VIDEO RECOMMENDATION SYSTEM AND METHOD THEREOF

• US 20130259399A1
• Filed: 06/12/2012
• Published: 10/03/2013
• Est. Priority Date: 03/30/2012
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Cheng-Yuan Ho, Chi-Hung Tsai, I-Heng Meng
• Inventors: HO, Cheng-Yuan, MENG, I-Heng, TSAI, Chi-Hung
• Granted Patent: US 8,804,999 B2
• Time in Patent Office: Days
• US Class Current: 382/276
• CPC Class Codes: G06F 16/7328 Query by example, e.g. a complete video frame or video sequence graphical querying G06F16/7335
• CPC Class Codes: G06F 16/783 using metadata automatically derived from the content
• CPC Class Codes: H04N 21/4332 by placing content in organized collections, e.g. local EPG data repository interfaces, Database management systems or updating for information retrieval G06F16/23; details of retrieval of video data and associated meta data in video database G06F16/739
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/4661 Deriving a combined profile for a plurality of end-users of the same client, e.g. for family members within a home user profiles in network data switching protocols H04L67/306
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/4756 for rating content, e.g. scoring a recommended movie
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments

Abstract

A video recommendation system is provided. The video recommendation system has: an interaction device configured to receive feedback information of a video from a user, wherein the videos are composed of a plurality of video segments; a feature calculating module configured to calculate object features of at least a first video segment corresponding to the feedback information in the plurality of video segments; and an analysis module configured to recommend at least one first recommended video segment to the user from the plurality of video segments according to the calculated object features and the feedback information.

Claims

1. A video recommendation system, comprising:

an interaction device configured to receive feedback information of a video from a user, wherein the video comprises a plurality of video segments;

a feature calculating module configured to calculate object features of at least a first video segment corresponding to the feedback information in the plurality of video segments; and

an analysis module configured to recommend at least one first recommended video segment to the user from the plurality of video segments according to the calculated object features and the feedback information.

2. The video recommendation system as claimed in claim 1, wherein the feedback information comprises at least one time information, and the feature calculating module further retrieves the at least one first video segment from the plurality of video segments according to the at least one time information, labels the feedback information to the at least one first video segment, and stores the plurality of video segments to a database.

3. The video recommendation system as claimed in claim 1, wherein the object features comprise at least one high level feature and at least one low level feature of the at least one first video segment.

4. The video recommendation system as claimed in claim 3, wherein the at least one high level feature comprises a face, an object, a scene, and/or a semantic concept of the at least one first video segment.

5. The video recommendation system as claimed in claim 3, wherein the at least one low level feature comprises a color histogram, color distribution, edge statistics, and/or a texture corresponding to the at least one first video segment.

6. The video recommendation system as claimed in claim 2, wherein the database stores a plurality of second videos comprising a plurality of second video segments, second object features corresponding to the plurality of second video segments, and second user information, and the analysis module further recommends a second recommended video segment to the user from the plurality of second video segments according to the second object features and the second user information.

7. The video recommendation system as claimed in claim 1, wherein the analysis module further analyzes the feedback information to retrieve user information of the user, and recommends at least one third recommended video segment to the user from the plurality of video segments according to the retrieved user information.

8. A video recommendation method applied in a video recommendation system, the method comprising:

receiving feedback information of a video from a user, wherein the video comprises a plurality of video segments;

calculating object features of at least a first video segment corresponding to the feedback information in the plurality of video segments; and

recommending at least one first recommended video segment to the user from the plurality of video segments according to the calculated object features and the feedback information.

9. The video recommendation method as claimed in claim 8, wherein the feedback information comprises at least one time information, and the method further comprises:

retrieving the at least one first video segment from the plurality of video segments according to the at least one time information;

labeling the feedback information to the at least one first video segment; and

storing the plurality of video segments to a database.

10. The video recommendation method as claimed in claim 8, wherein the object features comprise at least one high level feature and at least one low level feature of the at least one first video segment.

11. The video recommendation method as claimed in claim 10, wherein the at least one high level feature comprises a face, an object, a scene, and/or a semantic concept of the at least one first video segment.

12. The video recommendation method as claimed in claim 10, wherein the at least one low level feature comprises a color histogram, color distribution, edge statistics, and/or a texture corresponding to the at least one first video segment.

13. The video recommendation method as claimed in claim 9, wherein the database stores a plurality of second videos comprising a plurality of second video segments, second object features corresponding to the plurality of second video segments, and second user information, and the method further comprises:

recommending a second recommended video segment to the user from the plurality of second video segments according to the second object features and the second user information.

14. The video recommendation method as claimed in claim 8, further comprising:

analyzing the feedback information to retrieve user information of the user; and

recommending at least one third recommended video segment to the user according to the user information.

15. A video recommendation system, comprising:

an interaction device configured to receive feedback information of videos from multiple users, wherein the videos comprise a plurality of video segments;

a feature calculating module configured to calculate at least one object feature of the plurality of video segments corresponding to the feedback information; and

an analysis module configured to calculate popularity of the at least one object feature of the plurality of video segments, and recommend at least one recommended video segment from the plurality of video segments according to the popularity of the at least one object feature.

16. A video recommendation method applied in a video recommendation system, the method comprising:

receiving feedback information of videos from multiple users, wherein the videos comprise a plurality of video segments;

calculating at least one object feature of the plurality of video segments corresponding to the feedback information;

calculating the popularity of the at least one object feature of the plurality of video segments; and

recommending at least one recommended video segment from the plurality of video segments according to the popularity of the at least one object feature.