Leveraging Knowledge Graphs and LLM Reasoning to Identify Operational Bottlenecks for Warehouse Planning Assistance

TL;DR

This paper presents a novel framework combining Knowledge Graphs and Large Language Models to analyze warehouse simulation data, effectively identifying operational bottlenecks with high accuracy and reduced manual effort.

Contribution

It introduces an innovative approach that integrates KGs and LLMs for automated, iterative analysis of complex warehouse simulation outputs, improving diagnostic precision over existing methods.

Findings

Outperforms baseline methods in identifying bottlenecks.

Achieves near-perfect accuracy in operational inefficiency detection.

Demonstrates superior diagnostic capabilities for complex issues.

Abstract

Analyzing large, complex output datasets from Discrete Event Simulations (DES) of warehouse operations to identify bottlenecks and inefficiencies is a critical yet challenging task, often demanding significant manual effort or specialized analytical tools. Our framework integrates Knowledge Graphs (KGs) and Large Language Model (LLM)-based agents to analyze complex Discrete Event Simulation (DES) output data from warehouse operations. It transforms raw DES data into a semantically rich KG, capturing relationships between simulation events and entities. An LLM-based agent uses iterative reasoning, generating interdependent sub-questions. For each sub-question, it creates Cypher queries for KG interaction, extracts information, and self-reflects to correct errors. This adaptive, iterative, and self-correcting process identifies operational issues mimicking human analysis. Our DES approach for warehouse bottleneck identification, tested with equipment breakdowns and process irregularities, outperforms baseline methods. For operational questions, it achieves near-perfect pass rates in pinpointing inefficiencies. For complex investigative questions, we demonstrate its superior diagnostic ability to uncover subtle, interconnected issues. This work bridges simulation modeling and AI (KG+LLM), offering a more intuitive method for actionable insights, reducing time-to-insight, and enabling automated warehouse inefficiency evaluation and diagnosis.