GRAPH BASED CONTENT BROWSING AND DISCOVERY

Number: 20180285478
Published: 2018-10-04
Filed: 2017-04-03
Assignee: Disney Enterprises, Inc.
Inventors: WRIGHT; ANDREW J. et al.
CPC: G06F16/248; G06F16/9024; G06F16/24578
Verdict: Set aside content browsing/discovery, recommendation-adjacent
Source: Google Patents · FreePatentsOnline

Abstract

Systems and methods for using graph databases to make digital content recommendations are described. A graph database may be associated with tagged digital content. The graph database may include a node for each content tag and edges identifying a relationship between nodes. When a user accesses or searches a digital content item, the graph database may be traversed to identify and present related content recommendations to the user based on the traversed nodes. Node graph traversal may initiate from a root node associated with a tag of content item being presented to a user. Nodes may be searched based on their proximity to the root node as determined by edge connections of the graph. Initially searched nodes may include nodes in the graph database directly connected by edges to the root node. Subsequently searched nodes may include nodes one edge connected removed from the root node, and so forth.

Background

TECHNICAL FIELD

The present disclosure relates generally to making digital content recommendations, and more particularly, to using graph databases to make digital content recommendations.DESCRIPTION OF THE RELATED ART

The volume of digital content that users have access to through online services is increasing exponentially. In July 2015, 400 hours of new content was being uploaded to YouTube® every minute. In March 2016, Netflix® had over 4000 movies and 1100 TV shows on offer. This just illustrates some examples of the rapid growth of video content. When images, new articles, social posts, and other types of content are considered, the growing volume of digital content is vast. In such an environment, one of the challenges is providing a means for users navigate this vast array of content and discover new content.BRIEF SUMMARY OF THE DISCLOSURE

According to various embodiments, systems and methods are described for using graph databases to make digital content recommendations. Prior to making digital content recommendations, a graph database may be created to provide a mapping of the relationships of the content tags of media content files. The graph database may be created by ingesting media content files, tagging the media content file with one or more tags, associating each tag with a node, and connecting the nodes with edges that define the relationship between nodes.

In one embodiment, a method of making content recommendations may include: rec

Claims

1. A method of making content recommendations, the method comprising: receiving data identifying a content item being presented to a user; in response to receiving the data identifying the content item being presented to the user, selecting a node from a graph database to begin a search for related content recommendations, wherein the selected node is associated with a tag of the content item begin presented; searching for nodes in the graph database directly connected by edges to the selected node; and using at least the searched nodes directly connected by edges to the selected node to identify a set of content related to the content item being presented to the user, wherein each of the searched nodes is associated with a tag of a digital content item; and presenting related content recommendations to the user based on the identified set of related content. 12. A system, comprising: a graph database; and a non-transitory computer-readable medium operatively coupled to a processor and having instructions stored thereon that, when executed by the processor, causes the system to: receive data identifying a content item being presented to a user; in response to receiving the data identifying the content item being presented to the user, select a node from the graph database to begin a search for related content recommendations, wherein the selected node is associated with a tag of the content item begin presented to the user; search for nodes in the graph database directly connected by edges to the selected node; and use at least the searched nodes directly connected by edges to the selected node to identify a set of content related to the content item being presented to the user, wherein each of the searched nodes is associated with a tag of a content item; and display related content recommendations to the user based on the identified set of related content.