Official JD technology sharing platform. All the cutting‑edge JD tech, innovative insights, and open‑source solutions you’re looking for, all in one place.
This article examines the common pain points of on‑call debugging, explains how to extract useful information from error screenshots, and presents a Java‑based method call stack tracing tool that filters and visualizes stack frames to quickly locate code origins and improve troubleshooting efficiency.
The award‑winning project from Tsinghua University and JD Retail introduces re‑parameterization model design, cross‑scene adaptive learning, and platform‑aware compression to overcome accuracy‑efficiency trade‑offs in visual deep learning, achieving over 20% accuracy gains and more than 50% inference speedup in real‑world e‑commerce deployments.
The paper "Omniforce" from JD Exploration Research Institute presents a cloud‑edge collaborative AutoML system that uses model distillation, data governance, Bayesian training optimization, and cloud‑edge cooperation to reduce large‑model training costs by 70% and improve inference efficiency by an average of 30%, offering a reusable technical paradigm for scalable AI deployment.
This article examines ClickHouse’s high‑performance OLAP design, covering its MPP architecture, columnar storage, vectorized execution, pre‑sorting, table engines, extensive data‑type system, sharding and replication strategies, as well as its sparse and skip‑index mechanisms that together enable ultra‑fast analytics on massive datasets.
Amid the AI wave, large language models like DeepSeek R1 are poised to explode by 2025, driven by open-source, low-cost access and superior reasoning, with successful deployment requiring four key factors—domain expertise, knowledge bases, robust search, and engineered agent architectures—to unlock value beyond simple chat.
This article reviews recent advances in applying large language models to CPS advertising recommendation, outlines business requirements and core technical challenges, proposes an extensible multi‑task generative framework with explicit intent perception and multi‑objective optimization, and presents offline and online performance gains along with future research directions.
The JD Supply Chain algorithm team introduces TimeHF, a billion‑parameter time‑series large model that leverages RLHF to boost demand‑forecast accuracy by over 10%, detailing dataset construction, the PCTLM architecture, a custom RLHF framework (TPO), and extensive SOTA experimental results.
The article analyzes data‑consistency challenges caused by RPC timeouts, especially when interfaces lack idempotency or idempotency fails, and presents a lightweight mock/spy utility that can intercept, mock, or spy on service calls to quickly restore consistency in distributed systems.
This article presents a comprehensive AI‑driven pipeline that converts 2D video into immersive 3D spatial video by leveraging monocular depth estimation, depth‑warping novel view synthesis, a multi‑branch inpainting module, a large‑scale StereoV1K dataset, and efficient MV‑HEVC compression, with results validated at ICME 2025 and deployed in JD Vision services.
This article explains chaos engineering—its definition, core principles, experimental workflow, tool selection, AI‑driven enhancements, and practical case studies—providing a comprehensive guide for building resilient distributed systems across backend, cloud‑native, mobile, and AI‑enabled environments.
