Method and system for controlling skill acquisition interfaces
AssigneeInternational Business Machines Corporation
InventorsBrenda Dietrich, Jennifer Lai, Yan Liu
Life of this patent
Estimating the term…
Abstract
A method and system for capturing expert behavior that the expert is not even necessarily conscious of, such as gaze patterns, that are tied to positive outcomes, and to create a catalog (e.g. database) of these behaviors. The system compares the current behavior of a person, for example a novice, against this catalog of expert behaviors. If the current behavior is significantly different, the system would adapt various aspects of the interface to bring the current behavior closer in line to that of the expert.
Claims12
A computer-implemented method for acquiring skills comprising the steps of:
- tracking, using a gaze tracking device having a lens for real-time video capture, attributes of a viewing behavior of one or more first expert users when performing a task and storing said attributes of said viewing behavior in a memory storage device associated with a processor device, said attributes of viewing behavior comprising a user's gaze pattern including:
- locations where a viewing gaze is fixated, a gaze duration at said locations, a gaze path being tracked, and a location representing a weighted average of a plurality of gaze positions whose weights are associated with corresponding time values;
- tracking, using said gaze tracking device, said attributes of a viewing behavior of one or more second novice users when performing the task and storing said attributes of said novice user's viewing behavior in a memory storage device associated with a processor device;
- implementing a machine learning algorithm to learn differences between said attributes of viewing behavior of said one or more first expert users performing said task and said attributes of viewing behavior of said one or more second novice users performing the task and associating said learned differences with significant positive or negative outcomes of said task;
- storing in said memory storage a catalog of said learned differences for the task that are tied to said significant outcomes;
- and
- subsequently tracking, using said gaze tracking device, a further user's viewing behavior when subsequently performing the same task as said one or more first expert users;
- comparing, in real time, attributes of said further user's viewing behavior with said stored attributes of said first expert user's behavior tied to said significant outcomes to detect real-time viewing behavior differences;
- comparing, in real time, a detected difference against said catalog of stored learned differences that are tied to said significant outcomes;
- and
- providing an output indication for said further user to correct any said detected behavioral differences commensurate with said significant outcomes such that said further user acquires skills as said first expert user,
- wherein a processor coupled to a memory storage device is configured to perform the machine learning, the comparing to detect differences, the differences comparing, and the providing.
A system for controlling skill acquisition interfaces, the system comprising:
- at least one memory storage device;
- at least one processor coupled to the at least one memory storage device, and
- a gaze tracking device having a lens for real-time video capture, said gaze tracking device tracking attributes of a viewing behavior of one or more first expert users when performing a task and storing said attributes of said viewing behavior in a memory storage device associated with a processor device, said attributes of viewing behavior comprising a user's gaze pattern including:
- locations where a viewing gaze is fixated, a gaze duration at said locations, a gaze path being tracked, and a location representing a weighted average of a plurality of gaze positions whose weights are associated with corresponding time values;
- and
- said gaze tracking device further tracking said attributes of a viewing behavior of one or more second novice users when performing the task and storing said attributes of said novice user's viewing behavior in a memory storage device associated with a processor device;
- wherein the at least one processor is further configured to:
- implement a machine learning algorithm to learn differences between said attributes of viewing behavior of said one or more first expert users performing said task and said attributes of viewing behavior of said one or more second novice users performing the task and associate said learned differences with significant positive or negative outcomes of said task;
- store in said memory storage device a catalog of said learned differences for the task that are tied to said significant outcomes;
- and
- subsequently track, using said gaze tracking device, a further user's viewing behavior when subsequently performing the same task as said one or more first expert users;
- compare, in real time, attributes of said further user's viewing behavior with said stored attributes of said first expert user's behavior tied to said significant outcomes to detect real-time viewing behavior differences;
- compare, in real time, a detected difference against said catalog of stored learned differences that are tied to said significant outcomes;
- and
- provide an output indication for said further user to correct any said detected behavioral differences commensurate with said significant outcomes such that said further user acquires skills as said first expert user.
A computer program product comprising at least one non-transitory computer usable medium having computer readable program code logic to execute a machine instruction in a processing unit for controlling skill acquisition interfaces, said computer readable program code logic when executed by said processing unit performing steps to:
- track, using a gaze tracking device having a lens for real-time video capture, attributes of a viewing behavior of one or more first expert users when performing a task and storing said attributes of said viewing behavior in a memory storage device associated with a processor device, said attributes of viewing behavior comprising a user's gaze pattern including:
- locations where a viewing gaze is fixated, a gaze duration at said locations, a gaze path being tracked, and a location representing a weighted average of a plurality of gaze positions whose weights are associated with corresponding time values;
- track, using said gaze tracking device, said attributes of a viewing behavior of one or more second novice users when performing the task and storing said attributes of said novice user's viewing behavior in a memory storage device associated with a processor device;
- implement a machine learning algorithm to learn differences between said attributes of viewing behavior of said one or more first expert users performing said task and said attributes of viewing behavior of said one or more second novice users performing the task and associating said learned differences with significant positive or negative outcomes of said task;
- store in said memory storage a catalog of said learned differences for the task that are tied to said significant outcomes;
- and
- subsequently track, using said gaze tracking device, a further user's viewing behavior when subsequently performing the same task as said one or more first expert users;
- compare, in real time, attributes of said further user's viewing behavior with said stored attributes of said first expert user's behavior tied to said significant outcomes to detect real-time viewing behavior differences;
- compare, in real time, a detected difference against said catalog of stored learned differences that are tied to said significant outcomes;
- and
- provide an output indication for said further user to correct any said detected behavioral differences commensurate with said significant outcomes such that said further user acquires skills as said first expert user.
Dependencies are inferred from the claim text.