Tagged articles
Ele.me
10 articles · Page 1 of 1
Ele.me created a domain-specific AIGC image model built from scratch on its own data using the DiT backbone, a three-stage training pipeline (transformer pre-training, prompt alignment, aesthetic fine-tuning), custom T5‑E‑CLIP text and visual encoders, ControlNet for layout control, and evaluated via FID, CLIP scores and a human rubric, enabling automated dish-image generation and UI asset creation for its vertical business.
AIGCControlNetDiT
0 likes · 8 min read

A detailed eye‑tracking case study shows how the Ele.me team designed, tested, and refined a new “Frequent Order” tab by comparing card layouts, discount placement, and visual emphasis, ultimately identifying the most efficient UI for repeat purchases.
Ele.meUI designeye tracking
0 likes · 10 min read

Ele.me tackled the performance and user‑experience challenges of its major sales events by replacing traditional H5 containers with the Progressive Hybrid App (PHA) framework, enabling native‑rendered TabBar, persistent WebViews, pre‑loading, location‑aware manifests, and comprehensive optimizations that cut first‑screen load times by hundreds of milliseconds.
Ele.meHybrid AppNative integration
0 likes · 14 min read


ITPUBDec 3, 2018 · Databases
This talk details Ele.me’s three‑month rollout of a dual‑active (multi‑active) database system, covering design principles, architecture, migration steps, challenges such as data consistency and DDL handling, the tools built (DRC, D‑Bus, DCP, EMHA), and the performance and reliability benefits achieved.
DBAEle.meMulti-Active
0 likes · 14 min read

This article outlines the background of Ele.me's recommendation business, details the evolution of its recommendation algorithms from rule‑based models to deep learning and online learning, and explains the practical implementation of real‑time data pipelines, feature engineering, model training, and deployment.
Ele.memachine learningonline learning
0 likes · 13 min read

The article presents a comprehensive overview of Ele.me's food‑delivery recommendation system, detailing its business model, platform goals, unique challenges, market‑driven efficiency mechanisms, control strategies, system architecture, model evolution, and online‑learning techniques used to balance short‑term performance with long‑term ecosystem health.
AIEle.meRanking
0 likes · 15 min read

This article explains how Ele.me tackles big‑data challenges by designing a metadata governance platform that collects SQL execution data, parses lineage with Antlr, stores graph relationships in Neo4j, and enables table/column lineage queries, DAG scheduling, and hot‑data analysis.
Ele.meSQL parsingdata lineage
0 likes · 12 min read

This article introduces Ele.me's intelligent scheduling platform, focusing on the pressure‑balancing subsystem and demonstrating how machine‑learning models such as rider capacity estimation and team pressure‑coefficient prediction are designed, trained, and deployed to improve real‑time O2O delivery operations.
Ele.melogisticspressure balancing
0 likes · 14 min read


21CTOMay 9, 2017 · Backend Development
This article explains how Ele.me grew from a student startup to handling over nine million daily orders by evolving its website architecture, adopting SOA, splitting services, implementing a robust release system, and building comprehensive monitoring and data‑access layers.
Ele.mebackend-developmentdeployment
0 likes · 13 min read

The author recounts attending Ele.me's front‑end technology conference, summarizing seven sessions covering PWA implementation, evolving front‑back collaboration, dependency health monitoring, Vue usage, Flow and type theory, design perspectives on Element, and the exploration of a visual document editor, while sharing personal impressions.
Ele.meFlowPWA
0 likes · 6 min read
