Using machine learning and other models to determine a user preference to cancel a stream or download

Patent metadata

Field	Value
Publication number	US-12034989-B2
Application number	US-202318103378-A
Country	US
Kind code	B2
Filing date	Jan 30, 2023
Priority date	Nov 16, 2017
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

Training data for a machine learning model is generated. Generating the training data includes generating first training input, the first training input including first contextual information associated with a first user device of multiple user devices associated with a user account. The first contextual information identifies first location information corresponding to the first user device. A first target output for the first training input is generated. The first target output identifies an indication of a preference associated with the user account to cancel a first transmission of one or more media items to the first user device. The training data is provided to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

First claim

What is claimed is:

1. A method comprising:
generating training data for a machine learning model, wherein generating the training data comprises:
generating first training input, the first training input comprising first contextual information associated with a first user device of a plurality of user devices associated with a user account, the first contextual information identifying first location information corresponding to the first user device; and
generating a first target output for the first training input, wherein the first target output identifies an indication of a preference associated with the user account to cancel a first transmission of one or more media items to the first user device; and

training, based on the training data, the machine learning model on (i) a set of training inputs comprising the first training input, and (ii) a set of target outputs comprising the first target output.

2. The method of claim 1 , wherein generating the training data comprises:
generating second training input, the second training input comprising second contextual information associated with a second user device of the plurality of users devices,
and
wherein the set of training inputs comprises the second training input.

3. The method of claim 2 ,
wherein the user account is a shared user account associated with a plurality of users, wherein generating the training data further comprises:
generating third training input, the third training input comprising user profile activity information indicative of user activities associated with a particular user profile of the shared user account; and
wherein the set of training inputs comprises the first, the second, and the third training input.

4. The method of claim 1 ,
wherein the first contextual information associated with the first user device comprises user activity information indicative of user interaction with an application of the first user device, wherein the application is to receive at least one of the one or more media items.

5. The method of claim 1 ,
wherein the first contextual information associated with the first user device comprises device information indicative of a device type of the first user device.

6. The method of claim 1 ,
wherein the first location information is indicative of a geolocation of the first user device.

7. The method of claim 1 ,
wherein the first contextual information associated with the first user device comprises second location information indicative of a proximity of the first user device to other user devices associated with the user account.

8. The method of claim 1 ,
wherein the first contextual information associated with the first user device comprises third location information indicative of a contextual location of the first user device.

9. The method of claim 1 ,
wherein the first contextual information associated with the first user device comprises:
session information indicative of a user interaction with an application to receive at least one of the one or more media items during a session, wherein the session begins at an opening of the application and ends at a closing of the application, and
visit information indicative of a user interaction with the application during a visit, wherein the visit begins responsive to a user interaction with the application after a first period of user inactivity during the session and ends after a second period of user inactivity during the session.

10. The method of claim 1 , wherein each training input of the set of training inputs is mapped to the first target output in the set of target outputs.

11. A method for using a trained machine learning model to determine whether one or more transmissions to a plurality of user devices is to be canceled, the method comprising:
providing, by a processing device, to the trained machine learning model first input comprising first contextual information associated with a first user device of the plurality of user devices associated with a user account, the first contextual information identifying first location information corresponding to the first user device; and
obtaining, by the processing device from the trained machine learning model, one or more outputs identifying (i) a first transmission to the first user device, and (ii) a level of confidence for a preference associated with the user account to cancel the first transmission of one or more media items.

12. The method of claim 11 , further comprising:
providing second input comprising second contextual information associated with a second user device of the plurality of user devices; and
obtaining, from the trained machine learning model, the one or more outputs identifying a second transmission to the second user device and a level of confidence for a preference to cancel the second transmission.

13. The method of claim 12 , further comprising:
canceling either the first transmission or the second transmission in view of the level of confidence for the preference to cancel the first transmission and the second transmission.

14. The method of claim 13 , wherein canceling either the first transmission or the second transmission comprises:
determining whether the level of confidence for the preference to cancel either the first transmission or the second transmission exceeds a threshold level of confidence; and
responsive to determining that the level of confidence for at least one of the first transmission or the second transmission exceeds the threshold level, canceling a respective transmission.

15. The method of claim 12 , wherein the user account is a shared user account associated with a plurality of users, the method further comprising:
providing to the trained machine learning model third input comprising user activity information indicative of user activity associated with particular user profiles of the shared user account.

16. The method of claim 11 ,
wherein the first contextual information associated with the first user device comprises user activity information indicative of user interaction with an application of the first user device, wherein the application is to receive at least one of the one or more media items.

17. The method of claim 11 ,
wherein the first contextual information associated with the first user device comprises device information indicative of a device type of the first user device.

18. The method of claim 11 ,
wherein the first contextual information associated with the first user device comprises second location information indicative of a proximity of the first user device to other user devices associated with the user account.

19. A system, comprising:
a memory; and
a processing device, coupled to the memory, configured to perform operations comprising:
generating training data for a machine learning model, wherein generating the training data comprises:
generating first training input, the first training input comprising first contextual information associated with a first user device of a plurality of user devices associated with a user account, the first contextual information identifying first location information corresponding to the first user device; and
generating a first target output for the first training input, wherein the first target output identifies an indication of a preference associated with the user account to cancel a first transmission of one or more media items to the first user device; and

training, based on the training data, the machine learning model on (i) a set of trai

Assignees

• Google Llc

Inventors

• Lewis Justin
• Price Thomas

Classifications

• H04L67/10

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title

• H04L43/0817

  by checking functioning · CPC title

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• H04N21/25858

  involving client software characteristics, e.g. OS identifier · CPC title

• H04N21/25891

  being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18) · CPC title