IP Library › Granted Patent US 10,585,957
Granted Patent B2
US 10,585,957 · App. 15/818,432 · Granted Mar 10, 2020

Task driven user intents

Inventors: Larry Paul Heck (Los Altos, CA); Madhusudan Chinthakunta (Saratoga, CA); David Mitby (Mountain View, CA); Lisa Stifelman (Palo Alto, CA)
Assignee: Microsoft Technology Licensing, LLC
G06F16/9535
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,585,957
App. No.
15/818,432
Filed
Nov 20, 2017
Granted
Mar 10, 2020
Kind
B2
Art Unit
2659
USPC
704/9
Abstract

Identification of user intents may be provided. A plurality of network applications may be identified, and an ontology associated with each of the plurality of applications may be defined. If a phrase received from a user is associated with at least one of the defined ontologies, an action associated with the network application may be executed.

Claims (43)

1. A method for providing a user intent identification, comprising:

identifying a plurality of network-based applications;

generating an ontology associated with each of the plurality of network-based applications;

receiving, at a personal digital assistant, a single natural language phrase from a user;

comparing the single natural language phrase to one or more keywords associated with at least one ontology to automatically determine whether the single natural language phrase is associated with the at least one ontology associated with at least one of the network-based applications;

determining an intent of the single natural language phrase by identifying at least one intent keyword in the single natural language phrase;

determining a context of the single natural language phrase using one or more context keywords in the single natural language phrase; and

causing the personal digital assistant to automatically select and execute an agent action associated with the at least one of the plurality of network-based applications, the agent action being based, at least in part, on the determined intent and the determined context in the single natural language phrase.

2. The method of claim 1 , further comprising determining whether the keyword is included in the natural language phrase.

3. The method of claim 1 , further comprising determining one or more parameters for the agent action based, at least in part, on the natural language phrase.

4. The method of claim 1 , further comprising requesting additional information when it is determined the natural language phrase is not associated with the at least one ontology.

5. The method of claim 1 , wherein causing the personal digital assistant to execute an agent action comprises causing the personal digital assistant to execute an action specific to the at least one of the plurality of network-based applications.

6. A computing device, comprising:

at least one processor; and

a memory coupled to the at least one processor and storing instructions that, when executed by the at least one processor, perform a method, comprising:

identifying a plurality of network-based applications;

generating an ontology associated with each of the plurality of network-based applications;

receiving a single natural language phrase;

comparing the single natural language phrase to one or more keywords associated with at least one ontology to automatically determine whether the single natural language phrase is associated with at the least one ontology associated with at least one of the applications;

determining an intent of the single natural language phrase by identifying at least one intent keyword in the single natural language phrase;

determining a context of the single natural language phrase using one or more context keywords in the single natural language phrase; and

causing a personal digital assistant associated with the computing device to automatically select and execute an agent action associated with the at least one of the plurality of network-based applications, the agent action being based, at least in part, on the determined intent and the determined context.

7. The computing device of claim 6 , further comprising instructions for determining whether the keyword is included in the natural language phrase.

8. The computing device of claim 6 , further comprising instructions for determining one or more parameters for the agent action based, at least in part, on the natural language phrase.

9. The computing device of claim 6 , further comprising instructions for requesting additional information when it is determined that the natural language phrase is not associated with the at least one ontology.

10. The computing device of claim 6 , wherein causing the personal digital assistant to execute an agent action comprises causing the personal digital assistant to execute an action specific to the at least one of the plurality of network-based applications.

11. The computing device of claim 6 , further comprising instructions for providing at least one of the agent action and a result of the agent action on a display of the computing device.

12. A method, comprising:

identifying a plurality of network-based applications;

generating an ontology associated with each of the plurality of network-based applications;

causing a personal digital assistant associated with a computing device to receive a single natural language sentence;

comparing the single natural language sentence to one or more keywords associated with at least one ontology to determine that the single natural language sentence is associated with the at least one ontology;

determining an intent of the natural language sentence and a context associated with the natural language sentence;

and

causing the personal digital assistant to automatically select and execute an agent action associated with the at least one of the plurality of network-based applications, the agent action being based, at least in part, on the determined intent and the determined context of the single natural language sentence.

13. The method of claim 12 , further comprising causing a display of a result of the agent action on a display of the computing device.

14. The method of claim 12 , wherein the one or more keywords of the at least one ontology are obtained from parsing content associated with each of the plurality of network-based applications.

15. The method of claim 1 , wherein the one or more keywords are obtained from parsing content associated with each of the plurality of network-based applications.

16. The computing device of claim 6 , wherein the one or more keywords are obtained from parsing content associated with each of the plurality of network-based applications.

17. The method of claim 1 , further comprising causing a display of a result of the agent action on a display of a computing device.

18. The method of claim 1 , wherein the personal digital assistant automatically selects and executes the agent action in response to determining the single natural language phrase is associated with the at least one ontology.

19. The method of claim 12 , further comprising requesting additional information when it is determined that the natural language sentence is not associated with the at least one ontology.

20. The method of claim 12 , wherein the one or more keywords are obtained from parsing content associated with each of the plurality of network-based applications.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 4, 2019
From: HECK, LARRY PAUL; CHINTHAKUNTA, MADHUSUDAN; MITBY, DAVID; STIFELMAN, LISA
To: MICROSOFT CORPORATION
Reel/Frame 050267/0940 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 4, 2019
From: MICROSOFT CORPORATION
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 050271/0340 →
Continuity (2)
Continuation 13077396 · Mar 31, 2011
Related Publication 20180075151A1 · Mar 15, 2018
Cited By (30)
US 12,197,712 US 12,197,817 US 12,200,297 US 12,204,932 US 12,211,502 US 12,216,894 US 12,219,314 US 12,223,282 US 12,236,952 US 12,254,887 US 12,260,234 US 12,277,954 US 12,293,203 US 12,293,763 US 12,301,635 US 12,333,404 US 12,361,943 US 12,367,879 US 12,386,434 US 12,386,491 US 12,431,128 US 12,477,470 US 12,556,890 US 12,567,415 US 12,608,171 US 12,613,730 US 12,619,452 US 12,620,179 US 12,731,579 US 12,748,568