INFORMATION PROCESSING APPARATUS, SAMENESS DETERMINATION SYSTEM, SAMENESS DETERMINATION METHOD, AND COMPUTER PROGRAM

• US 20110305432A1
• Filed: 06/08/2011
• Published: 12/15/2011
• Est. Priority Date: 06/15/2010
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: MANABE, Yoshihiro, Abe, Yuichi, Noma, Hideki, Enami, Tsugutomo, Kashiwagi, Akifumi, Kawakami, Itaru
• Granted Patent: US 8,913,874 B2
• Time in Patent Office: Days
• US Class Current: 386/244
• 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 21/4884 for displaying subtitles
• CPC Class Codes: H04N 21/8133 specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video program

Abstract

There is provided an information processing apparatus which includes a subtitle processing unit for extracting a subtitle feature quantity representing a feature of a content from subtitle information included in the content, a subtitle feature quantity accumulation unit for associating and storing identification information capable of identifying the content and the subtitle feature quantity extracted from the content by the subtitle processing unit, a subtitle feature quantity collation unit for collating the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a subtitle feature quantity to be determined, thereby determining sameness between the content corresponding to the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a content corresponding to the subtitle feature quantity to be determined, and a collation result output unit for outputting a collation result of the subtitle feature quantity collation unit.

Claims

1. An information processing apparatus comprising:

a subtitle processing unit for extracting a subtitle feature quantity representing a feature of a content from subtitle information included in the content;

a subtitle feature quantity accumulation unit for associating and storing identification information capable of identifying the content and the subtitle feature quantity extracted from the content by the subtitle processing unit;

a subtitle feature quantity collation unit for collating the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a subtitle feature quantity to be determined, thereby determining sameness between the content corresponding to the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a content corresponding to the subtitle feature quantity to be determined; and

a collation result output unit for outputting a collation result of the subtitle feature quantity collation unit.

2. The information processing apparatus according to claim 1,

wherein the subtitle processing unit includes:

a subtitle information separation unit for separating subtitle information included in a content from the content; and

a subtitle feature quantity extraction unit for extracting at least an array including a time interval between subtitles as the subtitle feature quantity on the basis of the subtitle information separated by the subtitle information separation unit.

3. The information processing apparatus according to claim 2,

wherein the subtitle feature quantity extraction unit arranges the subtitle data representing a plurality of subtitle contents included in the content in a time sequence on the basis of display times of the subtitle data, and calculates, as an array of time interval between the subtitles, a numerical string including a difference of the display times of the subtitle data adjacent to each other in the time sequence.

4. The information processing apparatus according to claim 2,

wherein the subtitle feature quantity extraction unit further extracts, as a subtitle feature quantity, the subtitle data representing the subtitle content from the subtitle information.

5. The information processing apparatus according to claim 1,

wherein in a case where the subtitle feature quantity extracted by the subtitle processing unit matches, at least partially, the subtitle feature quantity to be determined, the subtitle feature quantity collation unit determines that the contents from which these subtitle feature quantities are extracted are the same.

6. The information processing apparatus according to claim 5,

wherein in a case where the subtitle feature quantity extracted by the subtitle processing unit partially matches the subtitle feature quantity to be determined, the subtitle feature quantity collation unit calculates a degree of match between these subtitle feature quantities.

7. The information processing apparatus according to claim 6,

wherein in a case where the subtitle feature quantity collation unit determines that there are a plurality of contents between which a degree of match is equal to or more than a predetermined rate, the collation result output unit outputs identification information of these contents as a collation result.

8. The information processing apparatus according to claim 1,

wherein the subtitle feature quantity accumulation unit stores the subtitle feature quantity using an N-gram method.

9. The information processing apparatus according to claim 1,

wherein in a case where the content is a terrestrial digital broadcasting content that is broadcasted in terrestrial digital broadcasting, the subtitle processing unit extracts the subtitle feature quantity on the basis of subtitle information of a one-segment broadcasting content that is broadcasted in one-segment broadcasting simultaneously with the terrestrial digital broadcasting content when the terrestrial digital broadcasting content does not include any subtitle information.

10. An information processing apparatus comprising:

a subtitle information separation unit for separating subtitle information included in a content from the content;

a subtitle feature quantity extraction unit for extracting a subtitle feature quantity representing a feature of the content on the basis of the subtitle information separated by the subtitle information separation unit; and

a comment information output unit for transmitting comment information to an information providing server providing a user'"'"'s comment on a network,

wherein the comment information is made by attaching the subtitle feature quantity extracted by the subtitle feature quantity extraction unit to the user'"'"'s comment made on the content.

11. A sameness determination system for determining a sameness of a content, the sameness determination system comprising:

an information processing apparatus for inputting a user'"'"'s comment on the content; and

an information providing server for providing, on a network, the user'"'"'s comment transmitted from the information processing apparatus,

wherein the information processing apparatus includes;

a subtitle information separation unit for separating subtitle information included in a content from the content;

a subtitle feature quantity extraction unit for extracting a subtitle feature quantity representing a feature of the content on the basis of the subtitle information separated by the subtitle information separation unit;

a comment input unit for inputting the user'"'"'s comment made on the content; and

a comment information output unit for transmitting comment information to an information providing server providing a user'"'"'s comment on a network, the comment information being made by attaching the subtitle feature quantity extracted by the subtitle feature quantity extraction unit to the user'"'"'s comment made on the content, and

the information providing server includes;

a subtitle processing unit for extracting a subtitle feature quantity representing a feature of a content from subtitle information included in the content;

a subtitle feature quantity accumulation unit for associating and storing identification information capable of identifying the content and a subtitle feature quantity extracted from the content by the subtitle processing unit;

a subtitle feature quantity collation unit for collating the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and the subtitle feature quantity included in the comment information transmitted from the information processing apparatus, thereby determining sameness between the content corresponding to the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a content corresponding to the subtitle feature quantity in the comment information; and

a collation result output unit for outputting a collation result of the subtitle feature quantity collation unit.

12. A sameness determination method comprising:

causing a subtitle information separation unit of an information processing apparatus for inputting a user'"'"'s comment made on a content to separate subtitle information included in a content from the content;

causing a subtitle feature quantity extraction unit of the information processing apparatus to extract a subtitle feature quantity representing a feature of the content on the basis of the subtitle information separated by the subtitle information separation unit;

causing a comment information output unit of the information processing apparatus to transmit comment information to an information providing server providing a user'"'"'s comment on a network, wherein the comment information is made by attaching the subtitle feature quantity extracted by the subtitle feature quantity extraction unit to the user'"'"'s comment made on the content input to the information processing apparatus;

causing a subtitle processing unit of the information providing server to extract a subtitle feature quantity representing a feature of a content from subtitle information included in the content;

collating the subtitle feature quantity stored in the subtitle feature quantity accumulation unit associating and storing identification information capable of identifying the content and a subtitle feature quantity extracted from the content by the subtitle processing unit and a subtitle feature quantity included in the comment information transmitted from the information processing apparatus, thereby determining sameness between the content corresponding to the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a content corresponding to the subtitle feature quantity of the comment information; and

causing the collation result output unit to output a collation result of the subtitle feature quantity collation unit.

13. A computer program for achieving a function of an information processing apparatus comprising:

a subtitle processing unit for extracting a subtitle feature quantity representing a feature of a content from subtitle information included in the content; and

a subtitle feature quantity collation unit for collating the subtitle feature quantity stored in a subtitle feature quantity accumulation unit, which associates and stores identification information capable of identifying the content and a subtitle feature quantity extracted from the content by the subtitle processing unit, and a subtitle feature quantity to be determined, thereby determining sameness between the content corresponding to the subtitle feature quantity stored in the subtitle feature quantity accumulation unit and a content corresponding to the subtitle feature quantity to be determined.