Methods and apparatuses for use of eye interpretation information

• US 7,881,493 B1
• Filed: 04/09/2004
• Issued: 02/01/2011
• Est. Priority Date: 04/11/2003
• Status: Expired due to Fees

• Current Assignee: Eyetools, Inc.
• Original Assignee: Eyetools, Inc.
• Inventors: Johnson, Colin, Edwards, Gregory T.
• Primary Examiner(s): Seth; Manav
• Application Number:
  US10/821,800
• Time in Patent Office: 2,489 Days
• Field of Search: 382/103, 382/117, 351/209, 348/78, 600/558
• US Class Current: 382/103
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris

Abstract

Eyetracking techniques and analysis techniques are disclosed. At least one interpretation of eyetracking data is received from an eye interpretation engine. A characteristic of an application is dynamically modified based on the interpretation of the eyetracking data. A portion of the application being viewed by a user may be determined. The determined portion may be modified in response to the interpretation of the eyetracking data for the user.

Claims

1. A method comprising:

receiving, from an eye interpretation engine, at least an interpretation of eyetracking data corresponding to a plurality of users that are presented with a base interface having a base set of features;

receiving external context data corresponding the interactions of the plurality of users with an application having the base interface, wherein the external context data is related to an operational state associated with a computing device running the application;

determining a user familiarity with the base interface; and

dynamically modifying a characteristic of a graphical user interface of the application based, at least in part, on the interpretation of the eyetracking data and the external context data by providing a simplified interface if a low level of familiarity is determined and by providing an enhanced set of features of a high level of familiarity is determined.

2. The method of claim 1 wherein dynamically modifying comprises one of:

modifying, creating, destroying, removing, invoking and configuring.

3. The method of claim 1 wherein dynamically acting on a characteristic of the application based, at least in part, on the interpretation of the eyetracking data comprises:

determining from the interpretation of the eyetracking data at least a portion of an interface that has not been viewed by one or more of the plurality of users;

modifying a format of the portion of the interface that has not been viewed by one or more of the plurality of users.

15. The method of claim 1 wherein the external context data comprise one or more of:

system information, location and/or z-order of windows and/or objects, Document Object Model (DOM) of a Web page or application being viewed, current application process state and/or visual state, task models, cognitive models describing the mental or physical steps or states required.

4. A method comprising:

receiving, from an eye interpretation engine, at least an interpretation of eyetracking data corresponding to a plurality of users that are presented with a base interface having a base set of features;

receiving external context data corresponding the interactions of the plurality of users with an application having the base interface, wherein the external context data is related to an operational state associated with a computing device running the application;

determining one or more areas that were skipped, skimmed and/or reread based on aggregated eyetracking data corresponding to the plurality of users;

dynamically modifying a graphical output of the application displayed on an output device based, at least in part, on the interpretation of the eyetracking data and the external context data to compensate for the determined skipping, skimming and/or rereading.

5. The method of claim 4 wherein acting on comprises one of:

modifying, creating, destroying, removing, invoking and configuring.

6. The method of claim 4 wherein dynamically acting on the output of the application based, at least in part, on the interpretation of the eyetracking data comprises:

determining from the interpretation of the eyetracking data at least a portion of content that has not been viewed by one or more of the plurality of users;

modifying a format of the portion of content that has not been viewed by one or more of the plurality of users.

16. The method of claim 4 wherein the external context data comprise one or more of:

system information, location and/or z-order of windows and/or objects, Document Object Model (DOM) of a Web page or application being viewed, current application process state and/or visual state, task models, cognitive models describing the mental or physical steps or states required.

7. An article comprising a non-transitory computer-readable medium having stored thereon instructions that, when executed, cause one or more processors to:

receive, from an eye interpretation engine, at least an interpretation of eyetracking data corresponding to a plurality of users that are presented with a base interface having a base set of features;

receive external context data corresponding the interactions of the plurality of users with an application having the base interface, wherein the external context data is related to an operational state associated with a computing device running the application;

determine a user familiarity with the base interface; and

dynamically modify a characteristic of a graphical user interface of the application based, at least in part, on the interpretation of the eyetracking data and the external context data by providing a simplified interface if a low level of familiarity is determined and by providing an enhanced set of features of a high level of familiarity is determined.

8. The article of claim 7 wherein dynamically modifying comprises one of:

modifying, creating, destroying, removing, invoking and configuring.

9. The article of claim 7 wherein the instructions that cause the one or more processors to dynamically act on a characteristic of the application based, at least in part, on the interpretation of the eyetracking data comprise instructions that, when executed cause the one or more processors to:

determine from the interpretation of the eyetracking data at least a portion of content that has not been viewed by one or more of the plurality of users;

modify a format of the portion of the interface that has not been viewed by one or more of the plurality of users.

17. The article of claim 7 wherein the external context data comprise one or more of:

system information, location and/or z-order of windows and/or objects, Document Object Model (DOM) of a Web page or application being viewed, current application process state and/or visual state, task models, cognitive models describing the mental or physical steps or states required.

10. An article comprising a non-transitory computer-readable medium having stored thereon instructions that, when executed, cause one or more processors to:

receive, from an eye interpretation engine, at least an interpretation of eyetracking data corresponding to a plurality of users that are presented with a base interface having a base set of features;

receive external context data corresponding the interactions of the plurality of users with an application having the base interface, wherein the external context data is related to an operational state associated with a computing device running the application;

determine one or more areas that were skipped, skimmed and/or reread based on aggregated eyetracking data corresponding to the plurality of users;

dynamically modify a graphical output of the application displayed on an output device based, at least in part, on the interpretation of the eyetracking data and the external context data to compensate for the determined skipping, skimming and/or rereading.

11. The article of claim 10 wherein dynamically modify comprises one of:

modifying, creating, destroying, removing, invoking and configuring.

12. The article of claim 10 wherein the instructions that cause the one or more processors to dynamically act on a characteristic of the application based, at least in part, on the interpretation of the eyetracking data comprise instructions that, when executed cause the one or more processors to:

determine from the interpretation of the eyetracking data at least a portion of content that has not been viewed by one or more of the plurality of users;

modify a format of the portion of the interface that has not been viewed by one or more of the plurality of users.

18. The article of claim 10 wherein the external context data comprise one or more of:

system information, location and/or z-order of windows and/or objects, Document Object Model (DOM) of a Web page or application being viewed, current application process state and/or visual state, task models, cognitive models describing the mental or physical steps or states required.

13. An article comprising a non-transitory computer—

readable medium having stored thereon instructions that, when executed, cause one or more processors to;

receive, from an eye interpretation engine, at least an interpretation of eyetracking data corresponding to a plurality of users that are presented with a base interface having a base set of features;

receive external context data corresponding the at least interactions of the plurality of users with an application having the base interface, wherein the external context data is related to an operational state associated with a computing device running the application;

determine a user familiarity with the base interface; and

dynamically modify a graphical user interface the application based, at least in part, on the interpretation of the eyetracking data and the external context data.

14. The article of claim 13 wherein dynamically modify comprises one of:

invoking, selecting, closing, creating and configuring.

19. The article of claim 13 wherein the external context data comprise one or more of:

system information, location and/or z-order of windows and/or objects, Document Object Model (DOM) of a Web page or application being viewed, current application process state and/or visual state, task models, cognitive models describing the mental or physical steps or states required.