# US 2021/0342686 A1 · Content management using one or more neural networks

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

- Number: US 2021/0342686 A1
- Document ID: US20210342686A1
- Status: Published application
- Kind: A1
- Application number: 16/862,976
- Filed: 2020-04-30
- Published: 2021-11-04
- Earliest claimed: 2020-04-30
- Assignees: NVIDIA Corporation
- Applicants: Nvidia Corporation
- Inventors: Pranit P. Kothari; Siddhant Pardeshi; Vinayak Vilas Gaikwad
- Web page: https://patentgrep.com/patent/US20210342686A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/063: using electronic means
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Apparatuses, systems, and techniques are presented to determine whether to render one or more content objects. In at least one embodiment, one or more neural networks can determine whether to render an object to be transmitted in media content based at least in part upon whether those objects were previously rendered for that content.

## Claims

### Claim 1

A processor, comprising:
one or more circuits to use one or more neural networks to render one or more objects based, at least in part, on whether the one or more objects were previously rendered.

### Claim 2 (depends on 1)

The processor of claim 1, wherein the one or more circuits are further to utilize the one or more neural networks to identify the one or more objects in one or more frames of media content, the one or more circuits to further cause text indicative of the one or more objects to be stored in cache.

### Claim 3 (depends on 2)

The processor of claim 2, wherein the one or more circuits are further to determine whether the one or more objects were previously rendered by comparing the text, indicative of the one or more objects, to text stored in the cache for one or more previously-rendered objects.

### Claim 4 (depends on 2)

The processor of claim 2, wherein the one or more circuits are further to encode the text, indicative of the one or more objects if previously rendered, in a transmission of the media content instead of including the one or more objects, wherein a recipient of the transmission having the one or more objects cached locally can utilize the locally-cached objects to generate the media content for presentation.

### Claim 5 (depends on 1)

The processor of claim 1, wherein the one or more neural networks include one or more convolutional neural networks (CNNs) to analyze individual frames of media content for object features and one or more long short-term memory (LSTM) recurrent neural networks (RNNs) to encode and output text indicative of the one or more objects.

### Claim 6 (depends on 1)

The processor of claim 1, wherein the one or more objects include video objects, image objects, or audio objects.

### Claim 7

A system comprising:
one or more processors to use one or more neural networks to render one or more objects based, at least in part, on whether the one or more objects were previously rendered.

### Claim 8 (depends on 7)

The system of claim 7, wherein the one or more processors are further to utilize the one or more neural networks to identify the one or more objects in one or more frames of media content, the one or more circuits to further cause text indicative of the one or more objects to be stored in cache.

### Claim 9 (depends on 8)

The system of claim 8, wherein the one or more processors are further to determine whether the one or more objects were previously rendered by comparing the text, indicative of the one or more objects, to text stored in the cache for previously-rendered objects.

### Claim 10 (depends on 8)

The system of claim 8, wherein the one or more processors are further to encode the text, indicative of the one or more objects if previously rendered, in a transmission of the media content instead of including the one or more objects, wherein a recipient of the transmission having the one or more objects cached locally can utilize the locally-cached objects to generate the media content for presentation.

### Claim 11 (depends on 7)

The system of claim 7, wherein the one or more neural networks include one or more convolutional neural networks (CNNs) to analyze individual frames of media content for object features and one or more long short-term memory (LSTM) recurrent neural networks (RNNs) to encode and output text indicative of the one or more objects.

### Claim 12 (depends on 7)

The system of claim 7, wherein the one or more objects include video objects, image objects, or audio objects.

### Claim 13

A method comprising:
using one or more neural networks to render one or more objects based, at least in part, on whether the one or more objects were previously rendered.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
utilizing the one or more neural networks to identify the one or more objects in one or more frames of media content, the one or more circuits to further cause text indicative of the one or more objects to be stored in cache

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
determining whether the one or more objects were previously rendered by comparing the text, indicative of the one or more objects, to text stored in the cache for previously-rendered objects.

### Claim 16 (depends on 14)

The method of claim 14, further comprising:
encoding the text, indicative of the one or more objects if previously rendered, in a transmission of the media content instead of including the one or more objects, wherein a recipient of the transmission having the one or more objects cached locally can utilize the locally-cached objects to generate the media content for presentation.

### Claim 17 (depends on 13)

The method of claim 13, wherein the one or more neural networks include one or more convolutional neural networks (CNNs) to analyze individual frames of media content for object features and one or more long short-term memory (LSTM) recurrent neural networks (RNNs) to encode and output text indicative of the one or more objects.

### Claim 18 (depends on 13)

The method of claim 13, wherein the one or more objects include video objects, image objects, or audio objects.

### Claim 19

A machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:
use one or more neural networks to render one or more objects based, at least in part, on whether the one or more objects were previously rendered.

### Claim 20 (depends on 19)

The machine-readable medium of claim 19, wherein the instructions if performed further cause the one or more processors to:
utilize the one or more neural networks to identify the one or more objects in one or more frames of media content, the one or more circuits to further cause text indicative of the one or more objects to be stored in cache.

### Claim 21 (depends on 20)

The machine-readable medium of claim 20, wherein the instructions if performed further cause the one or more processors to:
determine whether the one or more objects were previously rendered by comparing the text, indicative of the one or more objects, to text stored in the cache for previously-rendered objects.

### Claim 22 (depends on 20)

The machine-readable medium of claim 20, wherein the instructions if performed further cause the one or more processors to:
encode the text, indicative of the one or more objects if previously rendered, in a transmission of the media content instead of including the one or more objects, wherein a recipient of the transmission having the one or more objects cached locally can utilize the locally-cached objects to generate the media content for presentation.

### Claim 23 (depends on 19)

The machine-readable medium of claim 19, wherein the one or more neural networks include one or more convolutional neural networks (CNNs) to analyze individual frames of media content for object features and one or more long short-term memory (LSTM) recurrent neural networks (RNNs) to encode and output text indicative of the one or more objects.

### Claim 24 (depends on 19)

The machine-readable medium of claim 19, wherein the one or more objects include video objects, image objects, or audio objects.

### Claim 25

A media transmission system, comprising:
one or more processors to use one or more neural networks to identify one or more objects, in a video frame to be transmitted for display on a client device, that were previously transmitted and to instruct the client device to insert the previously-transmitted one or more objects into one or more identified locations in the video frame; and
memory for storing network parameters for the one or more neural networks.

### Claim 26 (depends on 25)

The media transmission system of claim 25, wherein the one or more processors are further to utilize the one or more neural networks to identify the one or more objects in the video frame of media content, the one or more circuits to further cause text indicative of the one or more objects to be stored in cache and used to instruct the client device to insert the previously-transmitted one or more objects.

### Claim 27 (depends on 26)

The media transmission system of claim 26, wherein the one or more processors are further to determine whether the one or more objects were previously transmitted by comparing the text, indicative of the one or more objects, to text stored in the cache for previously-transmitted objects.

### Claim 28 (depends on 26)

The media transmission system of claim 26, wherein the one or more processors are further to encode the text, indicative of the one or more objects if previously transmitted, in a transmission of the media content instead of including the one or more objects, wherein a recipient of the transmission having the one or more objects cached locally can utilize the locally-cached objects to generate the media content for presentation.

### Claim 29 (depends on 25)

The media transmission system of claim 25, wherein the one or more neural networks include one or more convolutional neural networks (CNNs) to analyze individual frames of media content for object features and one or more long short-term memory (LSTM) recurrent neural networks (RNNs) to encode and output text indicative of the one or more objects.

### Claim 30 (depends on 25)

The media transmission system of claim 25, wherein the one or more objects include video objects, image objects, or audio objects.
