Back to results
US 2006/0149775 A1Published application
Document segmentation based on visual gaps
AssigneeGoogle Inc.
InventorDaniel Egnor
Life of this patent
Estimating the term…
Abstract
A document may be segmented based on a visual model of the document. The visual model is determined according to an amount of visual white space or gaps that are in the document. In one implementation, the visual model is used to identify a hierarchical structure of the document, which may then be used to segment the document.
Claims26
A method for segmenting a document comprising:
- generating a visual model of the document;
- identifying a hierarchical structure of the document based on the visual model;
- and
- segmenting the document based on the hierarchical structure and the visual model of the document.
1 more element
A computer-readable medium containing programming instructions for execution by a processor, the computer-readable medium comprising:
- programming instructions for generating a visual model of a document that includes at least one geographical signal;
- programming instructions for identifying a hierarchical structure of the document based on the visual model;
- and
- programming instructions for associating the at least one geographical signal with portions of the document based on the identified hierarchical structure of the document.
1 more element
A method of indexing a document comprising:
- identifying geographic signals in the document;
- segmenting the document into a plurality of sections that correspond to different ones of the identified geographic signals based on a visual layout of the document;
- and
- indexing text in the plurality of sections of the document as corresponding to business information associated with the geographic signals.
1 more element
A system comprising:
- means for identifying geographic signals in a document;
- means for segmenting the document into a plurality of sections that correspond to different ones of the identified geographic signals based on a visual layout of the document;
- means for indexing text in the plurality of sections of the document as corresponding to business listings associated with the geographic signals;
- and
- means for storing the indexed text.
2 more elements
A device comprising:
- a processor;
- and
- a computer-readable memory coupled to the processor and containing instructions that when executed by the processor cause the processor to:
- identifying a document that includes signals,
- segment the document into a plurality of sections that correspond to different ones of the identified signals based on a visual layout of the document, and
- index text in the plurality of sections of the document as corresponding to the signals.
3 more elements
A method comprising:
- identifying a document for indexing into a search engine index;
- identifying references to business listings in the document;
- generating a model of the document based on a visual layout of a displayed version of the document;
- hierarchically segmenting the document based on the model and the references to the business listings;
- and
- associating content in the document with particular ones of the business listings based on the hierarchical segmentation of the document.
3 more elements
Dependencies are inferred from the claim text.