Real-time Analytics · Risk Management
Joint Electronic Toll Service needed to govern massive highway transaction and mobility data, support more than 25 million ETC users, and turn that data into AI-assisted operational decisions for tolling, traffic prediction, and road-network safety.
Reported impact
The platform improved development productivity, turned highway data into tradable products, and delivered AI-assisted traffic forecasting and anomaly detection that improve road-network operations and traveler safety.
Guangdong Joint Electronic Toll Service built a Huawei Cloud data and AI stack to turn highway transaction and mobility data into operational products and AI decisions. DataArts Studio standardizes and governs raw entry, exit, and gantry records across Guangdong's toll network, while Data Lake Insight (DLI) provides the analytical engine for multi-source traffic computation with a serverless, storage-compute-separated architecture that can scale to 20,000 cores in minutes. The governed data is organized into models, asset views, and six product lines with 63 data products. On top of that data base, the company uses ModelArts and domain algorithms for traffic-flow forecasting and smart toll auditing. Daily vehicle passage data, video feeds, and checkpoint images are cleaned and modeled, then processed for AI prediction, abnormal-transaction recognition, and decision support for operators, drivers, police, transport agencies, and emergency-management stakeholders.
Vehicle passage records, toll-station and gantry data, video-monitoring streams, and checkpoint images are standardized in DataArts Studio, then processed in DLI for batch and streaming analytics. The curated data feeds ModelArts and traffic-domain algorithms for forecasting and anomaly detection, with outputs delivered into toll auditing, network operations, and external decision-support workflows.
"DataArts Studio standardizes entrance, exit, and gantry traffic data, while DLI provides the multi-source analytics needed for traffic big data. (original: 通过华为云一站式数据治理中心DataArts Studio实现入口流水、出口流水、门架流水等交通原始数据标准化...基于华为云数据湖探索DLI的多模分析能力满足交通大数据复杂计算需求。)"
"Huawei Cloud helped Joint Electronic Toll Service handle massive data computation and analysis challenges, build six product lines for highway data assetization, and use AI to multiply the level of transport intelligence. (original: 华为云在大数据、人工智能等领先技术能力，助力联合电服成功应对海量数据计算和分析的挑战，构建6大产品生产线完成公路数据资产化交易，AI应用成倍提升交通智慧化水平。)"
"Joint Electronic Toll Service built a unified highway big-data base on Huawei Cloud, improved data-application development efficiency by 50%, completed daily aggregation and calculation for 1.1 billion records, and created 6 product lines with 63 data products. (original: 联合电服公司基于华为云大数据平台构建数据治理和开发体系...成功打造6大数据产品生产线，共63个大数据产品，构建了坚实的统一的高速公路大数据底座，数据应用开发效率提升50%，完成每天11亿条数据汇总计算。)"
"The company uses real-time vehicle traffic data and AI to improve toll-audit, peak-and-valley flow prediction, road-network situation awareness, and irregular-driving detection. (original: 基于实时的车辆通行数据，积极使用AI提升高速收费稽核、高峰低谷车流量预测、高速路网态势感知以及不规范行车等场景的识别精度。)"
"The traffic-flow prediction result achieved accuracy greater than 95%, and the smart toll-auditing application can proactively identify abnormal transactions and verify path-based charges. (original: 利用基于时空大数据的高速公路车流量预测算法...车流预测流量准确率大于95%...智能收费稽核应用实现了主动识别异常交易车辆，对所有交易进行路径拟合核对费额。)"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Huawei Cloud Sample Archived · May 11, 2026 Yunnan Communications Investment and Construction Group Yunnan Jiaotou needed a transport-domain AI system that could handle complex mountain highway construction, maintenance, operations, and safety workflows, but no mature transportation large model, no high-quality domain… accuracy greater than 90% AI platform toolchain · Green Beautiful Corridor transportation large model · Huawei Cloud Stack Huawei Cloud Sample Archived · Jan 15, 2026 Conch Group Conch needed to scale AI across cement production, but traditional model development was slow, hard to generalize, and too weak to support real-time quality, energy, equipment, and safety optimization at industrial… 28 equipment-monitoring scenarios AI training center · Huawei Cloud Stack · NLP large model Huawei Cloud Sample Archived · Sep 8, 2025 Ordos City Ordos needed a repeatable way to modernize hundreds of fragmented coal mines, but operators lacked shared standards, interoperable data, scalable AI infrastructure, and reusable models for safety, efficiency, and… 5 demonstration mines launched Huawei Cloud Stack · MaaS application marketplace · Pangu mining large model 