Automatic optimization of an examination recipe

Patent metadata

Field	Value
Publication number	US-11307150-B2
Application number	US-202016995728-A
Country	US
Kind code	B2
Filing date	Aug 17, 2020
Priority date	Aug 17, 2020
Publication date	Apr 19, 2022
Grant date	Apr 19, 2022

Abstract

There is provided a system and method of automatic optimization of an examination recipe. The method includes obtaining one or more inspection images each representative of at least a portion of the semiconductor specimen, the one or more inspection images being indicative of respective defect candidates selected from a defect map using a first classifier included in the examination recipe; obtaining label data respectively associated with the one or more inspection images and informative of types of the respective defect candidates; extracting inspection features characterizing the one or more inspection images; retraining the first classifier using the first features and the label data, giving rise to a second classifier; and optimizing the examination recipe by replacing the first classifier with the second classifier; wherein the optimized examination recipe is usable for examining a subsequent semiconductor specimen.

First claim

What is claimed is:

1. A computerized system of automatic optimization of an examination recipe usable for examining a sequence of semiconductor specimens in runtime, the system comprising:
a storage unit configured to store i) one or more inspection images acquired by an inspection tool during runtime examination of a first semiconductor specimen in the sequence, each inspection image being representative of a portion of the first semiconductor specimen corresponding to a respective defect candidate of a list of defect candidates, the list of defect candidates being selected from a defect map of the first semiconductor specimen using a first classifier included in the examination recipe; ii) label data informative of types of respective defect candidates in the list of defect candidates, the label data being obtained from a review tool and being respectively associated with the one or more inspection images corresponding to the respective defect candidates; and
a processing and memory circuitry (PMC) operatively connected to the storage unit and configured to, in parallel with the runtime examination:
extract, using at least an unsupervised model previously trained using a set of training inspection images, inspection features characterizing the one or more inspection images;
associate the inspection features with the label data of the one or more inspection images to obtain a training set;
retrain the first classifier using the training set to obtain a second classifier; and
in response to determining to optimize the examination recipe replace the first classifier with the second classifier to obtain an optimized examination recipe;
wherein the optimized examination recipe is usable for examining a subsequent semiconductor specimen in the sequence.

2. The computerized system according to claim 1 , wherein the defect map is generated by the inspection tool and is indicative of defect candidate distribution on the first semiconductor specimen.

3. The computerized system according to claim 1 , wherein each of the types of the respective defect candidates is indicative of at least one of the following: defect of interest (DOI), nuisance, and a class of a respective defect candidate.

4. The computerized system according to claim 1 , wherein the inspection features comprise a set of first features extracted by the unsupervised model previously trained using the set of training inspection images to extract representative features thereof.

5. The computerized system according to claim 4 , wherein the first classifier is previously trained using one or more training inspection images of the set of training inspection images with respectively associated label data.

6. The computerized system according to claim 4 , wherein the inspection features further comprise a set of second features extracted by a supervised model, the supervised model being previously trained using one or more training inspection images of the set of training inspection images with respectively associated label data to determine types of defect candidates.

7. The computerized system according to claim 6 , wherein the set of second features comprises at least one of i) one or more feature vectors characterizing the one or more inspection images, and ii) one or more label prediction features indicative of probability of each given defect candidate on an inspection image belonging to a specific type.

8. The computerized system according to claim 1 , wherein the PMC is configured to retrain the first classifier using a set of third features comprising at least one of: one or more tool features, one or more defect features and one or more specimen features, in addition to the inspection features and the label data.

9. The computerized system according to claim 6 , wherein the PMC is further configured to retrain at least one of the unsupervised model or the supervised model using the one or more inspection images and the label data, prior to the retraining of the first classifier.

10. The computerized system according to claim 1 , wherein the PMC is further configured to determine whether to optimize the examination recipe based on one or more parameters, and perform the optimizing and using in response to a positive determination.

11. The computerized system according to claim 10 , wherein the one or more parameters comprise at least one of: a recipe update frequency, a recipe performance history, a customer policy, and a situational analysis.

12. The computerized system according to claim 1 , wherein the examination recipe further comprises at least an additional first classifier, and the PMC is further configured to perform the obtaining, extracting and retraining for generating at least an additional second classifier corresponding to the at least additional first classifier, and optimize the examination recipe with the second classifier and the additional second classifier.

13. The computerized system according to claim 1 , wherein the storage unit stores a plurality of inspection images captured by multiple inspection tools, and wherein the retraining of the first classifier is in accordance with a working point selected based on a plurality of performance parameters including a tool-to-tool difference parameter indicative of variance between the multiple inspection tools.

14. The computerized system according to claim 1 , wherein the first semiconductor specimen comprises multiple layers, and the PMC is configured to perform the extracting, retraining and optimizing for the examination recipe for each layer of the multiple layers, and the PMC is further configured to train a general-purpose classifier based on training data from the multiple layers, wherein the general-purpose classifier is usable to perform classification for one or more new layers.

15. A computerized method of automatic optimization of an examination recipe usable for examining a sequence of semiconductor specimens in runtime, the method performed by a processing and memory circuitry (PMC), the method comprising:
obtaining one or more inspection images acquired by an inspection tool during runtime examination of a first semiconductor specimen in the sequence, each inspection image being representative of a portion of the first semiconductor specimen corresponding to a respective defect candidate of a list of defect candidates, the list of defect candidates being selected from a defect map of the first semiconductor specimen using a first classifier included in the examination recipe;
obtaining label data informative of types of respective defect candidates in the list of defect candidates, the label data being obtained from a review tool and being respectively associated with the one or more inspection images corresponding to the respective defect candidates; and
in parallel with the runtime examination:
extracting, using at least an unsupervised model previously trained using a set of training inspection images, inspection features characterizing the one or more inspection images;
associating the inspection features with the label data of the one or more inspection images to obtain a training set;
retraining the first classifier using the training set to obtain a second classifier; and
in response to determining to optimize the examination recipe, replacing the first classifier with the second classifier to obtain an optimized examination recipe;
wherein the optimized examination recipe is usable for examining a subsequent semiconductor specimen in the sequence.

16. The computerized method according to claim 15 , wherein the inspection features comprise a se

Assignees

• Applied Materials Israel Ltd

Inventors

• Bar Amir

Classifications

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G01N21/9501 Primary

  Semiconductor wafers (manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20) · CPC title

• G06T7/0004

  Industrial image inspection · CPC title