# US 2014/0196133 A1 · Cognitive-based captcha system

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

- Number: US 2014/0196133 A1
- Document ID: US20140196133A1
- Status: Published application
- Kind: A1
- Application number: 14/147,253
- Filed: 2014-01-03
- Published: 2014-07-10
- Earliest claimed: 2013-01-04
- Inventors: Gary Stephen Shuster
- Web page: https://patentgrep.com/patent/US20140196133A1

## CPC

- G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour}
- G06F 21/31: User authentication
- G06F 21/36: by graphic or iconic representation
- H04L 63/08: {for authentication of entities (cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32)}
- H04L 63/083: {using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226)}
- H04L 63/0853: {using an additional device, e.g. smartcard, SIM or a different communication terminal (cryptographic mechanisms or cryptographic arrangements for entity authentication involving additional secure or trusted devices H04L9/3234)}
- H04L 63/126: {the source of the received data}
- H04W 12/065: Continuous authentication
- G06F 2221/2133: Verifying human interaction, e.g., Captcha
- H04M 2203/2027: Live party detection
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

Systems and methods for verifying human users through cognitive processes that computers cannot imitate are described herein. Human cognitive language processing techniques may be used to verify human users. Visual patterns and tests may be used to distinguish between humans and computers because computer-based visual recognition is fundamentally different from human visual processing. Persistent plugins and tests may be used to continuously verify human users.

## Claims

### Claim 1

A computer system configured to validate language CAPTCHAs, the computer system comprising:
one or more hardware processors programmed, via executable code instructions, to implement:
a CAPTCHA generator configured to:
determine a phrase of words;
determine one or more spelling and/or grammatical errors to insert into respective words of the phrase; and
generate a language CAPTCHA comprising the phrase of words including the determined one or more errors, wherein the one or more errors are configured for human perception of the phrase of words based on the language CAPTCHA notwithstanding inclusion of the one or more errors in the language CAPTCHA;
a human validator configured to:
receive user input data associated with the language CAPTCHA;
compare the user input data to the phrase of words; and
determine whether the user input data was provided by a human based on said comparison.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the one or more errors are configured to not interfere with human perception of the phrase of words based on perception of only the language CAPTCHA.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein the one or more errors comprise changing one or more letters of respective words of the phrase while keeping the first and/or last letter of the respective words of the phrase the same.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the one or more errors comprise inserting non-letter characters into respective words of the phrase and/or substituting letters of respective words of the phrase with non-letter characters.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein the one or more errors comprise substituting one or more respective words of the phrase with a corresponding one or more homophones.

### Claim 6 (depends on 1)

The computer system of claim 1, wherein the one or more errors comprise replacing one or more characters of a first word of phrase having a first phoneme with one or more different characters having the same first phoneme.

### Claim 7 (depends on 1)

The computer system of claim 1, wherein the phrase of words when perceived together comprises one or more meanings associated with the phrase of words that assist human perception of the phrase of words.

### Claim 8 (depends on 1)

The computer system of claim 1, wherein the user input data comprises audio input.

### Claim 9

A computer system configured to validate heteronym CAPTCHAs, the computer system comprising:
one or more hardware processors programmed, via executable code instructions, to implement:
a CAPTCHA generator configured to:
determine a phrase of words, wherein the phrase of words when perceived together comprises one or more meanings associated with the phrase of words that assist human perception of the phrase of words, and further comprises one or more heteronyms based on the one or more meanings associated with the phrase of words; and
generate a heteronym CAPTCHA comprising the phrase of words including the one or more heteronyms, wherein the one or more heteronyms are configured for human perception based on the one or more meanings associated with the phrase of words;
a human validator configured to:
receive user input data associated with the heteronym CAPTCHA;
compare the user input data to two or more definitions corresponding to the one or more respective heteronyms; and
determine whether the user input data was provided by a human based on said comparison.

### Claim 10 (depends on 9)

The computer system of claim 9, wherein the heteronym CAPTCHA further comprises multiple choice answers based on two or more definitions corresponding to the one or more heteronyms.

### Claim 11 (depends on 9)

The computer system of claim 9, wherein the heteronym CAPTCHA further comprises playable audio data corresponding to the phrase of words including the determined one or more heteronyms.

### Claim 12 (depends on 9)

The computer system of claim 9, wherein the heteronym CAPTCHA is configured for a website.

### Claim 13

A computer system configured to validate visual CAPTCHAs, the computer system comprising:
one or more hardware processors programmed, via executable code instructions, to implement:
a CAPTCHA generator configured to generate a visual CAPTCHA comprising a visual pattern configured to be perceived as including a first object and/or action by a human user viewing the visual pattern, wherein an automated computer system analyzing the visual pattern cannot identify the first object and/or action; and
a human validator configured to:
receive user input data associated with the visual CAPTCHA,
compare the user input data to a description of the first object and/or action; and
determine whether the user input data was provided by a human based on said comparison.

### Claim 14 (depends on 13)

The computer system of claim 13, wherein the visual pattern is automatically generated.

### Claim 15 (depends on 13)

The computer system of claim 13, wherein the visual pattern comprises a moire pattern.

### Claim 16 (depends on 13)

The computer system of claim 13, wherein the visual pattern comprises a rorschach pattern.

### Claim 17 (depends on 13)

The computer system of claim 13, wherein the visual CAPTCHA is configured for a website.

### Claim 18 (depends on 13)

The computer system of claim 13, wherein the visual CAPTCHA is configured to persistently display throughout a session.

### Claim 19 (depends on 17)

The computer system of claim 17, wherein the persistent display of the visual CAPTCHA comprises visual alerts when user interaction is required.

### Claim 20 (depends on 13)

The computer system of claim 13, wherein the visual CAPTCHA further comprises a first visual pattern and a second visual pattern, wherein an answer to the first visual pattern is known and an answer to the second visual pattern is unknown; and
wherein the user input data comprises a first input data corresponding to the first visual pattern and a second input data corresponding to the second visual pattern, and the human validator is further configured to store the second input data based first input data.
