US 10,949,480 B2Granted

Personalized per-member model in feed

AssigneeMicrosoft Technology Licensing, LLC

InventorsBoyi Chen, Yijie Wang, Timothy Paul Jurka, Ying Xuan

Life of this patent

Estimating the term…

Loading patent…

Abstract

In an example embodiment, a GLMix model is utilized that models viewers and actors of feed items. This allows for random effects of individual viewers and actors to be taken into account without introducing biases. Additionally, in an example embodiment, predictions/recommendations are made more accurate by using three models, which are then combined, instead of a single GLMix model. Each of these models has different granularities and dimensions. A global model may model the similarity between user attributes (e.g., from the member profile or activity history) and item attributes. A per-viewer model may model user attributes and activity history of actors on feed items. A per-actor model may model user attributes and activity history of the viewers of feed items. The per-actor model may therefore, rely on information regarding how and what type of viewers interacted with items acted on by the particular actor.

Claims20

Dependent claims

A system for rendering a feed in a graphical user interface of a computing device display viewed by a first user, comprising:

a non-transitory computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to:
for each of a plurality of potential feed items:
obtain a first set of features derived from attributes of the first user in a social networking service;
obtain a second set of features derived from attributes of a second user in the social networking service, the second user being an actor on the potential feed item;
obtain a third set of features derived from activity of the first user, with respect to a plurality of feed items in the social networking service;
obtain a fourth set of features derived from activity of the second user, with respect to a plurality of feed items in the social networking service;
input the first and second sets of features into a machine-learned global model, producing a first computer-based numerical estimate of expected engagement of the first user with the potential feed item;
input the first and third sets of features into a machine-learned per-actor model, producing a second computer-based numerical estimate of expected engagement of the first user with the potential feed item;
input the second and fourth sets of features into a machine-learned per-viewer model, producing a third computer-based numerical estimate of expected engagement of the first user with the potential feed item;
and
combine the first, second, and third computer-based numerical estimates to produce an estimate of a likelihood that the first user will engage in an activity with the potential feed item in the social networking service.

8 more elements

A computerized method for rendering a feed in a graphical user interface of a computing device display viewed by a first user comprising:

obtaining a first set of features derived from attributes of the first user in a social networking service;
obtaining a second set of features derived from attributes of a second user in the social networking service, the second user being an actor on the potential feed item;
obtaining a third set of features derived from activity of the first user, with respect to a plurality of feed items in the social networking service;
obtaining a fourth set of features derived from activity of the second user, with respect to a plurality of feed items in the social networking service;
inputting the first and second sets of features into a machine-learned global model, producing a first computer-based numerical estimate of expected engagement of the first user with the potential feed item;
inputting the first and third sets of features into a machine-learned per-actor model, producing a second computer-based numerical estimate of expected engagement of the first user with the potential feed item;
inputting the second and fourth sets of features into a machine-learned per-viewer model, producing a third computer-based numerical estimate of expected engagement of the first user with the potential feed item;
and
combining the first, second, and third computer-based numerical estimates to produce an estimate of a likelihood that the first user will engage in an activity with the potential feed item in the social networking service.

6 more elements

A non-transitory machine-readable storage medium comprising instructions which, when implemented by one or more machines;

cause the one or more machines to perform operations for rendering a feed in a graphical user interface of a computing device display viewed by a first user, the operations comprising:
obtaining a first set of features derived from attributes of the first user in a social networking service;
obtaining a second set of features derived from attributes of a second user in the social networking service, the second user being an actor on the potential feed item;
obtaining a third set of features derived from activity of the first user;
with respect to a plurality of feed items in the social networking service;
obtaining a fourth set of features derived from activity of the second user, with respect to a plurality of feed items in the social networking service;
inputting the first and second sets of features into a machine-learned global model, producing a first computer-based numerical estimate of expected engagement of the first user with the potential feed item;
inputting the first and third sets of features into a machine-learned per-actor model, producing a second computer-based numerical estimate of expected engagement of the first user with the potential feed item;
inputting the second and fourth sets of features into a machine-learned per-viewer model, producing a third computer-based numerical estimate of expected engagement of the first user with the potential feed item;
and
combining the first, second, and third computer-based numerical estimates to produce an estimate of a likelihood that the first user will engage in an activity with the potential feed item in the social networking service.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/900,219Filed 20 Feb 2018
Published: US 2019/0258741 A122 Aug 2019
Granted: 16 Mar 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

G06F 16/9536
Querying, e.g. by the use of web search engines: search customisation based on social or collaborative filtering
G06F 16/24578
With adaptation to user needs: using ranking
G06F 16/9535
Querying, e.g. by the use of web search engines: search customisation based on user profiles and personalisation
G06N 20/00
Machine learning