Gaode’s technical report details an AI‑driven Interest Route (LOI) system that transforms massive real‑world travel data and user‑generated content into personalized classic and themed itineraries, describing data fusion, query rewriting, multi‑dimensional filtering, schema extraction, scoring, and AIGC content generation.
Leveraging a proprietary “large model + optimization” approach, Alibaba’s Ant Group and East China Normal University built a constraint-aware multi-agent framework that secured first place in the Original OS track and second in the DSL track of the IJCAI-2025 Autonomous Travel Planning Competition.
This article explores how mathematical modeling techniques—ranging from traveling salesman optimization and multi‑objective planning to ARIMA forecasting, queueing theory, and dynamic programming—can improve National Day holiday travel routes, predict visitor flows, optimize spending, and enhance traffic and safety management.
Alipay’s AI research team, together with Ant Group and East China Normal University, leveraged a self‑developed large‑model‑plus‑optimization framework to create a constraint‑aware multi‑agent system that won both the Original OS Track and DSL Track at the IJCAI‑2025 Autonomous Travel Itinerary Planning Competition.
This guide explains how the open‑source MCP protocol from Anthropic, now offered as a full‑lifecycle service on Alibaba Cloud Bailian, lets you quickly create a plug‑and‑play AI agent that integrates large models with external tools such as maps and weather APIs, all in under five minutes.
This article recounts L's attempt to change a train ticket, analyzes seat availability across four segments, and presents a minimal SQL model with table creation, data insertion, and a query that determines feasible seat combinations, demonstrating how segment‑wise seat allocation can enable complete journey booking.
