IP Library Granted Patent US 11,665,010
Granted Patent B2
US 11,665,010 · App. 17/402,278 · Granted May 30, 2023

Intelligent meeting recording using artificial intelligence algorithms

Inventor: Amit Mishra (Broomfield, CO)
Assignee: Avaya Management L.P.
H04L12/1831G06N20/00H04L12/1818
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 11,665,010
App. No.
17/402,278
Granted
May 30, 2023
Kind
B2
Abstract

A device may analyze data associated with a conference call. The device may provide at least a portion of the data to a machine learning model. The device may receive an output from the machine learning model in response to the machine learning model processing at least the portion of the data. The output may include a probability score associated with a determination made by the machine learning model with respect to capturing multimedia content associated with the conference call. The device may output a notification associated with capturing the multimedia content based on the output from the machine learning model.

Claims (97)

1. A method comprising:

analyzing data associated with a conference call;

providing at least a portion of the data to a machine learning model;

receiving an output from the machine learning model in response to the machine learning model processing the at least the portion of the data, the output comprising a probability score associated with a determination made by the machine learning model with respect to capturing multimedia content associated with the conference call;

outputting a notification associated with capturing the multimedia content based at least in part on the output from the machine learning model; and

capturing the multimedia content based on at least one of: a comparison result of the probability score and a threshold value; and a user input associated with the notification.

2. The method of claim 1 , wherein:

the data comprises identification information of at least one user associated with the conference call;

providing at least the portion of the data to the machine learning model comprises providing the identification information to the machine learning model; and

receiving the output from the machine learning model occurs in response to the machine learning model comparing the identification information and a user classification.

3. The method of claim 1 , wherein:

the data comprises identification information of at least one user associated with the conference call, wherein the at least one user is included in a meeting invitation associated with the conference call; and

wherein the output from the machine learning model comprises a second comparison result of:

the identification information of the at least one user; and

reference identification information of a set of users associated with at least one previous conference call.

4. The method of claim 1 , wherein:

the data comprises presence information of at least one user associated with the conference call; and

receiving the output from the machine learning model occurs in response to the machine learning model processing the presence information.

5. The method of claim 1 , wherein:

the data comprises a meeting invitation associated with the conference call;

analyzing the data comprises extracting content information included in the meeting invitation; and

receiving the output from the machine learning model occurs in response to the machine learning model processing the content information.

6. The method of claim 1 , wherein:

the data comprises a meeting invitation associated with the conference call;

analyzing the data comprises determining contextual information associated with the meeting invitation; and

receiving the output from the machine learning model occurs in response to the machine learning model processing the contextual information.

7. The method of claim 1 , wherein:

the data associated with the conference call comprises the multimedia content, wherein the multimedia content is received at a device associated with a user attending the conference call;

analyzing the data comprises extracting content information included in the multimedia content; and

receiving the output from the machine learning model occurs in response to the machine learning model processing the content information.

8. The method of claim 7 , wherein:

the content information comprises at least one word; and

receiving the output from the machine learning model occurs in response to the machine learning model comparing the at least one word and a set of words associated with initiating the capturing of the multimedia content.

9. The method of claim 7 , wherein:

the content information comprises at least one word; and

receiving the output from the machine learning model occurs in response to the machine learning model comparing a quantity of instances of the at least one word and a second threshold value.

10. The method of claim 7 , wherein the multimedia content comprises audio data, text data, video data, or a combination thereof.

11. The method of claim 1 , wherein:

the data associated with the conference call comprises the multimedia content, wherein the multimedia content is received at a device associated with a user attending the conference call;

analyzing the data comprises determining contextual information associated with the multimedia content; and

receiving the output from the machine learning model occurs in response to the machine learning model processing the contextual information.

12. The method of claim 1 , wherein:

the data comprises temporal information associated with the conference call;

providing at least the portion of the data to the machine learning model comprises providing the temporal information associated with the conference call to the machine learning model; and

receiving the output from the machine learning model is in response to the machine learning model comparing the temporal information associated with the conference call and second temporal information associated with a captured multimedia content of at least one previous conference call.

13. The method of claim 1 , wherein the output from the machine learning model comprises at least one of:

a first temporal instance associated with initiating the capturing of the multimedia content; and

a second temporal instance associated with ending the capturing of the multimedia content.

14. The method of claim 1 , wherein:

the output from the machine learning model comprises at least one of:

a second comparison result associated with content information of the conference call and content information of at least one previous conference call; and

a third comparison result associated with contextual information of the conference call and contextual information of the at least one previous conference call; and

outputting the notification is based at least in part on the output from the machine learning model, wherein the notification comprises a link associated with accessing captured multimedia content of the at least one previous conference call.

15. The method of claim 1 , wherein:

the output from the machine learning model comprises at least one of:

a second comparison result associated with content information of the conference call and content information of at least one previous conference call; and

a third comparison result associated with contextual information of the conference call and contextual information of the at least one previous conference call; and

the method further comprises:

generating aggregated multimedia content based at least in part on the output from the machine learning model, wherein the aggregated multimedia content comprises at least a portion of the captured multimedia content associated with the conference call and at least a portion of captured multimedia content associated with the at least one previous conference call.

16. The method of claim 1 , further comprising:

training the machine learning model based at least in part on training data, the training data comprising at least one of:

temporal information associated with capturing multimedia content associated with at least one previous conference call;

a meeting invitation associated with the at least one previous conference call;

identification information of at least one user associated with the at least one previous conference call;

attendance information of the at least one user with respect to the at least one previous conference call;

content information associated with the at least one previous conference call;

contextual information associated with the at least one previous conference call; and

a quantity of the at least one previous conference call,

wherein the output provided by the machine learning model is based at least in part on the training.

17. The method of claim 1 , further comprising:

training the machine learning model based at least in part on training data, the training data comprising at least one of:

a user input corresponding to the notification;

one or more previous outputs by the machine learning model; and

one or more user inputs corresponding to a notification associated with capturing multimedia content associated with at least one previous conference call,

wherein the output provided by the machine learning model is based at least in part on the training.

18. A device comprising:

a processor; and

a memory in electronic communication with the processor, wherein the memory stores data that, when executed by the processor, enables the processor to:

analyze data associated with a conference call;

provide at least a portion of the data to a machine learning model;

receive an output from the machine learning model in response to the machine learning model processing the at least the portion of the data, the output comprising a probability score associated with a determination made by the machine learning model with respect to capturing multimedia content associated with the conference call;

output a notification associated with capturing the multimedia content based at least in part on the output from the machine learning model; and

capture the multimedia content based on at least one of: a comparison result of the probability score and a threshold value; and a user input associated with the notification.

19. A system comprising:

a machine learning model;

a device comprising:

a processor; and

a memory in electronic communication with the processor, wherein the memory stores data that, when executed by the processor, enables the processor to:

analyze data associated with a conference call;

provide at least a portion of the data to the machine learning model;

receive an output from the machine learning model in response to the machine learning model processing the at least the portion of the data, the output comprising a probability score associated with a determination made by the machine learning model with respect to capturing multimedia content associated with the conference call, wherein the output from the machine learning model comprises at least one of:

a first temporal instance associated with initiating the capturing of the multimedia content; and

a second temporal instance associated with ending the capturing of the multimedia content; and

output a notification associated with capturing the multimedia content based at least in part on the output from the machine learning model.

20. The device of claim 18 , wherein the output from the machine learning model comprises at least one of:

a first temporal instance associated with initiating the capturing of the multimedia content; and

a second temporal instance associated with ending the capturing of the multimedia content.

Assignments (7)
INTELLECTUAL PROPERTY SECURITY AGREEMENT – SUPPLEMENT NO. 1 Recorded May 29, 2024
From: AVAYA LLC (FORMERLY KNOWN AS AVAYA INC.); AVAYA MANAGEMENT L.P.
To: WILMINGTON SAVINGS FUND SOCIETY, FSB, AS COLLATERAL AGENT
Reel/Frame 067559/0284 →
INTELLECTUAL PROPERTY SECURITY AGREEMENT Recorded Jul 31, 2023
From: AVAYA LLC (FORMERLY KNOWN AS AVAYA INC.); AVAYA MANAGEMENT L.P.
To: CITIBANK, N.A., AS COLLATERAL AGENT
Reel/Frame 064431/0001 →
RELEASE OF SECURITY INTEREST IN PATENTS (REEL/FRAME 61087/0386) Recorded May 18, 2023
From: WILMINGTON TRUST, NATIONAL ASSOCIATION, AS NOTES COLLATERAL AGENT
To: AVAYA MANAGEMENT L.P.; AVAYA INC.; INTELLISIST, INC.; AVAYA INTEGRATED CABINET SOLUTIONS LLC
Reel/Frame 063690/0359 →
INTELLECTUAL PROPERTY SECURITY AGREEMENT Recorded May 4, 2023
From: AVAYA INC.; AVAYA MANAGEMENT L.P.; INTELLISIST, INC.
To: CITIBANK, N.A., AS COLLATERAL AGENT
Reel/Frame 063542/0662 →
INTELLECTUAL PROPERTY SECURITY AGREEMENT Recorded May 3, 2023
From: AVAYA MANAGEMENT L.P.; AVAYA INC.; INTELLISIST, INC.; KNOAHSOFT INC.
To: WILMINGTON SAVINGS FUND SOCIETY, FSB [COLLATERAL AGENT]
Reel/Frame 063742/0001 →
INTELLECTUAL PROPERTY SECURITY AGREEMENT Recorded Aug 5, 2022
From: AVAYA INC.; INTELLISIST, INC.; AVAYA MANAGEMENT L.P.; AVAYA CABINET SOLUTIONS LLC
To: WILMINGTON TRUST, NATIONAL ASSOCIATION, AS COLLATERAL AGENT
Reel/Frame 061087/0386 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 9, 2021
From: MISHRA, AMIT
To: AVAYA MANAGEMENT L.P.
Reel/Frame 058055/0179 →
Continuity (1)
Related Publication 20230046881A1 · Feb 16, 2023