Toshiba Global Commerce Solutions Holdings Corporation

Andrei Khaitas

Jonathan M Waite

Charles Ray Kirk

Zachary McCain Darden

Evgeny Shevtsov

Yevgeni Tsirulnik

J Wacho Slaughter

Srija Ganguly

Brad Matthew Johnson

Susan Winter Brosnan

Andrew Norris

Abhishekh Padmanabhan

Adam Archambault

Valentine Mourzenok

The present disclosure provides a system and method for identifying items. The method includes scanning a first item using a first barcode scanner and a second barcode scanner and determining, based on signals from the first barcode scanner and the second barcode scanner, a first two-dimensional light grid indicating where the first item broke beams of the first barcode scanner and the second barcode scanner. The method also includes predicting, using a machine learning model and based on the first two-dimensional light grid, a first category for the first item, receiving, from a camera, an image of the first item, and comparing the image of the first item to a first set of images assigned to the first category to determine an identity of the first item.

Bi-optic object classification system

Computer vision grouping recognition is provided by receiving training images that include unpackaged items; identifying, by a computer vision model, a candidate identities for unpackaged items in a given training image; receiving, from a human user, a selected identity for the unpackaged item as feedback for the candidate identity; constructing a confusion matrix tallying matches and mismatches between candidate identities and the selected identities as analyzed across the training images for each unpackaged item; identifying at least one product category that includes at least a first unpackaged item and a second unpackaged item that the confusion matrix indicates as being misidentified for each other by the computer vision model; and reconfiguring the computer vision model to identify the product category instead of the first unpackaged item or the second unpackaged item when analyzing a given image including one or more of the first unpackaged item or the second unpackaged item.

Computer vision grouping recognition system

The disclosure provides a method of generating business rules for a retail system. Particularly, a computing device receives rule data from a user interface. The rule data comprises retail context information associated with a retail business operating the retail system. A business rule template is then generated based on the retail context information included in the rule data, and validated based on the retail context information and on sample business data. Validation may occur by conditionally performing one or more Point of Sale (POS) functions on the sample business data according to the retail context information. If valid, the business rule template is activated for use in the retail system.

Retail user interface for dynamic behavior configuration

Techniques for configuration management are provided. A plurality of configurations is received, where each of the plurality of configurations corresponds to a respective service and is associated with a first plan. The plurality of configurations is stored, in association with the first plan, without implementing the plurality of configurations. Upon receiving approval of the first plan, the first plan is implemented by, for each respective configuration of the plurality of configurations: identifying a respective corresponding service for the respective configuration and modifying a configuration of the respective corresponding service based on the respective configuration. Upon completing implementation of the first plan, each of the plurality of configurations is labeled with a production identifier.

Management of configuration modifications in distributed data systems

Growing community of inventors

McKinney, TX, United States of America

Andrei Khaitas