System and method for automated classification of text by time slicing

• US 6,990,496 B1
• Filed: 07/26/2000
• Issued: 01/24/2006
• Est. Priority Date: 07/26/2000
• Status: Expired due to Fees

• Current Assignee: Uniloc 2017 LLC (SoftBank Group Corp.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Dimitrova, Nevenka, McGee, III, Thomas Francis
• Primary Examiner(s): Corrielus, Jean M.
• Assistant Examiner(s): Woo, Isaac M.
• Application Number:
  US09/616,631
• Time in Patent Office: 2,008 Days
• Field of Search: 707200-205, 707 1- 10, 707100-1041, 345/300, 345/301, 345/302, 715/500, 715/515, 715/516, 715530-541
• US Class Current: 1/1
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 16/7844 using original textual content or text extracted from visual content or transcript of audio data
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

For use in an information processing system, there is disclosed a system and method for automatically classifying text. The system comprises a text classifier controller that reads text having one or more keywords contained within one or more story segments within the text. The text classifier controller identifies keywords within each line, and, in response to identifying at least one keyword within a line of text, classifies that line of text as a part of a story segment within the text. The text classifier controller also identifies keyword transition points in the text where the number of detected keywords in a particular category of keywords decreases below a threshold number. The text classifier controller also identifies keyword transition points in the text where the number of detected keywords in a particular category of keywords increases above a threshold number. The text classifier controller classifies story segments based on the location of the keyword transition points.

Claims

1. For use in an information processing system, an apparatus for automatically classifying video signals comprising:

a processor

a keyframe classifier for segmenting the video signals into an initial set of one or more story segments; and

a text classifier controller adapted for;

providing multiple classifications of text, said text classifier controller reading text having a plurality of keywords contained within at least one of the story segments,

identifying one or more keywords within each of two or more lines of said text,

in response to identifying at least one of said keywords, classifying each of said lines of text as a part of one or more classifications of said video signals that have been segmented into said at least one story segment, and

in response to a comparison of said identified keywords, identifying a keyword transition point within said at least one story segment between two adjacent portions of text, wherein a number of keywords detected in a keyword category for at least one line of text prior to the keyword transition point either decreases below a first threshold number or increases above a second threshold number.

2. The apparatus as set forth in claim 1 wherein said text classifier controller is adapted for sequentially comparing first and second lines of text to compare the number of keywords detected for each first line of text with the number of keywords detected for each second line of text.

3. The apparatus as set forth in claim 2 wherein said text classifier controller is adapted for classifying text between a beginning of the text and the keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point.

4. The apparatus as set forth in claim 2 wherein said text classifier controller is adapted for classifying text between the keyword transition point and a second keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point and the second keyword transition point.

5. The apparatus as set forth in claim 1 wherein said text classifier controller comprises an algorithm for reading lines of text to identify keywords contained within said lines of text, wherein said algorithm classifies each line of text in a keyword category that has the largest number of keywords in said line of text.

6. The apparatus as set forth in claim 1, wherein one or more of the keywords are located in a number of successive lines of text prior to the keyword transition, the number of successive lines of text exceeding a third threshold number.

7. An information processing system of the type comprising:

a video story segmentation device;

a keyword library; and

a classification device;

wherein said information processing system includes a text classifier controller adapted for;

reading text having a plurality of keywords contained within at least one story segment within said text,

identifying one or more keywords within each of two or more lines of said text,

in response to identifying at least one of said keywords, classifying each of said lines of text as a part of said at least one story segment into one or more classifications of said at least one story segment within said text, and

in response to a comparison of said identified keywords, identifying a keyword transition point within said at least one story segment between two adjacent portions of text, wherein a number of keywords detected in a keyword category for at least one line of text prior to the keyword transition point either decreases below a first threshold number or increases above a second threshold number.

8. The information processing system as set forth in claim 7 wherein said text classifier controller is adapted for sequentially comparing first and second lines of text to compare the number of keywords detected for each first line of text with the number of keywords detected for each second line of text.

9. The information processing system as set forth in claim 8 wherein said text classifier controller is adapted for classifying text between a beginning of the text and the keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point.

10. The information processing system as set forth in claim 8 wherein said text classifier controller is adapted for classifying text between the keyword transition point and a second keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point and the second keyword transition point.

11. The information processing system as set forth in claim 7 wherein said text classifier controller comprises an algorithm for reading lines of text to identify keywords contained within said lines of text, wherein said algorithm classifies each line of text in a keyword category that has the largest number of keywords in said line of text.

12. The information processing system as set forth in claim 7, wherein one or more of the keywords are located in a number of successive lines of text prior to the keyword transition, the number of successive lines of text exceeding a third threshold number.

13. For use in an information processing system, a computer-implemented method of automatically classifying audio and visual signals comprising the steps of:

initially segmenting the audio and visual signals based upon keyframe identification into one or more story segments;

reading text having a plurality of keywords contained within at least one story segment;

identifying one or more keywords within each of two or more lines of said text;

in response to identifying at least one of said keywords, classifying each of said lines of text as a part of one or more classifications of said audio and visual signals that have been segmented into said at least one story segment; and

in response to a comparison of said identified keywords, identifying a keyword transition point within said at least one story segment between two adjacent portions of text, wherein a number of keywords detected in a keyword category for at least one line of text prior to the keyword transition point either decreases below a first threshold number or increases above a second threshold number.

14. The computer-implemented method as set forth in claim 13 further comprising the step of:

sequentially comparing first and second lines of text to compare the number of keywords detected for each first line of text with the number of keywords detected for each second line of text.

15. The computer-implemented method as set forth in claim 14 further comprising the step of:

classifying text between a beginning of the text and the keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point.

16. The computer-implemented method as set forth in claim 14 further comprising the step of:

classifying text between the keyword transition point and a second keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point and the second keyword transition point.

17. The computer-implemented method as set forth in claim 13 further comprising the steps of:

sequentially comparing first and second lines of text to compare the number of keywords detected for each first line of text with the number of keywords detected for each second line of text;

identifying a plurality of keyword transition points in said text between adjacent portions of text; and

classifying the text between each two adjacent keyword transition points of said plurality of keyword transition points as a story segment of the text.

18. The computer-implemented method as set forth in claim 13, wherein one or more of the keywords are located in a number of successive lines of text prior to the keyword transition, the number of successive lines of text exceeding a third threshold number.

19. For use in a computerized information processing system, computer-executable instructions stored on a computer-readable storage medium for automatically classifying text, the computer-executable instructions comprising the steps of:

initially segmenting a video into one or more story segments based upon keyframes;

reading text having a plurality of keywords contained within at least one story segment;

identifying one or more keywords within each of two or more lines of said text;

in response to identifying at least one of said keywords, classifying each of said lines of text as a part of one or more classifications of said video that have been segmented into said at least one story segment; and

in response to a comparison of said identified keywords, identifying a keyword transition point within said at least one story segment between two adjacent portions of text, wherein a number of keywords detected in a keyword category for at least one line of text prior to the keyword transition point either decreases below a first threshold number or increases above a second threshold number.

20. The computer-executable instructions stored on a computer-readable storage medium as set forth in claim 19, the computer-executable instructions further comprising the step of:

sequentially comparing first and second lines of text to compare the number of keywords detected for each first line of text with the number of keywords detected for each second line of text.

21. The computer-executable instructions stored on a computer-readable storage medium as set forth in claim 20, the computer-executable instructions further comprising the step of:

classifying text between a beginning of the text and the keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point.

22. The computer-executable instructions stored on a computer-readable storage medium as set forth in claim 20, the computer-executable instructions further comprising the step of:

classifying text between the keyword transition point and a second keyword transition point as one story segment of the text when said text classifier controller identifies the keyword transition point and the second keyword transition point.

23. The computer-executable instructions stored on a computer-readable storage medium as set forth in claim 19, the computer-executable instructions further comprising the steps of:

sequentially comparing first and second lines of text to compare the number of keywords detected for each first line of text with the number of keywords detected for each second line of text;

identifying a plurality of keyword transition points in said text between adjacent portions of text; and

classifying the text between each two adjacent keyword transition points of said plurality of keyword transition points as a story segment of the text.

24. The computer-executable instructions stored on a computer-readable storage medium as set forth in claim 19, wherein one or more of the keywords are located in a number of successive lines of text prior to the keyword transition, the number of successive lines of text exceeding a third threshold number.