# US 2023/0147976 A1 · Coded substrate material identifier communication tool

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

- Number: US 2023/0147976 A1
- Document ID: US20230147976A1
- Status: Published application
- Kind: A1
- Application number: 17/524,677
- Filed: 2021-11-11
- Published: 2023-05-11
- Earliest claimed: 2021-11-11
- Assignees: Applied Materials, Inc.
- Applicants: Applied Materials, Inc.
- Inventors: Wolfgang Aderhold; Boris Axelrod; Maxim Shaposhnikov; Dayal Ramachandran; Bindusagar Marath Sankarathodi
- Web page: https://patentgrep.com/patent/US20230147976A1

## CPC

- G05B 19/41865: {characterised by job scheduling, process planning, material flow}
- H10P 95/00: Generic processes or apparatus for manufacture or treatments not covered by the other groups of this subclass
- G06F 16/907: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06N 20/00: Machine learning
- G05B 19/41875: {characterised by quality surveillance of production}
- G05B 2219/32096: Batch, recipe configuration for flexible batch control
- G05B 2219/32365: For resource planning
- G05B 2219/45031: Manufacturing semiconductor wafers
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Embodiments disclosed herein include methods of processing substrates in a tool. In an embodiment, the method of processing the substrate in the tool, comprises receiving an augmented recipe with a machine learning (ML) and/or an artificial intelligence (AI) module. In an embodiment, the augmented recipe comprises, a recipe for processing the substrate in the tool, and a matrix identifier that corresponds to one or more substrate properties. In an embodiment the method further comprises using the ML and/or AI module to retrieve a data set from a database, where the data set is associated with the matrix identifier, and using the ML and/or AI module to modify the augmented recipe to form a modified recipe, where the modification is dependent on the data set.

## Claims

### Claim 1

A method of processing a substrate in a tool, comprising:
receiving an augmented recipe with a machine learning (ML) and/or an artificial intelligence (AI) module, wherein the augmented recipe comprises:
a recipe for processing the substrate in the tool; and
a matrix identifier that corresponds to one or more substrate properties;
using the ML and/or AI module to retrieve a data set from a database, wherein the data set is associated with the matrix identifier; and
using the ML and/or AI module to modify the augmented recipe to form a modified recipe, wherein the modification is dependent on the data set.

### Claim 2 (depends on 1)

The method of claim 1, wherein the matrix identifier comprises a matrix with a single row and a plurality of columns, wherein each column represents a different context parameter.

### Claim 3 (depends on 2)

The method of claim 2, wherein the plurality of columns includes at least ten columns.

### Claim 4 (depends on 2)

The method of claim 2, wherein a plurality of the plurality of columns are populated with an indicator.

### Claim 5 (depends on 4)

The method of claim 4, wherein the indicator is a number between 1 and 1,000.

### Claim 6 (depends on 2)

The method of claim 2, wherein the matrix identifier provides a context parameter for one or more of: material type, a resistivity, a substrate thickness, a substrate surface reflectance, a chip layout, a chip size, a chip uniformity, a number of times the substrate has been processed with the recipe, and a position in a lot of substrates.

### Claim 7 (depends on 1)

The method of claim 1, wherein the matrix identifier is generated by a host computer, and wherein underlying substrate data used to generate the matrix identifier is not accessible by the ML and/or AI module.

### Claim 8 (depends on 1)

The method of claim 1, wherein the data set has no indication of the one or more substrate properties other than the matrix identifier.

### Claim 9 (depends on 1)

The method of claim 1, wherein the data set includes data from sensors in the tool during the processing of one or more substrates with the same matrix identifier.

### Claim 10 (depends on 9)

The method of claim 9, wherein the sensors include closed loop sensors and witness sensors.

### Claim 11 (depends on 1)

The method of claim 1, wherein the data set includes data from metrology of one or more substrates with the same matrix identifier.

### Claim 12

A method for building a database used by a machine learning (ML) and/or artificial intelligence (AI) module for processing substrates without knowing underlying substrate properties, comprising:
associating a matrix identifier with a first substrate, wherein the matrix identifier corresponds to one or more substrate properties of the first substrate;
processing the first substrate in a tool; and
storing sensor data from the tool during processing of the first substrate in the database, wherein the sensor data is associated with the matrix identifier.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
repeating the operations for a plurality of substrates.

### Claim 14 (depends on 12)

The method of claim 12, wherein the sensor data comprises control loop sensor data and witness sensor data.

### Claim 15 (depends on 12)

The method of claim 12, wherein the sensor data further comprises metrology data of the processed first substrate.

### Claim 16 (depends on 12)

The method of claim 12, wherein the matrix identifier comprises a matrix with a single row and a plurality of columns, wherein each column represents a different context parameter.

### Claim 17 (depends on 16)

The method of claim 16, wherein the plurality of columns includes at least ten columns.

### Claim 18 (depends on 16)

The method of claim 16, wherein a plurality of the plurality of columns are populated with an indicator.

### Claim 19

A semiconductor processing tool, comprising:
a host computer;
an artificial intelligence (AI) and/or machine learning (ML) module communicatively coupled to the host computer;
a database communicatively coupled to the AI and/or ML module; and
a processing chamber, wherein the processing chamber is operated in accordance with a recipe that is selected by the host computer and modified by the AI and/or ML module in view of a data set within the database.

### Claim 20 (depends on 19)

The semiconductor processing tool of claim 19, wherein the host computer assigns a matrix identifier to the recipe, and wherein the data set used by the AI and/or ML module is associated with the matrix identifier.
