System and method for knowledgebase generation and management

• US 6,246,787 B1
• Filed: 05/30/1997
• Issued: 06/12/2001
• Est. Priority Date: 05/31/1996
• Status: Expired due to Term

• Current Assignee: Rudolph Technologies Incorporated (Onto Innovation Inc.)
• Original Assignee: Texas Instruments, Inc.
• Inventors: Wong, Wan S., Kinokoglu, Pinar, Cleavelin, C. Rinn, Hennessey, A. Kathleen, Lin, YouLing, Hastings, Howard V. II, Reddy, Rajasekar
• Primary Examiner(s): Patel, Jay
• Application Number:
  US08/866,771
• Time in Patent Office: 1,474 Days
• Field of Search: 382/140-152, 382/155-161, 382/181, 382/194, 382/218, 382/219, 382/305, 382/217, 382/209, 382/276, 356/73, 356/237, 395/183.02, 395/500.35, 364/146, 364/150, 437/939, 250/559.45, 702/35, 706/900
• US Class Current: 382/141
• CPC Class Codes: G01N 21/95607 using a comparative method
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: H01L 22/12 for structural parameters, e.g. thickness, line width, refractive index, temperature, warp, bond strength, defects, optical inspection, electrical measurement of structural dimensions, metallurgic measurement of diffusions electrical measurement of diffusions H01L22/14
• CPC Class Codes: H01L 22/20 Sequence of activities consisting of a plurality of measurements, corrections, marking or sorting steps
• CPC Class Codes: H01L 2924/014 Solder alloys

Abstract

A method and system for generating and managing a knowledgebase for use in identifying anomalies on a manufactured object, such as a semiconductor wafer, includes measures for adding, deleting, and organizing data from the knowledgebase.

Claims

1. A method for generating a knowledgebase for use in labeling anomalies on a manufactured object, the method comprising the steps of:

capturing an image of the object having an anomaly;

preparing a pixel-based representation of the image;

decomposing the pixel-based representation of the image into a primitives-based representation of the image to obtain an image geometry;

isolating the anomaly on the primitives-based representation of the image without a reference image;

comparing the primitive-based representation of the image with primitive sets for known anomalies in a knowledge base to locate the primitive set having a maximum similarity;

presenting a label associated with the set of primitives having a maximum similarity to an operator;

entering a label to be associated with the primitive-based representation of the image.

2. A method for generating a knowledgebase for use in labeling anomalies on a manufactured object, the method comprising the steps of:

capturing an image of the object having an anomaly;

preparing a pixel-based representation of the image;

decomposing the pixel-based representation of the image into a primitives-based representation of the image to obtain an image geometry, the image geometry corresponding to the primitives-based representation;

isolating the anomaly on the primitives-based representation of the image;

storing the primitive-based representation of the image; and

associating an assigned label with the stored primitive based representation of the image.

3. A method for augmenting a knowledgebase for use in labeling anomalies on a manufactured object, the method comprising the steps of

capturing an image of the object having an anomaly;

preparing a pixel-based representation of the image,

decomposing the pixel-based representation of the image into a primitives-based representation of the image to obtain an image geometry;

isolating the anomaly on the primitives-based representation of the image;

comparing the primitives-based representation with primitive sets in a knowledgebase to find the primitive set with a maximum similarity;

obtaining a first label associated with the primitive set having a maximum similarity;

associating the first label with the primitives-based representation of the image provided that the similarity is greater than a predetermined similarity threshold; and

adding the primitive-based representation and associated first label to the knowledgebase.

4. The method of claim 3 wherein the step of adding the primitive-based representation comprises saving primitives in a computer'"'"'s operating system'"'"'s subdirectory.

5. The method of claim 4 wherein the step of saving primitives in an operating system subdirectory, comprises the steps of:

creating field names representative of the anomaly'"'"'s characteristics, each field name representing a subdirectory; and

filling in subdirectories from the characteristics concerning each anomaly.

6. The method of claim 5, wherein the step of saving primitives in an operating system subdirectory further comprises creating a pointer to records of the primitive-based representation.

7. The method of claim 5, wherein the step of saving primitives in an operating system subdirectory further comprises associating a field name with each manufactured layer of a semiconductor wafer to allow convenient access to layers.

8. The method of claim 3 wherein the step of comparing further comprises weighting more-highly-determinant primitives in each primitives set of the knowledgebase more heavily to improve accuracy.

9. The method of claim 3 wherein the step of comparing further comprises consulting a secondary validation table when more than one primitive set is within a predetermined similarity threshold to the primitive-base representation to determine which label should be associated with the primitive-based representation.