IP Library Granted Patent US 10,789,940
Granted Patent B2
US 10,789,940 · App. 15/937,251 · Granted Sep 29, 2020

Dynamic wake word identification

Inventors: John Carl Mese (Cary, NC); Nathan J. Peterson (Oxford, NC); Russell Speight VanBlon (Raleigh, NC)
Assignee: Lenovo (Singapore) PTE. LTD.
G10L15/08G06F3/013G10L15/22G10L2015/088
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 10,789,940
App. No.
15/937,251
Granted
Sep 29, 2020
Kind
B2
Abstract

For dynamic wake word identification, a processor identifies a temporary wake word based on a first response. The processor further identifies one or more content tags from the first response. The processor identifies a second query in response to receiving the temporary wake word and a first content tag, without receiving a permanent wake word.

Claims (30)

1. An apparatus comprising:

a microphone;

a processor;

a memory that stores code executable by the processor to:

identify a temporary wake word based on a first response and received by the microphone;

identify one or more content tags from the first response based on a usage histogram of a frequency that other content tags are associated with content in each content tag and a content significance based on a weighted average of a frequency that each content tag is employed in a query; and

identify a second query in response to receiving the temporary wake word and a first content tag within a wake word time interval, without receiving a permanent wake word.

2. The apparatus of claim 1 , wherein the temporary wake word is a specified temporary wake word phrase.

3. The apparatus of claim 1 , wherein the first response is generated in response to a first query comprising one or more of the permanent wake word, a user identification, and a continuous content feed.

4. The apparatus of claim 1 , wherein the first content tag is identified from eye tracking.

5. The apparatus of claim 1 , wherein the first content tag is identified from a selection of content in the first response.

6. The apparatus of claim 1 , wherein the code is further executable by the processor to display a content tag list and wherein the first content tag is selected from the content tag list.

7. The apparatus of claim 1 , wherein the content tag is identified based on a content tag history.

8. The apparatus of claim 1 , wherein the temporary wake word is identified based on a temporary wake word history.

9. The apparatus of claim 1 , wherein a specified maximum number of temporary wake words are active.

10. A method comprising:

identifying, by use of a processor, a temporary wake word based on a first response;

identifying one or more content tags from the first response based on a usage histogram of a frequency that other content tags are associated with content in each content tag and a content significance based on a weighted average of a frequency that each content tag is employed in a query; and

identifying a second query in response to receiving the temporary wake word and a first content tag within a wake word time interval, without receiving a permanent wake word.

11. The method of claim 10 , wherein the temporary wake word is specified temporary wake word phrase.

12. The method of claim 10 , wherein the first response is generated in response to a first query comprising one or more of the permanent wake word, a user identification, and a continuous content feed.

13. The method of claim 10 , wherein the first content tag is identified from one or more of eye tracking and a selection of content in the first response.

14. The method of claim 10 , wherein the method further comprises displaying a content tag list and wherein the first content tag is selected from the content tag list.

15. A program product comprising a non-transitory computer readable storage medium that stores code executable by a processor, the executable code comprising code to:

identify a temporary wake word based on a first response;

identify one or more content tags from the first response based on a usage histogram of a frequency that other content tags are associated with content in each content tag and a content significance based on a weighted average of a frequency that each content tag is employed in a query; and

identify a second query in response to receiving the temporary wake word and a first content tag within a wake word time interval, without receiving a permanent wake word.

16. The program product of claim 15 , wherein the temporary wake word is a specified temporary wake word phrase.

17. The program product of claim 15 , wherein the first response is generated in response to a first query comprising one or more of the permanent wake word, a user identification, and a continuous content feed.

18. The program product of claim 15 , wherein the first content tag is identified from one or more of eye tracking and a selection of content in the first response.

Assignments (4)
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 14, 2022
From: LENOVO (SINGAPORE) PTE LTD
To: LENOVO PC INTERNATIONAL LIMITED
Reel/Frame 060651/0634 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 28, 2020
From: MESE, JOHN CARL; PETERSON, NATHAN J.; VANBLON, RUSSELL SPEIGHT
To: LENOVO (SINGAPORE) PTE. LTD.
Reel/Frame 053328/0156 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 30, 2018
From: MESE, JOHN CARL; PETERSON, NATHAN J.; VANBLON, RUSSELL SPEIGHT
To: LENOVO (SINGAPORE) PTE. LTD.
Reel/Frame 045814/0269 →