System and method of providing and validating enhanced CAPTCHAs

• US 10,152,585 B2
• Filed: 09/26/2016
• Issued: 12/11/2018
• Est. Priority Date: 09/07/2015
• Status: Active Grant

• Current Assignee: Cerence Inc.
• Original Assignee: VoiceBox Technologies Corporation (Microsoft Corporation)
• Inventors: Bhosale, Vikrant, Rothwell, Spencer John, Elshenawy, Ahmad Khamis
• Primary Examiner(s): Dolly, Kendall
• Application Number:
  US15/275,720
• Publication Number:
  US 20170068809A1
• Time in Patent Office: 806 Days
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/36 by graphic or iconic representation
• CPC Class Codes: G06F 2221/2133 Verifying human interaction, e.g., Captcha

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.

Claims

1. A computer implemented method of distinguishing between computers and humans through an enhanced completely automated public turing test to tell computers and humans apart (e-captcha) through skill-based actions, 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:

receiving, by the computer system, a request comprising an e-captcha specification, wherein the e-captcha specification comprises one or more parameters that specify a particular skill needed to solve the e-captcha and a specific domain to which the skill needed to solve the e-captcha is related;

identifying, by the computer system, an e-captcha challenge based on the e-captcha specification, wherein the e-captcha challenge includes a skill-based action to be completed to validate that a user is a human user;

providing, by the computer system, the e-captcha challenge via the network responsive to the request;

receiving, by the computer system, a response to the e-captcha challenge via the network;

determining, by the computer system, whether the skill-based action was at least partially correctly completed;

generating, by the computer system, information indicating whether the skill-based action was at least partially correctly completed; and

providing, by the computer system, via the network, the information indicating whether the skill-based action was at least partially correctly completed.

2. The method of claim 1, wherein the e-captcha challenge comprises a math problem and the response comprises an attempted solution to the math problem.

3. The method of claim 1, wherein the e-captcha challenge comprises a question to be answered.

4. The method of claim 1, wherein the one or more parameters specify a type of e-captcha being requested, the method further comprising:

identifying, by the computer system, the e-captcha challenge based on the one or more parameters.

5. The method of claim 4, wherein the type of e-captcha being requested comprises a requested trivia question having a specified subject matter.

6. The method of claim 1, wherein providing the e-captcha challenge comprises:

providing, by the computer system, executable instructions that are configured to generate a user interface that includes the e-captcha challenge and at least one input configured to receive a response to the e-captcha challenge.

7. The method of claim 6, wherein the at least one input is configured to receive an audio input.

8. The method of claim 7, wherein the skill-based action comprises utterance of one or more words or phrases, and wherein determining whether the skill-based action was at least partially correctly completed comprises:

determining, by the computer system, an edit distance between text recognized from the utterance and text of the one or more words or phrases.

9. The method of claim 6, wherein the at least one input is configured to receive a text input, a gesture input, or a multiple choice input.

10. The method of claim 1, the method further comprising:

storing, by the computer system, an indication of whether the skill-based action was correctly completed in association with identifying information that identifies a user or an end user device associated with the response; and

determining, by the computer system, a number of times that the user or the end user device associated with the response has failed or passed skill-based actions based on the stored indication, wherein the number of times indicates a proficiency of the user or the end user device at correctly completing e-captcha challenges.

11. The method of claim 1, the method further comprising:

obtaining identifying information that identifies the user or a device associated with the user;

generating a score based on the determination of whether the skill-based action was at least partially correctly completed;

storing the score in association with the user identifying information; and

generating or updating a profile of the user based at least on the stored score, wherein the profile of the user indicates whether the user possesses the particular skill or indicates a level of the particular skill the user possesses.

12. The method of claim 1, the method further comprising:

obtaining a pre-stored profile of a subscriber that provides the e-captcha challenge to the user; and

identifying the e-captcha challenge from among a set of e-captcha challenges associated with the pre-stored profile.

13. 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 one or more storage devices that stores computer program instructions and one or more physical processors programmed with the computer program instructions that, when executed by the one or more physical processors, cause the computer system to;

receive a request comprising an e-captcha specification, wherein the e-captcha specification comprises one or more parameters that specify a particular skill needed to solve the e-captcha and a specific domain to which the skill needed to solve the e-captcha is related;

identify an e-captcha challenge based on the e-captcha specification, wherein the e-captcha challenge includes a skill-based action to be completed to validate that a user is a human user;

provide the e-captcha challenge via the network responsive to the request;

receive a response to the e-captcha challenge via the network;

determine whether the skill-based action was at least partially correctly completed;

generate information indicating whether the skill-based action was at least partially correctly completed; and

provide via the network the information indicating whether the skill-based action was at least partially correctly completed.

14. The system of claim 13, wherein the e-captcha challenge comprises a math problem and the response comprises an attempted solution to the math problem.

15. The system of claim 13, wherein the e-captcha challenge comprises a question to be answered.

16. The system of claim 13, wherein the one or more parameters specify a type of e-captcha being requested, and wherein the computer system is further programmed to:

identify the e-captcha challenge based on the one or more parameters.

17. The system of claim 16, wherein the type of requested e-captcha comprises a requested trivia question having a specified subject matter.

18. The system of claim 13, wherein to provide the e-captcha challenge, the computer system is programmed to:

provide executable instructions that are configured to generate a user interface that includes the e-captcha challenge and at least one input configured to receive a response to the e-captcha challenge.

19. The system of claim 18, wherein the at least one input is configured to receive an audio input.

20. The system of claim 19, wherein the skill-based action comprises utterance of one or more words or phrases, and wherein determining whether the skill-based action was at least partially correctly completed comprises:

determine an edit distance between text recognized from the utterance and text of the one or more words or phrases.

21. The system of claim 18, wherein the at least one input is configured to receive a text input, a gesture input, or a multiple choice input.

22. The system of claim 13, wherein the computer system is further programmed to:

store an indication of whether the skill-based action was correctly completed in association with identifying information that identifies a user or an end user device associated with the response; and

determine a number of times that the user or the end user device associated with the response has failed or passed skill-based actions based on the stored indication, wherein the number of times indicates a proficiency of the user or the end user device at correctly completing e-captcha challenges.