Print job aesthetics enhancements detection and modeling through combined user activity analysis and content matching

• US 7,898,696 B2
• Filed: 05/09/2007
• Issued: 03/01/2011
• Est. Priority Date: 05/09/2007
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Colombino, Tommaso, Marchesotti, Luca
• Primary Examiner(s): Haskins; Twyler L
• Assistant Examiner(s): BURLESON, MICHAEL L
• Application Number:
  US11/801,230
• Publication Number:
  US 20080278744A1
• Time in Patent Office: 1,392 Days
• Field of Search: 358/3.27, 358/1.9, 358/1.15, 358/504
• US Class Current: 358/3.27
• CPC Class Codes: G06F 3/1208 resulting in improved quality of the output result, e.g. print layout, colours, workflows, print preview
• CPC Class Codes: G06F 3/1256 User feedback, e.g. print preview, test print, proofing, pre-flight checks
• CPC Class Codes: G06F 3/1257 by using pre-stored settings, e.g. job templates, presets, print styles
• CPC Class Codes: G06F 3/1284 Local printer device
• CPC Class Codes: G06F 3/1285 Remote printer device, e.g. being remote from client or server
• CPC Class Codes: H04N 1/603 controlled by characteristics of the picture signal generator or the picture reproducer

Abstract

An automated method for processing a print job includes receiving a submitted print job, extracting features from the submitted print job for characterizing the print job, comparing the extracted features with a predictive model which is based on features extracted from prior print jobs and enhancement operations performed on the prior print jobs, and generating at least one proposed enhancement operation for the submitted print job based on the comparison. The proposed enhancement operations may be presented to an operator for verification or, if the enhancement operations are determined to have a threshold level of confidence, may be automatically applied to the print job.

Claims

1. An automated method for processing a print job comprising:

generating a predictive model, comprising, for each of multiple prior print jobs;

characterizing the prior print job through a set of features;

and

associating any enhancement operations performed on the prior print job with the characterized prior print job;

thereafter, receiving a submitted print job;

extracting features from the submitted print job for characterizing the print job;

comparing the extracted features of the submitted print job with the predictive model, including computing a similarity measure to identify at least one closest matching prior characterized print job based on its set of features; and

generating at least one proposed enhancement operation for the submitted print job based on the enhancement operations performed on the at least one closest matching prior print job identified in the comparison.

2. The method of claim 1 further comprising:

determining a confidence measure that a probability that the features of the submitted print job match the features of a prior print job stored in the model, such that the proposed at least one enhancement operation is appropriate for the submitted print job and, where the determined confidence exceeds a threshold level, automatically printing the print job with the at least one proposed enhancement operation.

3. The method of claim 1 further comprising:

presenting the print job with the at least one proposed enhancement operation to an operator and, if accepted by the operator, printing the print job incorporating the proposed at least one enhancement operation.

4. The method of claim 3, wherein the at least one proposed enhancement operation for the print job is presented to an operator via a graphical user interface.

5. The method of claim 3, wherein if at least one of the proposed enhancement operation is rejected by the operator, providing the operator access to manual enhancement operations.

6. The method of claim 5, further comprising, logging manual enhancement operations selected by the operator for updating the predictive model.

7. The method of claim 1, wherein the features are selected from the group consisting of:

print job level features related to the print job;

document level features related to a document within the print job;

object level features related to sub-parts which compose the document; and

combinations thereof.

8. The method of claim 7, wherein the features include at least one print job level feature selected from the group consisting of:

a customer identification;

a job type;

a number of copies of the same document;

a paper size;

an imposition method;

a time the job was launched;

a print range; and

combinations thereof.

9. The method of claim 7, wherein the features include at least one print document level feature selected from the group consisting of:

color mode;

relative amount of black toner to be using when printing grays and black;

number of pages; and

combinations thereof.

10. The method of claim 7, wherein the features include at least one object level feature selected from the group consisting of:

image mean contrast;

image saturation, image exposure;

image color balance;

number of text blocks;

header and footer characteristics;

ratio of a number of text blocks to a number of images;

background color; and

combinations thereof.

11. The method of claim 1, wherein the features are selected so as to characterize jobs from a given customer according to their typology.

12. The method of claim 1, wherein at least one of the printing parameters performed on the prior print jobs is selected from the group consisting of:

a selection of an emulation mode;

a tone reproduction curve selected for at least one of the available colorants to be used in rendering the print job;

a selection of a screening method;

a brightness modification;

a contrast modification;

a selection of a gray component replacement parameter;

a selection of an ink saving parameter; and

combinations thereof.

13. The method of claim 1, further comprising, prior to submitting the print job, generating the model.

14. The method of claim 1, wherein the associating of any enhancement operations includes creating a history track for a prior print job which links test print jobs, printed prior to production printing of the print job, and their associated enhancement operations with the prior print job.

15. A computer program product comprising a tangible computer-readable recording medium encoding instructions, which when executed on a computer causes the computer to perform the method of claim 1.

16. The method of claim 1, wherein the computing of the similarity measure includes computing a features vector for the submitted print job and comparing the computed features vector with features vectors of prior print jobs stored in the model.

24. The method of claim 8, wherein the at least one print job level feature include a customer identification and a job type.

17. A print management system for processing a print job comprising:

a model in which for each of multiple prior print jobs, features extracted from the prior print job are linked to enhancement operations which were performed on the prior print job, the features including an identification of a customer that submitted the print job; and

an automated aesthetics enhancement tool which extracts features from a submitted print job, compares the extracted features with the model and generates proposed enhancement operations for the submitted print job based on the comparison.

18. The print management system of claim 17, wherein the an automated aesthetics enhancement tool determines a confidence that the proposed enhancement operations are appropriate for the submitted print job and, where the confidence exceeds a threshold level, automatically causes the print job to be printed with the proposed enhancement operations.

19. A printing system comprising the print management system of claim 17 and a digital press for printing the print job on print media.

20. The printing system of claim 19, further comprising a user interface for presenting proposed enhancement operations to an operator and enabling the user to verify the proposed enhancement operations.

21. A method for generating a model for proposing automated enhancement operations for a submitted print job comprising:

for each of a plurality of print jobs;

characterizing the print job through a set of features including a print job level feature related to the print job, and at least one of a document level feature related to a document within the print job and an object level feature related to sub-parts which compose the document

associating any enhancement operations performed by an operator on the print job with the characterized print job, including, for each of a plurality of print jobs, creating a history track which links test print jobs printed prior to production printing and their associated enhancement operations with the print job; and

modeling the characterized print jobs and associated enhancement operations, whereby proposed enhancement operations for a submitted print job are generated when the model is accessed with features of the submitted print job.

22. The method of claim 21, wherein the characterizing of the print job through a set of features comprises computing a features vector and wherein the associating any enhancement operations performed by an operator on the print job comprises computing an enhancement operations vector.

23. The method of claim 21, wherein the modeling exploits a supervised learning method.