TECHNIQUES FOR TEMPLATE-BASED PREDICTIONS AND RECOMMENDATIONS

• US 20110251990A1
• Filed: 06/20/2011
• Published: 10/13/2011
• Est. Priority Date: 12/15/2009
• Status: Abandoned Application

• Current Assignee: Chieh-Yih Wan, Giuseppe Raffa, Lenitra M. Durham, Mark D. Yarvis, Philip Muse, Rita H. Wouhaybi, Sai P. Balasundaram, Sangita Sharma
• Original Assignee: Chieh-Yih Wan, Giuseppe Raffa, Lenitra M. Durham, Mark D. Yarvis, Philip Muse, Rita H. Wouhaybi, Sai P. Balasundaram, Sangita Sharma
• Inventors: Raffa, Giuseppe, Yarvis, Mark D., Wan, Chieh-Yih, Sharma, Sangita, Balasundaram, Sai P., Wouhaybi, Rita H., Muse, Philip, Durham, Lenitra M.
• Application Number:
  US13/164,002
• Publication Number:
  US 20110251990A1
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

An embodiment of the present invention provides a method of template-based prediction and recommendation, comprising utilizing templates that consist of a sequence of activities or locations to characterize a user'"'"'s day by a personal device, wherein as the user goes about a day, the personal device attempts to match pre-existing templates to the user'"'"'s location and activities, assigning a probability to each template; and using the matching templates to predict what the user will do next and thus narrow down a set of logical recommendations.

Claims

1. A method of template-based prediction and recommendation, comprising:

utilizing templates that consist of a sequence of activities or locations to characterize a user'"'"'s day by a personal device, wherein as said user goes about the day, said personal device attempts to match pre-existing templates to said user'"'"'s location and activities, assigning a probability to each template; and

using said matching templates to predict what said user will do next and thus narrow down a set of logical recommendations.

2. The method of claim 1, wherein creation of said templates constitutes a way to define trends and serve as a visualization tool where a user can be presented with a calendar colored according to said template of said user'"'"'s behavior during a given time.

3. The method of claim 1, wherein contextual inputs to said templates include not only location, but also include inputs including at least weather, stock market activity, social interactions, or emotional state.

4. An apparatus, comprising:

a personal device associated with a user adapted for template-based prediction and recommendation by utilizing templates that consist of a sequence of activities or locations to characterize said user'"'"'s day by said personal device, wherein as said user goes about the day, said personal device attempts to match pre-existing templates to said user'"'"'s location and activities, assigning a probability to each template; and

using said matching templates to predict what said user will do next and thus narrow down a set of logical recommendations.

5. The apparatus of claim 4, wherein creation of said templates constitutes another way to define trends and serve as a visualization tool where said user can be presented with a calendar colored according to said template of said user'"'"'s behavior during a given time.

6. The apparatus of claim 5, wherein contextual inputs to said templates include not only location, but also include inputs including at least weather, stock market activity, social interactions, or emotional state.

7. A non-volatile computer readable medium encoded with computer executable instructions, which when accessed, cause a machine to perform operations comprising:

providing template-based prediction and recommendation by utilizing templates that consist of a sequence of activities or locations to characterize a user'"'"'s day by a personal device, wherein as said user goes about the day, said personal device attempts to match pre-existing templates to said user'"'"'s location and activities, assigning a probability to each template; and

using said matching templates to predict what said user will do next and thus narrow down a set of logical recommendations.

8. The non-volatile computer readable medium of claim 7, wherein creation of said templates constitutes another way to define trends and serve as a visualization tool where said user can be presented with a calendar colored according to said template of said user'"'"'s behavior during a given time.

9. The non-volatile computer readable medium of claim 8, wherein contextual inputs to said templates include not only location, but also include inputs including at least weather, stock market activity, social interactions, or emotional state.

10. A mobile device, comprising:

a processor adapted for template-based prediction and recommendation by utilizing templates that consist of a sequence of activities or locations to characterize a user of said mobile device, wherein as said user goes about a day, said mobile device attempts to match pre-existing templates to said user'"'"'s location and activities, assigning a probability to each template; and

using said matching templates to predict what said user will do next and thus narrow down a set of logical recommendations.

11. The mobile device of claim 10, wherein creation of said templates constitutes another way to define trends and serve as a visualization tool where said user can be presented with a calendar colored according to said template of said user'"'"'s behavior during a given time.

12. The mobile device of claim 11, wherein contextual inputs to said templates include not only location, but also include inputs including at least weather, stock market activity, social interactions, or emotional state.