹节点序列等字段分析获得,以 N T , G , D为该轨迹数量。
车辆出行行为预测研究可行性的基础理论来源于车辆出行具有一定的规律性:若当前轨迹与某一条历史轨迹存在部分吻合,那么该车辆有一定概率正在重复该历史轨迹,可以将历史出行目的地预测为当前轨迹的潜在出行目的地,而这个概率与潜在出行目的地存在一一对应关系。最后,对比每一个潜在出行目的地的概率,选取概率最高的潜在出行目的地作为当前轨迹最终预测出行目的地。
基于该理论进行预测出行目的地预测,其预测准确度与轨迹的时空关联性密切相关,即历史轨迹与当前轨迹出行时段越接近、轨迹空间吻合程度越高,则出行目的地预测准确度越高。因此,出行轨迹的时间与空间关联性特征是构建出行目的地预测模型的两个关键要素。
时间关联性方面,根据宏观出行目的得集聚特征,将出行时段划分为工作日高峰时段、工作日平峰、周末及节假日3个时段,3个时段分别具有典型的出行特征:工作日高峰时段以司机车通勤出行为主,起终点通常为居住地或办公地;工作日平峰以商务出行为主,周末及节假日以休闲娱乐为主,起终点随机性较大。
空间关联性方面,车辆出行轨迹数据的获取来源是视频AI识别数据,因此采用视频AI识别检测点位的有序组合表示车辆出行轨迹。定义轨迹子区间,表示车辆出行轨迹中相邻轨迹节点区间的子轨迹。在此定义基础上,假定 G为出行轨迹, g 0 , g 1 , , g n依次为车辆出行轨迹中的轨迹节点,则车辆出行轨迹可表示为 G = { g 0 g 1 g n }; G j - 1 . j为轨迹 G的轨迹子区间,则轨迹子区间可表示为 G j - 1 . j = { g j - 1 g j } ( 1 j n)。
由时间关联性要素分析可知,车辆出行轨迹的目的地与当前出行时段存在关联。针对本文划分的工作日高峰、工作日平峰、周末及节假日等时段,历史轨迹中不同时段的出行轨迹与当前目的地预测的关联程度并不相同,而关联程度则与历史出行轨迹中该时段内经过轨迹且最终到达预期目的地的轨迹数量直接相关。假定一个场景,因工作日加班调休的原因,通勤时间发生变化,车辆在工作日平峰时段发生前往公司的通勤出行,当前出行轨迹为G,出行时段为工作日平峰T2,预期出行目的地为D。该场景下,在历史相同时段工作日平峰的轨迹中,经过该出行轨迹且去往出行目的地的轨迹数量为 N T 2 , G , D,另外在历史工作日高峰经过该出行轨迹且去往出行目的地的轨迹数量为 N T 1 , G , D,但比较发现 N T 1 , G , D远大于 N T 2 , G , D,该场景下工作日高峰的历史轨迹对当前出行目的地影响程度会高于工作日平峰的历史轨迹。因此,在预测当前出行目的地时,需综合考虑历史出行轨迹中不同时段的出行轨迹数据。
定义时间关联度用于描述出行时段对当前出行轨迹目的地预测的影响程度。采用某个出行时段轨迹数量在所有时段到达相同目的地的轨迹数量占比计算时间关联度。车辆当前出行轨迹 G = { g 0 g 1 g n },则在预测出行目的地为 D的过程中出行时段 T i的时间关联度 α T i , G , D的计算公式为
α T i , G , D = N T i , G , D N T 1 , G , D + N T 2 , G , D + N T 3 , G , D
式(3)中: N T i , G , D为出行时段 T i、经过轨迹 G、到达目的地 D的轨迹数量; i = { 1,2 , 3 }; T 1 T 2 T 3分别为工作日高峰时段、工作日平峰、周末及节假日, N T 1 , G , D N T 2 , G , D N T 3 , G , D分别为上述3个时段经过出行轨迹 G、到达目的地 D的轨迹数量。
由空间关联性要素分析可知,车辆出行轨迹的目的地与当前出行轨迹子区间存在关联。针对同一条出行轨迹的若干轨迹子区间,每一条轨迹子区间与出行轨迹最终目的地的关联程度并不相同,而关联程度则与历史出行轨迹中经过轨迹子区间且最终到达预期目的地的轨迹数量直接相关。假定当前出行轨迹为 G = { g 0 g 1 g n },包含了共计 n个轨迹子区间,通常出行轨迹子区间与轨迹的最终目的地并不是呈现一一对应的关系,例如在历史出行轨迹中,车辆经过轨迹子区间 G 0,1 = { g 0 g 1 }且去往出行目的地 D的轨迹数量为 N G 0,1 , D,车辆经过轨迹子区间 G 1,2 = { g 1 g 2 }且去往出行目的地 D的轨迹数量为 N G 1,2 , D,但 N G 0,1 , D N G 1,2 , D并不相等,由此导致了当前每一个轨迹子区间对出行目的地预测的影响程度均不相同。
定义空间关联度用于描述轨迹子区间对当前轨迹目的地预测的影响程度。采用同一时段经过某个轨迹子区间数量在所有到达相同目的地的轨迹子区间数量占比计算空间关联度。车辆当前出行轨迹为 G = { g 0 g 1 g n },出行时段为T,则在预测出行目的地为 D的过程中轨迹子区间 G j - 1 . j = { g j - 1 g j }的空间关联度计算公式为
β T , G j - 1 , j , D = N T , G j - 1 , j , D k = 1 n N T , G k - 1 , k , D
式(4)中: N T i , G j - 1 , j , D表示 T时段经过轨迹子区间 G j - 1 . j且目的地为 D的轨迹数量, 1 j n , n表示当前轨迹 G经过的轨迹节点数量。
与关联度计算方法同理,可以依托大量数据积累建立的历史出行轨迹库,统计分析历史中不同时段、不同空间轨迹子区间的轨迹数量,由此可以实现推算当前出行到达指定目的地的概率。采用历史轨迹库中指定时段、轨迹子区间、出行目的地的轨迹数量,与相同时段、轨迹子区间、无目的地限制的轨迹数量的比值,作为该指定出行目的地的基本概率,在此基础上进一步考虑出行时间关联度与空间关联度对概率的影响,分别设置模型权重参数,构建出行目的地预测模型。
假定车辆当前出行时段为 T,出行轨迹为 G = { g 0 g 1 g n },定义用户经过出行轨迹 G且最终到达目的地 D的概率为
P T , G , D = j = 1 n β T , G j - 1 , j , D i = 1 3 α T i , G j - 1 , j , D N T i , G j - 1 , j , D N T i , G j - 1 , j
式(5)中: α T i , G j - 1 , j , D为出行时段 T i的时间关联度; β T , G j - 1 , j , D为轨迹子区间 G j - 1 . j的空间关联度; N T i , G j - 1 , j , D为历史轨迹库中出行时段 T i、经过轨迹子区间 G j - 1 . j、到达目的地为 D的轨迹数量, N T i , G j - 1 , j历史轨迹库中出行时段 T i、经过轨迹子区间 G j - 1 . j的轨迹数量。
采用2023年7月1—31日深圳市福田中心区AI识别数据作为实验数据集,按照本文提出的历史出行轨迹切分方法,指定时间符合指数阈值P=0.8,建立历史轨迹库。考虑到出行轨迹的完整性、出行次数等数据特征及实例分析时间的限制,从实验数据集中挑选了具有代表性的2名出租车驾驶员与2名私家车驾驶员作为本次实例分析对象,分析每辆车总出行次数、出行起止点去重的出行次数、总行驶距离、每次出行平均行驶距离等指标。采用2023年8月1—31日上述4名驾驶员的AI识别数据作为测试分析数据,用于评估验证出行预测模型的准确性。
选取的4名驾驶员出行特征指标统计如表2所示,驾驶员出行起终点期望线如图3所示。
图3中驾驶员出行期望线的粗细表示了驾驶员出行频数。由表2图3可分析得到:驾驶员1与驾驶员2出行轨迹数量总体偏少,存在两条出行频数显著较高的出行轨迹,符合私家车工作日固定通勤、周末节假日灵活出游的出行特征,具有明显的规律性和稳定性;驾驶员3与驾驶员4出行轨迹数量总体偏多,不同出行轨迹的出行频数相对均衡,符合出租车无规律、高强度的出行特征。利用具有不同特征的驾驶员出行数据,可更好地评价模型的预测效果。
根据模型权重可知,当前已发生的行程多少对模型预测效果具有显著影响。定义轨迹完成度(trajectory completion, TC)为当前已出行轨迹节点数量占整个出行轨迹总数量的百分比,轨迹完成度越大,车辆距离出行目的地越近,通常情况下出行预测模型的预测准确度也越高。轨迹完成度计算公式为
T C = N c o m p l e t e N a l l × 100 %
式(6)中: N c o m p l e t e为车辆已发生出行轨迹中被检测到的节点数量; N a l l为车辆整个出行轨迹中被检测到的节点数量。
模型预测效果直接取决于出行目的地预测准确的概率。定义预测准确度(predictable accuracy, PA)为车辆在指定条件(轨迹完成度)下准确预测出行目的地的次数与总预测次数的比值。预测准确度越高,表示在该条件下出行预测模型预测效果越好。预测准确度计算公式为
P A = F r i g h t F a l l × 100 %
式(7)中: F r i g h t为车辆在指定条件下准确预测出行目的地的次数; F a l l为针对该车辆进行的总预测次数。
为了分析出行轨迹完成度对出行目的地预测的影响,针对4名驾驶员出行测试分析数据集,分别设定出行轨迹完成度20%、40%、60%、80%等场景,进行出行目的地预测,并与实际出行目的地结果进行比较,确定出行预测准确度。通过分析轨迹完成度与预测准确的关系,评估验证出行预测模型的有效性。
经过测试得到不同轨迹完成度下的出行目的地预测准确度结果如图4所示。
图4可以得出:出行预测准确度与轨迹完成度基本成正相关,4名驾驶员均表现出“轨迹完成度越大,出行预测准确度越高”的特征。其中,驾驶员1与驾驶员2的出行预测准确度高于驾驶员3与驾驶员4,驾驶员类型对于出行目的地预测准确度影响较大,以通勤出行为主的私家车出行预测效果会明显优于无规律出行的出租车。当轨迹完成度达到80%时,出行预测准确度基本都达到80%以上,预测效果较好,最高达到93.6%(驾驶员1),最低为82.7%(驾驶员3)。
为了进一步验证本文研究所提模型的有效性与准确性,选取常规基于历史轨迹的出行目的地预测模型进行实验对比。以常规出行目的地预测模型为基本模型,本文提出考虑时空关联度的出行目的地预测模型为改进模型,设定轨迹完成度为60%,对比4名驾驶员的出行预测准确度,如图5所示。
图5可以得出:针对4名驾驶员基于改进模型的出行预测准确度均高于基于基本模型的出行预测准确度,特别是无规律出行特征的驾驶员3与驾驶员4。仅考虑历史轨迹的基本模型,难以预测无固定通勤出行起终点的出行目的地,驾驶员3与驾驶员4的出行预测准确度分别为32.6%、28.8%;通过综合考虑出行时间与空间关联特征的影响,驾驶员3与驾驶员4的出行预测准确度分别为49.2%、51.9%,相比基本模型方法,预测准确度分别提高了16.6%、23.1%。
本研究模型充分考虑出行时间和空间的关联度,以个体车辆自身历史轨迹数据为模型输入,以个体车辆出行目的地预测概率为模型输出,在实例分析中选取的实验样本遵循随机抽样原则,同时满足规律性与无规律通勤等多种出行类别,保证实验样本的多样性和均衡性,结果表明模型不仅适用于少数类别车辆出行预测,对于私家车与出租车等车辆均能够进行有效预测,提升预测准确度。因此,研究方法具有较好的适用性,能够为具备良好车辆轨迹数据基础的城市大范围、大样本个体车辆出行预测研究提供参考借鉴。
以深圳市福田中心区视频AI识别与车辆卫星定位等数据为基础,在传统基于历史轨迹的出行目的地预测方法基础上,进一步考虑车辆出行时空特征,计算车辆出行时空关联度作为权重,建立出行目的地预测模型,预测分析不同类型车辆的出行目的地,得到以下结论。
(1)工作日高峰时段通勤特征明显的私家车出行目的地预测效果会明显优于其他类型车辆出行。
(2)针对同一个出行轨迹,轨迹完成度与出行目的地预测准确度基本成正相关,即轨迹完成度越大、出行预测准确度越高。当轨迹完成度达到80%时,出行预测准确度基本都达到80%以上,4名典型驾驶员中最高达到93.6%。
(3)本文在预测过程中综合考虑了车辆出行时空特征,相比常规基于历史轨迹的预测方法,出行目的地预测准确度得到显著提高。特别是无规律出行特征的2名出租车驾驶员,通过采用本文提出的预测方法,出行预测准确度分别提高了16.6%、23.1%。
本文提出的出行预测模型进行了若干简化和假设,例如基于现场检测设备可以获取研究范围内全样本车辆出行数据,低密度检测器布设、数据样本量低势必将导致出行轨迹数据获取困难、出行目的地预测准确度不足的问题。目前国内很多城市或重点片区的前端硬件检测设施都难以支撑实现大范围、全样本车辆出行数据获取,下一步的研究可
以考虑如何融合多种车辆出行数据(例如视频卡口、车辆卫星定位、收费流水等),提高获取数据的样本量,研究更加真实复杂城市场景下的个体车辆出行预测问题。
  • 广东省城市交通数字孪生企业重点实验室项目(2022B1212020005)
参考文献 引证文献
排序方式:
[1]
殷韫, 廖璟瑒, 吴克寒. 智慧出行服务新模式构建和出行需求优化系统设计[J]. 城市交通, 2023, 21(3): 98-105, 118.
Yin Yun, Liao Jingyang, Wu Kehan. Smart travel service new mode construction and travel demand optimization system design[J]. Urban Transport of China, 2023, 21(3): 98-105, 118.
[2]
梁泉, 翁剑成, 胡娟娟, 等. 多源数据驱动下公共交通出行行为特征挖掘与预测[J]. 科学技术与工程, 2021, 21(28): 11921-11931.
Liang Quan, Weng Jiancheng, Hu Juanjuan, et al. Feature mining and prediction for the trip behavior of public transport driven by multi-source data[J]. Science Technology and Engineering, 2021, 21(28): 11921-11931.
[3]
孔德学, 敖谷昌, 张惠玲, 等. 差异化收费下货车出行选择偏好分析及建模[J]. 深圳大学学报(理工版), 2023, 40(2): 210-217.
Kong Dexue, Ao Guchang, Zhang Huiling, et al. Analysis and modeling of trucks travel choice preference under differentiated charging[J]. Journal of Shenzhen University Science and Engineering, 2023, 40(2): 210-217.
[4]
杨亚璪, 唐浩冬, 彭勇. 考虑偏好差异的后疫情时代居民出行方式选择行为研究[J]. 交通运输系统工程与信息, 2022, 3: 15-24.
Yang Yazao, Tang Haodong, Peng Yong. Residents' travel mode choice behavior in post-COVID-19 era considering preference differences[J]. Journal of Transportation Engineering and Information, 2022, 3: 15-24.
[5]
甘蜜. 货车轨迹数据在公路货运系统中应用研究综述[J]. 交通运输系统工程与信息, 2021, 5: 91-101, 113.
Gan Mi. Review on application of truck trajectory data in highway freight system[J]. Journal of Transportation Engineering and Information, 2021, 5: 91-101, 113.
[6]
Ying J C, Lee W C, Tseng V S. Mining geographic-temporal-semantic patterns in trajectories for location prediction[J]. ACM Transactions on Intelligent Systems & Technology, 2014, 5(1): 1-33.
[7]
Jiang F, Lu Z N, Gao M, et al. DP-BPR: destination prediction based on Bayesian personalized ranking[J]. Journal of Central South University, 2021, 28(2): 494-506.
[8]
张国兴, 李亚东, 张磊, 等. 基于SDZ-RNN的出租车出行目的地预测方法[J]. 计算机工程与应用, 2018, 54(6): 143-149.
Zhang Guoxing, Li Yadong, Zhang Lei, et al. Taxi travel destination prediction based on SDZ-RNN[J]. Computer Engineering and Applications, 2018, 54(6): 143-149.
[9]
魏远, 林彦, 郭晟楠, 等. 融合出发地与目的地时空相关性的城市区域间出租车需求预测[J]. 计算机应用, 2023, 43(7): 2100-2106.
Wei Yuan, Lin Yan, Guo Shengnan, et al. Prediction of taxi demands between urban regions by fusing origin-destination spatial-temporal correlation[J]. Journal of Computer Applications, 2023, 43(7): 2100-2106.
[10]
龙小强, 苏跃江, 余畅, 等. 基于卡口车牌识别数据的车辆出行分析[J]. 交通运输系统工程与信息, 2019, 2: 66-72.
Long Xiaoqiang, Su Yuejiang, Yu Chang, et al. Analyzing methods of vehicle' travel using plate recognition data[J]. Journal of Transportation Engineering and Information, 2019, 2: 66-72.
[11]
程琳, 张晨皓, 于新莲, 等. 基于马尔可夫决策过程的出租车寻客路径优化[J]. 武汉理工大学学报, 2022(5): 40-46.
Cheng Lin, Zhang Chenhao, Yu Xinlian, et al. Route optimization of taxicab based on Markov decision process[J]. Journal of Wuhan University of Technology, 2022(5): 40-46.
[12]
胡明伟, 王守峰, 黄文柯, 等. 基于车牌识别数据的行驶轨迹重构和排放测算[J]. 深圳大学学报(理工版), 2020, 37(2): 111-120.
Hu Mingwei, Wang Shoufeng, Huang Wenke, et al. Vehicle trajectory reconstruction and emission estimation based on license plate recognition data[J]. Journal of Shenzhen University Science and Engineering, 2020, 37(2): 111-120.
2025年第25卷第11期
PDF下载
309
121
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2403271
  • 接收时间:2024-05-05
  • 首发时间:2025-07-09
  • 出版时间:2025-04-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-05
  • 修回日期:2024-08-01
基金
广东省城市交通数字孪生企业重点实验室项目(2022B1212020005)
作者信息
    1 深圳市城市交通规划设计研究中心股份有限公司, 深圳 518057
    2 中山大学智能工程学院, 深圳 518107
    3 广东省智能交通系统重点实验室, 深圳 518107

通讯作者:

* 刘诗昆(1997—),女,汉族,湖南衡阳人,博士研究生。研究方向:智能交通,交通环境。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403271
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏