Adjusting heavy users' affinity for heavy user entity-pairs in a social network

Patent metadata

Field	Value
Publication number	US-10673965-B2
Application number	US-201514839531-A
Country	US
Kind code	B2
Filing date	Aug 28, 2015
Priority date	Aug 28, 2015
Publication date	Jun 2, 2020
Grant date	Jun 2, 2020

Abstract

A system and method of adjusting an affinity score between an entity pair in a social network is disclosed. The method may include determining, with a processor, whether a first member of the entity pair is a heavy user member. The method further includes if the first member is the heavy user member, determining, with the processor, an affinity adjustment factor between the first member and the second member, and adjusting, with the processor, the affinity score between the first member and the second member of the entity pair in accordance with the adjustment factor to determine an adjusted affinity score. The method may include determining, with the processor, whether a number of interactions on content items indicates that the first member is the heavy user member. The second member is associated with a content item that is being considered for display to the first member.

First claim

What is claimed is:

1. A method comprising:
calculating a first affinity score for a first pair of members of an online network, the first pair of members including a first member and a second member of the online network, the first affinity score indicating an estimated affinity level between the first member and the second member;
calculating a second affinity score for a second pair of members of the online network, the second pair of members including the first member and a third member of the online network, the second affinity score indicating an estimated affinity level between the first member and the third member;
determining, based on activity data of the second member, a first number of content items that the second member has interacted with during a predetermined period of time;
determining, based on activity data of the third member, a second number of content items that the third member has interacted with during the predetermined period of time;
determining that the first number meets or exceeds a threshold number;
determining that the second number does not meet or exceed the threshold number;
in response to determining that the first number meets or exceeds the threshold number, increasing the first affinity score based on an affinity adjustment factor determined for the first pair or members, yielding a first adjusted affinity score, wherein the second affinity score is not adjusted as a result of the second number not meeting or exceeding the threshold number; and
ranking a set of content items posted to the online service for presentation to the first user, yielding a ranking, wherein the set of content items includes at least a first content item posted to the online network by the second member and a second content item posted to the online network by the third member, the first content item being ranked based on the first adjusted affinity score and the second content item is ranked based on the second affinity score;
determining, based on the ranking, an order in which to present the set of content items to the first user, yielding a determined order of the set of content items, wherein the first content item and the second content item are not included in either the content items that the second member has interacted with during the predetermined period of time nor the content items that the third member has interacted with during the predetermined period of time;
causing presentation of the first content item and the second content item to the first user based on the determined order of the set of content items, the first content item and the second content item presented to the first user within a user interface displayed on a display of a client device associated with the first user.

2. The method of claim 1 , wherein determining that the first number meets or exceeds the threshold number indicates that the first member is a heavy user member.

3. The method of claim 1 , herein determining that the first number meets or exceeds the threshold number comprises:
determining, based on the first number, a percentile of interactions of the second member relative to other members of the online network; and
determining the percentile of interactions meets or exceeds the threshold number.

4. The method of claim 1 , further comprising:
determining the affinity adjustment factor based on a number of interactions the first member performed with content items associated with the second member divided by a first expected number of interactions the first member would perform with content items associated with the second member multiplied with a second number of interactions the first member performed with content items associated with all members divided by a second expected number of second interactions the first member would perform with the content items associated with all members.

5. The method of claim 4 , wherein the first expected number of interactions the first member would perform with content items associated with the second member is determined by summing up a probability of interaction for each interaction associated with the second member.

6. The method of claim 1 , wherein increasing the first affinity score comprises:
multiplying the first affinity score by the affinity adjustment factor to determine the adjusted affinity score.

7. The method of claim 1 , wherein the estimated affinity level between the first member and the second member represents a likelihood that the first member will interact with content items where the second member either generated the content items or is a subject of the content items.

8. The method of claim 1 , wherein the online network includes a plurality of members including the first member and the second member, and the plurality of members are connected to other ones of the plurality of members via connections in the online network.

9. The method of claim 1 , wherein increasing the first affinity score comprises:
multiplying the first affinity score with the affinity adjustment factor.

10. The method of claim 1 , wherein ranking the set of content items comprises:
determining, based on the first adjusted affinity score and the second affinity score, a first likelihood value indicating a likelihood of the first user interacting with the first content item posted by the second user, and a second likelihood value indicating a likelihood of the first user interacting with the second content item posted by the third user;
ranking the first content item and the second based on the first likelihood value and the second likelihood value.

11. A system comprising:
one or more computer processors; and
one or more computer-readable mediums storing instructions that, when executed by the one or more computer processors, cause the system to perform operations comprising:
calculating a first affinity score for a first pair of members of an online network, the first pair of members including a first member and a second member of the online network, the first affinity score indicating an estimated affinity level between the first member and the second member;
calculating a second affinity score for a second pair of members of the online network, the second pair of members including the first member and a third member of the online network, the second affinity score indicating an estimated affinity level between the first member and the third member;
determining, based on activity data of the second member a first number of content items that the second member has interacted with during a predetermined period of time;
determining, based on activity data of the third member, a second number of content items that the third member has interacted with during the predetermined period of time;
determining that the first number meets or exceeds a threshold number;
determining that the second number does not meet or exceed the threshold number;
in response to determining that the first number meets or exceeds the threshold number, increasing the first affinity score based on an affinity adjustment factor determined for the first pair or members, yielding a first adjusted affinity score, wherein the second affinity score is not adjusted as a result of the second number not meeting or exceeding the threshold number; and
ranking a set of content items posted to the online service for presentation to the first user, yielding a ranking, wherein the set of content items includes at least a first content item posted to the online network by the second member and a second content item posted to the online network by the third member, the first content item being ranked based on the first adjusted affinity score and the second content item is r

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Obukhov Mikhail
• He Qi
• Chen Bee-Chung
• Agarwal Deepak

Classifications

• H04L67/20

  Electricity · mapped topic

• H04L67/306

  User profiles · CPC title

• H04L51/32

  Electricity · mapped topic

• H04L67/22 Primary

  Electricity · mapped topic

• G06Q50/01

  Physics · mapped topic