Automatic image generator using meeting content

Patent metadata

Field	Value
Publication number	US-11973608-B2
Application number	US-202217884627-A
Country	US
Kind code	B2
Filing date	Aug 10, 2022
Priority date	Aug 10, 2022
Publication date	Apr 30, 2024
Grant date	Apr 30, 2024

Abstract

Methods and systems disclosed herein describe generating virtual backgrounds for video communications. A virtual background generator may monitor a user's calendar and/or inbox for meetings. The virtual background generator may analyze the context of calendar invites and/or scheduled meetings to generate one or more virtual backgrounds for a video conference. A first background may be displayed for the video conference. Additionally, the virtual background generator may update the virtual background based on an analysis of one or more topics being discussed during the video conference. Based on the analysis of the one or more topics being discussed, the virtual background generator may generate a second virtual background to replace the first virtual background.

First claim

What is claimed is:

1. A computer-implemented method comprising:
training, by a computing device, a machine learning model to generate one or more background images based on one or more criteria contained in a meeting;
accessing, by the computing device and via an application programming interface (API), a user's calendar to identify one or more meetings;
identifying, by the computing device, a first meeting of the one or more meetings, wherein the first meeting comprises one or more first criteria;
parsing, by the computing device and using natural language processing, the one or more first criteria to generate a set of word embeddings;
inputting, by the computing device, the set of word embeddings to the machine learning model;
generating, by the computing device and using the machine learning model, one or more backgrounds for the first meeting based on the set of word embeddings;
sending, by the computing device and to the client device, a request for a selection from the one or more generated backgrounds;
receiving, by the computing device and from the client device, a selection of a first background from the one or more generated backgrounds; and
causing, by the computing device, display of the selected first background during a video conference associated with first meeting.

2. The computer-implemented method of claim 1 , wherein the accessing the user's calendar to identify the one or more meetings comprises:
sending, by the computing device and via the API, a request to access the user's calendar; and
receiving, by the computing device and via the API, a response indicating approval to access the user's calendar.

3. The computer-implemented method of claim 1 , wherein the one or more criteria comprises at least one of:
an attachment to the meeting;
an agenda associated with the meeting;
a list of attendees for the meeting;
a message body;
a set of e-mail addresses associated with the meeting; or
a subject message associated with the meeting.

4. The computer-implemented method of claim 1 , wherein the meeting comprises at least one of:
a video conference;
a webinar; or
an online meeting.

5. The computer-implemented method of claim 1 , wherein the one or more backgrounds comprise one or more of:
a static image;
a dynamic image;
an animated image;
a video;
a graphics interchange format (GIF) image;
a meeting agenda;
an action item list for the first meeting;
a presentation associated with the first meeting; or
an overlay.

6. The computer-implemented method of claim 1 , wherein the computing device comprises a server.

7. The computer-implemented method of claim 1 , further comprising:
receiving, from the user, a feedback score representing a relevance of the generated background image for the meeting; and
using the feedback score to train the machine learning model.

8. The computer-implemented method of claim 1 , further comprising:
analyzing, by the computing device and using the machine learning model, the one or more criteria contained in the first meeting to identify confidential information in the one or more criteria,
wherein the machine learning model is configured to exclude the confidential information when generating the one or more first backgrounds.

9. A computing device comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the computer device to:
train a machine learning model to generate one or more background images based on one or more criteria contained in a meeting;
access, via an application programming interface (API), a user's calendar to identify one or more meetings;
identify a first meeting of the one or more meetings, wherein the first meeting comprises one or more first criteria;
parse, using natural language processing, the one or more first criteria to generate a set of word embeddings;
input the set of word embeddings to the machine learning model;
generate, using the machine learning model, one or more backgrounds for the first meeting based on the set of word embeddings;
send, by the computing device and to the client device, a request for a selection from the one or more generated backgrounds;
receive, by the computing device and from the client device, a selection of a first background from the one or more generated backgrounds; and
cause, display of the selected first background during a video conference associated with first meeting.

10. The computing device of claim 9 , wherein the instructions to access the user's calendar to identify the one or more meetings cause the computing device to:
send, via the API, a request to access the user's calendar; and
receive, via the API, a response indicating approval to access the user's calendar.

11. The computing device of claim 9 , wherein the one or more criteria comprises at least one of:
an attachment to the meeting;
an agenda associated with the meeting;
a list of attendees for the meeting;
a message body;
a set of e-mail addresses associated with the meeting; or
a subject message associated with the meeting.

12. The computing device of claim 9 , wherein the video conference comprises at least one of:
a webinar; or
an online meeting.

13. The computing device of claim 9 , wherein the one or more backgrounds comprise one or more of:
a static image;
a dynamic image;
an animated image;
a video;
a graphics interchange format (GIF) image;
a meeting agenda;
an action item list for the first meeting;
a presentation associated with the first meeting; or
an overlay on an existing background.

14. The computing device of claim 9 , wherein the instructions cause the computing device to:
analyze, by the computing device and using the machine learning model, the one or more criteria contained in the first meeting to identify confidential information in the one or more criteria,
wherein the machine learning model is configured to exclude the confidential information when generating the one or more first backgrounds.

15. A non-transitory computer-readable media storing instructions that, when executed, cause a computing device comprising to:
train a machine learning model to generate one or more background images based on one or more criteria contained in a meeting;
access, via an application programming interface (API), a user's calendar to identify one or more meetings;
identify a first meeting of the one or more meetings, wherein the first meeting comprises one or more first criteria;
parse, using natural language processing, the one or more first criteria to generate a set of word embeddings;
input the set of word embeddings to the machine learning model;
generate, using the machine learning model, one or more backgrounds for the first meeting based on the set of word embeddings;
send, by the computing device and to the client device, a request for a selection from the one or more generated backgrounds;
receive, by the computing device and from the client device, a selection of a first background from the one or more generated backgrounds; and
cause, display of the selected first background during a video conference associated with first meeting.

16. The non-transitory computer-readable media of claim 15 , wherein the instructions to access the user's calendar to identify the one or more meetings cause the computing device to:
send, via the API, a request to access the user's calendar; and
receive, via the API, a response indicating approval to access the user's calendar.

17. The non-transitory compute

Assignees

• Capital One Services Llc

Inventors

• Kare Sarvani
• Tran Daniel
• Adcock Lee
• Shyamala Geeta
• Polk Benjamin

Classifications

• H04L12/18 Primary

  for broadcast or conference {, e.g. multicast} · CPC title

• G06T11/00 Primary

  Two-dimensional [2D] image generation · CPC title

• H04L12/1827

  Network arrangements for conference optimisation or adaptation · CPC title