US 12,608,733 B2 · Method, article of manufacture, and system for providing category suggestions

Abstract

A method for categorizing a product, the method including receiving information for the product; inputting the information into a trained machine learning model for a taxonomy tree; receiving a plurality of arrays, each array representing a level in the taxonomy tree and consisting of probabilities for each category represented in the level that the product is categorized in that category; choosing, from a highest level tier array, a category having a highest probability, thereby designating a tier prediction; collecting, from a second level tier array, all children of the tier prediction; determining whether a highest probability from the children of the tier prediction exceeds a threshold, and if yes, choosing the category with the highest probably as a new tier prediction; and repeating the determining; when the threshold is not exceeded or if the tier prediction has no children, and selecting the tier prediction as a predicted category.

Claims20

Dependent claims

A method comprising:

training a machine learning model to predict classes in a taxonomy tree, wherein the machine learning model comprises hidden layers connected to output layers, the training comprising:
configuring each of the output layers of the machine learning model to correspond to different levels of the taxonomy tree, wherein nodes in the levels of the taxonomy tree correspond to categories in the taxonomy tree and subcategories of a given node of the taxonomy tree form a subtree of the given node;
configuring an output of a given output layer of the machine learning model to be fed into subsequent hidden layers of the machine learning model;
and
adding class weights to mitigate class imbalances in a dataset used in the training;
and
determining, using the trained machine learning model, a predicted category in the taxonomy tree for an item.

4 more elements

One or more non-transitory computer readable media having stored thereon computer-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method comprising:

train a machine learning model to predict classes in a taxonomy tree, wherein the machine learning model comprises hidden layers connected to output layers, the training comprising:
configure each of the output layers of the machine learning model to correspond to different levels of the taxonomy tree, wherein nodes in the levels of the taxonomy tree correspond to categories in the taxonomy tree and subcategories of a given node of the taxonomy tree form a subtree of the given node;
configure an output of a given output layer of the machine learning model to be fed into subsequent hidden layers of the machine learning model;
and
add class weights to mitigate class imbalances in a dataset used in the training;
and
determine, using the trained machine learning model, a predicted category in the taxonomy tree for an item.

4 more elements

Dependencies are inferred from the claim text.

Method, article of manufacture, and system for providing category suggestions

Life of this patent

Method, article of manufacture, and system for providing category suggestions

Life of this patent

Abstract

Claims20