Official JD Tech public account delivering best practices and technology innovation.
This article explains why migrating AI applications from Nvidia GPUs to domestic graphics cards is urgent, outlines the technical challenges, and introduces JoyScale’s zero‑perception migration stack that enables end‑to‑end hardware, software, and model adaptation for reliable, high‑performance AI deployment.
The author recounts how, by modeling user intent with a multi‑layer Gaussian‑based PODM‑MI framework and addressing a novel ‘sand‑glass’ bottleneck in RQ‑VAE semantic identifiers, JD’s search ranking achieved significant UCVR gains, annual order increases of over ten million, and a SIGIR 2024 paper acceptance.
The article recounts how a risk‑control algorithm engineer progressively refined a generic large language model through four stages of prompt engineering—defining roles, dimensions, structured I/O, business rules, behavior fingerprints, and a dual‑hypothesis decision framework—to transform it into a precise e‑commerce fraud detection expert.
This article analyzes the multi‑dimensional challenges of building high‑availability systems—covering applications, databases, caches, message queues, containers, GC, and more—by sharing real JD engineering scenarios, common failure patterns, and concrete mitigation strategies to help engineers design more resilient services.
This article explores ClickHouse’s high‑performance OLAP architecture, covering its MPP design, columnar storage, vectorized execution, pre‑sorting, table engines, data types, sharding and replication strategies, as well as index designs that together enable rapid analysis of massive datasets.
This article explains the limitations of TCP and UDP for real‑time applications, introduces the KCP protocol as a UDP‑based solution that combines reliability with low latency, outlines its features, working principles, code usage, and real‑world deployment examples in gaming, video conferencing, live streaming, and IoT.
This article details JD Retail's AI‑driven virtual try‑on system, covering business challenges, technical hurdles, core algorithmic innovations, practical results from a major fashion brand, and future directions for personalized, automated, and predictive AI try‑on in e‑commerce.
This article examines the evolution of automation from basic scripting to AI‑driven intelligent systems, compares traditional and smart automation across multiple dimensions, and showcases practical implementations using Playwright, MidScene.js, and Chrome bridge mode with code examples for web and mobile testing.
This guide introduces the open‑source OxyGent multi‑agent framework, walks through a quick 20‑line installation, demonstrates environment configuration, tool integration, visualization, and advanced features such as RAG, Reflexion, and distributed deployment for AI applications.
JD’s internal technical salon reveals the rapid evolution of large‑model AI tools, outlining design principles, current capabilities like JoyAgent, OxyGent and JoyCode, real‑world applications across office, code review, logistics, and policy outlook, while highlighting future multi‑agent and embodied intelligence trends.
