Method and system for recommending content

• US 7,434,244 B2
• Filed: 08/23/2004
• Issued: 10/07/2008
• Est. Priority Date: 08/28/2003
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Shin, Hyo-seop, Popov, Andrei Vladimirovich
• Primary Examiner(s): KIM, CHONG HWA
• Application Number:
  US10/922,847
• Publication Number:
  US 20050076365A1
• Time in Patent Office: 1,506 Days
• Field of Search: 725/34
• US Class Current: 725/34
• CPC Class Codes: H04N 21/44213 Monitoring of end-user related data arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; 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 21/454 Content or additional data filtering, e.g. blocking advertisements
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

Provided are a method and system for recommending content. The method and system enable a user to be given recommendations of contents similar to what he/she likes. The method for recommending content includes creating a user profile according to a predetermined model based on a user'"'"'s reaction to the content, obtaining content features from one or more data sources, and creating a list of recommended contents according to a predetermined process based on the user profile and the content features. The system for recommending content includes a user profiling module that creates user profiles according to a predetermined model based on a user'"'"'s reaction to the content, a digital television module that obtains content metadata from one or more data sources, and a content rating module that creates a list of recommended contents based on the user profile and the content metadata received from the user profiling module and the digital television module. The user can be given recommendations of contents similar to what he/she likes.

Claims

1. A method for recommending content, comprising:

creating a user profile according to a predetermined model based on a user reaction to the content, wherein content fields are defined for specific content;

obtaining content features from one or more data sources; and

creating a list of recommended contents according to a predetermined process based on the user profile and the content features,

wherein the creating the user profile comprises defining user behaviors for each of the content fields, applying a different weight to each of the user behaviors, and calculating a content rating for the relevant content according to a predetermined method, and

wherein the content rating R is;

$R=\frac{\underset{i=1}{\overset{n}{\sum <br><br>}}<br><br>W_i}{T}$

wherein W is a weight for each behavior, n is the number of behaviors observed in the specific content, and T is a length of time during which a content item is run.

2. The method of claim 1, wherein in the obtaining content features, the one or more data sources comprise at least one of Advanced Television Systems Committee (ATSC) Program and System Information Protocol (PSIP) metadata and TV-Anytime metadata.

3. The method of claim 1, wherein the creating the list of recommended contents comprises calculating a content rating for each entity in a predetermined hierarchical classification structure using a content rating obtained from the user profile and the content features according to a predetermined calculation method and creating the list of recommended contents that contains contents with ratings exceeding a predetermined value.

4. A method for recommending content, comprising:

creating a user profile according to a predetermined model based on a user reaction to the content,

obtaining content features from one or more data sources;

creating a list of recommended contents according to a predetermined process based on the user profile and the content features, wherein

the creating the list of recommended contents comprises calculating a content rating for each entity in a predetermined hierarchical classification structure using a content rating obtained from the user profile and the content features according to a predetermined calculation methods and creating the list of recommended contents that contains contents with ratings exceeding a predetermined value, wherein

the predetermined calculation method is used to obtain an associative value of each

$\mathrm{entity}=\frac{n}{\frac{m}{N}+N}$

based on the content rating obtained from the user profile and the content features wherein N denotes the total number of levels in a given hierarchical structure, n denotes the level of a parent category in the overall hierarchical structure, and m denotes the depth from a parent category to a child category, and a content rating is obtained for each entity using the associative value obtained.

5. A computer system having a processor and memory under control of the processor, the memory storing instruction modules adapted to enable a processor of the computer to perform operations, the modules comprising:

a user profiling module that creates a user profile according to a predetermined model based on a user reaction to the content, wherein content fields are defined;

a digital television module that obtains content metadata from one or more data sources; and

a content rating module that creates a list of recommended contents based on the user profile and the content metadata received from the user profiling module and the digital television modules,

wherein the user profiling module comprises;

at least one profiler that observes user behaviors for each of the content fields; and

a user profile management unit that applies a different weight to each of the user behaviors observed by the at least one profiler and calculates a content rating for the relevant content according to a predetermined method, and

wherein the user profile management unit calculates the content rating R by;

$R=\frac{\underset{i=1}{\overset{n}{\sum <br><br>}}<br><br>W_i}{T}$

wherein W is a weight for each behavior, n is the number of behaviors observed in the specific content, and T is a length of time during which a content item is run.

6. The system of claim 5, wherein the digital television module comprises at least one data source containing at least one of a Program and System Information Protocol (PSIP) handler for handling Advanced Television Systems Committee (ATSC) PSIP metadata and a TV-Anytime metadata handler for handling TV-Anytime metadata.

7. The system of claim 5, wherein the content rating module comprises at least one of a keyword agent and a classifier agent, the keyword agent performing content rating by calculating a correlation coefficient between the user profile and the content metadata for each user and content, and the classifier agent performing content rating based on respective categories, comprising genres, languages, and channels.

8. A computer system having a processor and memory under control of the processor, the memory storing instruction modules adapted to enable a processor of the computer to perform operations, the modules comprising:

a user profiling module that creates a user profile according to a predetermined model based on a user reaction to the content;

a digital television module that obtains content metadata from one or more data sources;

a content rating module that creates a list of recommended contents based on the user profile and the content metadata received from the user profiling module and the digital television module, for outputting to the user, wherein

the content rating module comprises at least one of a keyword agent and a classifier agent, the keyword agent performing content rating by calculating a correlation coefficient between the user profile and the content metadata for each user and content, and the classifier agent performing content rating based on respective categories, comprising genres, languages, and channels, wherein

the classifier agent calculates an associative value of each entity based on the content rating obtained from the user profile and the content metadata, whereby;

$\mathrm{associative}<br><br><br><br>\mathrm{value}=\frac{n}{\frac{m}{N}+N}$

wherein N denotes the total number of levels in a given hierarchical structure, n denotes the level of a parent category in the overall hierarchical structure, and m denotes the depth from a parent category to a child category, and a content rating is obtained for each entity using the associative value obtained.