# US 2018/0027092 A1 · Selecting assets

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

- Number: US 2018/0027092 A1
- Document ID: US20180027092A1
- Status: Published application
- Kind: A1
- Application number: 15/215,922
- Filed: 2016-07-21
- Published: 2018-01-25
- Earliest claimed: 2016-07-21
- Assignees: Facebook, Inc.
- Applicants: Facebook, Inc.
- Inventors: Leif Erik Foged; Shaun Patric Allison
- Web page: https://patentgrep.com/patent/US20180027092A1

## CPC

- H04L 67/63: Routing a service request depending on the request content or context
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- H04L 67/306: User profiles
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In one embodiments, one or more computer systems receive, from a client device of a user, a request to access content. The computer systems access a plurality of assets representing the content. The computer devices calculate, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content. The computer devices selects one of the assets based on the probability. The computer devices send, to the client device, the selected asset.

## Claims

### Claim 1

A method comprising, by one or more computer systems:
receiving, from a client device of a user, a request to access content;
accessing a plurality of assets representing the content;
calculating, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content;
selecting one of the assets based on the probability; and
sending, to the client device, the selected asset.

### Claim 2 (depends on 1)

The method of claim 1, wherein the selected asset is an image asset.

### Claim 3 (depends on 2)

The method of claim 2, wherein the selected asset is determined based on a specified presentation format for the selected asset on the client device.

### Claim 4 (depends on 1)

The method of claim 1, wherein the probability of an interaction by a user is calculated in response to receiving the request to access content.

### Claim 5 (depends on 1)

The method of claim 1, wherein the features associated with the user comprise:
user profile information associated with the user;
device profile information associated with the client device;
information about the user's past interactions with the assets;
information about the user's past interactions with comparable assets;
information about the user's past interactions with the content; or
information about the user's past interactions with comparable content.

### Claim 6 (depends on 1)

The method of claim 1, wherein the features associated with the assets comprise:
historical performance of the assets;
image recognition data associated with the assets; or
a type or presentation format of the asset.

### Claim 7 (depends on 6)

The method of claim 6, wherein the historical performance of an asset of the plurality of assets is based on:
user interactions with one or more assets of the plurality of assets by a plurality of users;
demographic information associated with the plurality of users; or
context information for the user interactions with the one or more assets of the plurality of assets.

### Claim 8 (depends on 1)

The method of claim 1, wherein the features associated with the content comprise:
historical performance of the content;
a type of the content; or
information associated with the content.

### Claim 9 (depends on 8)

The method of claim 8, wherein the information associated with the content comprises:
a genre;
a functionality;
a language;
an identity of a creator, publisher, or distributer of the content;
a number of users who interact with the content per day;
a growth rate of the number of users who interact with the content per day;
an installation rate associated with the content;
an installation-to-play time duration associated with the content; or
a repeat-play value associated with the content.

### Claim 10 (depends on 1)

The method of claim 1, wherein the calculated probability of an interaction by the user comprises a probability of a click-through, a probability of a dismissal, or a probability of non-interaction.

### Claim 11 (depends on 10)

The method of claim 10, wherein the selected asset is determined based on the selected asset having a probability of a click-through that is greater than an average probability of a click-through for the plurality of assets.

### Claim 12 (depends on 1)

The method of claim 1, wherein the content is a game or a video clip.

### Claim 13 (depends on 1)

The method of claim 1, wherein the content is a game and wherein the calculated probability of an interaction by the user comprises a probability that the user will interact with the game for a particular duration of time.

### Claim 14 (depends on 1)

The method of claim 1, wherein the content is a game and wherein the calculated probability of an interaction by the user comprises a probability that the user will install the game.

### Claim 15

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
receive, from a client device of a user, a request to access content;
access a plurality of assets representing the content;
calculate, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content;
select one of the assets based on the probability; and
send, to the client device, the selected asset.

### Claim 16 (depends on 15)

The media of claim 15, wherein the selected asset is an image asset.

### Claim 17 (depends on 16)

The media of claim 16, wherein the selected asset is determined based on a specified presentation format for the selected asset on the client device.

### Claim 18 (depends on 15)

The media of claim 15, wherein the probability of an interaction by a user is calculated in response to receiving the request to access content.

### Claim 19 (depends on 15)

The media of claim 15, wherein the features associated with the user comprise:
user profile information associated with the user;
device profile information associated with the client device;
information about the user's past interactions with the assets;
information about the user's past interactions with comparable assets;
information about the user's past interactions with the content; or
information about the user's past interactions with comparable content.

### Claim 20

A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
receive, from a client device of a user, a request to access content;
access a plurality of assets representing the content;
calculate, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content;
select one of the assets based on the probability; and
send, to the client device, the selected asset.
