JAN 30, 2026
Agent-based RCA in Manufacturing (US)
19/466,208 · FP25176
Inventors
Taekwon Jee, Jihoon Jung, Jeng-Hun Suh
Applicant
SemiAI, Co.,Ltd.
Official Title
METHOD FOR PERFORMING ROOT CAUSE ANALYSIS IN MANUFACTURING PROCESS BY USING AGENT-BASED MULTIMODAL REASONING MODEL AND ROOT CAUSE ANALYZING DEVICE USING THE SAME
Summary
This invention proposes a method for root cause analysis (RCA) in manufacturing using an agent-based multimodal reasoning model. It integrates heterogeneous data such as process data, measurement data, charts, images, and logs to detect anomaly patterns. The system iteratively generates analysis tasks, visualizations, and explanations to refine hypotheses and identify root causes. It supports a traceable and interpretable workflow that enables users to understand causal relationships behind anomalies. Ultimately, it outputs final root cause information once predefined reliability or iteration conditions are satisfied.