Systems, apparatuses, methods, and computer program products for initiating performance of one or more item reconfiguration actions

Inventors

Villan, Ivan Borastero • Bardeskar, Sunil Anthon • Vel Murugan Chandra Mohan, Ananda • Srinivas, Chandrashekar Venkatappa • Bird, Douglas Duane

Assignees

Honeywell International Inc

Abstract

A method provided herein includes receiving item feature data representative of a plurality of item configuration features associated with a plurality of items. In some embodiments, the method includes generating a field item feature structure. In some embodiments, the method includes identifying an item of the plurality of items using the field item feature structure and an item reconfiguration candidate machine learning component of a composite machine learning model. In some embodiments, the method includes generating item reconfiguration data for the item of the plurality of items using the field item feature structure and at least one of a plurality of reconfiguration machine learning components of the composite machine learning model. In some embodiments, the method includes initiating performance of one or more item reconfiguration actions based on the item reconfiguration data.

Core Innovation

An item reconfiguration system receives item feature data representative of a plurality of item configuration features associated with a plurality of items. A first part of the item feature data is received from an internal item feature database, and a second part of the item feature data is received from an external item feature database. Based on the received item feature data, the system generates a field item feature structure comprising at least a portion of the item feature data and one or more field item predictions.

The system identifies an item of the plurality of items using the field item feature structure and an item reconfiguration candidate machine learning component of a composite machine learning model, wherein the item is a candidate for reconfiguration. The system then generates item reconfiguration data for the item using the field item feature structure and at least one of a plurality of reconfiguration machine learning components of the composite machine learning model. Predicted reconfigurations include predicted replacing of resin component and predicted replacing of metal component, as well as standardizing components and standardizing dimensions.

Based on the item reconfiguration data, the system initiates performance of one or more item reconfiguration actions. Examples of item reconfiguration actions include modifying an item inventory record and modifying an item manufacturing procedure, and rendering an item reconfiguration interface component. The composite machine learning model includes reconfiguration machine learning components for component standardization, item matching, item formation, and static item component reconfiguration, and the field item feature structure supports field item predictions derived by a field item data hub machine learning component.

Claims Coverage

The independent claims are clm-00001, clm-00012, and clm-00020, each covering a method, an apparatus, and a computer program product that together: receive internal and external item feature data, generate a field item feature structure with field item predictions, use a composite machine learning model with an item reconfiguration candidate machine learning component to identify a candidate item, use reconfiguration machine learning components to generate item reconfiguration data, and initiate item reconfiguration actions. The main inventive features are the internal/external data split, the field item feature structure with field item predictions, the composite machine learning model architecture, and the initiation of item reconfiguration actions based on the generated reconfiguration data.

Across the independent claims, the core coverage centers on using internal and external item feature databases to generate a field item feature structure with field item predictions, using an item reconfiguration candidate machine learning component within a composite machine learning model to identify an item candidate for reconfiguration, generating item reconfiguration data using reconfiguration machine learning components, and initiating one or more item reconfiguration actions based on that item reconfiguration data.

Stated Advantages

Documented Applications