Cognitive load assessment for digital documents

Patent metadata

Field	Value
Publication number	US-10108316-B2
Application number	US-201113995514-A
Country	US
Kind code	B2
Filing date	Dec 30, 2011
Priority date	Dec 30, 2011
Publication date	Oct 23, 2018
Grant date	Oct 23, 2018

Abstract

An embodiment of the invention includes a system that tracks a user's pupillary response to content located on a web page. The system then determines a cognitive load for the user that is based on the measured response. Cognitive load refers to the total amount of mental activity imposed on working memory in any one instant. Further, the system may aggregate the cognitive load data for one user over time, for many different users, and/or for many different users over time. The cognitive load may be determined for different portions of a displayed page, such as a document object model (DOM) included on the page. The cognitive load may be specified for different elements that make up the DOM. Also, cognitive load may be apportioned over several different DOM elements at one moment in time or over a period of time. Other embodiments are described herein.

First claim

What is claimed is:

1. At least one storage medium having instructions stored thereon for causing a system to perform a method comprising:
storing a first user's pupil activity data in the at least one storage medium, the first user's pupil activity data being derived from digital images that were captured by gaze tracker hardware;
processing the first user's pupil activity data, using at least one processor, to determine a first attribution of the first user's pupil activity data to first and second elements of a hierarchical user interface (UI) model included on a previously displayed digital first page that displays the first and second elements in a first spatial orientation to one another;
processing the first user's pupil activity data, using the at least one processor, to determine a second attribution of the first user's pupil activity data to the first and second elements included on a previously displayed digital second page that displays the first and second elements in a second spatial orientation to one another that is unequal to the first orientation;
determining a single aggregate attribution of pupil activity data for one of the first and second elements, but not an additional one of the first and second elements, based on both of the first and second attributions of the first user's pupil activity data;
determining an additional single aggregate attribution of pupil activity data for the additional one of the first and second elements based on both of the first and second attributions of the first user's pupil activity data; and
attributing first and second portions of the first attribution of the first user's pupil activity data respectively to the first and second elements included on the first page,
wherein (a) the first UI model includes a first document object model (DOM) and both of the first and second elements are included in a single hierarchal level of the first DOM, (b) each of the first and second elements has a parent node and a child node; and (c) the first and second portions correspond to a first instance of time.

2. The at least one medium of claim 1 , the method comprising:
processing a second user's pupil activity data, using the at least one processor, to determine a first attribution of the second user's pupil activity data to the first and second elements included on the first page;
processing the second user's pupil activity data, using the at least one processor, to determine a second attribution of the second user's pupil activity data to the first and second elements included on the second page;
storing the first and second attributions of the second user's pupil activity data in the at least one storage medium coupled to the at least one processor; and
determining the single aggregate attribution of pupil activity data based on both of the first and second attributions of the first user's pupil activity data and further based on both of the first and second attributions of the second user's pupil activity data.

3. The at least one medium of claim 1 , wherein:
processing the first user's pupil activity to determine the first attribution of the first user's pupil activity data includes one of (a) calculating the first attribution of the first user's pupil activity data based on data acquired via a processing system, and (b) receiving the first attribution of the first user's pupil activity data from the processing system after the first attribution of the first user's pupil activity data was calculated on the processing system.

4. The at least one medium of claim 1 , wherein on the first page the first element includes a first child node including first content and on the second page the first element includes a second child node including second content unequal to the first content.

5. The at least one medium of claim 1 , the method comprising:
attributing an additional portion of the first attribution of the first user's pupil activity data to the first element of the first UI model included on the first page at a second instance of time that immediately follows the first instance of time.

6. The at least one medium of claim 1 , the method comprising:
attributing an additional first portion of the first attribution of the first user's pupil activity data to the first element of the first UI model included on the first page at a second instance of time that immediately follows the first instance of time;
attributing a third portion of the first attribution of the first user's pupil activity data to the second element of the first UI model included on the first page at the first instance of time; and
attributing an additional third portion of the first attribution of the first user's pupil activity data to the second element of the first UI model included on the first page at the second instance of time.

7. An apparatus comprising:
at least one processor;
control logic, coupled to the at least one processor, to:
store a first user's pupil activity data in at least one machine accessible medium coupled to the at least one processor, the first user's pupil activity data being derived from digital images that were captured by gaze tracker hardware;
process the first user's pupil activity data, using the at least one processor, to determine a first attribution of the first user's pupil activity data to first and second hierarchical elements of a first hierarchical user interface (UI) model included on a previously displayed digital first page that displays the first and second elements in a first spatial orientation to one another;
process the first user's pupil activity data, using the at least one processor, to determine a second attribution of the first user's pupil activity data to the first and second elements included on a previously displayed digital second page that displays the first and second elements in a second spatial orientation to one another that is unequal to the first orientation;
determine a single aggregate attribution of pupil activity data for one of the first and second elements of the first UI model, but not an additional one of the first and second elements, based on both of the first and second attributions of the first user's pupil activity data; and
determine an additional single aggregate attribution of pupil activity data for an additional one of the first and second elements based on both of the first and second attributions of the first user's pupil activity data; and
attribute first and second portions of the first user's first attribution of the first user's pupil activity data respectively to the first and second elements included on the first page,
wherein (a) the first UI model includes a first document object model (DOM) and both of the first and second elements are included in a single hierarchal level of the first DOM, (b) each of the first and second elements has a parent node and a child node; and (c) the first and second portions correspond to a first instance of time.

8. The apparatus of claim 7 , wherein the control logic is to:
process a second user's pupil activity data, using the at least one processor, to determine a first attribution of the second user's pupil activity data to the first and second elements included on the first page;
process the second user's pupil activity, using the at least one processor, to determine a second attribution of the second user's pupil activity data to the first and second elements included on the second page; and
determine the single aggregate attribution of pupil activity data based on both of the first and second attributions of the first user's pupil activity data and further based on both of the first and second attributions of the second user's pupil activity data.

9. The apparatus of

Assignees

• Lyons Kenton M
• Intel Corp

Inventors

• Lyons Kenton M

Classifications

• G06F3/0484 Primary

  for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range · CPC title

• A61B3/113

  for determining or recording eye movement · CPC title

• G06K9/00442

  Physics · mapped topic

• G06F17/30905

  Physics · mapped topic

• G06F3/013

  Eye tracking input arrangements (G06F3/015 takes precedence) · CPC title