20240054385. EXPERIMENT POINT RECOMMENDATION DEVICE, EXPERIMENT POINT RECOMMENDATION METHOD, AND SEMICONDUCTOR DEVICE MANUFACTURING DEVICE simplified abstract (Hitachi High-Tech Corporation)
EXPERIMENT POINT RECOMMENDATION DEVICE, EXPERIMENT POINT RECOMMENDATION METHOD, AND SEMICONDUCTOR DEVICE MANUFACTURING DEVICE
Organization Name
Inventor(s)
EXPERIMENT POINT RECOMMENDATION DEVICE, EXPERIMENT POINT RECOMMENDATION METHOD, AND SEMICONDUCTOR DEVICE MANUFACTURING DEVICE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240054385 titled 'EXPERIMENT POINT RECOMMENDATION DEVICE, EXPERIMENT POINT RECOMMENDATION METHOD, AND SEMICONDUCTOR DEVICE MANUFACTURING DEVICE
Simplified Explanation
The abstract describes a machine learning model that takes control parameters of a semiconductor processing device as input and outputs shape parameters that represent the processed shape of a semiconductor sample.
- The experiment involves obtaining learning data to evaluate the contribution of each control parameter to the model's prediction.
- Feature quantity data, which is the value of a control parameter in the learning data, is used to assess the contribution of each parameter.
- The experiment focuses on selecting control parameters based on their contribution and evaluating the stability and uncertainty of the model's predictions in the parameter space defined by the selected parameters.
---
- Potential Applications
- Semiconductor manufacturing process optimization
- Quality control in semiconductor production
- Automated shape analysis in semiconductor industry
- Problems Solved
- Efficiently determining the impact of control parameters on the processed shape of semiconductor samples
- Improving prediction accuracy in semiconductor processing based on control parameters
- Benefits
- Enhanced understanding of the relationship between control parameters and processed shape
- Increased efficiency and accuracy in semiconductor manufacturing processes
- Potential for automated decision-making in semiconductor production.
Original Abstract Submitted
for a machine learning model that receives control parameters of a semiconductor processing device and outputs shape parameters that express a processed shape of a semiconductor sample processed by the semiconductor processing device, an experiment point obtaining learning data is recommended. a contribution of each control parameter to the prediction of the machine learning model is evaluated from feature quantity data that is a value of a control parameter of the learning data used for learning of the machine learning model, and the experiment point is recommended based on a stability evaluation and an uncertainty evaluation of the prediction by the machine learning model in a space defined by the control parameters selected based on the contribution as axes.