# US 2026/0230580 A1 · Video Stream Scoring and Selection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0230580 A1
- Document ID: US20260230580A1
- Status: Published application
- Kind: A1
- Application number: 19/646,412
- Filed: 2026-04-13
- Published: 2026-08-06
- Earliest claimed: 2022-01-26
- Assignees: Zoom Communications, Inc.
- Applicants: Zoom Communications, Inc.
- Inventors: Anna Deng; Yanjia Duan; Juntao Feng; Tianming Gu; Cynthia Eshiuan Lee; Bo Ling; Chong Lv; Jeffrey William Smith; Menglin Wang; Huixi Zhao; Xingguo Zhu
- Web page: https://patentgrep.com/patent/US20260230580A1

## CPC

- H04N 7/147: {Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q)}
- H04N 7/15: Conference systems
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A best available video stream is determined for each of multiple conference participants within a conference room including multiple cameras based on scores determined for video streams obtained from the cameras. The scores are determined based on representations of the conference participants within the video streams, for example, based on percentages of conference participant faces visible within the video streams, directions of conference participant faces relative to the cameras, directions of eye gaze of the conference participants relative to the cameras, and/or degrees to which conference participant faces are obscured within the video streams. The best available video streams are output for rendering within separate user interface tiles of conferencing software.

## Claims

### Claim 1

A method, comprising:
obtaining, from multiple cameras, multiple video streams each depicting a participant of a video conference;
determining, for each video stream of the multiple video streams, a score based on one or more of a percentage of a face of the participant that is visible within the video stream, a direction of the face relative to a camera from which the video stream is obtained, a direction the participant is looking relative to the camera, or a degree to which the face is obscured within the video stream;
selecting, from amongst the multiple video streams, a video stream based on the scores; and
providing the selected video stream for rendering within a user interface of the video conference.

### Claim 2 (depends on 1)

The method of claim 1, comprising:
identifying, within each video stream of the multiple video streams, a region of interest corresponding to the participant,
wherein providing the selected video stream for rendering within the user interface of the video conference comprises:
providing the region of interest of the selected video stream for rendering within the user interface.

### Claim 3 (depends on 1)

The method of claim 1, wherein providing the selected video stream for rendering within the user interface of the video conference comprises:
determining that a change policy related to at least one of a threshold time between video stream selection changes or a total number of video stream selection changes over a time period is met; and
providing the selected video stream for rendering within the user interface of the video conference based on the determination that the change policy is met.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining the score for a video stream of the multiple video streams comprises:
further determining the score based on one or more of a resolution at which the video stream is captured, a frame rate at which the video stream is captured, a resolution capability of the camera from which the video stream is obtained, or a frame rate capability of the camera.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining the score for a video stream of the multiple video streams comprises:
determining the score using one or more weights that are based on output of a machine learning model.

### Claim 6 (depends on 1)

The method of claim 1, wherein selecting the video stream based on the scores comprises:
selecting the video stream based on the scores and based on feedback obtained from one or more participant devices during the video conference.

### Claim 7 (depends on 1)

The method of claim 1, comprising:
changing a field of view of a camera of the multiple cameras based on the score determined for a video stream obtained from the camera.

### Claim 8 (depends on 1)

The method of claim 1, comprising:
determining, for each video stream of the multiple video streams, new scores on a discrete time interval basis or an event basis.

### Claim 9 (depends on 1)

The method of claim 1, comprising:
determining that a number of participants depicted within the multiple video streams meets a threshold; and
providing, based on the determination that the number of participants meets the threshold, video streams for rendering within the user interface only for participants who speak more than a threshold number of words during the video conference.

### Claim 10 (depends on 1)

The method of claim 1, comprising:
determining that a number of participants depicted within the multiple video streams meets a threshold; and
providing, based on the determination that the number of participants meets the threshold, video streams for rendering within the user interface only for participants who are identified as high priority using an organizational chart for an entity associated with the video conference.

### Claim 11

A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
obtaining, from multiple cameras, multiple video streams each depicting a participant of a video conference;
determining, for each video stream of the multiple video streams, a score based on one or more of a percentage of a face of the participant that is visible within the video stream, a direction of the face relative to a camera from which the video stream is obtained, a direction the participant is looking relative to the camera, or a degree to which the face is obscured within the video stream;
selecting, from amongst the multiple video streams, a video stream based on the scores; and
providing the selected video stream for rendering within a user interface of the video conference.

### Claim 12 (depends on 11)

The non-transitory computer readable medium of claim 11, wherein providing the selected video stream for rendering within the user interface of the video conference comprises:
providing a region of interest of the selected video stream for rendering within the user interface, wherein the region of interest corresponds to the participant.

### Claim 13 (depends on 11)

The non-transitory computer readable medium of claim 11, providing the selected video stream for rendering within the user interface of the video conference comprises:
providing the selected video stream for rendering within the user interface of the video conference based on a change policy related to at least one of a threshold time between video stream selection changes or a total number of video stream selection changes over a time period.

### Claim 14 (depends on 11)

The non-transitory computer readable medium of claim 11, wherein the score is further based on one or more of a resolution at which the video stream is captured, a frame rate at which the video stream is captured, a resolution capability of the camera from which the video stream is obtained, or a frame rate capability of the camera.

### Claim 15 (depends on 11)

The non-transitory computer readable medium of claim 11, wherein video streams are provided for rendering within the user interface only for participants who speak more than a threshold number of words during the video conference or who are identified as high priority.

### Claim 16

A system, comprising:
one or more memories; and
one or more processors configured to execute instructions stored in the one or more memories to:
obtain, from multiple cameras, multiple video streams each depicting a participant of a video conference;
determine, for each video stream of the multiple video streams, a score based on one or more of a percentage of a face of the participant that is visible within the video stream, a direction of the face relative to a camera from which the video stream is obtained, a direction the participant is looking relative to the camera, or a degree to which the face is obscured within the video stream;
select, from amongst the multiple video streams, a video stream based on the scores; and
provide the selected video stream for rendering within a user interface of the video conference.

### Claim 17 (depends on 16)

The system of claim 16, wherein a region of interest corresponding to the participant is provide for rendering within the user interface.

### Claim 18 (depends on 16)

The system of claim 16, wherein the selected video stream is provided for rendering within the user interface based on a change policy.

### Claim 19 (depends on 16)

The system of claim 16, wherein the score is determined using one or more weights that are based on output of a machine learning model.

### Claim 20 (depends on 16)

The system of claim 16, wherein the video stream is selected based on the scores and based on feedback obtained from one or more participant devices during the video conference.
