Method for automated document selection
AssigneeXerox Corporation
InventorsAnn L. McCarthy, Karen M. Braun, Steven J. Harrington
Life of this patent
Estimating the term…
Abstract
Provided is a method for the automated selection of sample documents or pages from a large collection, and more particularly an application of the method in a proof presentment environment—where the method is employed for selection and review of representative or extreme pages from a large document, such as one scheduled for printing. The method characterizes pages or documents in a multi-dimensional vector space based upon a set of characteristics, and then uses clustering techniques to group the pages, enabling the selection of typical pages from the groups, outlier pages from extremes lying outside of the groups, or both typical and outlier pages.
Claims15
A method for automated document subset selection from a stored body of knowledge, comprising:
- accessing the body of knowledge, including a plurality of documents therein;
- characterizing at least a portion of the body of knowledge in a characterization space wherein characterizing at least a portion of the body of knowledge processes each document in said body of knowledge, including determining, for each document, a plurality of vectors to represent each of a plurality of characteristics of the document, and representing each document in a multidimensional vector space based upon the plurality of vectors;
- grouping the documents into a plurality of groups;
- and
- automatically selecting, based upon said grouping, a subset of the body of knowledge for presentment.
In electronic document processing, a method for pre-flight checking at least one electronic document intended for printing, wherein the at least one electronic document represents a body of knowledge, including:
- characterizing a plurality of pages of the document, and the body of knowledge, in a multidimensional vector characterization space, by processing each page in said at least one document, including determining, for each page, a plurality of vectors to represent each of a plurality of characteristics of the page, and representing each page in a multidimensional vector space based upon the plurality of vectors;
- grouping at least some of the plurality of pages into at least one group;
- and
- selecting, based upon the grouping, at least one page from the body of knowledge for presentment.
A method for automated document subset selection for printing, from a stored body of knowledge, comprising:
- accessing the body of knowledge, including a plurality of documents therein;
- characterizing at least a portion of the body of knowledge in a multidimensional vector characterization space, wherein characterizing at least a portion of the body of knowledge further comprises locating, in the multidimensional vector characterization space, the position of a page as a function of the value of at least two document characteristics;
- grouping the documents into a plurality of groups;
- and
- automatically selecting, based upon said grouping, a subset of the body of knowledge for presentment, including printing at least one page of the subset as a proof page.
Dependencies are inferred from the claim text.