# US 2023/0053696 A1 · Method of predicting characteristics of semiconductor device and computing device performing the same

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

- Number: US 2023/0053696 A1
- Document ID: US20230053696A1
- Status: Published application
- Kind: A1
- Application number: 17/699,489
- Filed: 2022-03-21
- Published: 2023-02-23
- Earliest claimed: 2021-08-19
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Jonghyun LEE; Gwangnae GIL; Seyoung PARK; Sola WOO
- Web page: https://patentgrep.com/patent/US20230053696A1

## CPC

- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06N 3/047: Probabilistic or stochastic networks
- G06F 30/367: Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
- G06N 3/08: Learning methods
- G06F 2119/18: Manufacturability analysis or optimisation for manufacturability
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

To predict characteristics of a semiconductor device, basic training data corresponding to a combination of process data, device data and simulation result data are generated using a plurality of compact models. Each compact model generates the simulation result data indicating characteristics of a semiconductor device corresponding to the device data by performing simulation based on the device data, the plurality of compact models respectively corresponding to a plurality of process data and a plurality of semiconductor products. A deep learning model is trained based on the basic training data such that the deep learning model outputs prediction data indicating the characteristics of the semiconductor device. Target prediction data indicating characteristics of the semiconductor device included in a target semiconductor product are generated based on the deep learning model, the device data and the process data corresponding to the target semiconductor product.

## Claims

### Claim 1

A method of predicting characteristics of a semiconductor device included in a target semiconductor product, the method being performed by at least one processor executing program codes, the program codes stored in computer readable media, the method comprising:
generating basic training data corresponding to a combination of process data, device data, and simulation result data using a plurality of compact models, each of the plurality of compact models generating the simulation result data by performing a simulation based on the device data, the simulation result data indicating characteristics of semiconductor devices corresponding to the device data, the plurality of compact models respectively corresponding to a plurality of process data and a plurality of semiconductor products;
training a deep learning model based on the basic training data such that the deep learning model is configured to output prediction data; and
generating target prediction data based on the deep learning model, the device data, and the process data corresponding to the target semiconductor product such that the target prediction data indicates characteristics of the semiconductor device included in the target semiconductor product.

### Claim 2 (depends on 1)

The method of claim 1, wherein the target semiconductor product is a new semiconductor product that is not included in the plurality of semiconductor products corresponding to the plurality of compact models.

### Claim 3 (depends on 1)

The method of claim 1, wherein
the plurality of process data is determined depending on a process-group combination of a process type,
the process-group combination indicating a manufacturing process of each of the plurality of semiconductor products and a product group in which each of the plurality of semiconductor products is included.

### Claim 4 (depends on 3)

The method of claim 3, wherein the process-group combination of the target semiconductor product is a new process-group combination that is not included in the process-group combinations of the plurality of semiconductor products.

### Claim 5 (depends on 1)

The method of claim 1, wherein the plurality of semiconductor products and the target semiconductor product are memory devices.

### Claim 6 (depends on 1)

The method of claim 1, wherein
the device data indicate structure and operation condition of the plurality of semiconductor devices,
the simulation result data and the prediction data indicate electrical characteristics of the plurality of semiconductor device, and
the process data indicate condition of manufacturing processes of the plurality of semiconductor devices.

### Claim 7 (depends on 1)

The method of claim 1, wherein
input data of the plurality of compact models include the device data and do not include the process data, and
input data of the deep learning model include both of the process data and the device data.

### Claim 8 (depends on 1)

The method of claim 1, wherein the training the deep learning model includes training the deep learning model such that the deep learning model is configured to output uncertainty data, the uncertainty data indicating uncertainty of the prediction data.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
retraining the deep learning model based on the uncertainty data.

### Claim 10 (depends on 9)

The method of claim 9, wherein the uncertainty data include a model uncertainty value indicating the uncertainty of the prediction data caused by insufficiency of the basic training data.

### Claim 11 (depends on 10)

The method of claim 10, wherein retraining the deep learning model includes:
comparing the model uncertainty value with a model reference value;
generating addition training data using the compact model when the model uncertainty value is larger than the model reference value; and
retrain the deep learning model based on the addition training data,
wherein the addition training data is different from the basic training data.

### Claim 12 (depends on 11)

The method of claim 11, wherein retraining the deep learning model further includes:
determining an addition data range corresponding to a range of the device data such that the model uncertainty value is larger than the model reference value, and
wherein the addition training data correspond to a combination of the process data, the device data included in the addition data range, and the simulation result data.

### Claim 13 (depends on 11)

The method of claim 11, wherein the deep learning model that has been trained based on the basic training data is further trained based on the addition training data.

### Claim 14 (depends on 9)

The method of claim 9, wherein the uncertainty data include a data uncertainty value, the data uncertainty value indicating the uncertainty of the prediction data caused by noises of the basic training data.

### Claim 15 (depends on 14)

The method of claim 14, wherein retraining the deep learning model includes:
comparing the data uncertainty value with a data reference value;
providing measurement data by measuring the characteristics of the semiconductor device when the data uncertainty value is larger than the data reference value;
correcting the compact model based on the measurement data;
generating updated training data using the corrected compact model; and
retraining the deep learning model based on the updated training data.

### Claim 16 (depends on 15)

The method of claim 15, wherein retraining the deep learning model further includes:
determining a measurement data range corresponding to a range of data such that the data uncertainty value is larger than the data reference value, and
wherein the measurement data are provided by measuring characteristics of the semiconductor device corresponding to the device data included in the measurement data range.

### Claim 17 (depends on 15)

The method of claim 15, wherein the deep learning model that has been trained based on the basic training data is initialized, and the initialized deep learning model is trained based on the measurement data.

### Claim 18 (depends on 8)

The method of claim 8, wherein the deep learning model includes a Bayesian Neural Network (BNN).

### Claim 19

A method of predicting characteristics of a semiconductor device in a target semiconductor product, the method being performed by at least one processor executing program codes, the program codes stored in computer readable media, the method comprising:
generating basic training data corresponding to a combination of process data, device data and simulation result data using a plurality of compact models, each of the plurality of compact models generating the simulation result data by performing a simulation based on the device data, the simulation result data indicating characteristics of a semiconductor device corresponding to the device data, the plurality of compact models respectively corresponding to a plurality of process data and a plurality of semiconductor products;
training a deep learning model based on the basic training data such that the deep learning model is configured to output prediction data and uncertainty value, the prediction data indicating the characteristics of the semiconductor device and the uncertainty value indicating uncertainty of the prediction data;
retraining the deep learning model based on the uncertainty data; and
generating target prediction data based on the deep learning model, the device data, and the process data corresponding to the target semiconductor product such that the target prediction data indicates characteristics of the semiconductor device included in a target semiconductor product included in the target semiconductor product.

### Claim 20

A computing device comprising:
a computer readable medium storing program codes and a plurality of compact models, the program codes being executed by the at least one processor to generate a deep learning model using the plurality of compact models, each of the plurality of compact models generating simulation result data by performing a simulation based on the device data, the simulation result data indicating characteristics of semiconductor devices corresponding to the device data, the plurality of compact models respectively corresponding to a plurality of process data. and a plurality of semiconductor products; and
at least one processor, the at least one processor, when executing the program codes, configured to
generate basic training data corresponding to a combination of process data, device data and simulation result data using the plurality of compact models,
train the deep learning model based on the basic training data such that the deep learning model is configured to output prediction data; and
generate target prediction data based on the deep learning model, the device data and the process data corresponding to the target semiconductor product such that the target prediction data indicates characteristics of the semiconductor device included in the target semiconductor product.
