Method of generating quality affecting factor for semiconductor manufacturing process and generating system for the same

Patent metadata

Field	Value
Publication number	US-10254333-B2
Application number	US-201514955633-A
Country	US
Kind code	B2
Filing date	Dec 1, 2015
Priority date	Jan 14, 2015
Publication date	Apr 9, 2019
Grant date	Apr 9, 2019

Abstract

A quality affecting factor generation method for a semiconductor manufacturing process is provided. The method includes receiving data of a customer evaluation result obtained by a real use of shipped semiconductor products, preprocessing the data of the customer evaluation result, determining critical quality factors that affect a quality of the semiconductor products by applying a statistical model to the preprocessed data of the customer evaluation result; and determining a semiconductor product to be shipped to a customer company as a good product and a failed product using the determined critical quality factors and generating quality affecting factors of the semiconductor products to be managed to improve yield in a semiconductor manufacturing process.

First claim

What is claimed is:

1. A method for a semiconductor manufacturing process, the method comprising:
shipping semiconductor products that have been manufactured by the semiconductor manufacturing process;
receiving data of a customer evaluation result obtained by a real use of customer products in which the semiconductor products that have been shipped have been implemented;
preprocessing the customer evaluation data to match the customer evaluation data with manufacturing management evaluation data being managed for the semiconductor manufacturing process;
determining critical quality factors that affect a quality of the semiconductor products by applying a statistical model to the customer evaluation data that has been preprocessed; and
determining a semiconductor product to be shipped to a customer company as a good product and a failed product using the critical quality factors that have been determined and generating quality affecting factors of the semiconductor products to be managed, and controlling the semiconductor manufacturing process according to the quality affecting factors that have been generated, to improve yield in the semiconductor manufacturing process,
wherein the data includes a test condition related to a test of the semiconductor products that have been shipped, information of a test device used in the test, and defective item information of the semiconductor products that have been tested.

2. The method of claim 1 , wherein the data is received from at least one customer company that is using the semiconductor products that have been shipped.

3. The method of claim 1 , wherein the preprocessing comprises matching a form of the data to a form of the manufacturing management evaluation data.

4. The method of claim 3 , wherein the form comprises at least one of a module, a package and a wafer level.

5. The method of claim 1 , wherein the determining the critical quality factors comprises a feature set search operation based on a stepwise feature selection.

6. The method of claim 5 , wherein the stepwise feature selection comprises executing a sequential forward selection and a sequential backward selection in parallel.

7. The method of claim 5 , wherein the determining the critical quality factors further comprises a feature set search operation based on a test result obtained by adding k fold cross validation to the stepwise feature selection, where k is a natural number.

8. The method of claim 1 , further comprising providing the quality affecting factors that have been generated to a manufacturing system that controls the semiconductor manufacturing process.

9. The method of claim 1 , wherein the quality affecting factors that have been generated are transmitted to at least one customer server.

10. A method for a semiconductor manufacturing process, the method comprising:
shipping semiconductor products that have been manufactured by the semiconductor manufacturing process;
receiving data of a customer evaluation result obtained by a real use of customer products in which the semiconductor products that have been shipped have been implemented, the customer evaluation result being related to generation of quality affecting factors of the semiconductor products that have been shipped;
preprocessing the customer evaluation data to match manufacturing management evaluation data being managed for the semiconductor manufacturing process;
determining critical quality factors that affect quality of the semiconductor products that have been shipped, by applying a statistical model to the customer evaluation data that has been preprocessed;
dividing semiconductor products to be shipped to a customer company into a good product and a failed product using the critical quality factors that have been determined; and
generating quality affecting factors of the semiconductor products that are to be managed and controlling the semiconductor manufacturing process to improve a yield in the semiconductor manufacturing process by applying the semiconductor products to be shipped that have been divided, to a real customer company test environment to check the quality affecting factors that have been generated, with respect to the semiconductor products that have been divided,
wherein the data comprises a test condition related to a test of the semiconductor products that have been shipped, information of a test device used in the test, and defective item information of the semiconductor products that have been tested, according to a wafer level, a package level and a module level of the semiconductor products.

11. The method of claim 10 , wherein the data is received from a customer server of at least one customer company that purchased the semiconductor products that have been shipped.

12. The method of claim 10 , wherein the determining the critical quality factors comprises a feature set search operation based on a stepwise feature selection that executes a sequential forward selection and a sequential backward selection in parallel.

13. The method of claim 10 , wherein the determining the critical quality factors further comprises a feature set search operation based on a test result obtained by adding k fold cross validation to a stepwise feature selection, where k is a natural number.

14. The method of claim 10 , wherein the quality affecting factors that have been generated are transmitted to at least one customer server.

15. The method of claim 10 , further comprising:
a data base which is connected to a data processing device of at least one customer company through a communication network and collects data of a customer evaluation result obtained by an actual use of the shipped semiconductor products and related to generation of quality affected factors of the semiconductor products from the data processing device in real time; and
a supplier server in line with the data base to generate the quality affected factors.

16. A method for a semiconductor manufacturing process, the method comprising:
shipping semiconductor products that have been manufactured by the semiconductor manufacturing process;
performing an iterative feedback loop comprising:
receiving, from a customer, customer evaluation results obtained by testing the semiconductor products that have been shipped in customer products in which the semiconductor products have been implemented;
determining quality affecting factors of the semiconductor products for the customer based on the customer evaluation results that have been received, and shipping, to the customer, semiconductor products selected based on the quality affecting factors that have been determined, for testing in the customer products; and
controlling the semiconductor manufacturing process according to the quality affecting factors that have been determined for the customer in order to increase a yield of the semiconductor manufacturing process for the customer,
wherein the customer evaluation results include a test condition related to a test used in testing the semiconductor products that have been shipped, information of a test device used in the test, and defective item information of the semiconductor products that have been tested.

17. The method of claim 16 , wherein the determining the quality affecting factors comprises:
preprocessing the customer evaluation results to match manufacturing management evaluation data being managed for the semiconductor manufacturing process;
determining critical quality factors that affect quality of the semiconductor products that have been shipped, by applying a statistical model t

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Seungli
• Kang Bokyoung
• Kwon Ji-Youn
• Kim Gilhan
• Park Chanhun
• Cho Byonghun
• Kim Sehoon

Classifications

• H10P74/23

  characterised by multiple measurements, corrections, marking or sorting processes · CPC title

• G06Q30/0282

  Rating or review of business operators or products · CPC title

• G01R31/26

  Testing of individual semiconductor devices (testing of photovoltaic devices H02S50/10; testing or measuring during manufacture or treatment {H10P74/00}) · CPC title

• Y02P90/30

  Computing systems specially adapted for manufacturing · CPC title

• G06Q50/04 Primary

  Manufacturing · CPC title