IP Library Granted Patent US 11,138,971
Granted Patent B2
US 11,138,971 · App. 14/097,954 · Granted Oct 5, 2021

Using context to interpret natural language speech recognition commands

Inventors: Peter Hamilton Wetsel (Raleigh, NC); Jonathan Gaither Knox (Morrisville, NC); Suzanne Marion Beaumont (Wake Forest, NC); Russell Speight VanBlon (Raleigh, NC); Rod D. Waltermann (Rougemont, NC)
Assignee: Lenovo (Singapore) Pte. Ltd.
G10L15/22G06F3/167G10L2015/223G10L2015/228
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 11,138,971
App. No.
14/097,954
Granted
Oct 5, 2021
Kind
B2
Abstract

An embodiment provides a method, including: receiving, at an audio receiver of an information handling device, user voice input; identifying, using a processor, words included in the user voice input; determining, using the processor, one of the identified words renders ambiguous a command included in the user voice input; accessing, using the processor, context data; disambiguating, using the processor, the command based on the context data; and committing, using the processor, a predetermined action according to the command. Other aspects are described and claimed.

Claims (55)

1. A method, comprising:

receiving, at an audio receiver of an information handling device, user voice input;

identifying, using a processor, a command included in the user voice input, wherein the command comprises at least one deictic word that renders the command ambiguous, wherein the at least one deictic word is a trigger event that prompts the processor to access context data found within the voice input;

accessing, based on the trigger event and using the processor, the context data contained within the user voice input;

disambiguating, using the processor, the command based on the context data, said disambiguating comprising using information contained within the context data to correlate the at least one deictic word with a single object selection or a multiple object selection; and

automatically selecting, based on the disambiguating, one or more objects stored on the information handling device.

2. The method of claim 1 , wherein the context data comprises data derived from the voice input.

3. The method of claim 2 , wherein the data derived from the voice input includes an identified word included in the user voice input selected from the group of words consisting of a contact and an application name.

4. The method of claim 1 , wherein:

the at least one word of the identified words that renders the command ambiguous comprises a noun;

the context data comprises data derived from a list of open applications on the information handling device; and

the disambiguating comprises identifying a file associated with the noun based on the list of open applications on the information handling device.

5. The method of claim 1 , wherein:

the at least one word of the identified words that renders the command ambiguous comprises a noun;

the context data comprises data derived from a list of most recently used applications on the information handling device; and

the disambiguating comprises identifying a file associated with the noun based on the list of most recently used applications on the information handling device.

6. The method of claim 1 , wherein:

the at least one word of the identified words that renders the command ambiguous comprises a noun;

the context data comprises data derived from a list of most recently used objects on the information handling device; and

the disambiguating comprises identifying a file associated with the noun based on the list of most recently used objects on the information handling device.

7. The method of claim 6 , wherein the associating comprises linking a device object to the at least one word of the identified words that renders the command ambiguous using the context data.

8. The method of claim 7 , further comprising replacing the at least one other word of the identified words with a device object identifier.

9. The method of claim 8 , wherein the device object identifier is a file name pointing to the device object subject to the command.

10. An information handling device, comprising:

an audio receiver;

a processor; and

a memory device that stores instructions executable by the processor to:

receive, at the audio receiver of an information handling device, user voice input;

identify a command included in the user voice input, wherein the command comprises at least one deictic word that renders the command ambiguous, wherein the at least one deictic word is a trigger event that prompts the processor to access context data found within the voice input;

access, based on the trigger event, the context data contained within the user voice input;

disambiguate the command based on the context data by using information contained within the context data to correlate the at least one deictic word with a single object selection or a multiple object selection; and

automatically select, based on the disambiguating, one or more objects stored on the information handling device.

11. The information handling device of claim 10 , wherein the context data comprises data derived from the voice input.

12. The information handling device of claim 11 , wherein the data derived from the voice input includes an identified word included in the user voice input selected from the group of words consisting of a contact and an application name.

13. The information handling device of claim 10 , wherein:

the at least one word of the identified words that renders the command ambiguous comprises a noun;

the context data comprises data derived from a list of open applications on the information handling device; and

the processor disambiguates the command by identifying a file associated with the noun based on the list of open applications on the information handling device.

14. The information handling device of claim 10 , wherein:

the at least one word of the identified words that renders the command ambiguous comprises a noun;

the context data comprises data derived from a list of most recently used applications on the information handling device; and

the processor disambiguates the command by identifying a file associated with the noun based on the list of most recently used applications on the information handling device.

15. The information handling device of claim 10 , wherein:

the at least one word of the identified words that renders the command ambiguous comprises a noun;

the context data comprises data derived from a list of most recently used objects on the information handling device; and

the disambiguating comprises identifying a file associated with the noun based on the list of most recently used objects on the information handling device.

16. The information handling device of claim 15 , wherein the processor links a device object to the at least one word of the identified words that renders the command ambiguous using the context data.

17. The information handling device of claim 16 , further comprising replacing the at least one word of the identified words with a device object identifier.

18. A product, comprising:

a storage device having code stored therewith, the code being executable by a processor and comprising:

code that receives at an audio receiver of an information handling device, user voice input;

code that identifies a command included in the user voice input, wherein the command comprises at least one deictic word that renders the command ambiguous, wherein the at least one deictic word is a trigger event that prompts the processor to access context data found within the voice input;

code that accesses, based on the trigger event and using the processor, the context data contained within the user voice input;

code that disambiguates, using the processor, the command based on the source of context data by using information contained within the context data to correlate the at least one deictic word with a single object selection or a multiple object selection; and

code that automatically selects, based on the code that disambiguates, one or more objects stored on the information handling device.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 10, 2025
From: LENOVO PC INTERNATIONAL LIMITED
To: LENOVO SWITZERLAND INTERNATIONAL GMBH
Reel/Frame 069870/0670 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2022
From: LENOVO (SINGAPORE) PTE LTD
To: LENOVO PC INTERNATIONAL LIMITED
Reel/Frame 060638/0067 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 5, 2013
From: WETSEL, PETER HAMILTON; KNOX, JONATHAN GAITHER; BEAUMONT, SUZANNE MARION; VANBLON, RUSSELL SPEIGHT; WALTERMANN, ROD D.
To: LENOVO (SINGAPORE) PTE. LTD.
Reel/Frame 031767/0284 →
Continuity (1)
Related Publication 20150161997A1 · Jun 11, 2015