Method for enhanced defective die classification and early wafer yield detection

Abstract

A method to generate an inspection tool sampling plan is disclosed. More, particularly, a method to generate an inspection tool sampling plan for more accurate die loss projection assuming non-uniform defect density or distribution on a wafer is disclosed. More, particularly, a method to generate an inspection tool sampling plan for more accurate die loss projection using a machine learning defective die prediction model is disclosed. A method to optimize an inspection tool sampling plan is disclosed. More particularly, a method of optimizing a wafer region definition and sampling budget distribution for improved die loss projection without relying on rule-based threshold prediction models based on defect counts is disclosed. A computational probability prediction model, sampling plan optimizer, and defective die prediction model are disclosed to project die loss with improved accuracy and versatility to guide different wafers for inspection.

Images