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

Dec 21, 2023 · Operations

AIOps for Incident Management: Practices and Insights from Meituan

Meituan’s service‑operations team applies AIOps across prevention, detection, and post‑incident stages—using change‑risk analysis, real‑time graph‑based anomaly detection, similarity‑driven root‑cause diagnosis, and NLP‑powered incident recommendation—to achieve sub‑second detection, high precision, 28% faster fault handling, and plans for intelligent log and change recognition.

aiopsanomaly detectionincident management

0 likes · 24 min read

AIOps for Incident Management: Practices and Insights from Meituan

Meituan Technology Team

Nov 23, 2023 · Frontend Development

Multimodal UI Interaction Intent Recognition for Automated Front‑End Testing

Meituan’s in‑store platform team and Prof. Zhou Yangfan’s Fudan group built a lightweight multimodal UI interaction intent recognizer that fuses screenshots, visible text, and render‑tree attributes via a Vision‑Transformer and Chinese BERT self‑attention model, then clusters nodes with a supervised pairwise classifier, achieving the highest F1 scores among baselines on 158 annotated order‑page screenshots from four business lines, enabling automatically generated test cases that execute correctly on 89 % of 100 unseen pages and demonstrating robust, cross‑app generalization for large‑scale front‑end quality assurance.

Intent RecognitionUI Testingfrontend quality

0 likes · 27 min read

Multimodal UI Interaction Intent Recognition for Automated Front‑End Testing

Meituan Technology Team

Nov 9, 2023 · Artificial Intelligence

Deep Contextual Interest Network (DCIN) for CTR Prediction

The Deep Contextual Interest Network (DCIN) improves click‑through‑rate prediction by jointly modeling a clicked item with its surrounding display context using a position‑aware attention module, a two‑layer fusion MLP, and a DIN‑style matching layer, enabling offline pre‑computation of context‑aware interest vectors that reduce latency, handle much longer sequences, and achieve a 21 % relative AUC improvement and +1.5 % gains in CTR and RPM in large‑scale online advertising tests.

AdvertisingAttention MechanismCTR prediction

0 likes · 20 min read

Deep Contextual Interest Network (DCIN) for CTR Prediction

Meituan Technology Team

Oct 26, 2023 · Artificial Intelligence

First Tsinghua-MeiTuan Digital Life Joint Research Institute Academic Forum

The inaugural Tsinghua‑Meituan Digital Life Joint Research Institute Academic Forum, scheduled for November 1 2023, will convene Academician Zheng Weimin, Tsinghua scholars, and Meituan technical experts to discuss intelligent unmanned systems in the era of large‑scale models, sharing cutting‑edge research and addressing emerging challenges.

AI technologyResearch Instituteacademic forum

0 likes · 1 min read

First Tsinghua-MeiTuan Digital Life Joint Research Institute Academic Forum

Meituan Technology Team

Oct 20, 2023 · Industry Insights

How Meituan’s Fourth‑Gen Drone Redefined Urban Delivery at GITEX 2023

At GITEX GLOBAL 2023 in Dubai, Meituan showcased its fourth‑generation autonomous drone and a complete low‑altitude logistics system, demonstrating rapid food delivery, detailed hardware and software features, and the extensive regulatory and environmental preparations required for its first overseas flight.

GITEX 2023Meituanair logistics

0 likes · 6 min read

How Meituan’s Fourth‑Gen Drone Redefined Urban Delivery at GITEX 2023

Meituan Technology Team

Oct 12, 2023 · Operations

Pattern-Based Reliability Governance for Billion-Scale Traffic Systems

The article presents Meituan’s pattern‑mining approach to reliability governance for billion‑scale traffic systems, outlining engineering pain points, defining reusable patterns, leveraging big‑data traffic collection for automated testing, and demonstrating concrete practices in idempotency, dependency, and over‑privilege management.

Dependency GovernanceReliabilitybig data

0 likes · 16 min read

Pattern-Based Reliability Governance for Billion-Scale Traffic Systems

Meituan Technology Team

Oct 11, 2023 · Artificial Intelligence

Meituan Vision AI Research Highlights and Open‑Source Releases

The Meituan Vision AI Research Highlights compiles recent breakthroughs—including championship‑winning street‑scene segmentation at CVPR 2023, summaries of eight CVPR 2023 papers, the YOLOv6 3.0 release that outperforms YOLOv7‑E6E, a large‑scale Food2K dataset with a progressive region‑enhancement network, GPU inference service optimizations, quantized YOLOv6 deployment, YOLOv6 2.0 model specs, six CVPR 2022 papers, the Twins attention model, short‑video understanding techniques, and earlier CVPR 2019 and ICDAR 2019 contributions—alongside open‑source releases.

AI researchdeep learningobject detection

0 likes · 9 min read

Meituan Vision AI Research Highlights and Open‑Source Releases

Meituan Technology Team

Sep 21, 2023 · Backend Development

Code Change Risk Visualization and Quality Assurance Practices at Meituan

Meituan’s technical salon details the design and deployment of the Houyi code‑change risk visualization platform, which maps infrastructure, external and internal changes, tackles analysis and storage challenges with AST/ASM and graph databases, powers eight QA scenarios such as impact assessment and automated test recommendation, and plans to add dynamic analysis and LLM‑driven risk detection.

Microservicesbackendcode change

0 likes · 19 min read

Code Change Risk Visualization and Quality Assurance Practices at Meituan

Meituan Technology Team

Sep 14, 2023 · Artificial Intelligence

AdaScene: Adaptive Scenario Modeling for Multi‑Scene Recommendation in Meituan DSP

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.

AIKnowledge Transferadaptive modeling

0 likes · 20 min read

AdaScene: Adaptive Scenario Modeling for Multi‑Scene Recommendation in Meituan DSP

Meituan Technology Team

Aug 31, 2023 · Backend Development

Performance Optimization of Java Compression in MJDK Using ISA‑L Based mzlib

MJDK, Meituan’s OpenJDK‑based distribution, swaps the standard zlib for an ISA‑L‑derived mzlib, delivering 5‑10× faster java.util.zip compression and decompression with only a ~3% ratio increase, while preserving full API compatibility, providing Java code examples, Snappy integration, and proven production stability.

CompressionISA-LJDK

0 likes · 13 min read

Performance Optimization of Java Compression in MJDK Using ISA‑L Based mzlib