US 11,900,482 B2Granted

Optimal notification

AssigneePinterest, Inc.

InventorsBo Zhao, Samuel Seth Weisfeld-Filson, John William Gupta Egan, Burkay Birant Orten, Koichiro Narita

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods for generating user notifications to a set of users of a social networking service is presented. For each user of a set of users of the social networking service, one or more machine learning models selects an optimal notification channel, an optimal notification template, and optimal personalization content for configurable elements of a selected notification template. Each of these determinations/selections is made according to and based on a likelihood of increased user engagement with the social networking service. Upon determining the notification channel, notification template, and personalizations to the template, the notification is generated and sent to the corresponding user.

Claims19

Dependent claims

A computer-implemented method, comprising:

determining that a content item was posted to a social networking service by a first user of the social networking service;
identifying a first plurality of users of the social networking service that previously posted the content item to the social networking service;
determining, for each user of the first plurality of users and using a first trained machine learning model, a user engagement score in connection with the posting of the content item by the first user, wherein the user engagement score represents a first likelihood of increasing an engagement of a respective user with the social networking service and is based at least in part on:
an activity level of the respective user of the first plurality of users during a first time period;
and
a second likelihood that the respective user will engage with the social networking service based on the posting of the content item by the first user;
identifying a second plurality of users from the first plurality of users based at least in part on user engagement scores;
generating, for each user of the second plurality of users, a communication to be sent to each respective user;
transmitting the communication to the second plurality of users;
obtaining activity associated with the second plurality of users in response to the communication;
and
updating, based at least in part on the activity, the first trained machine learning model.

9 more elements

A computing system, comprising:

one or more processors;
and
a memory storing program instructions that when executed by the one or more processors, cause the one or more processors to at least:
determine that a content item was posted to a social networking service by a first user of the social networking service;
determine that at least a portion of the content item was re-posted to the social networking service by a second user of the social networking service;
determine, based at least in part on a first user history associated with the first user and using a first trained machine learning model, a first user engagement score associated with the first user and the re-posting of at least the portion of the content item by the second user, the first user engagement score being representative of a likelihood of increasing engagement of the first user with the social networking service;
determine that the first user engagement score exceeds an engagement score threshold;
generate, for the first user, a communication to be sent to the first user;
transmit the communication to the first user;
obtain activity associated with the first user in response to the communication;
and
update, based at least in part on the activity, the first trained machine learning model.

9 more elements

A computer-implemented method, comprising:

determining that a content item was posted to a social networking service by a first user of the social networking service;
determining that the content item was re-posted to the social networking service by a second user of the social networking service;
determining, using a first trained machine learning model, a first user engagement score associated with the first user and the re-posting of the content item, the first user engagement score being based at least in part on a user history associated with the first user and being representative of a likelihood of increasing engagement of the first user with the social networking service;
determining that the first user engagement score associated with the first user and the content item exceeds a threshold;
generating, for the first user, a communication to be sent to the first user;
transmitting the communication to the first user;
obtaining activity associated with the first user in response to the communication;
and
updating, based at least in part on the activity, the first trained machine learning model.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/347,005Filed 14 Jun 2021 · continuation
Priority: 7 Nov 2017
Published: US 2021/0304325 A130 Sep 2021
Granted: 13 Feb 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G06Q 10/40
Administration; Management: business processes related to social networking or social networking services
G06N 20/00
Machine learning
G06Q
Information and communication technology [ict] specially adapted for administrative, commercial, financial, managerial
G06N
AI and machine learning