# US 2026/0037735 A1 · Method and device for providing color that matches intent of user's utterance

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

- Number: US 2026/0037735 A1
- Document ID: US20260037735A1
- Status: Published application
- Kind: A1
- Application number: 19/060,163
- Filed: 2025-02-21
- Published: 2026-02-05
- Earliest claimed: 2024-08-01
- Assignees: Hyundai Motor Company; Kia Corporation
- Applicants: Hyundai Motor Company; Kia Corporation
- Inventors: Jang Sun Lee
- Web page: https://patentgrep.com/patent/US20260037735A1

## CPC

- G06F 40/30: Semantic analysis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method and device provide a color that matches an intent of a user's utterance. The method includes: generating one or more second natural language expressions, each corresponding to a color represented by each of first color codes, for one or more of the first color codes in a pre-created table; and generating a response based on a result of interpreting the user's utterance related to the color.

## Claims

### Claim 1

A method for providing a color that matches an intent of a user's utterance, the method comprising:
generating one or more second natural language expressions, each corresponding to a color represented by each of first color codes, for one or more of the first color codes in a pre-created table; and
generating a response based on a result of interpreting the user's utterance related to the color.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the response includes:
generating one or more second color codes based on the result of interpreting the user's utterance related to the color.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating the response further includes:
determining one color code that matches the intent of the user's utterance among the first color codes, based on a similarity between the first color codes and the one or more second color codes.

### Claim 4 (depends on 3)

The method of claim 3, wherein determining the one color code that matches the intent of the user's utterance includes:
calculating similarities between each of the first color codes and each of the second color codes;
calculating an average of the similarities for each of the first color codes; and
selecting the first color code with having a highest average value as the one color code that matches the intent of the user's utterance.

### Claim 5 (depends on 1)

The method of claim 1, wherein generating the response includes:
generating the response based on whether an entity name for a color among one or more entity names included in the result of interpreting the user's utterance related to the color is included in at least one of a first natural language expression which are pre-defined for the first color codes or the one or more second natural language expressions which are newly generated.

### Claim 6

A device for providing a color that matches an intent of a user's utterance, the device comprising:
at least one memory storing commands; and
at least one processor,
wherein the at least one processor is configured to execute the commands to perform:
generating one or more second natural language expressions, each corresponding to a color represented by each of first color codes, for one or more of the first color codes in a pre-created table, and
generating a response based on a result of interpreting the user's utterance related to the color.

### Claim 7 (depends on 6)

The device of claim 6, wherein generating the response includes:
generating one or more second color codes based on the result of interpreting the user's utterance related to the color.

### Claim 8 (depends on 7)

The device of claim 7, wherein generating the response further includes:
determining one color code that matches the intent of the user's utterance among the first color codes, based on a similarity between the first color codes and the one or more second color codes.

### Claim 9 (depends on 8)

The device of claim 8, wherein determining of the one color code that matches the intent of the user's utterance includes:
calculating similarities between each of the first color codes and each of the second color codes;
calculating an average of the similarities for each of the first color codes; and
selecting the first color code with having a highest average value as the one color code that matches the intent of the user's utterance.

### Claim 10 (depends on 6)

The device of claim 6, wherein generating the response includes:
generating the response based on whether an entity name for a color among one or more entity names included in the result of interpreting the user's utterance related to the color is included in at least one of a first natural language expression which are pre-defined for the first color codes or the one or more second natural language expressions which are newly generated.
