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.
This article provides a detailed, hands‑on analysis of HarmonyOS NEXT's native‑app signing process, covering certificate generation, CSR handling, leaf‑certificate issuance, profile creation, package signing, and the multi‑stage verification logic implemented in OpenHarmony's security modules.
AutoConsis is a research‑driven, AI‑powered workflow that automatically detects UI content inconsistencies across mobile app pages by combining target region recognition, OCR‑based extraction, and large language model reasoning, achieving low cost, high generalization, and high confidence as demonstrated on Meituan's large‑scale marketing scenarios.
This article highlights eight Meituan research papers accepted at CIKM 2024—spanning self‑supervised sequential recommendation, rating‑consistent explanation generation, CTR prediction via recommendation pre‑training, cross‑domain interest transfer, multimodal vector retrieval, design‑aware poster layout, order‑fulfillment cycle‑time forecasting, and delivery‑scope substitution—offering insights from both internal and university collaborations.
This article analyzes Meituan's Recce solution for dynamic front‑end containers, detailing performance bottlenecks, architectural classifications, interpreter and language choices, UI framework design, rendering layer decisions, optimization techniques, and future directions to achieve native‑level speed while retaining dynamic capabilities.
The Meituan Robotics Research Institute (MARS) is calling full‑time university scholars and researchers to submit independent research proposals for 2024 projects—selected from a predefined topic list, evaluated by Meituan and external experts on novelty, business value and feasibility, and eligible for up‑to ¥200,000 funding, on‑site interns, fast‑track graduate hiring and de‑identified data, with applications due 10 Nov 2024 and projects starting Dec 2024 or Jan 2025.
Meituan’s home‑page recommendation system adopts a multi‑stage global user‑modeling pipeline culminating in the EXIT framework, which explicitly transfers cross‑domain interests via interest‑combination labels and a scene‑selector network, thereby mitigating data sparsity and negative transfer and delivering significant offline and online performance gains.
The BlackPearl team leveraged large‑model strategies—including iterative self‑refinement, train‑time difficulty increase, test‑time augmentation, grafting‑learning, and boosting—to dominate the WhoIsWho‑IND, PST, and AQA tracks of the KDD 2024 OAG‑Challenge Cup, surpassing traditional feature‑engineered, GNN, and BERT baselines.
The article presents a next‑generation experiment analysis engine that standardizes the core AB testing framework, integrates advanced statistical solutions to tackle small‑sample and overflow challenges, and offers precise variance and P‑value calculations, thereby improving reliability and efficiency for multi‑side fulfillment platform experiments.
This article details Meituan Waimai's feed advertising system, covering business characteristics, the evolution of estimation models, and practical implementations such as decision‑path modeling, ultra‑long/wide user modeling, full‑reconstruction techniques, and the integration of large language models for CTR prediction.
The BlackPearl team from Meituan’s Dazhong Dianping division swept all three KDD 2024 OAG‑Challenge Cup tracks—WhoIsWho, PST, and AQA—by deploying innovative large‑model techniques such as iterative text clustering, graft‑learning‑enhanced BERT RAG pipelines, and a Boosting LLM‑for‑Vector search, and have released the code publicly on GitHub.
