# US 12,762,183 B2 · Virtual tabular data generation method and server 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 12,762,183 B2
- Document ID: US12762183B2
- Status: Granted
- Kind: B2
- Application number: 19/065,417
- Filed: 2025-02-27
- Published: 2025-09-11
- Granted: 2026-10-13
- Earliest claimed: 2024-03-11
- Assignees: KakaoBank Corp.
- Applicants: Kakaobank Corp.
- Inventors: Young Jun Kwak; Jung Min Son; Su Bin Kim
- Web page: https://patentgrep.com/patent/US12762183B2

## CPC

- G06F 16/9017: {using directory or table look-up (use of a directory or look-up table in file systems G06F16/13)}
- G06F 16/211: {Schema design and management}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method of generating virtual tabular data, performed on a server using a deep-learning module, comprising: generating a first prompt for generating a table schema, calibrating a table schema by comparing the table schema generated based on the first prompt with a predefined reference table schema, generating a second prompt by referring to the calibrated table schema, generating table condition data for first tabular data generated based on the second prompt, generating a third prompt by referring to the table condition data and the calibrated table schema, and deriving final tabular data through a verification operation on second tabular data generated based on the third prompt.

## Claims

### Claim 1

A method of generating virtual tabular data, performed on a server using a deep-learning module, comprising:
generating a first prompt for generating a table schema;
applying the first prompt to the deep-learning module and receiving the table schema as an output of the deep-learning module;
calibrating the table schema by comparing the table schema generated based on the first prompt with a predefined reference table schema;
generating a second prompt by referring to the calibrated table schema;
applying the second prompt to the deep-learning module and receiving first tabular data as an output of the deep-learning module;
generating table condition data for the first tabular data by comparing each column included in the first tabular data with predefined condition data;
generating a third prompt by referring to the table condition data and the calibrated table schema; and
deriving final tabular data through a verification operation on second tabular data generated based on the third prompt.

### Claim 2 (depends on 1)

The method of claim 1, wherein the calibrating the table schema comprises:
comparing the table schema with the predefined reference table schema; and
calibrating the table schema to include an item included in the predefined reference table schema in response to determining that the table schema does not include the item.

### Claim 3 (depends on 1)

The method of claim 1, wherein the generating the first prompt comprises:
receiving a data generation request including information on tabular data desired by a user from a user terminal linked with the server; and
generating the first prompt based on information included in the data generation request.

### Claim 4 (depends on 3)

The method of claim 3, wherein the generating the second prompt comprises generating the second prompt by referring to the calibrated table schema and the data generation request together, and
the generating the third prompt comprises generating the third prompt by referring to all of the table condition data, the calibrated table schema, and the data generation request.

### Claim 5 (depends on 1)

The method of claim 1, wherein the table condition data comprises a unary constraint or a binary constraint for each column included in tabular data, and
the unary constraint refers to a condition of having one of predetermined values, and
the binary constraint refers to a condition of including an operational expression with another column.

### Claim 6 (depends on 1)

The method of claim 1, wherein the deriving the final tabular data comprises:
applying the third prompt to the deep-learning module and receiving the second tabular data as an output of the deep-learning module;
applying the second tabular data to a data verification module and obtaining a data evaluation result as an output of the data verification module; and
determining the final tabular data based on the data evaluation result.

### Claim 7 (depends on 6)

The method of claim 6, wherein the second tabular data comprises a greater number of example data than the first tabular data, and
wherein the data verification module:
performs diversity verification on the example data included in the second tabular data, and
performs constraint satisfaction verification on columns to which a unary constraint or a binary constraint is applied in the example data.

### Claim 8 (depends on 6)

The method of claim 6, wherein the obtaining the data evaluation result comprises:
deriving a first evaluation value for diversity of each row data or each column data included in the second tabular data;
deriving a second evaluation value for whether each column data included in the second tabular data satisfies a unary constraint;
deriving a third evaluation value for whether each column data included in the second tabular data satisfies a binary constraint; and
determining whether reference values for the first to third evaluation values are satisfied, and generating the data evaluation result including a result thereof.

### Claim 9 (depends on 8)

The method of claim 8, wherein the determining the final tabular data comprises:
correcting data included in the second tabular data that do not satisfy the reference values to values that satisfy the reference values; and
determining the second tabular data with corrections reflected as the final tabular data.

### Claim 10 (depends on 6)

The method of claim 6, further comprising:
correcting the third prompt based on the data evaluation result;
regenerating the second tabular data by applying the corrected third prompt to the deep-learning module;
applying the regenerated second tabular data to the data verification module and re-obtaining the data evaluation result as an output of the data verification module; and
determining the final tabular data based on the re-obtained data evaluation result.

### Claim 11 (depends on 1)

A non-transitory computer-readable recording medium having recorded thereon a program that, when executed by a processor, executes the method set forth in claim 1.

### Claim 12

A server comprising:
a processor;
a memory configured to load a computer program executed by the processor; and
a database configured to store data generated in an execution process of the computer program,
wherein the computer program comprises:
generating a first prompt for generating a table schema;
applying the first prompt to a deep-learning module and receiving the table schema as an output of the deep-learning module;
calibrating a table schema by comparing the table schema generated based on the first prompt with a predefined reference table schema;
generating a second prompt by referring to the calibrated table schema;
applying the second prompt to the deep-learning module and receiving first tabular data as an output of the deep-learning module;
generating table condition data for the first tabular data by comparing each column included in the first tabular data with predefined condition data;
generating a third prompt by referring to the table condition data and the calibrated table schema;
deriving final tabular data through a verification operation on second tabular data generated based on the third prompt; and
storing the final tabular data in the database.

### Claim 13 (depends on 12)

The server of claim 12, wherein the calibrating the table schema comprises:
comparing the table schema with the predefined reference table schema; and
calibrating the table schema to include an item included in the predefined reference table schema in response to determining that the table schema does not include the item,
wherein the deriving the final tabular data comprises:
applying the third prompt to the deep-learning module and receiving the second tabular data as an output of the deep-learning module;
applying the second tabular data to a data verification module loaded into the memory and obtaining a data evaluation result as an output of the data verification module; and
determining the final tabular data based on the data evaluation result.

### Claim 14 (depends on 13)

The server of claim 13, wherein the table condition data comprises a unary constraint or a binary constraint for each column included in tabular data, and
the unary constraint refers to a condition of having one of predetermined values, and
the binary constraint refers to a condition of including an operational expression with another column.

### Claim 15 (depends on 13)

The server of claim 13, wherein the second tabular data comprises a greater number of example data than the first tabular data, and
wherein the data verification module:
performs diversity verification on the example data included in the second tabular data, and
performs constraint satisfaction verification on columns to which a unary constraint or a binary constraint is applied in the example data.

### Claim 16 (depends on 13)

The server of claim 13, wherein the obtaining the data evaluation result comprises:
deriving a first evaluation value for diversity of each row data or each column data included in the second tabular data;
deriving a second evaluation value for whether each column data included in the second tabular data satisfies a unary constraint;
deriving a third evaluation value for whether each column data included in the second tabular data satisfies a binary constraint; and
determining whether reference values for the first to third evaluation values are satisfied, and generating the data evaluation result including a result thereof.

### Claim 17 (depends on 16)

The server of claim 16, wherein the determining the final tabular data comprises:
correcting data included in the second tabular data that do not satisfy the reference values to values that satisfy the reference values; and
determining the second tabular data with corrections reflected as the final tabular data.

### Claim 18 (depends on 12)

The server of claim 12, wherein the generating the first prompt comprises:
receiving a data generation request including information on tabular data desired by a user from a user terminal linked with the server; and
generating the first prompt based on information included in the data generation request.

### Claim 19 (depends on 18)

The server of claim 18, wherein the generating the second prompt comprises generating the second prompt by referring to the calibrated table schema and the data generation request together, and
the generating the third prompt comprises generating the third prompt by referring to all of the table condition data, the calibrated table schema, and the data generation request.