METHOD AND APPARATUS FOR EXTRACTING ADVERTISEMENT KEYWORDS IN ASSOCIATION WITH SITUATIONS OF VIDEO SCENES

• US 20100217671A1
• Filed: 02/02/2010
• Published: 08/26/2010
• Est. Priority Date: 02/23/2009
• Status: Active Grant

• Current Assignee: Korea University Research and Business Foundation, Samsung Electronics Co. Ltd.
• Original Assignee: Korea University Research and Business Foundation, Samsung Electronics Co. Ltd.
• Inventors: Song, Young-in, LEE, Hyung-dong, Rim, Hae-chang, Lee, Jung-tae, Park, Hee-seon
• Granted Patent: US 9,043,860 B2
• Time in Patent Office: Days
• US Class Current: 705/14.530
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G11B 27/3027 used signal is digitally coded
• CPC Class Codes: H04H 20/10 Arrangements for replacing or switching information during the broadcast or the distribution
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/59 of video recognising characters or patterns in general G06F18/00, G06V20/00
• CPC Class Codes: H04H 60/63 for services of sales data processing systems or methods specially adapted for electronic commerce G06Q30/00
• CPC Class Codes: H04N 21/235 Processing of additional data, e.g. scrambling of additional data or processing content descriptors
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8405 represented by keywords
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

A method and apparatus for extracting advertisement keywords in association with situations of scenes of video include: establishing a knowledge database including a classification hierarchy for classifying situations of scenes of video and an advertisement keyword list, segmenting a video script corresponding to a received video in units of scenes, and determining a situation corresponding to each scene with reference to the knowledge database, and extracting an advertisement keyword corresponding to the situation of a scene of the received video with reference to the knowledge database.

Claims

1. A method of extracting advertisement keywords in association with situations of scenes of video, the method comprising:

establishing a knowledge database including a classification hierarchy for classifying situations of scenes of video and an advertisement keyword list;

segmenting a video script corresponding to a received video in units of scenes, and determining a situation corresponding to each scene with reference to the knowledge database; and

extracting an advertisement keyword corresponding to the situation of a scene of the received video with reference to the knowledge database.

2. The method of claim 1, wherein the deciding of the situation of each scene comprises:

inserting synchronization information into dialog of each video script segmented in units of scenes; and

performing text pre-processing tasks including stopword removal and stemming.

3. The method of claim 1, wherein the extracting of the advertisement keyword comprises extracting the advertisement keyword by calculating relevancy between the situation of the scene and advertisement keywords listed in the advertisement keyword list stored in the database according to a statistical method.

4. An advertising method to which information about situations of scenes of video is reflected, the method comprising:

receiving a video;

receiving a script corresponding to the video;

segmenting the script in units of scenes;

extracting an advertisement keyword corresponding to a situation of each scene;

combining advertisement contents corresponding to the extracted advertisement keyword with the video; and

providing the video combined with the advertisement contents.

5. An apparatus suitable for extracting advertisement keywords in association with situations of scenes of video, the apparatus comprising:

a database configured to store a knowledge database including a classification hierarchy for classifying situations of scenes of video and an advertisement keyword list;

is a preprocessor configured to;

segment a received video script in units of scenes;

insert synchronization information into a script of each scene; and

perform text pre-processing tasks including stopword removal and stemming; and

a keyword extractor configured to extract an advertisement keyword corresponding to the situation of the scene with reference to the database.

6. The apparatus of claim 5, wherein the keyword extractor is further configured to extract the advertisement keyword by calculating relevancy between the situation of the scene and advertisement keywords listed in the advertisement keyword list stored in the database according to a statistical method.

7. The apparatus of claim 5, wherein the preprocessor is further configured to:

compare dialog of the video script with dialog in captions; and

add temporal information of the dialog in captions to the dialog of the video script at appropriate locations.

8. The apparatus of claim 5, wherein the database is further configured to:

tag predetermined situation factors according to the questions words of “

who,”

“

where,”

“

what,”

“

why,”

“

when,” and

“

how;

” and

store the tagged predetermined situation factors in association with information of the questions words.