Customer Service Automation · Supply Chain Optimization
Shandong Port Group needed a better way to serve many kinds of logistics customers because information was fragmented, multimodal transport coordination was weak, and inconsistent service processes limited logistics efficiency and hurt the port business environment.
Reported impact
Shandong Port Group created a smarter customer-facing supply-chain service layer that can reduce friction across port logistics, improve transparency, and support long-term smart-port transformation.
Shandong Port Group used large-model technology to build six intelligent-agent applications for outward-facing supply-chain services: Shipowner Steward, Smart Route Pilot, Port Encyclopedia, Intelligent Tracking, Intelligent Customs Clearance, and Smart Price Inquiry. Instead of focusing only on back-office AI, the project targeted the operational pain points of ship owners, freight forwarders, cargo owners, customs stakeholders, and truck drivers. Each agent applies the pretrained model's language understanding, generation, reasoning, or BI analysis abilities to a different workflow: ship and KPI queries, navigation and yard guidance, policy and process Q&A, real-time container visibility, HS code matching and customs-process explanation, and route-and-cost planning. Together, the agents create a common intelligent service layer across the port group's fragmented workflows, helping logistics users get more consistent answers and faster execution while giving the port a reusable smart-supply-chain interface for ongoing expansion.
Port, customs, maritime, logistics, and shipment-status data feed the six supply-chain agents, each agent applies large-model reasoning to a specific customer workflow, and the results return as guidance, tracking, policy answers, or route recommendations to external users across the port ecosystem.
Each application targets different customer groups and supply-chain service scenarios using the pretrained large model's language understanding, generation, reasoning, and BI-analysis capabilities. (original: 基于预训练大语言模型已具备的文字理解、生成、逻辑推理、自然语言处理、BI分析等通用性的底层能力赋能供应链对外服务的不同场景和客户群体。)
Intelligent Customs Clearance matches HS codes and answers import-export customs-clearance questions for cargo owners and forwarders. (original: 智能通关：为货主、货代提供HSCODE货物编码匹配和进出口通关流程解答，优化通关效率。)
Intelligent Tracking gives customers real-time visibility into container status and cargo movement through the port. (original: 智能跟踪：通过实时追踪集装箱状态，帮助客户掌握货物在港口的流转情况，确保物流信息透明、可控。)
The initiative is meant to lower time spent by vehicles, ships, and cargo in port, reduce logistics cost, and improve the social efficiency of the logistics system. (original: 这将有助于降低“车船货”在港停时，减少物流成本，提升社会综合物流效率。)
The project built six agent applications — Shipowner Steward, Smart Route Pilot, Port Encyclopedia, Intelligent Tracking, Intelligent Customs Clearance, and Smart Price Inquiry — for outward-facing port supply-chain services. (original: 本次建设内容主要包括：船东管家、智途领航、口岸宝典、智能跟踪、智能通关以及智行问价六个智能体应用。)
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
Baidu AI Cloud Sample Jul 7, 2025 Deppon Express As order volume and service complexity grew, Deppon Express needed to lower communication cost, improve response speed, and deliver consistent service across many digital channels without overloading human agents. The platform connects more than 10 service entrances. Baidu Intelligent Customer Service · Baidu Keyue · Logistics Knowledge Base 
Mistral Sample Apr 24, 2026 Stellantis Stellantis wanted to improve customer interactions, speed product-development analysis, and streamline manufacturing operations, but those goals required faster interpretation of component data, anomaly signals, fleet… "Club Stellantis" virtual assistant · Bill of Materials Data Intelligence tool · Mistral LLMs 
BCG Sample Archived · Nov 15, 2025 PHOENIX group PHOENIX group faced the complexity of a pan-European pharmaceutical distribution network, where manual transport-invoice checks, repetitive customer-service work, fragmented data and uneven digital maturity made it… 24/7 service AI Customer Service Agent · AI-Powered Inventory Cockpit · GenAI Factory 