IP Library Granted Patent US 11,483,273
Granted Patent B2
US 11,483,273 · App. 16/928,706 · Granted Oct 25, 2022

Chat-based interaction with an in-meeting virtual assistant

Inventors: Mohamed Gamal Mohamed Mahmoud (Santa Clara, CA); Omar Tarek El-Sadany (Fremont, CA)
Assignee: Cisco Technology, Inc.
H04L51/42G06F40/289G10L15/22
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 11,483,273
App. No.
16/928,706
Granted
Oct 25, 2022
Kind
B2
Abstract

Chat-based interaction with an in-meeting virtual assistant may be provided. First, audio input associated with a meeting may be received. Next, an intent from the audio input may be detected. Text content associated with the audio input may then be generated in response to detecting the intent from the audio input. The text content may be displayed in a chat interface.

Claims (44)

1. A method comprising:

receiving an audio input associated with a meeting;

detecting an intent from the audio input;

generating text content associated with the audio input in response to detecting the intent from the audio input; and

displaying the text content in a chat interface;

displaying a message seeking a response to save or discard the text content;

discarding the text content in response to the response detected from the audio input comprising an indication of a desire of a participant in the meeting to have the text content discarded; and

discounting a subsampling factor in response to the response detected from the audio input comprising the indication of the desire of the participant in the meeting to have the text content discarded.

2. The method of claim 1 , further comprising receiving edits to the text content displayed in the chat interface.

3. The method of claim 1 , further comprising detecting the response to the message in the audio input.

4. The method of claim 1 , further comprising initiating the subsampling factor at a first predetermined level.

5. The method of claim 4 , wherein the first predetermined level is a highest level for the subsampling factor for the intent.

6. The method of claim 1 , wherein discounting the subsampling factor comprises discounting the subsampling factor by a predetermined amount for each indication of the desire of the participant in the meeting to have the text content discarded.

7. The method of claim 1 , wherein the subsampling factor cannot be discounted below a second predetermined level.

8. An system comprising:

a memory storage; and

a processing unit coupled to the memory storage, wherein the processing unit is operative to:

receive audio input associated with a meeting;

detect an intent from the audio input;

generate text content associated with the audio input in response to detecting the intent from the audio input;

display the text content in a chat interface;

display a message seeking a response to save or discard the text content;

discard the text content in response to the response detected from the audio input comprising an indication of a desire of a participant in the meeting to have the text content discarded; and

discount a subsampling factor in response to the response detected from the audio input comprising the indication of the desire of the participant in the meeting to have the text content discarded.

9. The system of claim 8 , wherein the processing unit is further operative to receive edits to the text content displayed in the chat interface.

10. The system of claim 8 , wherein the processing unit is further operative to:

detect the response to the message in the audio input.

11. The system of claim 8 , wherein the subsampling factor is initiated at a first predetermined level.

12. The system of claim 11 , wherein the first predetermined level is a highest level for the subsampling factor for the intent.

13. The system of claim 8 , wherein the processing unit being operative to discount the subsampling factor comprises the processing unit is further operative to discounting the subsampling factor by a predetermined amount for each indication of the desire of the participant in the meeting to have the text content discarded.

14. A non-transitory computer-readable medium that stores a set of instructions which when executed perform a method comprising:

receiving audio input associated with a meeting;

detecting an intent from the audio input;

generating text content associated with the audio input in response to detecting the intent from the audio input;

displaying the text content in a chat interface;

displaying a message seeking a response to save or discard the text content;

discarding the text content in response to the response detected from the audio input comprising an indication of a desire of a participant in the meeting to have the text content discarded; and

discounting a subsampling factor in response to the response detected from the audio input comprising the indication of the desire of the participant in the meeting to have the text content discarded.

15. The non-transitory computer-readable medium of claim 14 , further comprising receiving edits to the text content displayed in the chat interface.

16. The non-transitory computer-readable medium of claim 14 , further comprising detecting the response to the message in the audio input.

17. The computer-readable medium of claim 14 , further comprising initiating the subsampling factor at a first predetermined level.

18. The non-transitory computer-readable medium of claim 17 , wherein the first predetermined level is a highest level for the subsampling factor for the intent.

19. The non-transitory computer-readable medium of claim 14 , wherein discounting the subsampling factor comprises discounting the subsampling factor by a predetermined amount for each indication of the desire of the participant in the meeting to have the text content discarded.

20. The non-transitory computer-readable medium of claim 14 , wherein the subsampling factor cannot be discounted below a second predetermined level.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 14, 2020
From: MAHMOUD, MOHAMED GAMAL MOHAMED; EL-SADANY, OMAR TAREK
To: CISCO TECHNOLOGY, INC.
Reel/Frame 053206/0271 →
Continuity (2)
Provisional Application 62874479 · Jul 15, 2019
Related Publication 20210021558A1 · Jan 21, 2021
Cited By (4)
US 12,406,668 US 12,475,887 US 12,700,406 US 12,725,215