计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (8): 245-256.doi: 10.11896/jsjkx.250900014

• 人工智能 • 上一篇    下一篇

多源关联知识图谱增强的图网络交通预测模型

全景涛, 张磊, 刘佰龙, 王非凡   

  1. 中国矿业大学矿山数字化教育部工程研究中心 江苏 徐州 221116
    中国矿业大学计算机科学与技术学院 江苏 徐州 221116
  • 收稿日期:2025-09-01 修回日期:2025-12-18 出版日期:2026-08-15 发布日期:2026-08-17
  • 通讯作者: 张磊(zhanglei@cumt.edu.cn)
  • 作者简介:(ox8cccccccc@163.com)
  • 基金资助:
    中国矿业大学研究生创新计划(2024WLJCRCZL253);江苏省研究生科研与实践创新计划(SJCX24_1389)

Leveraging Multi-source Contextual Knowledge-enhanced Graph for Traffic Forecasting

QUAN Jingtao, ZHANG Lei, LIU Bailong, WANG Feifan   

  1. Engineering Research Center of Mine Digitalization of Ministry of Education, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China
    School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China
  • Received:2025-09-01 Revised:2025-12-18 Published:2026-08-15 Online:2026-08-17
  • About author:QUAN Jingtao,born in 2001,postgra-duate.His main research interests include knowledge graph and traffic prediction.
    ZHANG Lei,born in 1977,associate professor,is a member of CCF(No.12434S).His main research interest is spatio-temporal data mining.
  • Supported by:
    Postgraduate Innovation Program of China Universityof Mining and Technology(2024WLJCRCZL253) and Postgraduate Research & Practice Innovation Program of Jiangsu Province(SJCX24_1389).

PDF (PC)

106

摘要： 交通预测旨在基于历史的交通状态信息预测未来的交通状态,是智能交通系统领域的重要研究方向。尽管现有的交通预测模型在建模复杂时空模式方面取得了一定的成效,但其依赖于先进的深度学习技术,在多源关联知识的表示以及全局知识图拓扑信息的融合方面存在不足,难以充分刻画外部环境与内部网络中多种关联信息的影响,限制了模型的预测效果。对此,提出了多源关联知识图谱增强的图网络交通预测模型MCK-GWN(Multi-source Contextual Knowledge-enhanced Graph WaveNet)。在多源关联知识表示方面,通过构建多源关联知识图谱,丰富交通节点POI(Point of Interest)关联与交通节点间的语义关联,系统性表示了外部与内部的关联知识。在多源关联知识融合方面,设计了多源关联感知模块:POI异质感知单元聚焦外部环境属性关联,语义路径感知单元聚焦内部网络语义关系,提升了全局知识图拓扑信息的融合能力。在SZ-TAXI数据集上的实验结果表明,MCK-GWN模型在所有评估指标上都达到了最优的预测性能,相较于当前最佳基准模型KMHNet,其平均绝对误差(MAE)降低了3.15%。

关键词: 交通预测, 知识图谱, 图神经网络, 外部因素融合

Abstract: Traffic prediction aims to forecast future traffic conditions based on historical traffic conditions and is a crucial research topic in the field of intelligent transportation systems.Although existing traffic prediction models have achieved considerable progress in modeling complex spatio-temporal patterns,they still heavily rely on advanced deep learning techniques and exhibit limitations in representing multi-source contextual knowledge and integrating global graph-topological information.Consequently,they fail to fully capture the diverse context about external environments and internal networks,which constrains their perfor-mance.To address these issues,this paper proposes MCK-GWN(Multi-source Contextual Knowledge-enhanced Graph WaveNet),a graph-based traffic prediction model enhanced by multi-source contextual knowledgegraph.In terms of multi-source knowledge representation,a multi-source contextual knowledge graph is constructed to enrich the POI(Point of Interest) context of traffic nodes and the semantic context between nodes,effectively characterizing both external and internal contextual knowledge.In terms of multi-source knowledge fusion,the POI heterogeneity-aware unit focuses on modeling external environmental attributes,while the semantic path-aware unit focuses on internal network semantic relations,thereby enhancing the integration capability of global graph-topological information.Experimental results on the SZ-TAXI dataset demonstrate that MCK-GWN achieves the best performance across all evaluation metrics,reducing the mean absolute error(MAE) by 3.15% compared with the state-of-the-art baseline model KMHNet.

Key words: Traffic prediction, Knowledge graph, Graph neural network, External factor fusion

中图分类号: 

  • TP391
[1] LUO X,ZHU C,ZHANG D,et al.Stg4traffic:A survey andbenchmark of spatial-temporal graph neural networks for traffic prediction[J].arXiv:2307.00495,2023.
[2] YIN X,WU G,WEI J,et al.Deep learning on traffic prediction:Methods,analysis,and future directions[J].IEEE Transactions on Intelligent Transportation Systems,2021,23(6):4927-4943.
[3] SAYED S A,ABDEL-HAMID Y,HEFNY H A.Artificial intelligence-based traffic flow prediction:a comprehensive review[J].Journal of Electrical Systems and Information Technology,2023,10(1):13.
[4] WILLIAMS B M,HOEL L A.Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process:Theoretical basis and empirical results[J].Journal of Transportation Engineering,2003,129(6):664-672.
[5] OKUTANI I,STEPHANEDES Y J.Dynamic prediction of traffic volume through Kalman filtering theory[J].Transportation Research Part B:Methodological,1984,18(1):1-11.
[6] WU C H,HO J M,LEE D T.Travel-time prediction with support vector regression[J].IEEE Transactions on Intelligent Transportation Systems,2004,5(4):276-281.
[7] TEDJOPURNOMO D A,BAO Z,ZHENG B,et al.A survey on modern deep neural network for traffic prediction:Trends,methods and challenges[C]//2023 IEEE 39th International Conference on Data Engineering(ICDE).IEEE,2023:3795-3796.
[8] SHAO Z,WANG F,XU Y,et al.Exploring progress in multivariate time series forecasting:Comprehensive benchmarking and heterogeneity analysis[J].IEEE Transactions on Knowledge and Data Engineering,2024,37(1):291-305.
[9] CHEN M,GAN K,LI K,et al.A Spatial-temporal Graph Convolutional Network Model for Accurate and Robust Traffic Flow Prediction Based on Real-time Multimodal Spatial-temporal Data[J].Journal of Highway and Transportation Research and Development,2021,38(8):134-139,158.
[10] ZHANG X,JIANG Z,LOU P.Triple Dynamic Graph Convolutional Recurrent Network for Traffic Prediction[J].IEEE Transactions on Intelligent Transportation Systems,2025,26(8):12647-12660.
[11] LIU H,DONG Z,JIANG R,et al.Staeformer:Spatio-temporal adaptive embedding makes vanilla transformer SOTA for traffic forecasting[J].arXiv:2308.10425,2023.
[12] SHUAI S,KONG X,LIU L,et al.Hypernetwork-Enhanced Hierarchical Federated Learning for Long-Term Traffic Prediction with Transformer[J].ACM Transactions on Intelligent Systems and Technology,2025,17(3):1-24.
[13] ALI A,ULLAH I,AHMAD S,et al.An attention-driven spatio-temporal deep hybrid neural networks for traffic flow prediction in transportation systems[J].IEEE Transactions on Intelligent Transportation Systems,2025,26(9):14154-14168.
[14] ZHU J,WANG Q,TAO C,et al.AST-GCN:Attribute-augmented spatiotemporal graph convolutional network for traffic forecasting[J].IEEE Access,2021,9:35973-35983.
[15] ZHANG Y,ZHAO T,GAO S,et al.Incorporating multimodal context information into traffic speed forecasting through graph deep learning[J].International Journal of Geographical Information Science,2023,37(9):1909-1935.
[16] ZHU J,HAN X,DENG H,et al.KST-GCN:A knowledge-driven spatial-temporal graph convolutional network for traffic forecasting[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(9):15055-15065.
[17] HAN X,ZHANG X,WU Y,et al.Knowledge-based multiple relations modeling for traffic forecasting[J].IEEE Transactions on Intelligent Transportation Systems,2024,25(9):11844-11857.
[18] WANG S,LV Y,PENG Y,et al.Metro traffic flow prediction via knowledge graph and spatiotemporal graph neural network[J].Journal of Advanced Transportation,2022,2022(1):2348375.
[19] ZHOU Y,LIU Y,NING N,et al.Integrating knowledge representation into traffic prediction:a spatial-temporal graph neural network with adaptive fusion features[J].Complex & Intelligent Systems,2024,10(2):2883-2900.
[20] XIONG H,SHEN G,LAN X,et al.Hit-gcn:spatial-temporal graph convolutional network embedded with heterogeneous information of road network for traffic forecasting[J].Electronics,2023,12(6):1306.
[21] NING Y,LIU H,WANG H,et al.UUKG:unified urban knowledge graph dataset for urban spatiotemporal prediction[J].Advances in Neural Information Processing Systems,2023,36:62442-62456.
[22] ZHANG Y,WANG Y,GAO S,et al.Context-aware knowledge graph framework for traffic speed forecasting using graph neural network[J].IEEE Transactions on Intelligent Transportation Systems,2024,26(3):3885-3902.
[23] WU Z,PAN S,LONG G,et alGraph wavenet for deep spatial-temporal graph modeling[J].arXiv:1906.00121,2019.
[24] LIU Z,DU W,YAN D,et al.Short-term traffic flow forecasting based on combination of k-nearest neighbor and support vector regression[J].Journal of Highway and Transportation Research and Development(English Edition),2018,12(1):89-96.
[25] YU B,YIN H,ZHU Z.Spatio-temporal graph convolutional networks:A deep learning framework for traffic forecasting[J].arXiv:1709.04875,2017.
[26] SONG C,LIN Y,GUO S,et al.Spatial-temporal synchronous graph convolutional networks:A new framework for spatial-temporal network data forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:914-921.
[27] ZHANG X,PAN L,SHEN Q,et al.Trend-aware spatio-temporal fusion graph convolutional network with self-attention for traffic prediction[J].Neurocomputing,2025,637:130040.
[28] ZHOU Z,ZHU R,CHEN B,et al.Dynamic Graph Convolutional Traffic Flow Prediction Based on Multi-scale Downsampling Convolutional Interaction[J].Journal of Highway and Transportation Research and Development,2025,42(7):1-12.
[29] GUO S,LIN Y,WAN H,et al.Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting[J].IEEE Transactions on Knowledge and Data Engineering,2021,34(11):5415-5428.
[30] JIANG J,HAN C,ZHAO W X,et al.Pdformer:Propagation delay-aware dynamic long-range transformer for traffic flow prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2023:4365-4373
[31] GUO H F,XU H W,ZHOU Z S.Urban Traffic PredictionBased on Deep Spatio-temporal Hybrid Graph Convolution[J] Journal of Chinese Computer Systems,2025,46(1):97-103.
[32] ZHAO L,SONG Y,ZHANG C,et al.T-GCN:A temporal graph convolutional network for traffic prediction[J].IEEE Transactions on Intelligent Transportation Systems,2019,21(9):3848-3858.
[33] LONG W,XIAO Z,WANG D,et al.Unified spatial-temporal neighbor attention network for dynamic traffic prediction[J].IEEE Transactions on Vehicular Technology,2022,72(2):1515-1529.
[34] LI J,DONG W,GUI X.uTransformer:unified spatial-temporal transformer with external factors for traffic flow forecasting[J].The Journal of Supercomputing,2025,81(1):281.
[35] YANG R,SALIM F D,XUE H.Sstkg:Simple spatio-temporal knowledge graph for intepretable and versatile dynamic information embedding[C]//Proceedings of the ACM Web Conference 2024.2024:551-559.
[36] GONG J,LIU Y,LI T,et al.Empowering spatial knowledge graph for mobile traffic prediction[C]//Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems.2023:1-11.
[37] WANG Y,HU J,TENG F,et al.KaTaGCN:knowledge-aug-mented and time-aware graph convolutional network for efficient traffic forecasting[J].Information Fusion,2024,111:102542.
[38] WANG S,ZHANG Y,HU Y,et al.Knowledge fusion enhanced graph neural network for traffic flow prediction[J].Physica A:Statistical Mechanics and its Applications,2023,623:128842.
[39] LI M,ZHU Z.Spatial-temporal fusion graph neural networksfor traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4189-4196.
[40] BERNDT D J,CLIFFORD J.Using dynamic time warping tofind patterns in time series[C]//Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining.1994:359-370.
[41] LIN Y,LIU Z,SUN M.Knowledge representation learning with entities,attributes and relations[J].Ethnicity,2016,1:41-52.
[42] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.2013:2787-2795.
[43] SUN Z,DENG Z H,NIE J Y,et al.Rotate:Knowledge graph embedding by relational rotation in complex space[J].arXiv:1902.10197,2019.
[44] FLOYD R W.Algorithm 97:shortest path[J].Communications of the ACM,1962,5(6):345-345.
[45] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[46] LI Y,YU R,SHAHABI C,et al.Diffusion convolutional recurrent neural network:Data-driven traffic forecasting[J].arXiv:1707.01926,2017.
[47] BAI L,YAO L,LI C,et al.Adaptive graph convolutional recurrent network for traffic forecasting[J].Advances in Neural Information Processing Systems,2020,33:17804-17815.
[48] JIANG J,HAN C,JIANG W,et al.Libcity:A unified library towards efficient and comprehensive urban spatial-temporal prediction[J].arXiv:2304.14343,2023.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发