# US 2020/0003700 A1 · Guided inspection of a semiconductor wafer based on systematic defects

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0003700 A1
- Document ID: US20200003700A1
- Status: Published application
- Kind: A1
- Application number: 16/022,566
- Filed: 2018-06-28
- Published: 2020-01-02
- Earliest claimed: 2018-06-28
- Assignees: Applied Materials Israel Ltd.
- Applicants: Applied Materials Israel Ltd.
- Inventors: Yotam Sofer; Boaz Cohen; Saar Shabtay; Eli Buchman
- Web page: https://patentgrep.com/patent/US20200003700A1

## CPC

- G01N 21/9501: {Semiconductor wafers (manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20)}
- G01N 21/956: Inspecting patterns on the surface of objects {(contactless testing of electronic circuits G01R31/308; testing currency G07D; manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20)}
- G01N 21/95607: {using a comparative method}
- G01N 2021/8854: {Grading and classifying of flaws}
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)

## Abstract

A candidate defect may be identified at a semiconductor wafer. A determination may be made as to whether the candidate defect at the semiconductor wafer corresponds to a systematic defect or a random defect. In response to determining that the candidate defect at the semiconductor wafer corresponds to a systematic detect, the candidate defect at the semiconductor wafer may be provided to a defect review tool for review by the defect review tool.

## Claims

### Claim 1

A system comprising:
a memory; and
a processor, operatively coupled with the memory, to:
identify a candidate defect at a semiconductor wafer;
determine whether the candidate defect at the semiconductor wafer corresponds to a systematic defect or a random defect by:
identifying a pattern associated with the candidate defect;
identifying other candidate defects at the semiconductor wafer that are associated with the same pattern; and
generating a combined defect probability score for the candidate defect based on a defect probability score of the candidate defect and other defect probability scores of the other candidate defects that are associated with the same pattern; and
in response to determining that the candidate defect at the semiconductor wafer corresponds to a systematic detect, provide the candidate defect at the semiconductor wafer to a defect review tool for review by the defect review tool.

### Claim 2

(canceled)

### Claim 3 (depends on 1)

The system of claim 1, wherein the pattern associated with the candidate defect corresponds to a structure of the semiconductor wafer that is at or approximate to the candidate defect, and wherein the other candidate defects that are associated with the same pattern correspond to candidate defects that are at or approximate another structure of the semiconductor wafer with the same pattern.

### Claim 4 (depends on 1)

The system of claim 1, wherein the processor is further to:
determine that the candidate defect is a systematic defect when the combined defect probability score for the candidate defect satisfies a threshold value; and
determining that the candidate defect is a random defect when the combined defect probability score for the candidate defect does not satisfy the threshold value.

### Claim 5 (depends on 1)

The system of claim 1, wherein the combined defect probability score is higher when a number of the other candidate defects that are associated with the same pattern as the candidate defect is larger than when a number of the other candidate defects that are associated with the same pattern as the candidate defect is smaller.

### Claim 6 (depends on 1)

The system of claim 1, wherein the candidate defect is identified based on an optical image of the semiconductor wafer and wherein the candidate defect is determined to corresponds to a systematic defect or a random defect based on design data of the semiconductor wafer.

### Claim 7 (depends on 1)

The system of claim 1, wherein the processor is further to:
in response to determining that the candidate defect at the semiconductor wafer corresponds to a random detect, determine to not provide the candidate defect at the semiconductor wafer to the defect review tool for review by the defect review tool.

### Claim 8

A method comprising:
identifying a candidate defect at a semiconductor wafer;
determining, by a processor, whether the candidate defect at the semiconductor wafer corresponds to a systematic defect or a random defect by:
identifying a pattern associated with the candidate defect;
identifying other candidate defects at the semiconductor wafer that are associated with the same pattern; and
generating a combined defect probability score for the candidate defect based on a defect probability score of the candidate defect and other defect probability scores of the other candidate defects that are associated with the same pattern; and
in response to determining that the candidate defect at the semiconductor wafer corresponds to a systematic detect, providing the candidate defect at the semiconductor wafer to a defect review tool for review by the defect review tool.

### Claim 9

(canceled)

### Claim 10 (depends on 8)

The method of claim 8, wherein the pattern associated with the candidate defect corresponds to a structure of the semiconductor wafer that is at or approximate to the candidate defect, and wherein the other candidate defects that are associated with the same pattern correspond to candidate defects that are at or approximate another structure of the semiconductor wafer with the same pattern.

### Claim 11 (depends on 8)

The method of claim 8, further comprising:
determining that the candidate defect is a systematic defect when the combined defect probability score for the candidate defect satisfies a threshold value; and
determining that the candidate defect is a random defect when the combined defect probability score for the candidate defect does not satisfy the threshold value.

### Claim 12 (depends on 8)

The method of claim 8, wherein the combined defect probability score is higher when a number of the other candidate defects that are associated with the same pattern as the candidate defect is larger than when a number of the other candidate defects that are associated with the same pattern as the candidate defect is smaller.

### Claim 13 (depends on 8)

The method of claim 8, wherein the candidate defect is identified based on an optical image of the semiconductor wafer and wherein the candidate defect is determined to corresponds to a systematic defect or a random defect based on design data of the semiconductor wafer.

### Claim 14 (depends on 8)

The method of claim 8, further comprising:
in response to determining that the candidate defect at the semiconductor wafer corresponds to a random detect, determining to not provide the candidate defect at the semiconductor wafer to the defect review tool for review by the defect review tool

### Claim 15

A non-transitory computer readable medium comprising instructions, which when executed by a processor, cause the processor to perform operations comprising:
identifying a candidate defect at a semiconductor wafer;
determining, by the processor, whether the candidate defect at the semiconductor wafer corresponds to a systematic defect or a random defect by:
identifying a pattern associated with the candidate defect;
identifying other candidate defects at the semiconductor wafer that are associated with the same pattern; and
generating a combined defect probability score for the candidate defect based on a defect probability score of the candidate defect and other defect probability scores of the other candidate defects that are associated with the same pattern; and
in response to determining that the candidate defect at the semiconductor wafer corresponds to a systematic detect, providing the candidate defect at the semiconductor wafer to a defect review tool for review by the defect review tool.

### Claim 16

(canceled)

### Claim 17 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the pattern associated with the candidate defect corresponds to a structure of the semiconductor wafer that is at or approximate to the candidate defect, and wherein the other candidate defects that are associated with the same pattern correspond to candidate defects that are at or approximate another structure of the semiconductor wafer with the same pattern.

### Claim 18 (depends on 15)

The non-transitory computer readable medium of claim 15, the operations further comprising:
determining that the candidate defect is a systematic defect when the combined defect probability score for the candidate defect satisfies a threshold value; and
determining that the candidate defect is a random defect when the combined defect probability score for the candidate defect does not satisfy the threshold value.

### Claim 19 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the combined defect probability score is higher when a number of the other candidate defects that are associated with the same pattern as the candidate defect is larger than when a number of the other candidate defects that are associated with the same pattern as the candidate defect is smaller.

### Claim 20 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the candidate defect is identified based on an optical image of the semiconductor wafer and wherein the candidate defect is determined to corresponds to a systematic defect or a random defect based on design data of the semiconductor wafer.
