Wei Min Peng

US Patent:

8060512, Nov 15, 2011

Filed:

Jun 5, 2009

Appl. No.:

12/479392

Inventors:

Wei Peng - Webster NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 7/00
G06F 17/30

US Classification:

707737, 706 48

Abstract:

What is disclosed is a novel system and method for analyzing multi-dimensional cluster data sets to identify clusters of related documents in an electronic document storage system. Digital documents, for which multi-dimensional probabilistic relationships are to be determined, are received and then parsed to identify multi-dimensional count data with at least three dimensions. Multi-dimensional tensors representing the count data and estimated cluster membership probabilities are created. The tensors are then iteratively processed using a first and a complementary second tensor factorization model to refine the cluster definition matrices until a convergence criteria has been satisfied. Likely cluster memberships for the count data are determined based upon the refinements made to the cluster definition matrices by the alternating tensor factorization models. The present method advantageously extends to the field of tensor analysis a combination of Non-negative Matrix Factorization and Probabilistic Latent Semantic Analysis to decompose non-negative data.

US Patent:

8452770, May 28, 2013

Filed:

Jul 15, 2010

Appl. No.:

12/837021

Inventors:

Wei Peng - Webster NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 17/30

US Classification:

707737, 706 52

Abstract:

Methods and systems for clustering information items using nonnegative tensor factorization are disclosed. A processing device receives one or more class labels, each corresponding to an information item, a selection for a nonnegative tensor factorization model having an associated objective function and one or more parameter values, each corresponding to one of one or more penalty constraints. The processing device determines a constrained objective function based on the objective function associated with the selected nonnegative tensor factorization model, the one or more parameter values and the one or more class labels and including the one or more penalty constraints. The processing device determines clusters for the plurality of information items by evaluating the constrained objective function. Pairwise constraints may be received in addition to or instead of the class labels.

US Patent:

8521549, Aug 27, 2013

Filed:

Sep 19, 2011

Appl. No.:

13/236252

Inventors:

Wei Peng - Webster NY, US
Shi Zhao - Rochester NY, US
Sudhendu Rai - Fairport NY, US
David Thomas Ashby - Pittsford NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06Q 10/00

US Classification:

705 11, 705 263, 705 2635, 705 264, 705347

Abstract:

A method of recommending vendors to bid on a print job may include identifying a print job for which a recommendation of vendors to bid on the print job is desired and identifying one or more vendors as potential bidders for the print job. The method may include, for each identified vendor, determining, by a computing device, a bidding probability associated with the vendor, a winning probability associated with the vendor, a recommendation probability associated with the vendor, and identifying the vendor as a recommended vendor based on the associated recommendation probability. The method may include notifying a user of the recommended vendors.

US Patent:

8615713, Dec 24, 2013

Filed:

Jun 26, 2009

Appl. No.:

12/492709

Inventors:

Tong Sun - Penfield NY, US
Jonas Karlsson - Rochester NY, US
Wei Peng - Webster NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 3/00

US Classification:

715757, 715804

Abstract:

Embodiments described herein are directed to managing document interactions in a collaborative document area of a virtual world. Document interactions of avatars in the collaborative document area of the virtual world are captured by an interaction tool deployed in the collaborative document area. The document interactions are related to at least one document in the collaborative document area. The document interactions are associated with the at least one document based on a reference scheme applied to the collaborative document area by an interaction association unit.

US Patent:

20100332998, Dec 30, 2010

Filed:

Jun 26, 2009

Appl. No.:

12/492533

Inventors:

Tong Sun - Penfield NY, US
Jonas Karlsson - Rochester NY, US
Wei Peng - Webster NY, US

Assignee:

XEROX CORPORATION - Norwalk CT

International Classification:

G06F 3/048

US Classification:

715757

Abstract:

Embodiments described herein are directed to a collaborative document environment for reviewing a collection of documents stored in a repository of a document management system. A shared collaborative document area in a virtual world is associated with a corresponding collection of documents in a document management system. The shared collaborative document area is customized based on a semantic context of the documents in the collection of documents.

US Patent:

20110131536, Jun 2, 2011

Filed:

Dec 2, 2009

Appl. No.:

12/629401

Inventors:

Wei Peng - Webster NY, US
Tong Sun - Penfield NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 17/30
G06F 3/048
G06F 3/01

US Classification:

715848, 707748, 707769, 715753, 707E17014, 707E17017

Abstract:

Embodiments described herein are directed to forming information units. Digital documents associated with collaborative navigation behavior information can be identified and an information unit can be generated using transition probabilities calculated from collaborative navigation information. The information unit including at least a subset of the digital documents identified in the collaborative navigation behavior information. A rank of information unit based on the collaborative navigation behavior information can be calculated.

US Patent:

20120154850, Jun 21, 2012

Filed:

Dec 17, 2010

Appl. No.:

12/971846

Inventors:

Shi Zhao - Rochester NY, US
Sudhendu Rai - Fairport NY, US
Wei Peng - Sunnyvale CA, US

Assignee:

XEROX CORPORATION - Norwalk CT

International Classification:

G06F 17/00
G06F 3/12

US Classification:

358 115, 705400

Abstract:

A method of estimating the cost of a target print job may include identifying a target print job having a document type and one or more attributes, for each attribute of the target print job, determining a correlation between the attribute and a cost of the target print job using a plurality of historical print jobs associated with the document type, and identifying one or more of the attributes as cost drivers based on the correlation of the attribute to the cost of the target print job. The method may include identifying one or more relevant historical print jobs from the plurality of historical print jobs based on values for the identified cost drivers, estimating a cost of the target print job using the one or more relevant historical print jobs, and displaying the estimated cost associated with the target print job.

US Patent:

20150052120, Feb 19, 2015

Filed:

Aug 13, 2013

Appl. No.:

13/965924

Inventors:

- Norwalk CT, US
Saurabh Kataria - Webster NY, US
Wei Peng - Fremont CA, US
Tong Sun - Penfield NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 17/30

US Classification:

707723

Abstract:

A method, non-transitory computer readable medium, and apparatus for extracting text from a social media document are disclosed. For example, the method indexes a plurality of social media documents into a plurality of snippets, receives a query including one or more keywords and a purpose, identifies one or more of the plurality of snippets that include the one or more keywords in an index, ranks the one or more of the plurality of snippets in accordance with the purpose and provides the one or more plurality of snippets that are ranked in accordance with the purpose.