METHOD AND APPARATUS FOR MACHINE LEARNING BASED ON MANUFACTURING BIG DATA

• Main Authors: KWON JANG HWAN, PARK DEOK GEUN, KIM YOO JIN, SHIN YUN SOO, BAK WOO JIN
• Format: Patent
• Language: English; Korean
• Published: 31.05.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; COUNTING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

Provided, in the present specification, are a machine learning device and method based on manufacturing big data, wherein the method comprises: a step of receiving data related to manufacturing; a step of predicting, based on the received manufacturing-related data, indication of anomalies in a manufacturing step by using a manufacturing degree-of-risk prediction model configured to predict the indication of anomalies; and a step of providing the indication of anomalies in a predicted manufacturing step. 본 명세서에서는, 제조와 연관된 데이터를 수신하는 단계, 수신된 제조와 연관된 데이터를 기초로, 이상 징후를 예측하도록 구성된 제조 위험도 예측 모델을 이용하여, 제조 단계에서의 이상 징후를 예측하는 단계, 및 예측된 제조 단계에서의 이상 징후를 제공하는 단계를 포함하는, 제조 빅데이터 기반의 머신러닝 장치 및 방법이 제공된다.