Automatic analysis system for quality data based on machine learning

A system for manufacturing a product, the system comprising:

• a machine learning-based inference model that is trained in accumulated quality data for the product, the inference model to analyze quality data and operate as a simulator for adjusting a quality control standard for the product;
• a processor;
• and
• a computer-readable medium in communication with the processor and storing instructions that, when executed by the processor, cause the processor to control the inference model to perform:
• during manufacturing and testing of the product, receiving the quality data;
• analyzing the quality data with the inference model to generate an analysis report;
• receiving a user's selection of a plurality of adjustment process factors from a plurality of main process factors selected for machine learning training for the inference model;
• obtaining a plurality of adjustment factor values for the selected adjustment process factors;
• generating, using a simulator mode of the inference model, a determination based on the adjustment process factors, wherein the determination indicates a probability of a product being of acceptable or unacceptable quality;
• comparing the probability of the determination to a reference probability condition;
• repeating obtaining the adjustment factor values, generating the determination, and comparing the probability of the determination to the reference probability condition;
• when the probability of the determination meets the reference probability condition, selecting corresponding adjustment factor values as optimal factor values for the adjustment process factors;
• and
• changing, based on the optimal factor values, the quality control standard for the adjustment process factors used by the inference model for analyzing quality data for the product to confirm acceptable product quality during subsequent manufacturing of the product.

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause a processor to control a machine learning-based inference model, that is trained in accumulated quality data for a product, to analyze quality data and as a simulator for adjusting a quality control standard for the product by performing:

• during manufacturing and testing of the product, receiving the quality data;
• analyzing the quality data with the inference model to generate an analysis report;
• receiving a user's selection of a plurality of adjustment process factors from a plurality of main process factors selected for machine learning training for the inference model;
• obtaining a plurality of adjustment factor values for the selected adjustment process factors;
• generating, using a simulator mode of the inference model, a determination based on the adjustment process factors, wherein the determination indicates a probability of a product being of acceptable or unacceptable quality;
• comparing the probability of the determination to a reference probability condition;
• repeating obtaining the adjustment factor values, generating the determination, and comparing the probability of the determination to the reference probability condition;
• when the probability of the determination meets the reference probability condition, selecting corresponding adjustment factor values as optimal factor values for the adjustment process factors;
• and
• changing, based on the optimal factor values, the quality control standard for the adjustment process factors used by the inference model for analyzing quality data for the product to confirm acceptable product quality during subsequent manufacturing of the product.