Methods, systems, and media for presenting recommended content based on social cues

Patent metadata

Field	Value
Publication number	US-9811521-B2
Application number	US-201314042335-A
Country	US
Kind code	B2
Filing date	Sep 30, 2013
Priority date	Sep 30, 2013
Publication date	Nov 7, 2017
Grant date	Nov 7, 2017

Abstract

Methods, systems, and media for presenting recommended content based on social cues are provided. In accordance with some embodiments, a method for presenting recommended content is provided comprising: receiving a query associated with a user; generating a list of relevant media content items based on the query; selecting items for presentation to the user based on social relevance scores based on social connections of the user that have consumed a relevant item and contextual relevance scores for each item; causing the selected items to be presented to the user; and indicating that a particular item was consumed by a particular social connection.

First claim

What is claimed is:

1. A method for presenting recommended content, the method comprising:
receiving, using a hardware processor, a query associated with a user, wherein the query indicates a media content item currently being presented on a user device associated with the user;
generating a list of relevant media content items from a database of media content items based on the query;
selecting at least one media content item from the list of relevant media content items for presentation to the user based at least in part on a social relevance score for each media content item and a contextual relevance score for each media content item, wherein the selecting further comprises:
identifying one or more other users that are social connections of the user based on various user information of the user that is indicative of social connection with the other users;
determining an influence score for each social connection based at least in part on social links between the user and the social connection;
determining, for each social connection, which media content items of the relevant media content items have been consumed by that social connection;
determining, for each relevant media content item consumed by a particular social connection, an engagement score indicative of a degree to which that social connection enjoyed the media content item;
determining the social relevance score for each media content item in the list of relevant media content items based at least in part on a combination of the influence score and the engagement score associated with each social connection that was determined to have consumed the media content item;
determining a first weight associated with the social relevance score and a second weight associated with the contextual relevance score based on a relative importance of the social relevance score and the contextual relevance score, wherein the relative importance of the social relevance score and the contextual relevance score is based on an origin of the received query, and wherein the contextual relevance score for each media content item indicates a similarity of each media content item to the media content item currently being presented on the user device; and
ranking the media content items in the list of relevant media content items based on the social relevance score for each media content item weighted by the first weight and the contextual relevance score for each media content item weighted by the second weight, wherein the at least one selected media content item is selected based on the ranking;

causing the at least one selected media content item to be presented to the user as a selectable media content item; and
causing an indication that a particular media content item of the presented media content items was consumed by a particular social connection to be presented in association with the particular media content item based at least in part on the engagement score of the particular social connection for the particular media content item.

2. The method of claim 1 , wherein the query is received as a search query specified by the user.

3. The method of claim 1 , wherein the query is automatically generated based on metadata of a media content item consumed by the user.

4. The method of claim 1 , wherein user information of the user that is indicative of social connection with the other users includes at least one of the following: the existence of reciprocal links in a social network between the user and the other user; information indicating that the user is a follower of the other user; and information indicating that the user and the other user have exchanged electronic messages.

5. The method of claim 1 , wherein social links between the user and the social connection include at least one of: a designation of the social connection as a particular type of social connection by the user; a frequency of communication between the user and the social connection; a response time to communications from the social connection; and a frequency of interaction with items shared by the social connection on a social networking service on which the user is connected to the social connection.

6. The method of claim 1 , wherein the engagement score is based at least in part on a percentage of the item of content consumed by the social contact.

7. The method of claim 1 , wherein the media content item is a video.

8. A system for presenting recommended content, the system comprising:
a hardware processor that is programmed to:
receive a query associated with a user, wherein the query indicates a media content item currently being presented on a user device associated with the user;
generate a list of relevant media content items from a database of media content items based on the query;
select at least one media content item from the list of relevant media content items for presentation to the user based at least in part on a social relevance score for each media content item and a contextual relevance score for each media content item, wherein the selecting further comprises:
identify one or more other users that are social connections of the user based on various user information of the user that is indicative of social connection with the other users;
determine an influence score for each social connection based at least in part on social links between the user and the social connection;
determine, for each social connection, which media content items of the relevant media content items have been consumed by that social connection;
determine, for each relevant media content item consumed by a particular social connection, an engagement score indicative of a degree to which that social connection enjoyed the media content item;
determine the social relevance score for each media content item in the list of relevant media content items based at least in part on a combination of the influence score and the engagement score associated with each social connection that was determined to have consumed the media content item;
determine a first weight associated with the social relevance score and a second weight associated with the contextual relevance score based on a relative importance of the social relevance score and the contextual relevance score, wherein the relative importance of the social relevance score and the contextual relevance score is based on an origin of the received query, and wherein the contextual relevance score for each media content item indicates a similarity of each media content item to the media content item currently being presented on the user device; and
rank the media content items in the list of relevant media content items based on the social relevance score for each media content item weighted by the first weight and the contextual relevance score for each media content item weighted by the second weight, wherein the at least one selected media content item is selected based on the ranking;

cause the at least one selected media content item to be presented to the user as a selectable media content item; and
cause an indication that a particular media content item of the presented media content items was consumed by a particular social connection to be presented in association with the particular media content item based at least in part on the engagement score of the particular social connection for the particular media content item.

9. The system of claim 8 , wherein the query is received as a search query specified by the user.

10. The system of claim 8 , wherein the query is automatically generated based on metadata of a media content item consumed by the user.

11. The system of claim 8 , wherein user informatio

Assignees

• Google Inc

Inventors

• Sanio Jason Robert Richard
• Freund Martin Brandt

Classifications

• G06F16/48 Primary

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F17/30038 Primary

  Physics · mapped topic