# US 2022/0046074 A1 · Scalable multi-level collaborative content moderation

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

- Number: US 2022/0046074 A1
- Document ID: US20220046074A1
- Status: Published application
- Kind: A1
- Application number: 17/165,269
- Filed: 2021-02-02
- Published: 2022-02-10
- Earliest claimed: 2020-08-05
- Assignees: Agora Lab, Inc.
- Applicants: Agora Lab, Inc.
- Inventors: Sheng Zhong
- Web page: https://patentgrep.com/patent/US20220046074A1

## CPC

- H04L 65/765: {intermediate}
- H04N 21/2187: Live feed
- H04L 65/403: 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)
- H04L 65/61: for supporting one-way streaming services, e.g. Internet radio
- H04L 65/80: Responding to QoS
- 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
- H04N 21/23418: {involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)}
- H04N 21/2743: Video hosting of uploaded data from client
- H04N 21/4542: {Blocking scenes or portions of the received content, e.g. censoring scenes}
- H04N 21/4788: communicating with other users, e.g. chatting {(arrangements for providing for computer conferences, e.g. chat rooms, to substation in data switching networks H04L12/1813; distributed application using peer-to-peer [P2P] networks H04L67/104)}
- H04L 65/65: Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A method for content moderation in real-time communication includes receiving a first portion of a media stream from a sending user; scaling the first portion of the media stream to obtain a scaled first portion of the media stream; transmitting, to a centralized content moderation device, the scaled first portion of the media stream; receiving, from the centralized content moderation device, a centralized determination of whether the first portion is appropriate; and, in response to the centralized determination indicating that the first portion of the media stream is inappropriate: blurring the first portion to obtain a blurred first portion; and transmitting, to a receiving user, the blurred first portion.

## Claims

### Claim 1

A method for content moderation in real-time communication, comprising:
receiving a first portion of a media stream from a sending user;
scaling the first portion of the media stream to obtain a scaled first portion of the media stream;
transmitting, to a centralized content moderation device, the scaled first portion of the media stream;
receiving, from the centralized content moderation device, a centralized determination of whether the first portion is appropriate; and
in response to the centralized determination indicating that the first portion of the media stream is inappropriate:
blurring the first portion to obtain a blurred first portion; and
transmitting, to a receiving user, the blurred first portion.

### Claim 2 (depends on 1)

The method of claim 1, wherein transmitting, to the receiving user, the blurred first portion comprises:
transmitting the blurred first portion to a forwarding device, wherein the forwarding device transmits the blurred first portion to the receiving user.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
in response to the centralized determination indicating that the first portion of the media stream is appropriate:
transmitting, to the receiving user, the first portion.

### Claim 4 (depends on 1)

The method of claim 1, wherein receiving, from the centralized content moderation device, the centralized determination comprises:
in response to not receiving the centralized determination from the centralized content moderation device within a predetermined period of time, using a policy to determine a value of the centralized determination.

### Claim 5 (depends on 4)

The method of claim 4, wherein the policy is a policy of the centralized content moderation device.

### Claim 6 (depends on 4)

The method of claim 4, wherein the policy is a permissive policy.

### Claim 7 (depends on 4)

The method of claim 4, wherein the policy is a restrictive policy.

### Claim 8

A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising operations to:
receive a first portion of a media stream from a sending device of a sending user;
scale the first portion of the media stream to obtain a scaled first portion of the media stream;
forward the scaled first portion of the media stream to a centralized content moderation device that is in communication with the sending device;
receive, from the centralized content moderation device, a centralized determination as to whether the first portion of the media stream is inappropriate; and
use the centralized determination to determine whether to transmit the first portion or a blurred first portion of the first portion to a receiving user.

### Claim 9 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, wherein the operations further comprise operations to:
receive a second portion of the media stream; and
determine, by the sending device, whether the second portion of the media stream is not appropriate for sending to the receiving user.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein to determine whether the second portion of the media stream is not appropriate comprises to:
determine that the second portion of the media stream is inappropriate for transmitting to the receiving user or determine with an uncertainty whether the second portion is appropriate or inappropriate.

### Claim 11 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the operations further comprise operations to:
in response to determining that the second portion is not appropriate, transmitting a portion related to the second portion to the centralized content moderation device, wherein the portion related to the second portion being one of the second portion or a second scaled down version of the second portion.

### Claim 12 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the operations further comprise operations to:
in response to determining that the second portion is appropriate, transmit the second portion to the receiving user.

### Claim 13 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the operations further comprise operations to:
in response to determining that the second portion inappropriate, transmit a blurred version of the second portion to the receiving user.

### Claim 14

An apparatus for content moderation in real-time communication, comprising:
a memory; and
a processor configured to execute instructions stored in the memory to:
receive a first portion of a media stream from a sending user;
determine that the first portion of the media stream is classified as uncertain for transmission to a receiving user, wherein a classification of uncertain indicates that the first portion cannot be determined with certainty whether the first portion is appropriate or inappropriate for transmission to the receiving user; and
in response to the determining that the first portion of the media stream is classified as uncertain for transmission to the receiving user:
blur the first portion to obtain a blurred first portion; and
transmit the blurred first portion to the receiving user.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein the instructions further comprise instructions to:
transmit, to a centralized content moderation device, a second portion of the media stream, wherein the centralized content moderation device determines a centralized determination of whether the second portion is appropriate;
in response to the centralized determination indicating that the second portion is appropriate, transmit the second portion to the receiving user; and
in response to the centralized determination indicating that the second portion is inappropriate, transmit a blurred second portion of the second portion to the receiving user.

### Claim 16 (depends on 14)

The apparatus of claim 14, wherein the first portion of the media stream comprises an audio portion, and wherein to blur the first portion of the media stream to obtain the blurred first portion comprises to:
distort the audio portion to obtain a distorted audio portion; and
transmit the distorted audio portion to the receiving user.

### Claim 17 (depends on 14)

The apparatus of claim 14, wherein the first portion of the media stream comprises a visual portion, and wherein to blur the first portion of the media stream to obtain the blurred first portion comprises to:
blur the visual portion to obtain a blurred visual portion.

### Claim 18 (depends on 14)

The apparatus of claim 14, wherein to determine that the first portion of the media stream is classified as uncertain for transmission to the receiving user comprises to:
scale the first portion to obtain a scaled first portion;
provide the scaled first portion to a local content moderation module of the apparatus; and
obtain, from the local content moderation module, the classification of the scaled first portion.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein the local content moderation module is a machine learning model.

### Claim 20 (depends on 19)

The apparatus of claim 19, wherein to scale the first portion to obtain the scaled first portion comprises to:
scale the first portion to a size of images that is used to train the machine learning model.
