Over 10,000 engineers powering China’s leading lifestyle services e‑commerce platform. Supporting hundreds of millions of consumers, millions of merchants across 2,000+ industries. This is the public channel for the tech teams behind Meituan, Dianping, Meituan Waimai, Meituan Select, and related services.
The article details Meituan's design and deployment of a code‑change risk visualization platform—named Houyi—covering risk categories, system architecture, technical challenges, eight practical application scenarios, and future plans to enhance code analysis and risk detection.
AdaScene introduces an adaptive scenario modeling framework for Meituan’s DSP that mitigates negative transfer and extreme data sparsity across heterogeneous display scenes by employing a knowledge‑transfer network with scene‑specific feature adaptation and gated expert sharing, alongside a gradient‑based scene‑aggregation process that clusters similar scenarios, yielding consistent performance gains for both high‑traffic and low‑traffic channels.
The article explains how MJDK, Meituan's OpenJDK‑based distribution, integrates the Intel ISA‑L‑optimized mzlib library into java.util.zip, preserving API and format compatibility while delivering a five‑to‑ten‑fold increase in compression and decompression throughput, backed by benchmark results on the Silesia corpus.
This article presents a comprehensive guide to designing, implementing, and analyzing a reliable A/B testing platform for Meituan's multi‑side fulfillment business, covering statistical pitfalls, experiment types, traffic‑splitting frameworks, automated analysis engines, and practical solutions for overflow effects, small samples, and fairness constraints.
The article showcases seven Meituan research papers accepted at KDD 2023—spanning feed‑stream, cross‑domain, takeaway, bonus allocation, contour‑based segmentation, living‑needs prediction, and multilingual recommendation—detailing their novel methods, real‑world deployments, and concluding with an invitation for academic collaboration.
The article details Meituan’s Rome front‑end framework, covering its business and technical background, the engineering ecosystem and evolution path, large‑scale upgrades, IDE‑based development assistance, efficiency and quality improvements, metric collection, real‑world adoption across 1,400+ projects, and future trends such as deeper dev‑chain integration and AI‑assisted coding.
Meituan’s Street‑Scene Understanding team built a high‑precision, efficient segmentation system that aligns motion and static semantics, mines hard examples, iterates models via a data‑model loop, and pursues unified open‑world segmentation, winning multiple CVPR 2023 awards and powering map production, autonomous delivery and store‑scene reconstruction.
Meituan’s food‑delivery team built a novelty‑focused recommendation pipeline—combining dual‑tower recall, novelty‑aware ranking, personalized mixed‑ranking weights, and reinforcement‑learning insertion—to surface merchants unseen by users, achieving 19% higher exposure novelty, 25% more order novelty, and improved ratings while keeping RPM loss under 0.5%.
Meituan’s delivery team created an intelligent, real‑time companion‑type search guidance system for its waimai platform—combining a smart in‑box word refresh triggered by edge‑intelligence intent signals and a unified multi‑scenario query‑recommendation model with self‑supervised pre‑training and multi‑objective optimization—delivering over 1 % DAU growth, 1.7 % UV_RPM increase, and up to 187 % CTR lifts while outlining future extensions to more pages and large‑model embeddings.
The article details how Meituan built a MySQL autonomous platform by constructing kernel observability to split OnCPU/OffCPU wait time, capturing full SQL directly from the kernel with compression, designing a safe exception‑handling workflow, and generating cost‑based index‑tuning suggestions—including what‑if analysis and workload‑driven recommendations—to enable comprehensive SQL governance.
