Method and system for providing personalized contents

• US 8,856,845 B2
• Filed: 12/21/2012
• Issued: 10/07/2014
• Est. Priority Date: 12/21/2012
• Status: Active Grant

• Current Assignee: TCL Research America, Inc. (TCL Technology Group Corp.)
• Original Assignee: TCL Research America, Inc. (TCL Technology Group Corp.)
• Inventors: Wang, Haohong
• Primary Examiner(s): Featherstone, Mark D
• Assistant Examiner(s): Huang, Jen-Shi
• Application Number:
  US13/726,001
• Publication Number:
  US 20140181878A1
• Time in Patent Office: 655 Days
• Field of Search: 725 9- 11, 725/15, 725/34, 725/46
• US Class Current: 725/87
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/44222 Analytics of user selections, e.g. selection of programs or purchase activity monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies

Abstract

A method is provided for a personalized content delivery system. The method includes detecting a viewing activity of at least one user of a content-presentation device capable of presenting multiple programs in one or more channels, and determining a plurality of user identities of the at least one user. The method also includes discovering available video contents for the at least one user based on the plurality of user identities, and determining personalized video contents for the at least one user by merging the plurality of user identities. Further, the method includes recommending the determined personalized video contents to the at least one user, and delivering the recommended personalized video contents to the at least one user such that the personalized video contents are presented on the content-presentation device.

Claims

1. A method for a personalized content delivery system, comprising:

detecting a viewing activity on a content-presentation device capable of presenting multiple programs in one or more channels;

determining a plurality of user identities based on a plurality of separate user identity determining means, including at least a first user identity based on a wearable device of an individual user, a second user identity based on viewing history of the plurality of user identities, and a third identity determined by a usage of a remote control of the content-presentation device, wherein the first user identity is determined by a communication between the wearable device and the content-presentation device, and the second user identity is determined by the viewing history of the multiple programs in one or more channels;

merging the plurality of user identities using a statistical algorithm to determine a target user from the plurality of user identities;

discovering available video contents for the target user;

determining personalized video contents for recommendation to the target user based on the available video contents;

recommending the determined personalized video contents to the target user; and

delivering the recommended personalized video contents to the target user such that the personalized video contents are presented on the content-presentation device,

wherein merging the plurality of user identities further includes;

determining function between the multiple programs and users having wearable devices by, provided that P={p₁, p₂, . . . p_n} represents the multiple programs, n is a natural number, and U={u₁, u₂, . . . u_s} represents the users having wearable devices, s is a natural number, setting T(P, U) to represent the function between P and U;

determining function between the multiple programs and users using the smart remote control by, provided that V={v₁, v₂, . . . v_t} represents the users using the smart remote control, and t is a natural number, setting T(P, V) to represent the function between P and V;

merging the function between the multiple programs and users having wearable devices and the function between the multiple programs and users using the smart remote control, based on the viewing history of all users, to determine the target user as a user having most similarity between the users having wearable devices and the users using the smart remote control by;

generating a merged user set W={w₁, w₂, . . . w_r} that W belongs to U+V, wherein r is a natural number; and

finding a pair of {u_i, v_j} that map to the same user in W such that the same user is determined as the target user, wherein i and j are natural numbers.

2. The method according to claim 1, further including:

obtaining user input from a user after detecting the viewing activity.

3. The method according to claim 1, wherein discovering available video contents further includes:

discovering a first type of contents available for general users;

discovering a second type of contents available based on a subscription of the target user; and

generating a content pool including the first type of contents and the second type of contents for the target user.

4. The method according to claim 1, wherein delivering the recommended personalized video contents further includes:

delivering the recommended personalized video contents to the target user such that the personalized video contents are presented on the content-presentation device on a single dedicated channel.

5. The method according to claim 1, further including:

detecting a video streaming quality condition; and

feeding back the detected video streaming quality condition to configure the delivering the recommended personalized video contents.

6. A personalized content delivery system, comprising:

a viewer discovery module to;

detect a viewing activity on a content-presentation device capable of presenting multiple programs in one or more channels,

determine a plurality of user identities based on a plurality of separate user identity determining means, including at least a first user identity based on a wearable device of an individual user, a second user identity based on viewing history of the plurality of user identities, and a third identity determined by a usage of a remote control of the content-presentation device, wherein the first user identity is determined by a communication between the wearable device and the content-presentation device, and the second user identity is determined by the viewing history of the multiple programs in one or more channels, and

merge the plurality of user identities using a statistical algorithm to determine a target user from the plurality of user identities by applying respective weights on the plurality of separate user identity determining means;

a streaming source discovery module to discover available video contents for the target user,

a recommendation engine to determine personalized video contents for recommendation to the target user based on the available video contents, and to recommend the determined personalized video contents to the target user; and

a video stream renderer to deliver the recommended personalized video contents to the target user such that the personalized video contents are presented on the content-presentation device;

wherein, to merge the plurality of user identities, the viewer discovery module is further to;

determine function between the multiple programs and users having wearable devices by, provided that P={p₁, p₂, . . . p_n} represents the multiple programs, n is a natural number, and U={u₁, u₂, . . . u_s} represents the users having wearable devices, s is a natural number, setting T(P, U) to represent the function between P and U;

determine function between the multiple programs and users using the smart remote control by, provided that V={v₁, v₂, . . . v_t} represents the users using the smart remote control, and t is a natural number, setting T(P, V) to represent the function between P and V; and

merge the function between the multiple programs and users having wearable devices and the function between the multiple programs and users using the smart remote control, based on the viewing history of all users, to determine the target user as a user having most similarity between the users having wearable devices and the users using the smart remote control by;

generating a merged user set W={w₁, w₂, . . . w_r} that W belongs to U+V, wherein r is a natural number; and

finding a pair of {u_i, v_j} that map to the same user in W such that the same user is determined as the target user, wherein i and j are natural numbers.

7. The personalized content delivery system according to claim 6, further including:

a user interaction module configured to obtain user input from a user after detecting the viewing activity.

8. The personalized content delivery system according to claim 6, wherein the streaming source discovery module is further to:

discover a first type of contents available for general users;

discover a second type of contents available based on a subscription of the target user; and

generate a content pool including the first type of contents and the second type of contents for the target user.

9. The personalized content delivery system according to claim 6, wherein the video stream renderer is further to:

delivering the recommended personalized video contents to the target user such that the personalized video contents are presented on the content-presentation device on a single dedicated channel.

10. The personalized content delivery system according to claim 6, wherein the video stream renderer is further to:

detect a video streaming quality condition; and

feed back the detected video streaming quality condition to configure the delivering the recommended personalized video contents.