# US 2026/0037799 A1 · Deep learning-based apparatus and method for detecting profanity

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

- Number: US 2026/0037799 A1
- Document ID: US20260037799A1
- Status: Published application
- Kind: A1
- Application number: 19/284,918
- Filed: 2025-07-30
- Published: 2026-02-05
- Earliest claimed: 2024-07-30
- Assignees: Chung Ang University Industry Academic Cooperation Foundation
- Applicants: Chung Ang University Industry Academic Cooperation Foundation
- Inventors: YOUNG BIN KIM; SEUNG UK YU
- Web page: https://patentgrep.com/patent/US20260037799A1

## CPC

- G06N 3/08: Learning methods
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 40/30: Semantic analysis
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method for detecting profanity according to an embodiment is performed in a computing device that includes one or more processors and a memory storing one or more programs executed by the one or more processors includes acquiring sequence data converted from a sentence input by a user, and generating embedded data containing one or more tokens by embedding the acquired sequence data, and training a neural network model to output information on whether the sentence contains profanity by inputting the generated embedded data into the neural network model.

## Claims

### Claim 1

A method performed in a computing device that includes one or more processors and a memory storing one or more programs executed by the one or more processors, the method comprising:
acquiring sequence data converted from a sentence input by a user, and generating embedded data containing one or more tokens by embedding the acquired sequence data; and
training a neural network model to output information on whether the sentence contains profanity by inputting the generated embedded data into the neural network model.

### Claim 2 (depends on 1)

The method of claim 1, wherein the neural network model includes a neural network configured to derive information on whether the sentence contains profanity by analyzing the acquired embedded data, and
the training of the neural network model includes adjusting weights of the parameters constituting the neural network of the neural network model so that a difference between the information derived on whether the sentence contains profanity and information labeled on whether the sentence contains profanity is minimized.

### Claim 3 (depends on 1)

The method of claim 1, wherein the training of the neural network model includes:
deriving a plurality of sequential CLS tokens each corresponding to each of attention layers by sequentially passing the embedded data through a plurality of attention layers that perform attention;
deriving a final token from two or more CLS tokens among the plurality of CLS tokens according to a preset criterion; and
classifying whether the sentence contains profanity based on the final token.

### Claim 4 (depends on 3)

The method of claim 3, wherein the final token is derived by averaging of the plurality of CLS tokens.

### Claim 5 (depends on 3)

The method of claim 3, wherein the final token is derived from the largest CLS token among the plurality of CLS tokens.

### Claim 6 (depends on 3)

The method of claim 3, wherein the final token is derived by combining a first CLS token and a last CLS token among the plurality of sequential CLS tokens.

### Claim 7 (depends on 3)

The method of claim 3, wherein the final token is derived by combining the plurality of CLS tokens after applying a weight to each of the plurality of CLS tokens.

### Claim 8 (depends on 7)

The method of claim 7, wherein a first CLS token and a last CLS token among the plurality of sequential CLS tokens have a greater weight than that of the remaining CLS tokens.

### Claim 9 (depends on 8)

The method of claim 8, wherein the weights of the plurality of sequential CLS tokens gradually decrease and then increase from the first CLS token to the last CLS token among the plurality of sequential CLS tokens.

### Claim 10

An apparatus for detecting profanity that includes one or more processors and a memory storing one or more programs executed by the one or more processors, the apparatus comprising:
an embedding module configured to acquire sequence data converted from a sentence input by a user, and to generate embedded data containing one or more tokens by embedding the acquired sequence data; and
a determination module configured to train a neural network model to output information on whether the sentence contains profanity by inputting the generated embedded data into the neural network model.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the neural network model includes a neural network configured to derive information on whether the sentence contains profanity by analyze the acquired embedded data, and
the determination module is configured to adjust weights of the parameters constituting the neural network of the neural network model so that a difference between the information derived on whether the sentence contains profanity and information labeled on whether the sentence contains profanity is minimized.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein the determination module is configured to:
derive a plurality of sequential CLS tokens each corresponding to each of the attention layers by sequentially passing the embedded data through a plurality of attention layers that perform attention;
derive a final token from two or more CLS tokens among the plurality of CLS tokens according to a preset criterion; and
classify whether the sentence contains profanity based on the final token.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the final token is derived by combining the plurality of CLS tokens after applying a weight to each of the plurality of CLS tokens.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein a first CLS token and a last CLS token among the plurality of sequential CLS tokens have a greater weight than that of the remaining CLS tokens.

### Claim 15

A computer program stored in a non-transitory computer readable storage medium, wherein the computer program includes one or more instructions, and the instructions, when executed by a computing device including one or more processors, cause the computing device to perform:
acquiring sequence data converted from a sentence input by a user, and generating embedded data containing one or more tokens by embedding the acquired sequence data; and
training a neural network model to output information on whether the sentence contains profanity by inputting the generated embedded data into the neural network model.
