Selective content sharing

Patent metadata

Field	Value
Publication number	US-11489889-B2
Application number	US-202117162185-A
Country	US
Kind code	B2
Filing date	Jan 29, 2021
Priority date	Jan 29, 2021
Publication date	Nov 1, 2022
Grant date	Nov 1, 2022

Abstract

Co-browsing allows a providing party to access visual content on a computing device for sharing with one or more other parties. The parties receiving the shared image may have dissimilar security authorizations. Accordingly, systems and methods are provided that enable shared content, such as a document, web page viewed in a browser, etc., to automatically be redacted to block those parties who are not authorized to view the content. For example, a neural network may be utilized to scan the document and provide specific redacted copies to the parties so each can view the image of the content with unauthorized content redacted.

First claim

What is claimed is:

1. A system, comprising:
a network interface to a network;
a data storage;
a processor configured with machine-readable instructions maintained in a non-transitory memory; and
wherein the processor:
receives a submitted image from a first communication device;
determines, for each of a number of portions of the submitted image, a security requirement;
accesses, for ones of a number of recipients, an authorization attribute;
generates, for ones of the number of recipients, corresponding ones of presentation images to comprise the submitted image modified to redact the number of portions of the submitted image that are not authorized for the corresponding ones of the number of recipients, wherein authorization is determined to be absent when the security requirement is more restrictive than the authorization attribute for the corresponding ones of the number of recipients; and
transmits the presentation images to the corresponding ones of the number of recipients; and

wherein a neural network is trained in a first stage using a first training set, wherein the first training set comprises a collected set of confidential document portions, a modified set of confidential document portions, and a set of non-confidential document portions;
wherein a neural network is further trained in a second stage, comprising the first training set and the set of non-confidential document portions that are incorrectly detected as confidential after the first stage;
wherein the processor further:
generates a preview image comprising indicia of the number of portions of the submitted image that are not authorized for ones of the number of recipients;

provides the preview image to the first communication device;
receives an override signal identifying one of the number of portions of the submitted image that are not authorized for ones of the number of recipients to be provided to the ones of the number of recipients; and

wherein the one of the number of portions of the submitted image that are not authorized is provided as one of the set of non-confidential document portions that are incorrectly detected as confidential.

2. The system of claim 1 , wherein the security requirement, for at least one of the number of portions of the submitted image, is determined to be more restrictive than the authorization attribute for the corresponding ones of the number of recipients, upon receiving an output from the neural network trained to determine the security requirement.

3. The system of claim 1 , wherein the processor further:
generates a second preview image comprising indicia of the number of portions of the submitted image that are not authorized for ones of the number of recipients;
provides the second preview image to the first communication device;
receives an override signal identifying one of the number of portions of the submitted image that are authorized for ones of the number of recipients to be provided to the ones of the number of recipients; and
wherein the one of the number of portions of the submitted image that are authorized is provided as one of the first training set.

4. The system of claim 1 , wherein the submitted image comprises an image of at least one of a document, a website, or an application as captured by the first communication device.

5. The system of claim 4 , wherein:
the submitted image comprises a dynamic image updated at least one of a change in a visual element of the at least one of the document, website, or application; and
the processor regenerates the corresponding ones of the presentation images to comprise the dynamic image modified to redact the number of portions of the submitted image having the security requirement that is more restrictive than the authorization attribute for corresponding ones of the number of recipients.

6. The system of claim 1 , wherein the submitted image comprises an image of a media file presented by a media player application.

7. The system of claim 1 , wherein the accessing, for ones of the number of recipients, an authorization attribute, further comprises accessing a group authorization attribute for a group comprising the ones of the number of recipients.

8. The system of claim 7 , wherein the group authorization attribute comprises at least one of department, division, role, rank, title, position, or license.

9. A method, comprising:
receiving a submitted image from a first communication device;
determining, for each of a number of portions of the submitted image, a security requirement;
accessing, for ones of a number of recipients, an authorization attribute;
generating, for ones of the number of recipients, corresponding ones of presentation images to comprise the submitted image modified to redact the number of portions of the submitted image that are not authorized for the corresponding ones of the number of recipients, wherein authorization is determined to be absent when the security requirement is more restrictive than the authorization attribute for the corresponding ones of the number of recipients;
training a neural network in a first stage using a first training set, wherein the first training set comprises a collected set of confidential document portions, a modified set of confidential document portions, and a set of non-confidential document portions;
training the neural network in a second stage, comprising the first training set and the set of non-confidential document portions that are incorrectly detected as confidential after the first stage
generating a preview image comprising indicia of the number of portions of the submitted image that are not authorized for ones of the number of recipients;
providing the preview image to the first communication device;
receiving an override signal identifying one of the number of portions of the submitted image that are not authorized for ones of the number of recipients to be provided to the ones of the number of recipients;
providing the one of the number of portions of the submitted image that are not authorized as one of the set of non-confidential document portions that are incorrectly detected as confidential; and
transmitting the presentation images to the corresponding ones of the number of recipients.

10. The method of claim 9 , wherein the security requirement, for at least one of the number of portions of the submitted image, is determined to be more restrictive than the authorization attribute for the corresponding ones of the number of recipients, upon receiving an output from a neural network trained to determine the security requirement.

11. The method of claim 9 , further comprising:
generating a second preview image comprising indicia of the number of portions of the submitted image that are not authorized for ones of the number of recipients;
providing the second preview image to the first communication device;
receiving an override signal identifying one of the number of portions of the submitted image that are authorized for ones of the number of recipients to be provided to the ones of the number of recipients; and
providing the one of the number of portions of the submitted image that are authorized as one of the first training set.

12. The method of claim 9 , wherein the submitted image comprises an image of at least one of a document, a website, or an application as captured by the first communication device.

13. The method of claim 12 , wherein:
the submitted image comprises a dynamic image updated at least one of a change in a visual element of the at least one of the document, website, or application; and
wherein generating, for ones of the number of re

Assignees

• Avaya Man Lp

Inventors

• Matula Valentine C
• Negi Manish
• Ray Divakar Kumar
• Gole Sujata Anand

Classifications

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06N3/08

  Learning methods · CPC title

• H04L67/02

  based on web technology, e.g. hypertext transfer protocol [HTTP] · CPC title

• H04L65/4015 Primary

  where at least one of the additional parallel sessions is real time or time sensitive, e.g. white board sharing, collaboration or spawning of a subconference · CPC title

• H04L65/403

  Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title