Security and content protection by continuous identity verification

Patent metadata

Field	Value
Publication number	US-10977595-B2
Application number	US-201815939056-A
Country	US
Kind code	B2
Filing date	Mar 28, 2018
Priority date	Dec 27, 2017
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

A system includes one or more server hardware computing devices includes one or more processors and memory storing instructions that, when executed by the one or more processors, cause the system to receive a request to verify an identity of a user attempting to complete an examination provided by an online proctored examination platform to a candidate user authorized to complete the examination and repeatedly, at a predefined interval during the examination, determine, based at least in part on user data collected by the online proctored examination platform during the examination, the user data identifying the user at a time that the interval elapses, whether the user is the candidate user, and, responsive to a determination that the user is not the candidate user, perform one or more of a plurality of actions associated with a failed identity verification, the plurality of actions including stopping the examination.

First claim

The invention claimed is:

1. A system, comprising one or more server hardware computing devices communicatively coupled to a network, the one or more server hardware computing devices comprising one or more processors and memory storing:
decision logic executable by the one or more processors and comprising one or more image processing algorithms for matching a subject across a plurality of images; and
specific computer-executable instructions that, when executed by the one or more processors, cause the system to:
receive a first message associated with a first user account of an online proctored examination platform;
determine that the first message includes a request to begin an examination using a client device associated with the first user account;
establish a video data connection between a first server of the one or more server hardware computing devices and the client device via the network;
receive, from the client device, video data comprising a live feed captured by a video capture device associated with the client device;
obtain a first image from the video data;
execute the decision logic using the first image to produce a first identity verification indicating that the first image depicts a candidate associated with the first user account and authorized to take the examination;
responsive to the first identity verification, cause the examination to begin;
during the examination, receive user input collected by the client device;
obtain, from the user input, current user identity information identifying a user of the client device when the user input was collected;
compare the current user identity information to stored identifying information of the candidate to produce one of a current identity verification indicating the user is the candidate, and a failed identity verification indicating the user is not the candidate; and
responsive to the failed identity verification, perform one or more actions associated with a potential cheating incident, comprising:
updating a risk score stored within a database coupled to the network, by replacing an existing risk score with an updated risk score comprising a reduced value;
responsive to a determination that the updated risk score is below a threshold within the database or the decision logic, selecting, from a pool of on-demand proctors within the database, at least one additional proctor, wherein the at least one additional proctor shares at least one common attribute with the candidate within the database, wherein the at least one common attribute includes a requirement for a proctor trained in high risk security procedures; and
assigning the at least one additional proctor to the candidate by associating the at least one additional proctor in the database with the first user account.

2. The system of claim 1 , wherein the video data comprising the live feed is continuously received by the online proctored examination platform during the examination, the user input comprises the video data, and the instructions, when executed by the one or more processors, further cause the system to:
obtain, as the current user identity information, a current image from the video data;
obtain, as the stored identifying information of the candidate, a stored image depicting the candidate; and
to compare the current user identity information to the stored identifying information, execute the decision logic using the current image and the stored image to:
identify, in the current image, the user of the client device; and
determine a likelihood that the user depicted in the current image is the candidate depicted in the stored image;
responsive to the likelihood meeting a predetermined threshold similarity, produce the current identity verification; and
responsive to the likelihood falling below a predetermined threshold similarity, produce the failed identity verification.

3. The system of claim 1 , wherein the instructions, when executed by the one or more processors, cause the system to:
obtain, as the current user identity information, biometric data from the user input, the biometric data describing the user's usage of the client device during the examination;
obtain, as the stored identifying information of the candidate, historical candidate data describing one or more identifying markers identified from previous user input submitted to the online proctored examination platform by the candidate during one or more previous examinations;
to compare the current user identity information to the stored identifying information, compare the biometric data to the historical candidate data to determine whether the user has the one or more identifying markers of the candidate;
responsive to a determination that the user has the one or more identifying markers, produce the current identity verification; and
responsive to a determination that the user does not have the one or more identifying markers, produce the failed identity verification.

4. The system of claim 1 , wherein the user input is continuously received by the online proctored examination platform during the examination, and the one or more processors cause the system to automatically produce a chain of identification during the examination by repeatedly, at a predefined interval during the examination and responsively to the current identity verification being produced at an immediately previous interval, executing the instructions to obtain the current user identity information and compare the current user identity information to the stored identifying information of the candidate to produce either the current identity verification indicating or the failed identity verification.

Assignees

• Pearson Education Inc

Inventors

• Anderson Gregory
• Bailey Wayne
• Dolan Colleen M
• Fajobi Jide
• Jensen Darrick
• Lancaster Jr Ronald D
• Maloney Matthew
• Nealis Michael
• Nordberg Steven C
• Pascale Peter
• Stockinger Andrew
• Schaffer Julianne Michael

Classifications

• H04L67/306

  User profiles · CPC title

• H04L67/60

  Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources (admission control or resource allocation H04L47/70) · CPC title

• H04L67/52

  specially adapted for the location of the user terminal · CPC title

• H04L67/01

  Protocols · CPC title

• G06V20/46

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title