Task prediction

• US 8,326,859 B2
• Filed: 11/02/2009
• Issued: 12/04/2012
• Est. Priority Date: 11/02/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Paek, Timothy S., Meek, Christopher A.
• Primary Examiner(s): FILIPCZYK, MARCIN R
• Application Number:
  US12/610,392
• Publication Number:
  US 20110107242A1
• Time in Patent Office: 1,128 Days
• Field of Search: 707/759, 707/797, 707/766, 707/767, 707/999.006, 707/999.101, 707/999.102, 715/257, 704/9
• US Class Current: 707/767
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

This patent application pertains to computing scenarios that allow users to more readily accomplish desired tasks. One implementation includes at least one dictionary of potential auto-suggestions that can be generated in relation to user-input. The implementation also includes a text framework configured to weight at least some of the potential auto-suggestions based upon one or more parameters. This implementation further includes a task engine configured to associate tasks with at least some of the potential auto-suggestions.

Claims

1. A system, comprising:

multiple topic specific dictionaries of potential auto-suggestions for completing a text entry received from a user via user-input;

instructions configured to;

weight and rank at least some of the potential auto-suggestions from the multiple topic specific dictionaries based upon one or more parameters, the one or more parameters comprising at least one user preference parameter or at least one user history parameter,

determine and rank, based on the user-input, tasks that the user may be attempting to accomplish with the user-input,

associate the ranked tasks with the ranked auto-suggestions,

obtain corresponding task shortcuts for the ranked tasks, the task shortcuts comprising graphics selectable by the user to cause actions for accomplishing the ranked tasks, and

present at least some of the ranked auto-suggestions and at least some of the graphics concurrently in response to the user-input so that the user can accomplish an individual ranked task in a single step by selecting an individual graphic corresponding to the individual ranked task; and

a processor configured to execute the instructions.

2. The system of claim 1, wherein the instructions are further configured to consider individual dictionaries selected by the user for inclusion in the multiple topic specific dictionaries.

3. The system of claim 1, embodied as a single computing device.

4. The system of claim 1, wherein the instructions are further configured to, upon user selection of the individual graphic, accomplish the individual ranked task according to defined conditions of a corresponding individual dictionary.

5. The system of claim 1, wherein the instructions are further configured to rank the tasks based on influence by a third party.

6. A hardware computer-readable storage media having instructions stored thereon that when executed by a processor of a computing device cause the processor to perform acts, the acts comprising:

receiving, by the processor, a user-input comprising a text entry entered by a user;

predicting, by the processor, user intent based on the user-input, the predicting comprising;

identifying, from one or more dictionaries, potential auto-suggestions for completing the text entry of the user-input,

ranking the potential auto-suggestions from the one or more dictionaries according to one or more parameters, the one or more parameters comprising at least one user preference parameter or at least one user history parameter,

determining potential tasks that the user may be trying to accomplish with the user-input, the potential tasks having corresponding graphical shortcuts selectable by the user to accomplish the potential tasks, and

selecting individual graphical shortcuts to display to the user with individual ranked auto-suggestions in response to the user-input, the individual graphical shortcuts being selected based on relative probabilities that the user intends to accomplish individual potential tasks corresponding to the individual graphical shortcuts; and

displaying, by the processor, the individual graphical shortcuts and the individual ranked auto-suggestions to the user concurrently responsive to receiving the user-input.

7. The hardware computer-readable storage media according to claim 6, wherein the one or more parameters comprise the at least one user preference parameter.

8. The hardware computer-readable storage media according to claim 7, wherein the at least one user preference parameter indicates the user ranks sports relatively higher than entertainment.

9. The hardware computer-readable storage media according to claim 8, the acts further comprising:

in an instance when the text entry comprises part of both a movie title and a name of a sports team, including the name of the sports team but not the movie title in the individual ranked auto-suggestions that are displayed to the user.

10. The hardware computer-readable storage media according to claim 6, wherein the one or more parameters comprise another parameter relating to behavior of other users.

11. The hardware computer-readable storage media according to claim 10, wherein the another parameter indicates the other users select a first word to autocomplete the text entry more often than a second word to autocomplete the text entry.

12. The hardware computer-readable storage media according to claim 11, wherein the first word is “

pizza,”

the second word is “

pirates,” and

the text entry is “

pi.”

13. The hardware computer-readable storage media according to claim 6, wherein the one or more parameters comprise a monetization parameter reflecting that a party or entity has paid or will pay to have a first one of the individual ranked auto-suggestions ranked more highly than other individual ranked auto-suggestions.

14. A method comprising:

receiving a user-input comprising a text entry entered by a user;

predicting user intent based on the user-input, the predicting comprising;

identifying, from one or more dictionaries, auto-suggestions for completing the text entry of the user-input,

ranking the auto-suggestions from the one or more dictionaries according to one or more parameters, wherein;

the one or more parameters comprise at least one user preference parameter or at least one user history parameter, and

the one or more parameters provide weighting for the ranking, and

determining tasks that the user is likely trying to accomplish with the user-input, wherein the tasks are associated with at least some of the ranked auto-suggestions;

identifying graphical shortcuts that are selectable by the user to accomplish the tasks; and

in response to receiving the user-input, concurrently displaying at least;

a first one of the graphical shortcuts that is selectable by the user to accomplish a first one of the tasks, and

a first one of the ranked auto-suggestions that is associated with the first task,

wherein at least the identifying the graphical shortcuts is performed by a computing device.

15. The method of claim 14, further comprising:

associating the first task with the first ranked auto-suggestion.

16. The method of claim 14, further comprising:

concurrently displaying, with the first graphical shortcut and the first ranked auto-suggestion, at least;

a second one of the graphical shortcuts that is selectable by the user to accomplish a second one of the tasks, and

a second one of the ranked auto-suggestions corresponding to the second task.

17. The method of claim 16, wherein the first ranked auto-suggestion and the second ranked auto-suggestion are displayed in ranked order with the first ranked auto-suggestion being ranked higher than the second ranked auto-suggestion.

18. The method according to claim 17, further comprising synchronizing with an update manager to update the one or more parameters.

19. The method according to claim 18, further comprising:

ranking the auto-suggestions again based on the updated parameters with the second ranked auto-suggestion being ranked higher than the first ranked auto-suggestion, and

concurrently displaying the first graphical shortcut, the first ranked auto-suggestion, the second graphical shortcut, and the second ranked auto-suggestion again with the second ranked auto-suggestion being displayed in ranked order higher than the first ranked auto-suggestion.

20. The method of claim 16, wherein:

the first graphical shortcut is selectable by the user to call a business associated with the first ranked auto-suggestion, and

the second graphical shortcut is selectable by the user to purchase an item associated with the second ranked auto-suggestion.