System and method for remote test administration and monitoring

• US 8,926,335 B2
• Filed: 05/12/2011
• Issued: 01/06/2015
• Est. Priority Date: 05/12/2010
• Status: Active Grant

• Current Assignee: Verificient Technologies, Inc.
• Original Assignee: Verificient Technologies, Inc.
• Inventors: Kumar, Rajnish, Dutta, Apratim
• Primary Examiner(s): Musselman, Timothy A
• Application Number:
  US13/106,279
• Publication Number:
  US 20110279228A1
• Time in Patent Office: 1,335 Days
• Field of Search: 713182-186, 434156-185, 434/219, 434322-365, 434236-238
• US Class Current: 434/322
• CPC Class Codes: G08B 21/182 Level alarms, e.g. alarms responsive to variables exceeding a threshold
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A system and method for remote test administration are disclosed. The system includes a testing station having a processor and a memory in communication with the processor. The memory configured to store processor executable instructions configured to acquire biometric information related to a user, wherein the user is substantially adjacent to the testing station; identify at least one biometric vector within the acquired biometric information; and communicate the identified biometric vector. The system further includes a monitoring station configured to receive the biometric vector communicated by the testing station, the monitoring station having a processor and a memory in communication with the processor. The memory configured to store processor executable instructions configured to: compare the received biometric vector to a stored biometric vector and determine a recognition weight; group the biometric vector into one or more polling clusters based on the recognition weight and one or more recognition thresholds; and monitor the user at the testing station based on feature vectors associated with the one or more polling clusters.

Claims

1. A system for remote administration of a test, including a plurality of testing units each having a memory, a processor and a biometric capture unit, with the processor in each testing unit executing a program performing the steps of:

acquiring biometric information related to a user taking the test or a similar test by the biometric capture unit;

identifying at least one biometric vector for the user within the acquired biometric information;

generating at least one feature vector for the each user based on the at least one biometric vector;

outlier information

receiving at least one outlier feature vector from a test administration unit, the outlier feature vector being based on the at least one biometric vector of other of the users taking the test or a substantially similar test;

comparing the feature vector with each of the at least one outlier feature vectors to determine a deviation weight for each user;

grouping the at least one biometric vector into one or more polling clusters based on a deviation weight of the user and one or more deviation thresholds;

monitoring the biometric information of the user based on feature vectors associated with the one or more polling clusters to determine whether at least one feature vector of the user is substantially similar to at least one outlier feature vector; and

transmitting a notification to the test administration unit if at least one feature vector is substantially similar to at least one outlier feature vector.

2. The system of claim 1, wherein the biometric information is a digital image of the user.

3. The system of claim 2, wherein identifying at least one biometric vector comprises implementing a facial recognition algorithm.

4. The system of claim 1, wherein each of the polling clusters is associated with a different polling period.

5. The system of claim 1, wherein the biometric information is acquired via an input device selected from the group consisting of:

a fingerprint scanner;

a digital imaging device;

a keyboard device; and

an audio capture device.

6. The system of claim 1, including the step of comparing each of the monitored feature vectors associated with the user with respect to a group of biometric vectors that includes all of the biometric vector grouped into the one or more polling clusters.

7. The system of claim 6, including the step of determining the level of similarity between a plurality of tests.

8. The system of claim 7, including the step of notifying a proctor of the identified at least one outlier feature vector.

9. The system of claim 8, including the step of notifying the user associated with the identified at least one outlier feature vector.

10. A remote test administration system including a testing station having a processor, a memory and a biometric capture unit, and a program executing in the memory of the testing system, the program performing the steps of:

acquiring biometric information related to a user interacting with a testing station from the biometric capture unit;

identifying at least one biometric vector based on the acquired biometric information;

communicating the identified biometric vector to a centralized monitoring station for compiling with a plurality of identified biometric vectors acquired from a plurality of different users;

comparing the identified biometric vector to the plurality of identified biometric vectors to determine a recognition weight;

gathering the plurality of identified biometric vectors associated with the plurality of users participating in one or more similar tests;

grouping the identified biometric vector into one or more clusters based on the recognition weight and one or more recognition thresholds;

identify at least one outlier biometric vector, the outlier biometric vector being based on the identified biometric vectors of all of the users taking the test or substantially similar tests;

monitoring the user at the testing station based on biometric vectors associated with the one or more clusters to determine whether at least one biometric vectors is substantially similar to the at least one outlier biometric vector; and

transmitting a notification to the testing station if at least one feature vector is substantially similar to at least one outlier vector.

11. The method of claim 10, wherein acquiring biometric information comprises acquiring a digital image of the user.

12. The method of claim 11, wherein identifying at least one biometric vector comprises implementing a facial recognition algorithm.

13. The method of claim 10, wherein monitoring the user comprises monitoring each user within the one or more clusters according to a different polling period associated with each cluster.

14. The method of claim 10 further comprising:

comparing each of the monitored feature vectors associated with one or more users with respect to a group of biometric vectors that includes all of the biometric vector grouped into the one or more clusters.