Using cross-site relationships to generate recommendations
First Claim
1. A system for generating recommendations, comprising:
- a processor to execute modules, including;
a communications module to receive a message requesting recommendations via a network, the message specifying a label identifying an item, a predicate describing a type of the item and at least one constraint on one or more items to be returned as recommendations;
a canonicalization module to generate canonicalized representations of relationships by associating each component of the relationship data with a unique identifier (ID), the relationship data including a label component identifying an item, a predicate describing a type of the item and an intent describing an action that established the relationship;
a relationship storage module for storing the canonicalized representations in a memory; and
a recommendation generation module for generating recommendations based on the canonicalized representations of the relationships stored in the memory by performing collaborative filtering to identify a set of items related to the items identified in the message requesting recommendations and satisfying the at least one constraint.
12 Assignments
0 Petitions
Accused Products
Abstract
A relationship server tracks end-user interactions across multiple web sites and generates recommendations. The web sites observe relationships established by end-user interactions. If end-users provide the same personally identifiable information to multiple web sites, the sites generate the same unique identifier for those end-users. The web sites send messages to the relationship server that reference the end-users using the identifiers and describe the relationships observed for the end-users. The relationship server receives messages from multiple web sites and canonicalizes them to produce an efficient representation of the relationships. Upon receiving a message requesting a recommendation based on an item, the relationship server performs collaborative filtering using the relationship data to identify a list of items to recommend. The relationship server sends the recommendations to the requesting entity and the recommendations are presented to the end-user.
-
Citations
25 Claims
-
1. A system for generating recommendations, comprising:
-
a processor to execute modules, including; a communications module to receive a message requesting recommendations via a network, the message specifying a label identifying an item, a predicate describing a type of the item and at least one constraint on one or more items to be returned as recommendations; a canonicalization module to generate canonicalized representations of relationships by associating each component of the relationship data with a unique identifier (ID), the relationship data including a label component identifying an item, a predicate describing a type of the item and an intent describing an action that established the relationship; a relationship storage module for storing the canonicalized representations in a memory; and a recommendation generation module for generating recommendations based on the canonicalized representations of the relationships stored in the memory by performing collaborative filtering to identify a set of items related to the items identified in the message requesting recommendations and satisfying the at least one constraint. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A system for providing recommendations of items to an end-user comprising:
-
a processor to execute modules, including; a relationship observation module for observing relationships established by the end-user through interactions with a web site; a communications module for sending messages having relationship data describing the observed relationships to a relationship server via a computer network and to receive a message requesting recommendations for the end-user based at least in part on observed relationships described by messages sent by a plurality of web sites, the message specifying a label identifying an item, a predicate describing a type of the item and at least one constraint on one or more items to be returned as recommendations; and a recommendations module to perform collaborative filtering to identify a set of items related to the items identified in the message requesting recommendations and satisfying the at least one constraint. - View Dependent Claims (8, 9, 10, 11, 12, 13, 14, 15)
-
-
16. A computer generated method of providing recommendations, comprising:
-
receiving a message requesting recommendations, the message specifying a label identifying an item, a predicate describing a type of the item and at least one constraint on one or more items to be returned as recommendations; establishing a set of relationships by associating each component of relationship data with a unique identifier (ID), the relationship data including a label component identifying an item, a predicate describing a type of the item and an intent describing an action that established the relationship; generating recommendations of items by performing collaborative filtering to identify a set of items related to the items identified in the message requesting recommendations and satisfying the at least one constraint; and providing the recommendations to the an end-user. - View Dependent Claims (17)
-
-
18. A computer program product having a non-transitory computer-readable medium having computer program instructions embodied therein for providing recommendations of items to an end-user, comprising:
-
a communications module for sending messages having relationship data describing the observed relationships to a relationship server via a computer network and to receive a message requesting recommendations for the end-user based at least in part on observed relationships described by messages sent by a plurality of web sites, the message specifying a label identifying an item, a predicate describing a type of the item and at least one constraint on one or more items to be returned as recommendations; and a recommendations module to perform collaborative filtering to identify a set of items related to the items identified in the message requesting recommendations and satisfying the at least one constraint. - View Dependent Claims (19, 20, 21, 22, 23, 24, 25)
-
Specification