Granted Patent B2

US 12,566,876 · App. 18/193,204 · Granted Mar 3, 2026

Inventor: Alejandro Paiuk (West Hartford, CT)

Assignee: Zoom Communications, Inc.

G06F21/6218G06V20/41

Abstract

Claims (61)

1 . A method, comprising:

receiving a video stream captured by a camera device of a first participant of a video conference, wherein the video stream includes sensitive information that is not to be presented to a second participant intended to receive the video stream;

analyzing the video stream during the video conference to identify portions of the video stream containing the sensitive information presented by the first participant and captured by the camera device, wherein the sensitive information is displayed on a physical object presented to the camera device;

determining a type of the physical object presented to the camera device;

visually masking the portions of the video stream containing the sensitive information to generate a redacted video stream;

outputting the redacted video stream during the video conference for display at a display device of the second participant of the video conference; and

automatically triggering a workflow for the second participant based on the type of the physical object, wherein a first workflow is triggered for a first type and a second workflow is triggered for a second type.

2 . The method of claim 1 , wherein the first participant is a user of a contact center, and the second participant is an agent of the contact center.

3 . The method of claim 1 , further comprising:

extracting the sensitive information from the video stream; and

providing the sensitive information as an input of a customer service software application.

4 . The method of claim 1 , wherein the type is selected from a group comprising a payment card, an identification card, and a receipt.

5 . The method of claim 1 , further comprising:

extracting the sensitive information from the video stream; and

executing a workflow for the second participant to interact with the first participant based on contents of the extracted sensitive information.

6 . The method of claim 1 , further comprising:

extracting the sensitive information from the video stream; and

unlocking a physical object located near the first participant based on contents of the extracted sensitive information.

7 . The method of claim 1 , wherein masking the video stream comprises:

modifying a portion of a video frame containing the sensitive information.

8 . The method of claim 1 , wherein masking the video stream comprises:

removing at least one frame containing the sensitive information from the video stream.

9 . An apparatus, comprising:

a network communication interface;

a memory; and

a processor configured to execute instructions stored in the memory to:

receive a video stream captured by a camera device of a first participant of a video conference, wherein the video stream includes sensitive information that is not to be presented to a second participant intended to receive the video stream;

analyze the video stream during the video conference to identify portions of the video stream containing the sensitive information presented by the first participant and captured by the camera device, wherein the sensitive information is displayed on a physical object presented to the camera device;

determine a type of the physical object presented to the camera device;

visually mask the portions of the video stream containing the sensitive information to generate a redacted video stream;

output the redacted video stream during the video conference for display at a display device of the second participant of the video conference; and

automatically trigger a workflow for the second participant based on the type of the physical object, wherein a first workflow is triggered for a first type and a second workflow is triggered for a second type.

10 . The apparatus of claim 9 , wherein the video stream is received by the network communication interface from a first device and the redacted video stream is output by the network communication interface to a second device.

11 . The apparatus of claim 9 , wherein the first participant is a user of a contact center and the second participant is a remote agent of the contact center.

12 . The apparatus of claim 9 , wherein the first participant is a user of a contact center and the second participant is a local agent of the contact center.

13 . The apparatus of claim 9 , wherein the processor is further configured to execute instructions stored in the memory to:

extract the sensitive information from the video stream; and

transmit the sensitive information to a customer service application.

14 . The apparatus of claim 9 , wherein the processor is further configured to execute instructions stored in the memory to:

extract the sensitive information from the video stream; and

send a signal to unlock a physical object located near one of the first participant or the second participant based on contents of the extracted sensitive information.

15 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, perform operations comprising:

receiving a video stream captured by a camera device of a first participant of a video conference, wherein the video stream includes sensitive information that is not to be presented to a second participant intended to receive the video stream;

analyzing the video stream during the video conference to identify portions of the video stream containing the sensitive information presented by the first participant and captured by the camera device, wherein the sensitive information is displayed on a physical object presented to the camera device;

determining a type of the physical object presented to the camera device;

visually masking the portions of the video stream containing the sensitive information to generate a redacted video stream;

outputting the redacted video stream during the video conference for display at a display device of the second participant of the video conference; and

automatically triggering a workflow for the second participant based on the type of the physical object, wherein a first workflow is triggered for a first type and a second workflow is triggered for a second type.

16 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:

extracting the sensitive information from the video stream;

determining a workflow based on content of the sensitive information; and

providing the sensitive information as an input of a customer service software application implementing the workflow.

17 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:

providing the sensitive information as an input of a customer service software application implementing the workflow.

18 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:

extracting the sensitive information from the video stream; and

unlocking a physical object located near the second participant based on contents of the extracted sensitive information.

19 . The non-transitory computer-readable medium of claim 15 , wherein masking the video stream comprises;

blurring a portion of a video frame containing the sensitive information.

20 . The non-transitory computer-readable medium of claim 15 , wherein masking the video stream comprises:

blurring at least one frame of the video stream containing the sensitive information.

Assignments (2)

Continuity (1)

References Cited (54)