JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

2026-06-26

AI Summary

This work addresses three key challenges in billion-scale SKU scenarios: rapidly evolving product concepts, the need for high-quality knowledge production, and diverse downstream applications. To tackle these issues, we propose a product knowledge production and service platform leveraging large language models (LLMs) and vision-language models (VLMs). The core innovations include a human-in-the-loop dynamic ontology engineering framework, a semantic retrieval-to-discrimination (S2D) knowledge identification architecture, a self-evolving yet controllable multimodal model training mechanism, and a unified product service interface. The system processes hundreds of millions of daily product updates across tens of thousands of categories, achieving strong performance with 94.2% knowledge precision, 82.8% recall, and 80.4% search traffic coverage. It has reduced product information issues by 37% and enabled automatic population of core attributes at a rate exceeding 80%.

Abstract

JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, and higher operational efficiency-yet producing and serving it poses three industrial-scale challenges: fast-emerging concepts, high-quality knowledge production for massive SKUs, and diverse downstream requirements. To address these challenges, we present the JD Oxygen AI Item Center (Oxygen AIIC), an industrial-scale platform built on LLMs/VLMs for item-knowledge production and service. Oxygen AIIC is built around four core pillars: (i) ontology engineering driven by efficient human-AI collaboration, which supports the dynamic evolution and agile expansion of an ontology with millions of entries; (ii) a "Semantic Search then Discrimination"(S2D) knowledge identification architecture that, combined with throughput improvement strategies, enables scalable, extensible, and high-throughput AI Item Library production for tens of billions of SKUs; (iii) self-evolving item-understanding LLMs/VLMs that improve in a stable and controllable manner, enabling knowledge production with 94.2% precision and 82.8% recall; and (iv) a unified item tunnel that serves as the data and service hub. Oxygen AIIC now covers tens of thousands of JD categories and processes hundreds of millions of item updates per day on Huawei Ascend NPUs. It has accumulated hundreds of billions of item-knowledge assets. Deployed across core business scenarios-including search, recommendation, operations, category planning-Oxygen AIIC has delivered measurable gains at scale. Search-traffic coverage reaches 80.4%, item-information quality issues drop by 37%, the automated fill rate of core attributes during item listing exceeds 80%.

Problem

• item understanding
• large-scale e-commerce
• structured knowledge
• industrial-scale challenges
• SKU management

Innovation

• LLM/VLM
• Semantic Search then Discrimination
• Ontology Engineering
• Industrial-Scale Knowledge Production
• Self-Evolving Models