基于规则判别的末端配送停留点识别与出行链特征

doi:10.16097/j.cnki.1009-6744.2024.06.020

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (6): 232-241.DOI: 10.16097/j.cnki.1009-6744.2024.06.020

基于规则判别的末端配送停留点识别与出行链特征

姜晓红¹，陈庆炜¹，严亚丹^*2，韩兵^3,4，李家伟¹

1. 南京林业大学，汽车与交通工程学院，南京210037；2.郑州大学，土木工程学院，郑州450001； 3. 南京大学，建筑与城市规划学院，南京210093；4.苏州规划设计研究院股份有限公司，江苏苏州215006

收稿日期:2024-08-26 修回日期:2024-09-22 接受日期:2024-09-24 出版日期:2024-12-25 发布日期:2024-12-18
作者简介:姜晓红(1985- )，女，江苏常州人，副教授，博士。
基金资助:
国家自然科学基金 (52302392)。

Rule-based Discriminative Identification and Travel Chain Characterization of Last-mile Delivery Stops

JIANG Xiaohong¹,CHEN Qingwei¹,YANYadan^*2,HAN Bing^3,4,LI Jiawei¹

1. Automotive and Transportation College, Nanjing Forest University, Nanjing 210037, China; 2. School of Civil Engineering, Zhengzhou University, Zhengzhou 450001, China; 3. Department ofArchitecture and Urban Planning, Nanjing University, Nanjing 210093, China; 4. SuzhouAcademy of Urban Planning and Design Co Ltd, Suzhou 215006, Jiangsu, China

Received:2024-08-26 Revised:2024-09-22 Accepted:2024-09-24 Online:2024-12-25 Published:2024-12-18
Supported by:
NationalNaturalScienceFoundation of China (52302392)。

摘要/Abstract

摘要： 响应需求的末端配送方案可显著提升顾客满意度，识别并提取末端配送快递三轮车配送停留点特征是分析配送时空分布和动态需求的基础。因此，本文提出结合兴趣点(POI)与停留时长规则的停留点识别方法。首先，利用POI信息和瞬时速度初步筛选快递三轮车轨迹数据；然后，引入停留时长阈值作为二次筛选条件；最后，合并临近的聚集点，形成完整的停留点集。采用人工校验识别结果的准确性，并借助熵率法计算停留链的熵率，量化评估不同识别方法的精确度。以苏州市顺丰速运快递网点的快递三轮车配送轨迹数据为实证对象，将所提出的方法与货运卡车停留点识别中常用的基于密度的聚类算法(Density-BasedSpatialClusteringofApplications with Noise, DBSCAN)进行对比分析。结果表明，DBSCAN算法易将交通信号灯等待误判为配送停留点，而本文所提出的方法则有效规避了该问题，实现高达98%的精确率和召回率；同时，熵率法的应用进一步验证了所提方法在准确率上的有效性。在此基础上，扩大研究范围并识别配送停留点后，分析快递三轮车的出行链与配送时空分布特征。结果表明，8:00左右的高峰期配送车辆数显著多于16:00左右的高峰期；住宅区为配送热点，车辆数最多，且出行距离和工作时长最长；酒店类配送呈现停留时长较短的特点；此外，停留点空间分布亦揭示了部分配送距离偏远的情况。

关键词: 综合运输, 货物运输组织, 停留点识别, 规则判别, 快递三轮车, 末端配送, 出行链特征

Abstract: Responding to demand of last-mile delivery programs can significantly improve customer satisfaction. Identifying and extracting characteristics of stopping points made by last-mile express tricycle deliveries is fundamental to analyze spatial-temporal distribution patterns and dynamic demand. This paper proposes a stopping point identification method by combining Point of Interest (POI) data with stopping time rules. The POI information and instantaneous speeds are utilized to screen express tricycle trajectory data. The stopping time threshold is introduced as secondary filtering criteria. The neighboring aggregation points are merged to create a complete set of stopping points. The accuracy of the identification results is verified through manual verification, and the entropy rate of the stop chain is calculated using the entropy rate method to quantitatively evaluate the accuracy of different identification methods. Taking trajectory data of express tricycles from Shun Feng Express courier outlets in Suzhou city as the empirical object, this paper compares the proposed method with the commonly used the density-based spatial clustering algorithm of applications with noise to identify stopping points of cargo trucks. The results show that the DBSCAN algorithm is prone to misidentifying traffic signal waiting as a delivery stop, while the proposed method effectively avoids this issue, achieving both precision and recall rates of up to 98%. Furthermore, the application of the entropy rate method further validates the effectiveness of the proposed method in terms of accuracy. On this basis, by expanding the research scope and identifying distribution stopping points, this paper analyzes the travel chains and spatial-temporal distribution characteristics of express tricycles. The results indicate that the number of delivery vehicles during the peak period around 8:00 am is significantly higher than that during the peak period around 4:00 pm. Residential areas are hotspots for distribution, with the highest concentration of vehicles, the longest travel distances, and the longest working hours. Hotel deliveries, on the other hand, exhibit shorter stopping times. Additionally, the spatial distribution of stopping points also reveals the delivery conditions to the remote locations.

Key words: integrated transportation, freight transportation organization, stopping point identification, rule discrimination, express tricycles, last-mile delivery, travel chain characteristics

中图分类号:

U121

姜晓红, 陈庆炜, 严亚丹, 韩兵, 李家伟. 基于规则判别的末端配送停留点识别与出行链特征[J]. 交通运输系统工程与信息, 2024, 24(6): 232-241.

JIANG Xiaohong, CHEN Qingwei, YANYadan, HAN Bing, LI Jiawei. Rule-based Discriminative Identification and Travel Chain Characterization of Last-mile Delivery Stops[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 232-241.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.06.020

http://www.tseit.org.cn/CN/Y2024/V24/I6/232

参考文献

[1] 甘蜜,卿三东,刘晓波,等.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, 21(5): 91-101, 113. [GAN M, QING S D, LIU X B, et al. Review on application of truck trajectory data in highway freight system[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(5): 91-101, 113.]

[2] ALHO A R, YOU L L, LUFP,etal. Next-generation freight vehicle surveys: Supplementing truck GPS tracking with a driver activity survey[C]//Proceedings of the 21st International Conference on Intelligent Transportation Systems, Maui, Hawaii, USA, 2018: 2974-2979.

[3] LARANJEIRO P F, MERCHAN D, GODOY L A, et al. Using GPS data to explore speed patterns and temporal fluctuations in urban logistics: The case of Sao Paulo, Brazil[J]. Journal of Transport Geography, 2019, 76: 114 129.

[4] ZANJANI A B, PINJARI A, KAMALI M, et al. Estimation of statewide origin-destination truck flows from large streams of GPS data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2015, 2: 87-96.

[5]陈传明,龚杉,杨峰,等.基于停留区域识别的子轨迹异常检测方法[J]. 地球信息科学学报, 2023, 25(4): 684-697. [CHEN C M, GONG S, YANG F, et al. Sub trajectory anomaly detection method based on stay area recognition[J]. Journal of Geo-information Science, 2023, 25(4): 684-697.]

[6] YANG Y T, JIA B, YAN X Y, et al. Identifying intercity freight trip ends of heavy trucks from GPS data[J]. Transportation Research Part C: Emerging Technologies, 2022, 157: 102590.

[7] GONG L, SATO H, YAMAMOTO T, et al. Identification of activity stop locations in GPS trajectories by density based clustering method combined with support vector machines[J]. Journal of Modern Transportation, 2015, 23 (3): 202-213.

[8] PATEL V, MALEKI M, KARGAR M, et al. A cluster driven classification approach to truck stop location identification using passive GPS data[J]. Journal of Geographical Systems, 2022, 24(4): 657-677.

[9] 姚雅慧,张戎.基于轨迹数据的货车停车目的识别方法[J]. 交通运输系统工程与信息,2023, 23(2): 92-99. [YAO Y H, ZHANG R. Truck stop purpose identification method based on trajectory data[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(2): 92-99.]

[10] SIRIPIROTE T, SUMALEE A, HO H W. Statistical estimation of freight activity analytics from global positioning system data of trucks[J]. Transportation Research Part E: Logistics and Transportation Review, 2020, 140: 101986.

[11] BERMINGHAM L, LEE I. Mining place-matching patterns from spatio-temporal trajectories using complex real-world places[J]. Expert Systems with Applications, 2019, 122: 334-350.

[12] 崔洪军, 赵锐,朱敏清,等.基于熵率的公交乘客出行重复性度量方法[J]. 公路交通科技,2020, 37(9): 97 103, 112. [CUI H J, ZHAO R, ZHU M Q, et al. A method for measuring repeatability of bus passenger travel based on entropy rate[J]. Journal of Highway and Transportation Research and Development, 2020, 37(9): 97-103, 112.]

[13] 高万晨,路世昌,李丹.基于智能刷卡数据的乘客上车站点估计研究[J].交通运输系统工程与信息,2023,23 (6): 307-318. [GAO W C, LU S C, LI D. Estimation algorithms of passenger boarding stops based on smart card data[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(6): 307-318.]

[14] 赵卫锋,李清泉,李必军.利用城市POI数据提取分层地标[J]. 遥感学报, 2011, 15(5): 973-988. [ZHAO W F, LI Q Q, LI B J. Extracting hierarchical landmarks from urban POI data[J]. National Remote Sensing Bulletin, 2011, 15(5): 973-988].

[15] 薛冰,赵冰玉,肖骁,等.基于POI大数据的资源型城市功能区识别方法与实证:以辽宁省本溪市为例[J].人文地理,2020, 35(4): 81-90. [XUE B, ZHAO B Y, XIAO X, et al. A POI data-based study on urban functional areas of the resources-based city: A case study of Benxi, Liaoning[J]. Human Geography, 2020, 35(4): 81-90.

[16] 谢孟, 程怡诺,范胜龙.基于POI数据的福州城市功能区识别[J]. 农业与技术, 2023, 43(13): 107-112. [XIE M, CHENG Y N, FAN S L. Identification of urban functional areas in Fuzhou based on POI data[J]. Agriculture and Technology, 2023, 43(13): 107-112.

基于规则判别的末端配送停留点识别与出行链特征

Rule-based Discriminative Identification and Travel Chain Characterization of Last-mile Delivery Stops

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	万民, 匡海波, 贾鹏, 余方平, 马千里, 张益阁, 赵素娥. 考虑损耗的粮食装载方式与运输路径联合优化[J]. 交通运输系统工程与信息, 2025, 25(1): 15-23.
[2]	杨华龙, 于果. 碳交易价格不确定下冷链多式联运路径优化[J]. 交通运输系统工程与信息, 2024, 24(6): 5-14.
[3]	冯芬玲, 董开云, 张泽, 方源. 基于级联失效的西部陆海新通道网络脆弱性分析[J]. 交通运输系统工程与信息, 2024, 24(6): 15-29.
[4]	梁辉, 景云, 孙国锋, 宋琦. 考虑过轨运营模式的市域铁路时刻表优化研究[J]. 交通运输系统工程与信息, 2024, 24(6): 126-134.
[5]	周金龙, 张英贵, 肖杨, 王娟. 不确定时间下多式联运多目标路径优化模型与算法[J]. 交通运输系统工程与信息, 2024, 24(6): 193-205.
[6]	段力伟, 杨航, 陈坚. 考虑枢纽延误的集装箱公铁联运多目标路径优化[J]. 交通运输系统工程与信息, 2024, 24(6): 275-285.
[7]	王小寒, 靳志宏. 海铁联运港站共享堆场的箱区分配及转场联合优化[J]. 交通运输系统工程与信息, 2024, 24(5): 283-294.
[8]	王娟, 程玉丽, 杨雨菡, 张英贵. 考虑碳排放的长大货物多式联运路径优化[J]. 交通运输系统工程与信息, 2024, 24(4): 1-11.
[9]	王宗保, 钟鸣. 基于整体规划建模的公平性区域货运碳税规划方法[J]. 交通运输系统工程与信息, 2024, 24(4): 12-22.
[10]	刁璀洁, 王文敏, 蔡佳芯, 靳志宏, 郭姝娟. 考虑双重集卡优先的闸口通道与场桥配置协同优化[J]. 交通运输系统工程与信息, 2024, 24(3): 310-322.
[11]	杨东, 李艳红, 田春林. 交通运输行业碳排放自然达峰特征与峰值预测研究[J]. 交通运输系统工程与信息, 2024, 24(2): 34-44.
[12]	孙宗胜, 帅斌, 杨俊杰, 许旻昊. 客观赋权对快捷货运各方式间临界运距影响分析[J]. 交通运输系统工程与信息, 2024, 24(2): 45-52.
[13]	王爽, 孙翔. 基于车船直取模式的集装箱海铁联运衔接优化[J]. 交通运输系统工程与信息, 2024, 24(2): 53-62.
[14]	李宁海, 陈硕, 梁肖, 田佩宁. 我国交通运输业碳达峰时间预测[J]. 交通运输系统工程与信息, 2024, 24(1): 2-13.
[15]	汪玲, 王琪, 唐磊. 中国交通枢纽城市生态交通效率时空特征分析[J]. 交通运输系统工程与信息, 2024, 24(1): 14-23.