Apparatus and method for predicting wafer test data

By preprocessing WAT data into positional embedding vectors and using an AI model, the electrical characteristic distribution of a wafer is accurately predicted with limited test data, improving positional resolution and accuracy.

JP2026116586APending Publication Date: 2026-07-10DIGWISE TECH CORP LTD

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
DIGWISE TECH CORP LTD
Filing Date
2024-12-16
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing methods struggle to accurately represent the electrical characteristic distribution of a wafer using limited test data.

Method used

A method involving preprocessing wafer acceptance test (WAT) data to convert positional information into embedding vectors and inputting chip probing (CP) data into an artificial intelligence model to generate predicted WAT data with a higher number of data points, using an electronic device with a processing circuit and memory to execute the AI model.

Benefits of technology

The method effectively predicts the electrical characteristic distribution across the entire wafer with a relatively small amount of test data, enhancing positional resolution and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026116586000001_ABST
    Figure 2026116586000001_ABST
Patent Text Reader

Abstract

This invention provides a wafer test data prediction method and electronic apparatus for predicting the electrical characteristic distribution on a wafer using a relatively small amount of test data. [Solution] The prediction method includes preprocessing the wafer acceptance test (WAT) data of the wafer to convert the positional information of the WAT data within the wafer into positional embedding vectors. The WAT data has a first number of data points. The prediction method also inputs the chip probing (CP) data and positional embedding vectors of the wafer into an artificial intelligence model to cause the artificial intelligence model to generate predicted WAT data for the wafer. The predicted WAT data has a second number of data points, which is greater than the first number.
Need to check novelty before this filing date? Find Prior Art