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.
The article details JD Health’s OPC team’s adoption of Anthropic’s open‑source product‑management Skills to create a repeatable, evidence‑driven workflow that guides problem validation, requirement definition, roadmap planning, sprint execution, and post‑launch review without a dedicated product manager.
JD donated its self‑developed Oxygen xLLM large‑model inference engine to the OpenAtom Open Source Foundation under Apache 2.0, highlighting its service‑engine decoupled architecture, heterogeneous‑chip support, proven performance gains in e‑commerce, power and public‑safety use cases, and a roadmap to become the domestic AI‑infra standard.
JD’s JoyAI‑Echo framework, released on June 3, tackles the three major hurdles of long‑form AI video—character inconsistency, unstable voice timbre, and slow generation—by introducing a cross‑modal memory bank, a memory‑driven training pipeline that speeds inference 7.5×, a conversational Director Agent for selective editing, and real‑time super‑resolution, achieving leading benchmark scores and open‑source availability.
DongSQL V1.2.0 introduces a suite of kernel upgrades—including group‑commit unicast, semi‑sync replication tweaks, plan‑cache, single‑point query enhancements, massive‑table fast startup, SIMD acceleration, hotspot‑row updates and high‑volume testing support—delivering significant performance and stability improvements across diverse retail workloads.
The article details how JD’s Oxygen Vision leverages AI to overhaul cross‑border product visual creation, cutting SKU image‑generation cost and time by over 90%, automating multi‑platform compliance, multilingual localization, and high‑quality output through a three‑step workflow.
This article walks through the rationale, common functions, and real‑world case studies of storing and querying JSON columns in a relational database, exposing issues with null handling, batch updates, and dynamic SQL generation, and presents step‑by‑step debugging and robust solutions.
The article analyzes how to design a high‑availability architecture for large‑scale e‑commerce systems, detailing layered risk isolation, stateful storage strategies for flow and state data, unified document‑ID routing, multi‑replica databases, multi‑datacenter synchronization, and real‑world JD case studies that demonstrate elastic scaling and disaster recovery.
Facing explosive merchant growth and soaring order volumes, JD redesigned its B‑side POP order storage by isolating large tenants, applying double‑hash routing, expanding clusters, buffering updates, and automating data archiving, ultimately delivering a high‑performance, scalable Elasticsearch platform that sustains massive traffic spikes.
A test‑developer explores how AI can design and implement a query‑recording function for an insurance policy platform, comparing a code‑savvy approach with a low‑code approach, detailing architecture, AOP interception, async handling, code generation, review, and testing considerations.
This article analyzes JD's end‑to‑end upgrade of its retail coupon search infrastructure, detailing the business drivers, data‑skew challenges, the shift from dual KV and batch pipelines to a unified stream‑batch model built on Apache Doris, and the resulting performance, resource and stability gains across multiple scenarios.
