# US 2026/0064009 A1 · Method for training opc modeling parameter

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

- Number: US 2026/0064009 A1
- Document ID: US20260064009A1
- Status: Published application
- Kind: A1
- Application number: 19/184,246
- Filed: 2025-04-21
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: Shanghai Huali Integrated Circuit Corporation
- Applicants: Shanghai Huali Integrated Circuit Corporation
- Inventors: Shunkui KE
- Web page: https://patentgrep.com/patent/US20260064009A1

## CPC

- G03F 7/70441: {Optical proximity correction [OPC]}
- G03F 7/705: {Modelling or simulating from physical phenomena up to complete wafer processes or whole workflow in wafer productions}
- G03F 7/70625: {Dimensions, e.g. line width, critical dimension [CD], profile, sidewall angle or edge roughness}
- G03F 7/706841: {Machine learning}
- G06N 3/08: Learning methods
- G03F: PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR; (phototypographic composing devices B41B; photosensitive materials or processes for photographic purposes G03C; electrophotography, sensitive layers or processes therefor G03G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure provides a method for training an OPC modeling parameter, including: step 1: designing a plurality of OPC patterns according to a design requirement for a lithography process layer layout; selecting at least one model parameter as a selected model parameter requiring training, and setting a plurality of different values for the selected model parameter; and collecting wafer pattern data formed by performing a lithography process on each OPC pattern; step 2: generating a sample unit and a sample set based on the collected data; step 3: inputting data of the sample set into a neural network for training; and step 4: performing OPC modeling using the trained neural network, where during the OPC modeling, an optimal value of the selected model parameter is obtained using the trained neural network, and the optimal value of the selected model parameter is used to perform the OPC modeling.

## Claims

### Claim 1

A method for training an OPC modeling parameter, comprising the following steps:
step 1: collecting OPC modeling data, comprising:
designing a plurality of OPC patterns according to a design requirement for a lithography process layer layout;
selecting at least one model parameter as a selected model parameter requiring training, and setting a plurality of different values for each selected model parameter; and
collecting wafer pattern data formed by performing a lithography process on each OPC pattern based on different values of the selected model parameter;
step 2: generating a sample unit and a sample set based on the collected data;
step 3: inputting data of the sample set into a neural network for training; and
step 4: performing OPC modeling using the trained neural network, wherein during the OPC modeling, an optimal value of the selected model parameter is obtained using the trained neural network, and the optimal value of the selected model parameter is used to perform the OPC modeling.

### Claim 2 (depends on 1)

The method for training an OPC modeling parameter according to claim 1, wherein in step 1, the designed OPC patterns are required to cover all circuit layout pattern requirements in the lithography process layer layout.

### Claim 3 (depends on 2)

The method for training an OPC modeling parameter according to claim 2, wherein the lithography process layer layout comprises a hole layer layout.

### Claim 4 (depends on 3)

The method for training an OPC modeling parameter according to claim 3, wherein the OPC patterns corresponding to the hole layer layout comprise:
a grating formed by an arrangement of vias;
a head-to-head structure between a via and a metal line in a via layer;
a head-to-head structure between vias in the via layer;
a via array structure; and
a weak point pattern.

### Claim 5 (depends on 4)

The method for training an OPC modeling parameter according to claim 4, wherein the via array comprises N×N rectangular vias, 3×3 rectangular vias, 5×5 rectangular vias, and 1×N rectangular vias, wherein N is an integer greater than 5.

### Claim 6 (depends on 5)

The method for training an OPC modeling parameter according to claim 5, wherein the via array comprises rectangular vias comprising square vias.

### Claim 7 (depends on 4)

The method for training an OPC modeling parameter according to claim 4, wherein the OPC patterns comprise patterns of a minimum critical dimension and a minimum pitch under a design rule.

### Claim 8 (depends on 1)

The method for training an OPC modeling parameter according to claim 1, wherein in step 2, each sample unit comprises the OPC pattern, the corresponding value of the selected model parameter, and the corresponding wafer pattern data; and
the sample set is formed by aggregating all the sample units.

### Claim 9 (depends on 8)

The method for training an OPC modeling parameter according to claim 8, prior to aggregating for forming the sample set in step 2, further comprising performing a cleaning operation for removing all unsuitable sample units, the unsuitable sample units comprising:
the OPC pattern that fails to be properly exposed; and
the wafer pattern with an ADI critical dimension measurement value less than the minimum critical dimension under a design rule.

### Claim 10 (depends on 1)

The method for training an OPC modeling parameter according to claim 1, wherein in step 3, the neural network comprises a BP neural network.

### Claim 11 (depends on 10)

The method for training an OPC modeling parameter according to claim 10, wherein the BP neural network comprises an input layer, more than one hidden layer, and an output layer.

### Claim 12 (depends on 1)

The method for training an OPC modeling parameter according to claim 1, wherein the selected model parameter comprises an optical diameter.

### Claim 13 (depends on 1)

The method for training an OPC modeling parameter according to claim 1, wherein in step 4, a step of obtaining the optimal value of the selected model parameter comprises:
obtaining a first curve of a simulation error varying with the values of the selected model parameter using the trained neural network; and
obtaining the optimal value of the selected model parameter based on a convergence trend of the first curve.
