Print path obfuscation method and system for document content analytics assessment

Patent metadata

Field	Value
Publication number	US-2016132277-A1
Application number	US-201414539492-A
Country	US
Kind code	A1
Filing date	Nov 12, 2014
Priority date	Nov 12, 2014
Publication date	May 12, 2016
Grant date	—

Abstract

Disclosed is a method and system of differential processing a print job including one or more original documents to render an obfuscated version of the print job. According to an exemplary method, the differential process replaces letters of an original document with randomly selected characters of substantially the same size and location as the original document and objects such as images/graphics are replaced with blurred versions of substantially the same size and locations as the objects in the original document. The differential process creates an obfuscated version of the print job which is illegible and useful for further processing where privacy of documents included in the print job is required.

First claim

What is claimed is:

1 . A computer-implemented method of differential processing a print job to be printed by a printing device, the differential process generating an obfuscated version of the print job for further processing, the method comprising:
a) acquiring a PDL version of the print job destined for the printing device, the PDL version of the print job including one or more of textual content and image content; and b) differential processing the PDL version of the print job to generate the obfuscated version of the print job, the differential processing obfuscating the textual content with a first differential process and obfuscating one or more portions of the image content with a second differential process, the first and second differential processes obfuscating one or more portions of the textual content and image content, respectively, such that the textual content and image content is illegible while preserving an overall shape and location of the textual content and image content.

2 . The method of differential processing a print job according to claim 1 , comprising:
c) labeling the obfuscated version of the print job according to one or more of a plurality of categories.

3 . The method of differential processing a print job according to claim 2 , wherein the categories include one or more of emails, tables, reports, letters, forms, and articles.

4 . The method of differential processing a print job according to claim 2 , wherein step c) is performed manually by a person.

5 . The method of differential processing a print job according to claim 2 , wherein step c) accesses a categorization model to label the obfuscated version of the print job, the categorization model based on a plurality of obfuscated versions of training print jobs.

6 . The method of differential processing a print job according to claim 2 , wherein steps a) and b) are performed at a location associated with the printing device and step c) is performed by a third-party at a location remote from the printing device.

7 . The method of differential processing a print job according to claim 1 , wherein the first differential process replaces a plurality of textual characters with random characters.

8 . The method of differential processing a print job according to claim 1 , wherein the second differential process performs one or more of blurring, size-adaptive blurring, pixel randomization and replacement of the image content with a fixed pattern.

9 . An image processing system comprising memory storing instructions for performing the computer-implemented method of differential processing a print job to be printed by a printing device according to claim 1 , and a processor operatively communicating with the memory which executes the instructions.

10 . The method of differential processing a print job according to claim 1 , comprising:
c) generating a categorization model to label the PDL print job, the categorization model based, in part, on the obfuscated version of the print job generated in step b).

11 . The method of differential processing a print job according to claim 10 , comprising:
d) labeling the PDL print job according to one or more of a plurality of categories associated with the categorization model.

12 . The method of differential processing a print job according to claim 11 , wherein steps a), b) and d) are performed at a location associated with the printing device and step c) is performed by a third-party at a location remote from the printing device.

13 . The method of differential processing a print job according to claim 10 , wherein the first differential process replaces a plurality of textual characters with random characters.

14 . The method of differential processing a print job according to claim 10 , wherein the second differential process performs one or more of blurring, size-adaptive blurring, pixel randomization and replacement of the image content with a fixed pattern.

15 . A system for differential processing a print job to be printed by a printing device, the differential process generating an obfuscated version of the print job for further processing, the system comprising:
an acquiring component, the acquiring component configured to acquire a PDL version of the print job destined for the printing device, the PDL version of the print job including one or more of textual content and image content; a differential processing component, the differential processing unit configured to generate the obfuscated version of the print job, the differential processing component obfuscating one or more portions of the textual content with a first differential process and obfuscating one or more portions of the image content with a second differential process, the first and second differential process obfuscating the textual content and image content, respectively, such that the textual content and image content is illegible while preserving an overall shape and location of the textual content and image content; and a processor configured to implement the acquiring component and differential processing component.

16 . The system for differential processing a print job according to claim 15 , comprising:
a labeling component, the labeling component labeling the obfuscated version of the print job according to one of a plurality of categories.

17 . The system for differential processing a print job according to claim 16 , wherein the categories include one or more of emails, tables, reports, letters, forms and articles.

18 . The system for differential processing a print job according to claim 16 , wherein the labeling component is configured to receive a manually provided input to label the obfuscated version of the print job.

19 . The system for differential processing a print job according to claim 16 , wherein the labeling component accesses a categorization model to label the obfuscated version of the print job, the categorization model based on a plurality of obfuscated versions of training print jobs.

20 . The system for differential processing a print job according to claim 15 , wherein the first differential process replaces a plurality of textual characters with random characters.

21 . The system for differential processing a print job according to claim 15 , wherein the second differential process performs one or more of blurring, size-adaptive blurring, pixel randomization and replacement of the image content with a fixed pattern.

22 . The system for differential processing a print job according to claim 15 , comprising:
a labeling component, the labelling component labeling the PDL print job according to one of a plurality of categories, wherein the labeling component accesses a categorization model based, in part, on an obfuscated version of the print job.

23 . The system for differential processing a print job according to claim 22 , wherein the categorization model is based on a plurality of obfuscated versions of training print jobs generated by the differential processing component, the training print jobs including one or more of the PDL version of the print job destined for the printing device and other PDL print jobs.

24 . A computer-implemented method for performing paper analytics associated with one or more printing devices, the method comprising:
a) acquiring PDL versions of the print jobs destined for the one or more printing devices; b) differential processing

Assignees

• Xerox Corp

Inventors

• Csurka Gabriela
• Pouyadou Jerome
• Willamowski Jutta Katharina
• Hoppenot Yves

Classifications

• G06K15/4095 Primary

  Secure printing (computer driven secure printing G06F3/1238) · CPC title

• G06K15/1867 Primary

  Post-processing of the composed and rasterized print image (scanning, transmission or reproduction of documents H04N1/00) · CPC title

• G06F40/12

  Use of codes for handling textual entities · CPC title

• H04N1/00

  Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof · CPC title

• G06F3/1238 Primary

  Secure printing, e.g. user identification, user rights for device usage, unallowed content, blanking portions or fields of a page, releasing held jobs · CPC title