Kyocera Document Solutions Inc.

Matthew Yoshio Morikawa

Javier A Morales

Oleg Y Zakharov

A printing system includes a printing device. The printing system also includes a preflight system that checks incoming print jobs for possible errors or issues before commencing printing operations. The preflight system implements a generative adversarial network to facilitate the identification of possible problems with printing. The generative adversarial network includes a generative neural network and a discriminatory neural network. The generative neural network introduces errors into input data to train the discriminatory neural network in identifying problems with print jobs. The discriminatory neural network backpropagates its output to train the generative neural network.

Machine learning preflight printing system and methods

System(s)/method(s) relate to machine learning to automatically respond for troubleshooting a device. A programmed computer system obtains a training dataset from at least one database including historical customer complaint records and maintenance service records with resolution codes. The training dataset is parsed by a natural language extraction engine to extract data including extracting keyword data from the historical customer complaint records. The extracted data is grouped into bags-of-words with a natural language association engine. The bags-of-words are mapped to one or more of the resolution codes with an SVM to provide corresponding mapping vectors. A current customer complaint record is received and information therein is parsed to provide a request bag-of-words. One or more of the mapping vectors having one or more most likely fits to the request bag-of-words is determined. One or more of the resolution codes associated with the one or more of the mapping vectors is provided.

Growing community of inventors

Concord, CA, United States of America

Matthew Yoshio Morikawa