METHOD AND APPARATUS FOR RECOMMENDING PERSONALIZED CONTENT

• US 20100125544A1
• Filed: 10/22/2009
• Published: 05/20/2010
• Est. Priority Date: 11/18/2008
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: CHO, Kee-seong, LEE, Kang-yong, KIM, Bong-tae
• Granted Patent: US 8,418,205 B2
• Time in Patent Office: Days
• US Class Current: 706/54
• 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 21/4667 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

Disclosed are a method and apparatus for recommending personalized content in an Internet Protocol Television (IPTV) service environment. The content recommending method includes: acquiring a user'"'"'s viewing history information regarding broadcasting content; analyzing the user'"'"'s preference for each content item based on the user'"'"'s viewing history information; creating a list of recommended content items based on the analysis of the user'"'"'s preference; and providing the list of recommended content items to the user'"'"'s terminal. Accordingly, it is possible to recommend personalized content according to users'"'"' preference.

Claims

1. A method of recommending personalized content to users in an Internet Protocol television (IPTV) service environment, comprising:

acquiring a user'"'"'s viewing history information of a user regarding broadcasting content;

analyzing the user'"'"'s preference for each content item based on the user'"'"'s viewing history information;

creating a list of recommended content items based on the analysis of the user'"'"'s preference; and

providing the list of recommended content items to the user'"'"'s terminal.

2. The method of claim 1, wherein the user'"'"'s viewing history information includes the user'"'"'s identifier, a content identifier and a timestamp.

3. The method of claim 2, wherein the user'"'"'s identifier is a Session Initiation Protocol-Uniform Resource Identifier (SIP-URI).

4. The method of claim 2, wherein the timestamp is a Content Reference Identifier (CRID) to identify individual content according to a standard developed by the TV-Anytime Forum.

5. The method of claim 2, wherein the timestamp includes information on a time at which the user'"'"'s viewing history information has been created.

6. The method of claim 1, wherein the user'"'"'s viewing history information is acquired by using a session initiation protocol (SIP)-based presence service.

7. The method of claim 1, wherein the acquiring of the user'"'"'s viewing history information comprises determining whether the user'"'"'s viewing history information meets a validity condition, and considering the user'"'"'s viewing history information as valid information if the user'"'"'s viewing history information meets the validity condition.

8. The method of claim 2, wherein the acquiring of the user'"'"'s viewing history information comprises subtracting a time indicated by a timestamp included in just previously acquired viewing history information of the user from a time indicated by the timestamp included in the user'"'"'s viewing history information, and considering the user'"'"'s viewing history information as valid information if a value obtained by dividing the resultant value of the subtraction by a whole length of content associated with the user'"'"'s viewing history information exceeds a reference value.

9. The method of claim 1, wherein the analyzing of the user'"'"'s preference for each content item comprises:

acquiring information on the lower items of each content description parameter of a content item corresponding to a content identifier included in the user'"'"'s viewing history information;

incrementing a usage counter of a corresponding lower item according to the acquired information on the lower items of each content description parameter, with respect to a user identifier included in the user'"'"'s viewing history information;

calculating degrees of the user'"'"'s sensitivities to the respective lower items based on usage counters of the lower items; and

obtaining a degree of the user'"'"'s preference for each content item that is to be served, based on the calculated degrees of the user sensitivities to the lower items.

10. The method of claim 9, wherein the analyzing of the user'"'"'s preference for each content item comprises:

acquiring information on the lower items of each context description parameter of a content item corresponding to a content identifier included in the user'"'"'s viewing history information regarding broadcasting content which meets a validity condition;

incrementing a usage counter of a corresponding lower item according to the acquired information on the lower items of each content description parameter, with respect to the user identifier included in the user'"'"'s viewing history information;

calculating degrees of the user'"'"'s sensitivities to the respective lower items based on usage counters of the lower items; and

obtaining a degree of the user'"'"'s preference for each content item that is to be served, based on the calculated degrees of the user'"'"'s sensitivities to the lower items.

11. The method of claim 10, wherein the content description parameter of the content item includes at least one of genre, actor and producer.

12. The method of claim 10, wherein a degree of the user'"'"'s sensitivity to each lower item is calculated by subtracting an average value of usage counters of all lower items belonging to a corresponding content description parameter from a usage counter of the lower item, squaring the value of the subtraction, and dividing the squared value by a square of a standard deviation of the usage counters of all lower items.

13. The method of claim 12, wherein the degree of the user'"'"'s preference for each content item that is to be served is calculated by summing all the user'"'"'s sensitivities calculated for the respective lower items of the content item.

14. The method of claim 13, wherein the creating of the list of recommended content items comprises creating a list of recommended content items arranged in a descending order of degrees of the user'"'"'s preference.

15. The method of claim 1, wherein the providing of the list of recommended content items to the user'"'"'s terminal comprises a Content Reference Identifier (CRID) corresponding to the list of recommended content items to the user'"'"'s terminal.

16. An apparatus of recommending personalized content in an Internet Protocol television (IPTV) service environment, comprising:

a viewing history profile storage in which viewing history information of each user regarding broadcasting content is stored;

a content profile storage in which content description parameters for each content item and lower items of each content description parameter are stored;

a viewing history information manager to acquire a user'"'"'s viewing history information regarding broadcasting content and store the acquired user'"'"'s viewing history information in the viewing history profile storage, and to acquire information on lower items of each content description parameter of a content item associated with the user'"'"'s viewing history information from the content profile storage, increment a usage counter of a corresponding lower item with respect to a user identifier included in the user'"'"'s viewing history information, and store the usage counter of the lower item in the viewing history profile storage; and

a user sensitivity calculator to calculate degrees of the user'"'"'s sensitivities to the lower items based on information stored in the viewing history profile storage; and

a content recommendation unit to create a list of recommended content items based on the degrees of the user'"'"'s sensitivities to the lower items and provide the list of recommended content items to the user'"'"'s terminal.

17. The apparatus of claim 16, wherein the viewing history information manager acquires the user'"'"'s viewing history information from the user'"'"'s terminal by using a Session Initiation Protocol (SIP) presence service.

18. The apparatus of claim 16, wherein the user'"'"'s viewing history information includes the user'"'"'s identifier, a content identifier and a timestamp.

19. The apparatus of claim 16, wherein the viewing history information manager stores the user'"'"'s viewing history information in the viewing history profile storage when the user'"'"'s viewing history information meets a validity condition.

20. The apparatus of claim 19, wherein the viewing history information manager determines whether the user'"'"'s viewing history information meets the validity condition in consideration of a length of a content item corresponding to a content identifier and a timestamp included in the user'"'"'s viewing history information.