# US 2026/0279223 A1 · Method for generating grading data for coding test, device for generating grading data, and system for generating grading data

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

- Number: US 2026/0279223 A1
- Document ID: US20260279223A1
- Status: Published application
- Kind: A1
- Application number: 19/529,302
- Filed: 2026-02-04
- Published: 2026-09-17
- Earliest claimed: 2025-02-12
- Assignees: Branch and Bound Co., Ltd.
- Applicants: Branch and Bound Co., Ltd.
- Inventors: Seung Yong Lee; Dong Hyun Kim; Tae Yang Kim; Hyung Jin Kim; Gyo Jun Youn; Sang Hun Lee; Jae Hwi Kim
- Web page: https://patentgrep.com/patent/US20260279223A1

## CPC

- G09B 19/0053: {Computers, e.g. programming}
- G06F 8/71: Version control (security arrangements therefor G06F21/57); Configuration management
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0475: Generative networks
- G06N 3/048: Activation functions
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06N 3/10: Interfaces, programming languages or software development kits, e.g. for simulating neural networks
- G06N 3/045: Combinations of networks
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Provided are a method for generating grading data for a coding test, a device for generating grading data, and a system for generating grading data. The method for generating grading data for a coding test includes receiving a problem through a user interface, generating a plurality of problem information based on the problem using a first neural network, generating an input data generator for the problem based on the plurality of problem information using a second neural network, executing the input data generator to generate test input data for the problem, generating a solution code for the problem based on the plurality of problem information using a third neural network, and generating test output data for the test input data based on the solution code to generating grading data.

## Claims

### Claim 1

A method for generating grading data for a coding test, the method comprising:
receiving a problem through a user interface;
generating a plurality of problem information based on the problem using a first neural network;
generating an input data generator for the problem based on the plurality of problem information using a second neural network;
executing the input data generator to generate test input data for the problem;
generating a solution code for the problem based on the plurality of problem information using a third neural network; and
generating test output data for the test input data based on the solution code to generate the grading data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the problem includes a text which is a natural language, and
the first neural network is a language model configured to perform natural language processing.

### Claim 3 (depends on 1)

The method of claim 1, wherein at least some of the plurality of problem information includes a text which is a natural language, and
the second neural network is configured to output a program code of the input data generator based on the plurality of problem information.

### Claim 4 (depends on 1)

The method of claim 1, wherein the plurality of problem information includes at least one of a problem description, an input format, an input restriction, an output format, an input/output example, and restriction information for the problem.

### Claim 5 (depends on 1)

The method of claim 1, wherein the second neural network includes an encoder module configured to generate an embedding vector based on the plurality of problem information and a decoder module configured to generate the input data generator based on the embedding vector.

### Claim 6 (depends on 1)

The method of claim 1, wherein the generating of the grading data includes executing the solution code to generate the test output data based on the test input data.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
verifying validity of the test input data through a validator generated based on a fourth neural network.

### Claim 8 (depends on 7)

The method of claim 7, wherein the validator is generated through the fourth neural network based on the plurality of problem information.

### Claim 9 (depends on 7)

The method of claim 7, wherein the second neural network, the third neural network, and the fourth neural network are transfer-learned separately from one another.

### Claim 10 (depends on 9)

The method of claim 9, wherein the third neural network is trained based on the solution code and a prestored test case.

### Claim 11

A device for generating grading data, the device comprising:
a processor;
an accelerator; and
a memory,
wherein the processor is configured to execute a program stored in the memory to perform:
receiving a problem through a user interface;
generating a plurality of problem information based on the problem using a first neural network computed by the accelerator;
generating an input data generator for the problem based on the plurality of problem information using a second neural network computed by the accelerator;
executing the input data generator to generate test input data for the problem;
generating a solution code for the problem based on the plurality of problem information using a third neural network computed by the accelerator; and
generating test output data for the test input data based on the solution code to generate the grading data.

### Claim 12 (depends on 11)

The device of claim 11, wherein the problem includes a text which is a natural language,
at least some of the plurality of problem information includes a text which is a natural language, and
the first neural network is a language model configured to perform natural language processing.

### Claim 13 (depends on 11)

The device of claim 11, wherein the plurality of problem information includes at least one of a problem description, an input format, an input restriction, an output format, an input/output example, and restriction information for the problem.

### Claim 14 (depends on 11)

The device of claim 11, wherein the second neural network includes an encoder module configured to generate an embedding vector based on the plurality of problem information and a decoder module configured to generate the input data generator based on the embedding vector.

### Claim 15 (depends on 11)

The device of claim 11, wherein the processor is further configured to verify validity of the test input data through a validator generated based on a fourth neural network, and
the validator is generated through the fourth neural network based on the plurality of problem information.

### Claim 16 (depends on 15)

The device of claim 15, wherein the second neural network, the third neural network, and the fourth neural network are transfer-learned separately from one another.

### Claim 17 (depends on 16)

The device of claim 16, wherein the third neural network is trained based on the solution code and a prestored test case.

### Claim 18

A system for generating grading data, the system comprising:
a problem information extraction module configured to receive a problem and generate a plurality of problem information based on the problem;
an input data generator generation module configured to generate an input data generator configured to generate test input data for the problem based on the plurality of problem information;
a validator generation module configured to generate a validator verifying validity of the test input data based on the plurality of problem information; and
a solution code generation module configured to generate a solution code for the problem based on the plurality of problem information.

### Claim 19 (depends on 18)

The system of claim 18, wherein the input data generator generation module includes a first neural network,
the validator generation module includes a second neural network,
the solution code generation module includes a third neural network, and
the first to third neural networks are transfer-learned separately from one another.

### Claim 20 (depends on 18)

The system of claim 18, wherein the solution code is executed to generate test output data for the test input data based on the test input data.
