AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction

TL;DR

AutoPKG is an innovative multi-agent LLM framework that automatically constructs and maintains a dynamic product-attribute knowledge graph from multimodal e-commerce content, enhancing attribute extraction and increasing marketplace GMV.

Contribution

The paper introduces AutoPKG, a novel multi-agent LLM framework for automatic, dynamic construction and maintenance of product-attribute knowledge graphs in e-commerce.

Findings

Achieves up to 0.953 WKE for product types on Lazada data.

Improves attribute extraction F1 score by 0.152 on public benchmarks.

Increases GMV in production by up to 7.89% through derived attributes.

Abstract

Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type and key validity, consolidation quality, and edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE for attribute keys, and 0.531 edge-level F1 for multimodal value extraction. Across three public benchmarks, our method improves edge-level exact-match F1 by 0.152 and yields a precision gain of 0.208 on the attribute extraction application. Online A/B tests show that AutoPKG-derived attributes increase Gross Merchandise Value (GMV) in Badge by 3.81 percent, in Search by 5.32 percent, and in Recommendation by 7.89 percent, supporting the practical value of AutoPKG in production.