Systems and methods for electronic document genre classification using document grammars
AssigneeXerox Corporation
InventorJohn C. Handley
Life of this patent
Estimating the term…
Abstract
A system for classifying a genre of an electronic document may include a network processor configured to receive an electronic document and convert the electronic document to rich text format (RTF). The processor may be configured to parse the RTF document into lines of text ordered from top to bottom and left to right and assign tokens to each line of text based on content of the line and to line separators based on space between blocks of lines. The network processor may be configured to sequence the tokens, parse the tokenized document with a number of pre-defined document grammars, determine a probability for each genre corresponding to the electronic document, and classify the electronic document as the genre with the highest probability.
Claims11
A system for classifying a genre of an electronic document, comprising:
- a network processor configured to receive an electronic document;
- convert the electronic document to rich text format (RTF) using optical character recognition technology;
- parse the RTF document into lines of text ordered from top to bottom and left to right, and into line separators based on space between blocks of the lines of text;
- assign tokens to each of the lines of text based on content of the line of text and to each of the line separators;
- sequence the tokens;
- parse the tokenized document with a number of pre-defined document grammars;
- determine a probability for each genre corresponding to the electronic document based on the parsed tokenized document;
- classify the electronic document as the genre with the highest probability;
- and route the electronic document to at least one output device based on the genre classification.
A method for classifying a genre of an electronic document, comprising:
- receiving an electronic document;
- converting the electronic document to rich text format (RTF) using optical character recognition technology;
- parsing the RTF document into lines of text ordered from top to bottom and left to right, and into line separators based on space between blocks of the lines of text;
- assigning tokens to each of the lines of text based on the content the line of text and to each of the line separators;
- sequencing the tokens;
- parsing the tokenized document with a number of pre-defined document grammars;
- determining a probability for each genre corresponding to the electronic document based on the parsed tokenized document;
- classifying the electronic document as the genre with the highest probability;
- and
- routing the electronic document to at least one output device based on the classification.
Dependencies are inferred from the claim text.