Author

Meituan Technology Team

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.

646

Articles

Likes

Views

Comments

Latest from Meituan Technology Team

100 recent articles max

Meituan Technology Team

Mar 28, 2024 · Artificial Intelligence

Large-Scale Heterogeneous Graph Modeling and GraphET Engine for Meituan Food Delivery Search Advertising

The paper describes how Meituan’s food‑delivery search advertising uses a heterogeneous billion‑node graph and the GraphET engine to boost weak‑supply recall, detailing a progression from fine‑grained modeling to GPT‑enhanced pre‑training, and presenting a scalable training and low‑latency inference architecture that handles hundreds of billions of edges.

GraphETLarge-Scale GraphMeituan

0 likes · 27 min read

Large-Scale Heterogeneous Graph Modeling and GraphET Engine for Meituan Food Delivery Search Advertising

Meituan Technology Team

Mar 21, 2024 · Artificial Intelligence

Algorithmic Practices for Meituan's Content Intelligent Distribution

This article outlines Meituan’s end‑to‑end content‑intelligent distribution pipeline, detailing challenges of massive multimodal search, supply labeling, semantic and personalized recall, multi‑objective ranking with distillation and MMoE/PPNet, heterogeneous mixing, and future plans for automated detection and large‑language‑model integration.

AIRankingSearch Optimization

0 likes · 17 min read

Algorithmic Practices for Meituan's Content Intelligent Distribution

Meituan Technology Team

Mar 14, 2024 · Databases

Meituan Large‑Scale KV Storage: Challenges and Architectural Practices

Meituan’s large‑scale KV storage journey—from early Memcached and Redis through Alibaba Tair to its own in‑memory Squirrel and persistent Cellar systems—addresses massive scalability and availability challenges by optimizing gossip with Merkle‑tree summaries, introducing fork‑less snapshots, witness‑node voting, cross‑region sync, lock‑free memory engines, bulk‑load pipelines, and advanced scheduling, while planning cloud‑native deployment, kernel‑bypass I/O and hardware accelerators to further boost performance and reliability.

KV storageMeituandistributed-systems

0 likes · 32 min read

Meituan Large‑Scale KV Storage: Challenges and Architectural Practices

Meituan Technology Team

Feb 29, 2024 · Mobile Development

Meituan Technical Salon #77: Client‑Side Robustness Testing via Interface Data Mutation for Billion‑Traffic Systems

Meituan’s Technical Salon #77 presented a client‑side robustness testing framework that mutates API responses using semantic rules, injects them via a proxy, and detects crashes or hangs through static code scans and dynamic monitoring, employing array‑deduplication techniques to cut test volume while maintaining coverage, now deployed in Meituan and Youxuan apps.

Fault Injectionclient-side qualitydata mutation

0 likes · 15 min read

Meituan Technical Salon #77: Client‑Side Robustness Testing via Interface Data Mutation for Billion‑Traffic Systems

Meituan Technology Team

Jan 25, 2024 · Artificial Intelligence

Design and Implementation of a Distributed Causal Forest Framework on Meituan's Fulfillment Platform

Meituan’s Fulfillment Platform team built a high‑performance distributed causal‑forest framework—named Causal On Spark—that trains hundreds of trees on hundreds of millions of samples within minutes using MapReduce‑based histogram splitting, extensive memory optimizations, Parquet model serving, and novel distributed evaluation metrics, enabling scalable causal inference for pricing, subsidies, and marketing.

Model ServingSparkcausal forest

0 likes · 23 min read

Design and Implementation of a Distributed Causal Forest Framework on Meituan's Fulfillment Platform

Meituan Technology Team

Jan 18, 2024 · Information Security

Meituan Java RASP: Architecture, Challenges, and Performance Optimizations

Meituan’s Java RASP protects applications at runtime by using a bootstrap jar, agent jar, and hot‑replaceable plugin loaded through a custom classloader, offering two deployment modes—dynamic agentmain and stable premain—while addressing challenges such as diverse environments, CPU and latency overhead, upgrade and monitoring difficulties through gray‑deployment, traffic pre‑warm, soft‑degrade, and optimized premain stubs, achieving only 0.06‑3.73 % CPU increase, modest memory growth, and near‑zero tail‑latency spikes, and supporting a wide range of vulnerabilities with future plans for lightweight containers and zero‑impact injection.

JavaRASPRuntime protection

0 likes · 27 min read

Meituan Java RASP: Architecture, Challenges, and Performance Optimizations

Meituan Technology Team

Jan 4, 2024 · Backend Development

Key Insights from the Meituan Robotics Institute Academic Annual Meeting on Embodied Intelligence and AI‑Driven Robotics

At the Meituan Robotics Institute’s 2023 academic annual meeting in Shenzhen, leading scholars highlighted embodied intelligence as a learning “child,” emphasized large‑scale models and big data as catalysts for advanced perception and control, identified logistics, manufacturing, elder‑care and scientific research as near‑term markets, and called for deeper industry‑academia collaboration to accelerate robot deployment and explore new applications.

Industry-Academia CollaborationLogisticsManufacturing

0 likes · 30 min read

Key Insights from the Meituan Robotics Institute Academic Annual Meeting on Embodied Intelligence and AI‑Driven Robotics

Meituan Technology Team

Dec 28, 2023 · Frontend Development

Improving Large‑Scale Frontend Development Efficiency and Practice

The article details Meituan’s evolution from isolated native and web stacks to a unified multi‑terminal large‑frontend framework, describing a four‑step standardization (standardization, online‑ization, automation, digitalization) that streamlines research‑development collaboration, introduces a dynamic continuous‑delivery platform with configurable pipelines, DevOps workflow engine, and plug‑in infrastructure, and outlines future AI‑driven automation to achieve fully digital, data‑centric front‑end development.

Continuous deliveryDevOpsStandardization

0 likes · 21 min read

Improving Large‑Scale Frontend Development Efficiency and Practice

Meituan Technology Team

Dec 21, 2023 · Artificial Intelligence

Meituan Robotics Institute Academic Annual Meeting and Low‑Altitude Drone Challenge Summary

At its Dec 19, 2023 academic annual meeting in Shenzhen’s Tsinghua International Graduate School, Meituan Robotics Institute reviewed a year of progress, announced 2024 research collaborations on embodied intelligence, autonomous robots and unmanned systems, introduced scholarships and internships, hosted a round‑table on robot trends, and showcased the inaugural Low‑Altitude Economy Drone Management Challenge in which 71 university teams competed and eight won top honors, while simultaneously demonstrating a campus‑delivery drone service that transports fresh juice, underscoring the institute’s data‑driven, university‑partnered push to translate advanced robot technologies into real‑world applications since its 2022 founding.

Artificial IntelligenceChallengeRobotics

0 likes · 7 min read

Meituan Robotics Institute Academic Annual Meeting and Low‑Altitude Drone Challenge Summary