AI Agent-Driven Framework for Automated Product Knowledge Graph Construction in E-Commerce

TL;DR

This paper presents an automated AI agent-driven framework utilizing Large Language Models to construct comprehensive product knowledge graphs from unstructured e-commerce data, enhancing scalability and data quality.

Contribution

It introduces a novel fully automated method that leverages LLMs for ontology creation, refinement, and knowledge graph population without manual schema design.

Findings

Achieves over 97% property coverage in product KGs

Demonstrates high semantic coherence and minimal redundancy

Validates effectiveness on real-world product data

Abstract

The rapid expansion of e-commerce platforms generates vast amounts of unstructured product data, creating significant challenges for information retrieval, recommendation systems, and data analytics. Knowledge Graphs (KGs) offer a structured, interpretable format to organize such data, yet constructing product-specific KGs remains a complex and manual process. This paper introduces a fully automated, AI agent-driven framework for constructing product knowledge graphs directly from unstructured product descriptions. Leveraging Large Language Models (LLMs), our method operates in three stages using dedicated agents: ontology creation and expansion, ontology refinement, and knowledge graph population. This agent-based approach ensures semantic coherence, scalability, and high-quality output without relying on predefined schemas or handcrafted extraction rules. We evaluate the system on a real-world dataset of air conditioner product descriptions, demonstrating strong performance in both ontology generation and KG population. The framework achieves over 97\% property coverage and minimal redundancy, validating its effectiveness and practical applicability. Our work highlights the potential of LLMs to automate structured knowledge extraction in retail, providing a scalable path toward intelligent product data integration and utilization.