Real-time content integration based on machine learned selections

Patent metadata

Field	Value
Publication number	US-11582292-B2
Application number	US-202117321711-A
Country	US
Kind code	B2
Filing date	May 17, 2021
Priority date	May 31, 2017
Publication date	Feb 14, 2023
Grant date	Feb 14, 2023

Abstract

A content integration system is configured to rapidly select online content for distribution in response to a user-generated request. The content integration system can analyze available online content items and data describing the user to generate one or more numerical likelihoods estimating how the user will interact with each of the given online content items. The highest scoring content can be selected and transmitted to the user without a noticeable delay.

First claim

What is claimed is:

1. A method comprising:
receiving, by a network platform, from a user device, a request for a plurality of content items, at least one of the plurality of content items being an interactive content item that can be activated by performing a user device input action while the interactive content item is displayed;
in response to the request for the plurality of content items, automatically identifying a plurality of candidate content items submitted to the network platform by a plurality of other user devices;
automatically generating, using a machine learning scheme, a set of first values indicating a likelihood that a user of the device will perform a first user input action if presented with each of the plurality of candidate content items, and a second set of values indicating the user of the device will perform a second user input action if presented with each of the plurality of candidate content items, the first user input being different than the second user input action;
generating, by adding corresponding values from the set of first values and the set of second values, relevancy values for the plurality of candidate content items, each relevancy value indicating a likelihood that a user of the user device will perform the first user input action in response to being presented one of the plurality of candidate content items corresponding to the relevancy value;
automatically selecting a candidate content item from the plurality of candidate content items based on the candidate content item having a high relevancy value generated by the machine learning scheme; and
causing, on the user device, presentation of the plurality of content items with the selected candidate content item.

2. The method of claim 1 , wherein the selected candidate content item is selected based on the high relevancy value being higher than relevancy values of the other plurality of candidate content items.

3. The method of claim 1 , wherein the selected candidate content item is configured to request an additional content in response to a user input action being performed on the user device while the selected candidate content item is displayed.

4. The method of claim 1 , wherein the request for the plurality of content items is generated in an active network session of an application executing on the user device of the user.

5. The method of claim 4 , further comprising:
identifying historical user data of past user actions of past users using the application; and
training the machine learning scheme on the historical user data.

6. The method of claim 5 , wherein the past user actions include browse path data, subscription data, and user profile data.

7. The method of claim 6 , wherein the browse path data describes a browse path of a past user as the past user navigates in the application.

8. The method of claim 6 , wherein the subscription data indicates whether a past user has subscribed to content using the application.

9. The method of claim 6 , wherein the user profile data comprises user preference data of the application.

10. The method of claim 1 , wherein the user device input action comprises one or more of:
a tap or a swipe.

11. The method of claim 1 , wherein the machine learning scheme implements a random forest scheme.

12. A system comprising:
one or more processors of a machine; and
a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising:
receiving, from a user device, a request for a plurality of content items, at least one of the plurality of content items being an interactive content item that can be activated by performing a user device input action while the interactive content item is displayed;
in response to the request for the plurality of content items, automatically identifying a plurality of candidate content items submitted by a plurality of other user devices;
automatically generating, using a machine learning scheme, a set of first values indicating a likelihood that a user of the device will perform a first user input action if presented with each of the plurality of candidate content items, and a second set of values indicating the user of the device will perform a second user input action if presented with each of the plurality of candidate content items, the first user input being different than the second user input action;

generating, by adding corresponding values from the set of first values and the set of second values, relevancy values for the plurality of candidate content items, each relevancy value indicating a likelihood that a user of the user device will perform the first user input action in response to being presented one of the plurality of candidate content items corresponding to the relevancy value;
automatically selecting a candidate content item from the plurality of candidate content items based on the candidate content item having a high relevancy value generated by the machine learning scheme; and
causing, on the user device, presentation of the plurality of content items with the selected candidate content item.

13. The system of claim 12 , wherein the selected candidate content item is selected based on the high relevancy value being higher than relevancy values of the other plurality of candidate content items.

14. The system of claim 12 , wherein the selected candidate content item is configured to request an additional content in response to a user input action being performed on the user device while the selected candidate content item is displayed.

15. The system of claim 12 , wherein the request for the plurality of content items is generated in an active network session of an application executing on the user device of the user.

16. The system of claim 15 , the operations further comprising:
identifying historical user data of past user actions of past users using the application; and
training the machine learning scheme on the historical user data.

17. The system of claim 16 , wherein the past user actions include browse path data, subscription data, and user profile data.

18. The system of claim 17 , wherein the browse path data describes a browse path of a past user as the past user navigates in the application.

19. A non-transitory machine-readable storage device embodying instructions that, when executed by a machine, cause the machine to perform operations comprising:
receiving, from a user device, a request for a plurality of content items, at least one of the plurality of content items being an interactive content item that can be activated by performing a user device input action while the interactive content item is displayed;
in response to the request for the plurality of content items, automatically identifying a plurality of candidate content items submitted by a plurality of other user devices;
automatically generating, using a machine learning scheme, a set of first values indicating a likelihood that a user of the device will perform a first user input action if presented with each of the plurality of candidate content items, and a second set of values indicating the user of the device will perform a second user input action if presented with each of the plurality of candidate content items, the first user input being different than the second user input action;

generating, by adding corresponding values from the set of first values and the set of second values, relevancy values for the plurality of candidate content items, each relevancy value indicating a

Assignees

• Snap Inc

Inventors

• Brewer Jason
• Farnham Rodrigo B
• Lue David B
• Stucky-Mack Nicholas J

Classifications

• G06N20/20 Primary

  Ensemble learning · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• H04L67/14

  Session management (for real-time applications in data packet communications networks H04L65/1066) · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title