US 9,519,766 B1Granted

System and method of providing and validating enhanced CAPTCHAs

AssigneeVoiceBox Technologies, Inc.

InventorsVikrant Bhosale, Spencer John Rothwell, Ahmad Khamis Elshenawy

Life of this patent

Estimating the term…

Loading patent…

Abstract

The invention relates to a system and method of automatically distinguishing between computers and human based on responses to enhanced Completely Automated Public Turing test to tell Computers and Humans Apart (“e-captcha”) challenges that do not merely challenge the user to recognize skewed or stylized text. A given e-captcha challenge may be specific to a particular knowledge domain. Accordingly, e-captchas may be used not only to distinguish between computers and humans, but also determine whether a respondent has demonstrated knowledge in the particular knowledge domain. For instance, participants in crowd-sourced tasks, in which unmanaged crowds are asked to perform tasks, may be screened using an e-captcha challenge. This not only validates that a participant is a human (and not a bot, for example, attempting to game the crowd-source task), but also screens the participant based on whether they can successfully respond to the e-captcha challenge.

Claims26

Dependent claims

A computer implemented method of distinguishing between computers and humans through enhanced completely automated public turing test to tell computers and humans apart (e-captcha), the method being implemented in a computer system having one or more physical processors programmed with computer program instructions that, when executed by the one or more physical processors, cause the computer system to perform the method, the method comprising:

providing, by the computer system, via a network, executable instructions configured to generate a user interface that includes an e-captcha challenge, wherein the e-captcha challenge requires one or more words or phrases to be uttered;
receiving, by the computer system, an audio input via at least one input configured to receive the audio input, the audio input comprising a response to the e-captcha challenge;
using, by the computer system, an automated speech recognition engine to convert the audio input to text;
determining, by the computer system, an edit distance between the one or more words or phrases to be uttered and the text converted from the audio input;
determining, by the computer system, whether the one or more words or phrases to be uttered were at least partially correctly uttered based on the edit distance;
responsive to a determination that the one or more words or phrases were at least partially correctly uttered, causing, by the computer system, information indicating that the response is valid to be provided;
and
responsive to a determination that the one or more words or phrases were not at least partially correctly uttered, causing, by the computer system, information indicating that the response is invalid to be provided.

5 more elements

A system of distinguishing between computers and humans through enhanced completely automated public turing test to tell computers and humans apart (e-captcha), comprising:

a computer system having a memory that stores computer program instructions and one or more physical processors programmed with the computer program instructions that, when executed by the memory and one or more physical processors, cause the computer system to:
provide, via the network, executable instructions configured to generate a user interface that includes an e-captcha challenge, wherein the e-captcha challenge requires-one or more words or phrases to be uttered;
receive an audio input via at least one input configured to receive the audio input, the audio input comprising a response to the e-captcha challenge;
use an automated speech recognition engine to convert the audio input to text;
determine an edit distance between the one or more words or phrases and the text converted from the audio input;
determine whether the one or more words or phrases to be uttered were was at least partially correctly uttered based on the edit distance;
responsive to a determination that the one or more words or phrases were at least partially correctly uttered, cause information indicating that the response is valid to be provided;
and
responsive to a determination that the one or more words or phrases were not at least partially correctly uttered, cause information indicating that the response is invalid to be provided.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/846,923Filed 7 Sep 2015
Granted: 13 Dec 2016
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06F 21/36
User authentication: by graphic or iconic representation
G06F 21/31
Authentication, i.e. establishing the identity or authorisation of security principals: user authentication
G06F 21/32
User authentication: using biometric data, e.g. fingerprints, iris scans or voiceprints
G06F 2221/2133
Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for…:…

Family

No related US applications are recorded in the indexed filing history.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key