Activity centric resource recommendations in a computing environment
AssigneeInternational Business Machines Corporation
InventorsElizabeth A. Brownholtz, Casey Dugan, Werner Geyer, Michael Muller, Jianqiang Shen
Life of this patent
Estimating the term…
Abstract
Embodiments of the present invention address deficiencies of the art in respect to context sensitive resource recommendations and provide a method, system and computer program product for activity sensitive context sensitive resource recommendations. In an embodiment of the invention, an activity-centric resource recommendation method can be provided. The method can include inferring an activity from a workspace in a graphical user interface, identifying resources from amongst a set of resources that are relevant to the inferred activity, and displaying the identified resources in the graphical user interface.
Claims15
An activity-centric resource recommendation method comprising:
- retrieving into memory of a computer contextual data provided by different graphical user interface elements disposed within a workspace in a graphical user interface;
- inferring an activity based upon deduction from the retrieved contextual data provided by different graphical user interface elements disposed within the workspace in the graphical user interface by training a Bayesian predictor with words known to appear in connection with different activities, monitoring active windows in the workspace to extract window titles from the active windows and to place the window titles in a finite queue and providing the titles in the finite queue to the Bayesian predictor to compute a probability set of activities for the window titles;
- identifying resources from amongst a set of resources that are relevant to the inferred activity;
- and,
- displaying the identified resources in the graphical user interface.
A resource recommendation data processing system comprising:
- a host computing platform comprising at least one computer with memory and at least one processor;
- a Bayesian predictor executing in the memory of the host computing platform, coupled to a workspace of a graphical user interface provided by a processor of the host computing platform, and trained with a bag of words associated with different activities performed through the host computing platform;
- and,
- resource recommendation logic also executing in the host computing platform, the logic comprising program code enabled to retrieve into memory of the host computing platform contextual data provided by different graphical user interface elements disposed within a workspace in a graphical user interface, to infer an activity based upon deduction from the retrieved contextual data provided by different graphical user interface elements disposed within workspace in the graphical user interface using the titles extracted from windows in the workspace and the Bayesian predictor by monitoring active windows in the workspace to extract window titles from the active windows and to place the window titles in a finite queue and providing the titles in the finite queue to the Bayesian predictor to compute a probability set of activities for the window titles, to identify resources from amongst a set of resources that are relevant to the inferred activity, and to display the identified resources in the graphical user interface.
A computer program product comprising a computer usable storage device that medium stores thereon computer usable program code for activity-centric resource recommendation, the computer program product comprising:
- computer usable program code for retrieving contextual data provided by different graphical user interface elements disposed within a workspace in a graphical user interface;
- computer usable program code for inferring an activity based upon deduction from the retrieved contextual data provided by different graphical user interface elements disposed within the workspace in the graphical user interface by training a Bayesian predictor with words known to appear in connection with different activities, monitoring active windows in the workspace to extract window titles from the active windows and to place the window titles in a finite queue and providing the titles in the finite queue to the Bayesian predictor to compute a probability set of activities for the window titles;
- computer usable program code for identifying resources from amongst a set of resources that are relevant to the inferred activity;
- and,
- computer usable program code for displaying the identified resources in the graphical user interface.
Dependencies are inferred from the claim text.