IP Library › Granted Patent US 12,192,180
Granted Patent B1
US 12,192,180 · App. 18/525,185 · Granted Jan 7, 2025

Privacy preserving user group expansion

Inventors: Wei Huang (Kirkland, WA); Fabio Soldo (Los Altos, CA); Surbhi Maheshwari (Sunnyvale, CA)
Assignee: Google LLC
H04L63/0421G06N3/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,192,180
App. No.
18/525,185
Granted
Jan 7, 2025
Kind
B1
Abstract

This document describes techniques for expanding user groups while preserving user privacy and data security. In one aspect, a method includes receiving, by a content platform and from a client device of a user, a request for a digital component that also includes a user identifier. A determination is made that the user identifier is included in a user list that includes multiple user identifiers respectively corresponding to multiple users in a user action group. In response to determining that the unique identifier is included in the user list, a digital component of the entity for which the user list is generated is selected and provided to the client device of the user for display to the user of the client device.

Claims (75)

1. A method comprising:

obtaining a first user list comprising first user identifiers for first users that performed one or more specified actions with respect to an electronic resource of an entity;

identifying, for each first user identifier of one or more of the first user identifiers, one or more user interest groups that include the first user identifier as a member;

identifying a plurality of second users that are members of the one or more user interest groups identified for each of the one or more first user identifiers;

generating an expanded user list that includes second user identifiers for at least a portion of the second users and the first user identifiers of the first user list; and

distributing digital components to the first and second users based on the expanded user list.

2. The method of claim 1 , wherein generating the expanded user list comprises:

identifying, for each second user, a geographic identifier that indicates a geographic location of the second user; and

selecting, for inclusion in the expanded user list, each second user for which the geographic identifier satisfies a location condition for the expanded user list.

3. The method of claim 1 , wherein generating the expanded user list comprises:

identifying, for each second user, a level of online activity of the second user;

ranking the second users based on the level of online activity of each second user; and

selecting, for inclusion in the expanded user list, a proper subset of the second users based on the ranking.

4. The method of claim 1 , wherein generating the expanded user list comprises:

identifying, for each second user, user embeddings that indicate user preferences of the second user;

ranking the second users based on the user embeddings for each second user; and

selecting, for inclusion in the expanded user list, a proper subset of the second users based on the ranking.

5. The method of claim 1 , wherein generating the expanded user list comprises:

generating, for each second user, a score based on a set of data for the second user, the set of data for each second user comprising one or more of: (i) the second user identifier for the second user, (ii) one or more user interest groups, (iii) an entity group of the entity, (iv) electronic resources of the entity, and (v) keywords associated with the entity; and

selecting, for inclusion in the expanded user list, each user having a score that satisfies a threshold score condition for the expanded user list.

6. The method of claim 5 , wherein generating the score for each second user comprises:

providing the set of data for the second user as input to a machine learning model; and

receiving the score as an output of the machine learning model.

7. The method of claim 1 , wherein distributing digital components to the first and second users based on the expanded user list comprises providing one or more digital components of the entity to each user having a user identifier in the expanded user list.

8. The method of claim 1 , wherein distributing digital components to the first and second users based on the expanded user list comprises:

receiving a digital component request from a client device of a given user;

determining that an identifier for the given user is included in the expanded user list; and

providing a digital component of the entity to the client device of the given user in response to determining that the identifier for the given user is included in the expanded user list.

9. A system comprising:

one or more processors; and

one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

obtaining a first user list comprising first user identifiers for first users that performed one or more specified actions with respect to an electronic resource of an entity;

identifying, for each first user identifier of one or more of the first user identifiers, one or more user interest groups that include the first user identifier as a member;

identifying a plurality of second users that are members of the one or more user interest groups identified for each of the one or more first user identifiers;

generating an expanded user list that includes second user identifiers for at least a portion of the second users and the first user identifiers of the first user list; and

distributing digital components to the first and second users based on the expanded user list.

10. The system of claim 9 , wherein generating the expanded user list comprises:

identifying, for each second user, a geographic identifier that indicates a geographic location of the second user; and

selecting, for inclusion in the expanded user list, each second user for which the geographic identifier satisfies a location condition for the expanded user list.

11. The system of claim 9 , wherein generating the expanded user list comprises:

identifying, for each second user, a level of online activity of the second user;

ranking the second users based on the level of online activity of each second user; and

selecting, for inclusion in the expanded user list, a proper subset of the second users based on the ranking.

12. The system of claim 9 , wherein generating the expanded user list comprises:

identifying, for each second user, user embeddings that indicate user preferences of the second user;

ranking the second users based on the user embeddings for each second user; and

selecting, for inclusion in the expanded user list, a proper subset of the second users based on the ranking.

13. The system of claim 9 , wherein generating the expanded user list comprises:

generating, for each second user, a score based on a set of data for the second user, the set of data for each second user comprising one or more of: (i) the second user identifier for the second user, (ii) one or more user interest groups, (iii) an entity group of the entity, (iv) electronic resources of the entity, and (v) keywords associated with the entity; and

selecting, for inclusion in the expanded user list, each user having a score that satisfies a threshold score condition for the expanded user list.

14. The system of claim 13 , wherein generating the score for each second user comprises:

providing the set of data for the second user as input to a machine learning model; and

receiving the score as an output of the machine learning model.

15. The system of claim 9 , wherein distributing digital components to the first and second users based on the expanded user list comprises providing one or more digital components of the entity to each user having a user identifier in the expanded user list.

16. The system of claim 9 , wherein distributing digital components to the first and second users based on the expanded user list comprises:

receiving a digital component request from a client device of a given user;

determining that an identifier for the given user is included in the expanded user list; and

providing a digital component of the entity to the client device of the given user in response to determining that the identifier for the given user is included in the expanded user list.

17. A non-transitory computer readable storage medium carrying instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

obtaining a first user list comprising first user identifiers for first users that performed one or more specified actions with respect to an electronic resource of an entity;

identifying, for each first user identifier of one or more of the first user identifiers, one or more user interest groups that include the first user identifier as a member;

identifying a plurality of second users that are members of the one or more user interest groups identified for each of the one or more first user identifiers;

generating an expanded user list that includes second user identifiers for at least a portion of the second users and the first user identifiers of the first user list; and

distributing digital components to the first and second users based on the expanded user list.

18. The non-transitory computer readable storage medium of claim 17 , wherein generating the expanded user list comprises:

identifying, for each second user, a geographic identifier that indicates a geographic location of the second user; and

selecting, for inclusion in the expanded user list, each second user for which the geographic identifier satisfies a location condition for the expanded user list.

19. The non-transitory computer readable storage medium of claim 17 , wherein generating the expanded user list comprises:

identifying, for each second user, a level of online activity of the second user;

ranking the second users based on the level of online activity of each second user; and

selecting, for inclusion in the expanded user list, a proper subset of the second users based on the ranking.

20. The non-transitory computer readable storage medium of claim 17 , wherein generating the expanded user list comprises:

identifying, for each second user, user embeddings that indicate user preferences of the second user;

ranking the second users based on the user embeddings for each second user; and

selecting, for inclusion in the expanded user list, a proper subset of the second users based on the ranking.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 6, 2023
From: HUANG, WEI; SOLDO, FABIO; MAHESHWARI, SURBHI
To: GOOGLE LLC
Reel/Frame 065777/0919 →
Continuity (1)
Continuation 17397089 · Aug 9, 2021
References Cited (11)
US 10839349B1 · Goyette · 2020 [cited by examiner]
US 20110307551A1 · Danezis · 2011 [cited by examiner]
US 20140108961A1 · Sundsten · 2014 [cited by examiner]
US 20200342961A1 · Baughman · 2020 [cited by examiner]
US 20230163978A1 · Turner · 2023 [cited by examiner]
US 20230205915A1 · Wang · 2023 [cited by examiner]
GitHub.com [online], “Evaluation of Cohort Algorithms for the FLoC API,” Oct. 2020, retrieved on Aug. 6, 2021, retrieved from URL<https://github.com/google/ads-privacy/tree/master/proposals/FLoC>, 2 pages. [cited by applicant]
GitHub.com [online], “Federated Learning of Cohorts (FLoC),” Jan. 2021, retrieved on Aug. 6, 2021, retrieved from URL<https://github.com/WICG/floc>, 6 pages. [cited by applicant]
GitHub.com [online], “Whitepaper: Evaluation of Cohort Algorithms for the FLoC API,” Oct. 2020, retrieved on Aug. 6, 2021, retrieved from URL<https://github.com/google/ads-privacy/blob/master/proposals/FLoC/FLOC-Whitepa… [cited by applicant]
Support.Google.com [online], “About remarketing,” Aug. 2021, retrieved on Aug. 6, 2021, retrieved from URL<https://support.google.com/google-ads/answer/2453998?hl=en>, 2 pages. [cited by applicant]
Support.Google.com [online], “Building a privacy-first future for web advertising,” Jan. 2021, retrieved on Aug. 6, 2021, retrieved from URL<https://blog.google/products/ads-commerce/2021-01-privacy-sandbox>, 6 pages. [cited by applicant]