US 12,596,740 B2 · Inferring right leaf-category for a product using LLM

Abstract

A categorization method is provided. Training data is received that relates to assigning a first category to a first item using first item data. The first category is based on a first node and a first sub-node associated with the first node. A machine learning model is trained to categorize the first item using the first item data. Second item data associated with a second item is received. A second category is assigned to the second item with the second item data using a machine learning model trained with the training data. The second category is based on a second node and a second sub-node associated with the second node. Additional training data is iteratively received over time to train the machine learning model over time. The additional training data relates to assigning a third category to a third item using third item data associated with the third item.

Claims20

Dependent claims

A method, comprising:

parsing training data by a machine learning model, the training data comprising assignments of first items to categories, the categories being organized in a hierarchical structure with nodes and sub-nodes under the nodes, a result of the parsing comprising at least one key:value pair for each item where a key is a subject and a value is a descriptor of the item;
training the machine learning model, based on the training data and the key:value pairs, to categorize items;
receiving a search request that includes a second item;
assigning, by the machine learning model, a second key-value pair to the second item;
assigning a second category to the second item, using the trained machine learning model, based on the search request and the second key-value pair, the second category corresponding to a second node and a second sub-node of the second node;
identifying items by the machine learning model based on the second key-value pair and the second category;
and
returning a search result including the items.

5 more elements

A non-transitory machine-readable medium having instructions embodied thereon, the instructions executable by a processor of a machine to perform operations comprising:

parsing training data by a machine learning model, the training data comprising assignments of first items to categories, the categories being organized in a hierarchical structure with nodes and sub-nodes under the nodes, a result of the parsing comprising at least one key value pair for each item where a key is a subject and a value is a descriptor of the item;
training the machine learning model, based on the training data and the key:value pairs, to categorize items;
receiving a search request that includes a second item;
assigning, by the machine learning model, a second key-value pair to the second item;
assigning a second category to the second item, using the trained machine learning model, based on the search request and the second key-value pair, the second category corresponding to a second node and a second sub-node of the second node;
identifying items by the machine learning model based on the second key-value pair and the second category;
and
returning a search result including the items.

5 more elements

A device, comprising:

a processor;
and
memory including instructions that, when executed by the processor, cause the device to perform operations including:
parsing training data by a machine learning model, the training data comprising assignments of first items to categories categories being organized in a hierarchical structure with nodes and sub-nodes under the nodes, a result of the parsing comprising at least one key:value pair for each item where a key is a subject and a value is a descriptor of the item;
training the machine learning model, based on the training data and the key:value pairs, to categorize items;
receiving a search request that includes a second item;
assigning, by the machine learning model, a second key-value pair to the second item;
assigning a second category to the second item, using the trained machine learning model, based on the search request and the second key-value pair, the second category corresponding to a second node and a second sub-node of the second node;
identifying items by the machine learning model based on the second key-value pair and the second category;
and
returning a search result including the items.

8 more elements

Dependencies are inferred from the claim text.

Inferring right leaf-category for a product using LLM

Life of this patent

Inferring right leaf-category for a product using LLM

Life of this patent

Abstract

Claims20