Recommendation engine apparatus and methods

Patent metadata

Field	Value
Publication number	US-11012749-B2
Application number	US-201916430279-A
Country	US
Kind code	B2
Filing date	Jun 3, 2019
Priority date	Mar 30, 2009
Publication date	May 18, 2021
Grant date	May 18, 2021

Abstract

Recommendation engine apparatus and associated methods provide content compiled from various sources and selected to match user preferences. In one embodiment, the recommendation apparatus comprises a headend entity; in another, it is co-located on a user's CPE. In one embodiment, the recommendation engine creates content records from content metadata for comparison to a user profile. The user profile is pre-programmed; however has the ability to dynamically shift toward a user's preferences as the user takes actions regarding content. Client applications are utilized to compile and present content; feedback mechanisms are utilized to enable “learning” from user activities to generate more precise recommendations as well as to “unlearn” stale preferences. Recommended content is displayed in the form of a playlist, or as a continuous stream on a virtual channel, or presented in an electronic program guide. A business rules “engine” useful in implementing operational or business goals is also disclosed.

First claim

What is claimed is:

1. A computerized method of recommending content targeted to a particular user in a content delivery network, said computerized method comprising:
receiving user action data relating to the particular user;
generating a plurality of data records regarding user actions associated with the particular user, each record relating at least one action of the particular user to an individual digitally rendered content element and based at least in part on the received user action data;
utilizing said plurality of data records to generate a first training data record, the first training data record comprising a first data set and a corresponding second data set;
updating said first training data record for subsequent ones of said user action data received relating to the individual digitally rendered content element;
based at least on the updating of the first training data record, algorithmically generating data representative of a user profile for the particular user, the data representative of the user profile comprising at least a portion of the first data set and a corresponding modified version of the second data set, the data representative of the user profile being configured for use by a computerized recommendation engine in generating one or more target content recommendations for the particular user; and
in accordance with at least a portion of the modified second data set, cause display of at least a portion of the generated one or more target content recommendations for the particular user via a personalized user interface, the personalized user interface personalized for the particular user.

2. The computerized method of claim 1 , wherein the personalized user interface is configured to at least render data associated with an electronic program guide (EPG) on a display device via the personalized user interface.

3. The computerized method of claim 1 , wherein the updating of said first training data record comprises generating a vector and combining the generated vector by a weighting factor, the weighting factor being determined based on at least a portion of the plurality of data records regarding user actions.

4. The computerized method of claim 1 , further comprising:
evaluating the individual digitally rendered content element against the data representative of the user profile to determine whether a similarity measure associated with the individual digitally rendered content element meets a prescribed threshold level; and
based on the similarity measure meeting the prescribed threshold level, adding the individual digitally rendered content element in a prioritized list to the particular user.

5. The computerized method of claim 4 , further comprising:
generating data representative of at least another user profile correlated to at least another user, the data representative of a user profile and the data representative of the at least another user profile corresponding to a particular client device; and
allocating respective weights to the user profile and the at least another user profile based at least on respective ones of the (i) plurality of data records regarding user actions associated with the particular user and (ii) plurality of data records regarding user actions associated with the at least another user.

6. The computerized method of claim 1 , further comprising:
identifying one or more secondary content comprising at least one contextual attribute;
comparing at least one contextual attribute of the individual digitally rendered content element with the at least one contextual attribute of the one or more secondary content to determine whether respective similarity measures associated with the one or more secondary content meets a prescribed threshold level; and
generating a list of secondary content having respective similarity measures that meet the prescribed threshold level.

7. The computerized method of claim 1 , further comprising:
evaluating the generated one or more target content recommendations with respect to a specified attribute associated therewith; and
based on the evaluating, restricting access, by the personalized user interface, to another portion of the generated one or more target content recommendations for the particular user.

8. A computerized network apparatus configured to track interactions of a user with one or more content elements in order to recommend additional content elements for delivery to the user via a streaming content delivery transport, the computerized network apparatus comprising:
digital processor apparatus;
a data interface in data communication with the digital processor apparatus and configured to transact data packets with a distribution network; and
storage apparatus in data communication with the digital processor apparatus and comprising at least one computer program, the at least one computer program configured to, when executed by the digital processor apparatus, cause the computerized network apparatus to:
receive first data relating to one or more first user interactions with the one or more content elements;
generate a first data structure comprising first training data, the generation of the first data structure based at least on the received first data;
use at least the generated first data structure to generate a first recommendation for additional content elements;
receive second data relating to one or more second user interactions with the one or more content elements;
generate an updated version of the first data structure based at least on the received second data, the generation of the updated version comprising a combination of the first data structure with a second data structure that is representative of user profile data, the updated first data structure comprising second training data;
use at least the generated updated first data structure to adjust the first recommendation, the adjustment comprising a change to the additional content elements of the first recommendation; and
cause streaming delivery of at least one of the additional content elements of the adjusted first recommendation to the user via the streaming content delivery transport.

9. The computerized network apparatus of claim 8 , wherein said first data structure, the updated first data structure, and the second data structure each comprises an m×n vector.

10. Computerized apparatus configured to recommend content to a user of a content distribution network and comprising:
a data interface for receiving data relating to user action;
a storage apparatus adapted to store a plurality of records regarding one or more actions of the user, each of the plurality of records relating at least one of the one or more actions of the user to an individual content element; and
a digital processor apparatus in data communication with the storage apparatus and adapted to run at least one computer program thereon, said at least one computer program configured to, when executed:
utilize data representative of at least a portion of said plurality of records to generate a first training record, the first training record configured for identifying at least one recommended content element, the generation of the first training recording comprising (i) generation of a content record for each of said individual content element to which said one or more user actions relate, said content record comprising a vector having an identical number of columns and rows as a user profile associated with said one or more user actions; (ii) association of said one or more user actions with a weighting factor; and (iii) combination of said vector with said weighting factor;
update said first training record for subsequent ones of said received data re

Assignees

• Time Warner Cable Entpr Llc

Inventors

• Kimble David
• Chin Fee Ling

Classifications

• H04N21/44224

  Monitoring of user activity on external systems, e.g. Internet browsing · CPC title

• H04N21/4667

  Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections · CPC title

• H04N21/4826

  using recommendation lists, e.g. of programmes or channels sorted out according to their score · CPC title

• H04N21/4668 Primary

  for recommending content, e.g. movies · CPC title

• H04N21/2668

  Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles {(information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063)} · CPC title