Device, system and method for identifying sections of documents

• US 9,001,390 B1
• Filed: 10/04/2012
• Issued: 04/07/2015
• Est. Priority Date: 10/06/2011
• Status: Active Grant

• Current Assignee: MounTavor Inc.
• Original Assignee: Uri Zernik
• Inventors: Zernik, Uri
• Primary Examiner(s): TRAN, DUNG D
• Application Number:
  US13/644,340
• Time in Patent Office: 915 Days
• Field of Search: None
• US Class Current: 358/448
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: H04N 1/32352 Controlling detectability or arrangements to facilitate detection or retrieval of the embedded information, e.g. using markers for decoding, detection or retrieval operations H04N1/32149 and subgroups take precedence
• CPC Class Codes: H04N 1/40 Picture signal circuits H04N1/387 takes precedence
• CPC Class Codes: H04N 2201/3249 data relating to a linked page or object, e.g. hyperlink
• CPC Class Codes: H04N 2201/3254 Orientation, e.g. landscape or portrait; Location or order of the image data, e.g. in memory

Abstract

A method for identifying sections of contracts. This method works well with documents that originated from scanned images, i.e., documents that could possibly include noise and misleading cues.

Claims

1. A method for determining document structure, comprising using computerized storage, processing and programming embodied on a non-transitory computerized storage medium for:

identifying and extracting potential section markers of an input document;

identifying similar types of said potential section markers;

distinguishing between references and section markers and weeding out references, thereby identifying real section markers among said potential section markers;

said computerized programming automatically identifying legitimate and illegitimate numbering sequences, lettering sequences, or combined numbering and lettering sequences of said real section markers without operator intervention;

said computerized programming automatically identifying structural inclusion relations among said real section markers which are identified to adhere to said legitimate numbering sequences, lettering sequences, or combined numbering and lettering sequences without operator intervention; and

said computerized programming automatically generating a structured table of contents from said real, legitimately-sequenced section markers without operator intervention.

2. The method of claim 1, said potential section markers comprising letter indicators, number indicators, or both;

section indicators; and

in-line mini-section indicators.

3. The method of claim 2, said identifying similar types of said potential section markers comprising comparing and segregating said letter indicators, number indicators, or both, section indicators and in-line mini-section indicators of similar type.

4. The method of claim 3, said weeding out references comprising determining by context that a potential section marker is not in fact acting as a heading to a section, and therefor identifying said potential section marker as a reference and not a real section marker.

5. The method of claim 4, said identifying legitimate and illegitimate numbering/lettering sequences comprising comparing all of the real section markers of a given type to determine if their numbering sequence, lettering sequence, or combined numbering and lettering sequence is in fact a legitimate, ordered sequence;

and segregating legitimate sequences from illegitimate sequences.

6. The method of claim 5, said identifying structural inclusion relations comprising determining hierarchical relationships among said real, legitimately-sequenced section markers.

7. A structured table of contents product-by-process in the form of computerized text produced by a computerized device and represented in a non-transitory computerized storage medium, produced by a method for determining document structure, said method comprising:

identifying and extracting potential section markers of an input document;

identifying similar types of said potential section markers;

distinguishing between references and section markers and weeding out references, thereby identifying real section markers among said potential section markers;

said computerized device identifying legitimate and illegitimate numbering sequences, lettering sequences, or combined numbering and lettering sequences of said real section markers without operator intervention;

said computerized device identifying structural inclusion relations among said real section markers which are identified to adhere to said legitimate numbering sequences, lettering sequences, or combined numbering and lettering sequences without operator intervention; and

said computerized device generating a structured table of contents from said real, legitimately-sequenced section markers without operator intervention.

8. The product-by-process of claim 7, said method further comprising said potential section markers comprising letter indicators, number indicators, or both;

section indicators; and

in-line mini-section indicators.

9. The product-by-process of claim 8, said method further comprising said identifying similar types of said potential section markers comprising comparing and said letter indicators, number indicators, or both, section indicators and in-line mini-section indicators of similar type.

10. The product-by-process of claim 9, said method further comprising said weeding out references comprising determining by context that a potential section marker is not in fact acting as a heading to a section, and therefor identifying said potential section marker as a reference and not a real section marker.

11. The product-by-process of claim 10, said method further comprising said identifying legitimate and illegitimate numbering/lettering sequences comprising comparing all of the real section markers of a given type to determine if their numbering sequence, lettering sequence, or combined numbering and lettering sequence is in fact a legitimate, ordered sequence;

and segregating legitimate sequences from illegitimate sequences.

12. The product-by-process of claim 11, said method further comprising said identifying structural inclusion relations comprising determining hierarchical relationships among said real, legitimately-sequenced section markers.

13. An apparatus for determining document structure, comprising computerized storage, processing and programming embodied on a non-transitory computerized storage medium for:

identifying and extracting potential section markers of an input document;

identifying similar types of said potential section markers;

distinguishing between references and section markers and weeding out references, thereby identifying real section markers among said potential section markers;

said computerized programming automatically identifying legitimate and illegitimate numbering sequences, lettering sequences, or combined numbering and lettering sequences of said real section markers without operator intervention;

said computerized programming automatically identifying structural inclusion relations among said real section markers which are identified to adhere to said legitimate numbering sequences, lettering sequences, or combined numbering and lettering sequences without operator intervention; and

said computerized programming automatically generating a structured table of contents from said real, legitimately-sequenced section markers without operator intervention.

14. The apparatus of claim 13, said potential section markers comprising letter indicators, number indicators, or both;

section indicators; and

in-line mini-section indicators.

15. The apparatus of claim 14, said identifying similar types of said potential section markers comprising comparing and segregating said letter number indicators, number indicators, or both, section indicators and in-line mini-section indicators of similar type.

16. The apparatus of claim 15, said weeding out references comprising determining by context that a potential section marker is not in fact acting as a heading to a section, and therefor identifying said potential section marker as a reference and not a real section marker.

17. The apparatus of claim 16, said identifying legitimate and illegitimate numbering/lettering sequences comprising comparing all of the real section markers of a given type to determine if their numbering sequence, lettering sequence, or combined numbering and lettering sequence is in fact a legitimate, ordered sequence;

and segregating legitimate sequences from illegitimate sequences.

18. The apparatus of claim 17, said identifying structural inclusion relations comprising determining hierarchical relationships among said real, legitimately-sequenced section markers.