Product classification data transfer and management

Patent metadata

Field	Value
Publication number	US-10915557-B2
Application number	US-201514847944-A
Country	US
Kind code	B2
Filing date	Sep 8, 2015
Priority date	Jan 31, 2013
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

Computerized data processing and electronic file management methods of organizing and indexing electronic records in an electronic database for categorizing new products that are being added to an existing database of product offerings and computerized digital data processing methods of transferring digital information between a plurality of computers and employing computer instructions to categorize new products that are being added to an existing database of product offerings. Multiple classification models classify a description of a particular product and the classifications are compared, and if found to be equivalent, are added to the existing database of product offerings. If the classifications from the models are not equivalent, then the description is sent to multiple people for classification and the classifications from the people are compared, and if found to be equivalent, are added to the existing database of product offerings.

First claim

What is claimed is:

1. A computerized data processing and electronic file management method of organizing and indexing electronic records in an electronic database for categorizing new products that are being added to an existing database of product offerings, the method comprising:
classifying a particular product of the new products with at least one processor using Naïve Bayes to produce a first classification of the particular product;
classifying the particular product with the at least one processor using K-Nearest-Neighbors to produce a second classification of the particular product;
classifying the particular product with the at least one processor using Multiclass Perceptron to produce a third classification of the particular product;
evaluating, with the at least one processor, whether at least two of the first classification, the second classification or the third classification are not identical but near each other in a top-down hierarchy within a predetermined equivalence threshold, the predetermined equivalence threshold being one percent of an entire scope of classifications within the top-down hierarchy;
when the at least two of the first classification, the second classification or the third classification are not identical but near each other in the top-down hierarchy within the predetermined equivalence threshold, adding, with the at least one processor, a description of the particular product to the existing database of product offerings at each of the at least two of the first classification, the second classification or the third classification that are not identical but near each other in the top-down hierarchy within the predetermined equivalence threshold, the existing database of product offerings comprising the top-down hierarchy comprising a root level at a top of the top-down hierarchy, a product level at a bottom of the top-down hierarchy, and a product type level located between the root level and the product level;
when the first classification, the second classification, and the third classification are all not identical and all not near each other in the top-down hierarchy within the predetermined equivalence threshold:
sending, with the at least one processor, through at least one computer network, the description of the particular product and at least a portion of the top-down hierarchy to at least three different people for classification to be performed by each of the at least three different people based on the description of the particular product;
accessing, with the at least one processor, from at least two of the at least three different people, at least a fourth classification and a fifth classification of the particular product; and
when the fourth classification and the fifth classification are identical or near each other in the top-down hierarchy within the predetermined equivalence threshold, adding, with the at least one processor, the description of the particular product to the existing database of product offerings at the fourth classification; and

repeating the method for each of the new products.

2. A computerized digital data processing method of transferring digital information between a plurality of computers and employing computer instructions to categorize new products that are being added to an existing database of product offerings, the method comprising:
receiving, with a first at least one processor, from a second at least one processor, through a computer network, a description of a particular product of the new products, wherein the first at least one processor and the second at least one processor are spatially distributed;
establishing a classification of the particular product with the first at least one processor using a first classification model and using the description of the particular product to produce a first classification of the particular product;
establishing a classification of the particular product with the first at least one processor using a second classification model and using the description of the particular product to produce a second classification of the particular product, wherein the second classification model is different than the first classification model;
establishing a classification of the particular product with the first at least one processor using a third classification model and using the description of the particular product to produce a third classification of the particular product, wherein the third classification model is different than the first classification model and the third classification model is different than the second classification model;
evaluating, with the first at least one processor, whether at least two of the first classification of the particular product, the second classification of the particular product, or the third classification of the particular product are not identical but near each other in a top-down hierarchy within a predetermined equivalence threshold, the predetermined equivalence threshold being one percent of an entire scope of classifications within the top-down hierarchy;
when the at least two of the first classification of the particular product, the second classification of the particular product, or the third classification of the particular product are not identical but near each other in the top-down hierarchy within the predetermined equivalence threshold, adding, with the first at least one processor, the description of the particular product to the existing database of product offerings at each of the at least two of the first classification of the particular product, the second classification of the particular product, or the third classification of the particular product that are not identical but near each other in the top-down hierarchy within the predetermined equivalence threshold, the existing database of product offerings comprising the top-down hierarchy comprising a root level at a top of the top-down hierarchy, a product level at a bottom of the top-down hierarchy, and a product type level located between the root level and the product level;
when the first classification of the particular product, the second classification of the particular product, and the third classification of the particular product are all not identical and all not near each other in the top-down hierarchy within the predetermined equivalence threshold:
transferring, through the computer network, from the first at least one processor, the description of the particular product and at least a portion of the top-down hierarchy to a first person for classification to be performed by the first person based on the description of the particular product;
receiving, through the computer network, at the first at least one processor, from the first person, a fourth classification of the particular product;
transferring, through the computer network, from the first at least one processor, the description of the particular product and at least a portion of the top-down hierarchy to a second person for classification to be performed by the second person based on the description of the particular product;
receiving, through the computer network, at the first at least one processor, from the second person, a fifth classification of the particular product;
evaluating, with the first at least one processor, whether the fourth classification of the particular product and the fifth classification of the particular product are near each other in the top-down hierarchy within the predetermined equivalence threshold; and
adding, with the first at least one processor, the description of the particular product to the existing database of product offerings at the fourth classification of the particular product when the fourth classification of the particular product and the fifth classification of the particular product are identical or near each other

Assignees

• Wal Mart Stores Inc
• Walmart Apollo Llc

Inventors

• Garera Nikesh Lucky
• Rampalli Narasimhan
• Ravikant Dintyala Venkata Subrahmanya
• Subramaniam Srikanth
• Sun Chong
• Yalin Heather Dawn

Classifications

• G06F16/285 Primary

  Clustering or classification · CPC title

• G06Q10/087

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title