System and method for supporting document navigation on mobile devices using segmentation and keyphrase summarization

• US 8,601,393 B2
• Filed: 09/30/2008
• Issued: 12/03/2013
• Est. Priority Date: 01/28/2008
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Carter, Scott, Chen, Francine, Chiu, Patrick
• Primary Examiner(s): Bashore, William
• Assistant Examiner(s): SHREWSBURY, NATHAN K
• Application Number:
  US12/242,757
• Publication Number:
  US 20090193337A1
• Time in Patent Office: 1,890 Days
• Field of Search: 715/277, 715/784, 715/821
• US Class Current: 715/821
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance

Abstract

Described is a system that characterizes segments of a document with one or more keyphrases and then uses the keyphrases to help users find interesting parts of a document. The keyphrases are displayed with information about the location of the phrase in the document and are used as pointers to quickly move to from an overview to a section of potential interest.

Claims

1. A method of navigating a document, comprising:

dividing the document into a plurality of segments;

generating, for at least one of the plurality of segments, at least one keyphrase, which is representative of content of the at least one of the plurality of segments, and associating the generated at least one keyphrase with the at least one of the plurality of segments represented by the generated at least one keyphrase;

displaying the generated at least one keyphrase;

upon a user'"'"'s selection of the generated at least one keyphrase, enabling the user to view a corresponding segment of the document; and

displaying a visual representation for each of the plurality of segments,

wherein the position of each visual representation with respect to each of the plurality of generated keyphrases depends on a degree of relatedness between each of plurality of generated keyphrases and the corresponding segment.

2. The method of claim 1, wherein the plurality of segments of the document are identified using a layout analysis or an optical character recognition (OCR) performed on the document.

3. The method of claim 1, wherein the plurality of segments of the document are identified using at least one tag associated with the document.

4. The method of claim 1, wherein the plurality of segments of the document are identified using heuristics based on line spacing, font height or indentation.

5. The method of claim 1, wherein the at least one keyphrase is generated by tagging a part of speech (POS) of a text of the document and identifying POS tag sequences corresponding to a noun phrase.

6. The method of claim 1, wherein during the displaying, the generated least one keyphrase is overlaid over the corresponding identified segment of the document.

7. The method of claim 1, wherein the segments are highlighted on an icon next to a keyphrase to represent each segment'"'"'s location to a corresponding document.

8. The method of claim 7, wherein the segments are highlighted on a bar to represent each segment'"'"'s location to a corresponding page in a document.

9. The method of claim 1, wherein the determining at least one keyphrase is generated by utilizing a statistical method based on at least one of:

number of times a term occurs in a given section;

number of times a term occurs in a document;

number of documents in which a term occurs at least once in an English corpus;

number of sections in a document in which a term occurs at least once;

number of times the candidate keyphrase has previously been selected as a keyphrase;

number of tokens in the keyphrase; and

location of first mention of the term in the paragraph.

29. The method of claim 1, further comprising:

displaying a plurality of generated keyphrases, each of the plurality of keyphrases representative of at least one of the plurality of segments; and

wherein a size of each visual representation depends on a function of a number of occurrences of all of the plurality of generated keyphrases in the corresponding segment.

10. A non-transitory computer readable medium storing a sequence of instructions, which, when executed by one or more processors, cause the one or more processors to execute a process for document navigation, the process comprising:

dividing the document into a plurality of segments;

generating, for at least one of the plurality of segments, at least one keyphrase, which is representative of content of the at least one of the plurality of segments, and associating the generated at least one keyphrase with the at least one of the plurality of segments represented by the generated at least one keyphrase;

displaying the generated at least one keyphrase;

upon a user'"'"'s selection of the generated least one keyphrase, enabling the user to view the corresponding segment of the document, and

displaying a visual representation for each of the plurality of segments,

wherein the position of each visual representation with respect to each of the plurality of generated keyphrases depends on a degree of relatedness between each of plurality of automatically generated keyphrases and the corresponding segment.

11. The computer readable medium of claim 10, wherein the plurality of segments of the document are identified using a layout analysis or an optical character recognition (OCR) performed on the document.

12. The computer readable medium of claim 10, wherein the plurality of segments of the document are identified using at least one tag associated with the document.

13. The computer readable medium of claim 10, wherein the plurality of segments of the document are identified using heuristics based on line spacing, font height or indentation.

14. The computer readable medium of claim 10, wherein the at least keyphrase is generated by tagging a part of speech (POS) of a text of the document and identifying POS tag sequences corresponding to a noun phrase.

15. The computer readable medium of claim 10, wherein during the displaying, the generated least one keyphrase is overlaid over the corresponding identified segment of the document.

16. The computer readable medium of claim 10, wherein the determining at least one keyphrase is generated by utilizing a statistical method based on at least one of:

number of times a term occurs in a given section;

number of times a term occurs in a document;

number of documents in which a term occurs at least once in an English corpus;

number of sections in a document in which a term occurs at least once;

number of times the candidate keyphrase has previously been selected as a keyphrase;

number of tokens in the keyphrase; and

location of first mention of the term in the paragraph.

17. The computer readable medium of claim 10, wherein the segments are highlighted on an icon next to a keyphrase to represent each segment'"'"'s location to a corresponding document.

18. The computer readable medium of claim 17, wherein the segments are highlighted on a bar to represent each segment'"'"'s location to a corresponding page in a document.

30. The computer readable medium of claim 10, further comprising:

displaying a plurality of generated keyphrases, each of the plurality of keyphrases representative of at least one of the plurality of segments; and

wherein a size of each visual representation depends on a function of a number of occurrences of all of the plurality of generated keyphrases in the corresponding segment.

19. A device, comprising:

a display unit;

a sensing unit, operable to sense input;

a processing unit, operable to process the input, to divide a document into a plurality of segments; and

to forward instructions to a display controller to highlight, zoom, or navigate through the identified document segments;

the display controller operable to process the forwarded instructions and to generate a resulting visual representation for display on the display unit, wherein the processing unit is further operable to generate, for at least one of the plurality of segments, at least one keyphrase, which is representative of content of the at least one of the plurality of segments, and associate the generated at least one keyphrase with the at least one of the plurality of segments represented by the generated at least one keyphrase; and

displaying a visual representation for each of the plurality of segments,

wherein the position of each visual representation with respect to each of the plurality of generated keyphrases depends on a degree of relatedness between each of plurality of generated keyphrases and the corresponding segment.

20. The device of claim 19, wherein the sensing unit further comprises receiving input of a user'"'"'s selection of at least one keyphrase;

and

the processing unit further comprises forwarding instructions to the display controller to enable the user to view the corresponding segment of the document.

21. The device of claim 20, wherein the processing unit further comprises forwarding instructions to the display controller to overlay the generated least one keyphrase over a corresponding identified segment of a document.

22. The device of claim 19, wherein the processing unit further comprises a recognition module operable to determine the at least one keyphrase by tagging a part of speech (POS) of a text of the document and identifying POS tag sequences corresponding to a noun phrase.

23. The device of claim 19, wherein the processing unit further comprises a memory unit operable to store processing instructions for identifying the plurality of segments of the document.

24. The device of claim 19, wherein the processing unit further comprises a document processing module operable to identify the plurality of segments of the document using at least one tag associated with a document.

25. The device of claim 19, wherein the processing unit further comprises a document processing module operable to identify the plurality of segments of the document using heuristics based on line spacing, font height or indentation.

26. The device of claim 24, wherein the processing unit further comprises a document processing module operable to identify the plurality of segments of the document using a layout analysis or an optical character recognition (OCR) performed on the document.

27. The device of claim 19, wherein the processing unit determines at least one keyphrase by utilizing a statistical method based on:

number of times a term occurs in a given section;

number of times a term occurs in a document;

number of documents in which a term occurs at least once in an English corpus;

number of sections in a document in which a term occurs at least once;

number of times the candidate keyphrase has previously been selected as a keyphrase;

number of tokens in the keyphrase; and

location of first mention of the term in the paragraph.

31. The device of claim 19, wherein the display controller controls the display to:

displaying a plurality of generated keyphrases, each of the plurality of keyphrases representative of at least one of the plurality of segments; and

wherein a size of each visual representation depends on a function of a number of occurrences of all of the plurality of generated keyphrases in the corresponding segment.

28. A non-transitory computer readable medium storing a sequence of instructions, which, when executed by one or more processors, cause the one or more processors to execute a process for document navigation, the process comprising:

displaying documents as visual representations and grouping the documents based on the occurrences of keyphrases, which are representative of the content of the documents;

wherein the size of each visual representation depends on a function of the number of occurrences of all keyphrases in the corresponding document;

highlighting all of the visual representations with at least one occurrence of a selected keyphrase; and

when multiple keyphrases are selected, highlighting only visual representations with at least one occurrence of each of the multiple keyphrases selected .