RECOMMENDATION ENGINE APPARATUS AND METHODS

• US 20160212484A1
• Filed: 12/14/2015
• Published: 07/21/2016
• Est. Priority Date: 03/30/2009
• Status: Active Grant

• Current Assignee: Time Warner Cable Enterprises LLC (Charter Communications Incorporated)
• Original Assignee: Time Warner Cable Enterprises LLC (Charter Communications Incorporated)
• Inventors: KIMBLE, DAVID, Chin, Fee Ling
• Granted Patent: US 10,313,755 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2668 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 Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38
• CPC Class Codes: H04N 7/17318 Direct or substantially direct transmission and handling of requests

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.

Claims

1-45. -45. (canceled)

46. A user action tracking apparatus, said user action tracking apparatus configured for data communication with at least a computer program configured to recommend content to a user of a content delivery network, said user action tracking apparatus comprising:

a storage apparatus configured to store a plurality of records regarding user actions, each record relating at least one action of a user to an individual content element; and

a digital processor apparatus in data communication with the storage apparatus and configured to run a computer program thereon, said computer program configured to, when executed on said digital processor apparatus;

receive user action data from a content delivery network;

generate said plurality of data records regarding user actions based at least on said user action data;

utilize said plurality of data records to generate a first training data record; and

update said first training data record for subsequent ones of said user action data received.

47. The tracking apparatus of claim 46, wherein said content delivery network comprised a managed content delivery network having at least one headend and a plurality of subscribers, and said tracking apparatus comprises part of the headend of the managed content delivery network, said user action data relating to at least one of said plurality of subscribers.

48. The tracking apparatus of claim 47, wherein said plurality of data records regarding user actions comprise at least:

(i) data regarding one or more digitally rendered content elements to which said user action relates, (ii) data relating to a chronological reference, and (iii) data relating to a description or descriptor of said user action.

49. The tracking apparatus of claim 46, wherein said generation of said first training data record comprises:

generation of a content record for each of said individual content element to which said individual user actions relate, said content record comprising a vector having an identical number of columns and rows as a user profile associated with said user action;

association of said description of said user action associated with said individual content element in said record regarding user actions with a weighting factor; and

multiplication of said content record vector by said weighting factor.

50. The tracking apparatus of claim 49, wherein said update of said first training record comprises:

association of said description of said user action associated with said individual content element in said record regarding user actions with a weighting factor; and

multiplication of said first training record by said weighting factor to arrive at an updated training data record.

51. The tracking apparatus of claim 46, wherein said tracking apparatus is further configured to distribute said updated training data record to said computer program configured to recommend content to a user for use thereby, said computer program configured to recommend content also configured to utilize said updated training data record without further transformation thereof.

52. The tracking apparatus of claim 46, wherein said apparatus is further configured to:

receive at least one user profile, said user profile represented as a vector; and

utilize said updated training data record to update said user profile by at least an addition of said updated training data record to said profile;

wherein said user profile and said updated training data record comprise vectors having an identical number of rows and columns as one another.

53. A method of substantially automatically recommending content targeted to a particular user in a content delivery network, said method comprising:

receiving user action data relating to the particular user from an entity of the content delivery network;

generating a plurality of data records regarding user actions, 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 configured for use by a computerized recommendation engine in generating one or more targeted content recommendations for the user; and

updating said first training data record for subsequent ones of said user action data received relating to the digitally rendered content element.

54. The method of claim 53, wherein said content delivery network comprised a managed content delivery network having at least one headend and a plurality of subscribers, said user action data relates to at least one of said plurality of subscribers, and said acts of generating, utilizing and updating are performed at a computerized entity of the headend of the managed content delivery network.

55. The method of claim 53, wherein said plurality of data records regarding user actions comprise at least:

(i) data identifying content to which a given user action relates, (ii) data relating to a chronological reference, and (iii) data relating to a description or descriptor of said user action.

56. The method of claim 53, wherein said generating said first training data record comprises:

generating a content data record for each of said individual content element to which said individual user actions relate, said content data record comprising a vector having an identical number of columns and rows which a user profile associated with said user action possesses;

associating said description of said user action associated with said individual content element in said record regarding user actions with a weighting factor; and

multiplying said content data record vector by said weighting factor.

57. The method of claim 56, wherein said updating said first training data record comprises:

associating said description of said user action associated with said individual content in said first training data record regarding user actions with a weighting factor; and

multiplying said first training data record by said weighting factor to arrive at an updated training data record.

58. The method of claim 53, further comprising:

receiving at least one user profile, said user profile represented as a vector; and

utilizing said updated training data record to update said user profile by an addition of said training data record to said profile;

wherein said user profile and said training data record comprise vectors having an identical number of rows and columns as one another.

59. A computer readable apparatus comprising a storage medium, the storage medium comprising at least one computer program having a plurality of instructions, said plurality of instructions which are configured to, when executed on a digital processing apparatus:

receive user action data from a user device associated with a content delivery network;

generate a plurality of records regarding user actions, each record derived at least in part from the received user action data and relating at least one action of the user taken via the user device and relating to an individual content element delivered to the user device via the network;

utilize said plurality of records to generate at least one training data record; and

based at least upon subsequent receipt of additional user action data from the user device relating to the individual content element, update said at least one training data record so as to maintain said at least one training data current for said user and said individual content element.

60. The computer readable apparatus of claim 59, wherein said plurality of instructions are further configured to, when executed on the digital processing apparatus:

receive further user action data from the user device relating to another content element;

generate at least one record regarding one or more user actions, the at least one record derived at least in part from the received further user action data and relating at least one action of the user taken via the user device and relating to the another content element delivered to the user device via the network;

identify at least one relationship between the another content element and the individual content element; and

merge at least a portion of the at least one record with the plurality of records.

61. The computer readable apparatus of claim 59, wherein the received user action data comprises data relating to one or more implicit user behaviors, and the method further comprises, based at least on the received user action data, generating data relating to at least one inferred user behavior, the inferred user behavior being inferred from the implicit behavior data.

62. The computer readable apparatus of claim 61, wherein said data relating to one or more implicit user behaviors comprises data indicating that a user tunes away from advertising content, and the inferred user behavior comprises disinterest in the advertising content.

63. The computer readable apparatus of claim 61, wherein said data relating to one or more implicit user behaviors comprises data indicating that a user fails to tune away from the individual content element during a prescribed period, and the inferred user behavior comprises at least one of (i) interest in the content element, and/or (ii) lack of disinterest in the content element.