Walmart Apollo, LLC

Abhinandan Krishnan

Abon Chaudhuri

Alessandro Magnani

Venkatesh Kandaswamy

Shreyansh Prakash Gandhi

Samrat Kokkula

Yanxin Pan

Swagata Chakraborty

Aakash Mayur Mehta

Kyu Bin Kim

Edison Mingtao Zhang

Shie Mannor

Abilash Amarthaluri

Ajinkya More

Bodhisattwa Prasad Majumder

Aditya Subramanian

Tom Ben Zion Zahavy

A system including one or more processors and one or more non-transitory computer-readable storage media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: training a neural network detection model with a training dataset comprising synthetic training images by: using a transformation algorithm to create the synthetic training images by appending edge case training images to one or more compliant images; receiving, at the neural network detection model, as trained, at least one image; and determining, using the neural network detection model, as trained, whether the at least one image comprises non-compliant content. Other embodiments are disclosed herein.

Systems, methods, and techniques for training neural networks and utilizing the neural networks to detect non-compliant content

A method including obtaining image data and attribute information of a first item in an item catalog. The method also can include generating candidate variant items from the item catalog for the first item using a combination of (a) a k-nearest neighbors approach to search for first candidate variant items based on text embeddings for the attribute information of the first item, and (b) an elastic search approach to search for second candidate variant items based on image embeddings for the image data of the first item. The method additionally can include performing respective classifications based on respective pairs comprising the first item and each of the candidate variant items to filter the candidate variant items. The method further can include determining a respective distance between the first item and each of the candidate variant items, as filtered. The method additionally can include determining one or more items in the candidate variant items, as filtered, to include in a variant group for the first item, based on a decision function using a predetermined threshold and the respective distance for the each of the candidate variant items, as filtered. Other embodiments are described.

Automatically determining items to include in a variant group

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform obtaining a set of items that have been grouped together as matching items in a group; performing an ensemble mismatch detection; performing multiple detection models on the set of items to generate respective outputs regarding mismatches; combining the respective outputs to determine whether a quantity of detected mismatches is at least a predetermined threshold; when the quantity of detected mismatches is at least the predetermined threshold, the acts also can include separating at least one of the set of items from the group; and when the quantity of detected mismatches is not at least the predetermined threshold, the acts additionally can include maintaining each item of the set of items in the group. Other embodiments are disclosed.

Mismatch detection model

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of receiving attribute data comprising a set of unstructured attribute data and a set of structured attribute data, analyzing the set of unstructured attribute data by processing through a first set of one or more Long Short Term Memory (LSTM) layers, to obtain an unstructured semantic signature, analyzing the set of the structured attribute data by processing through a first set of one or more Convolutional Neural Network (CNN) layers, to obtain a structured semantic signature, analyzing the unstructured semantic signature and the structured semantic signature, and classifying the item in one or more item categories. Other embodiments are disclosed herein.

Systems and methods for classification using structured and unstructured attributes

A system can include one or more processors and one or more non-transitory computer-readable storage media storing computing instructions configured to run on the one or more processors and perform: generating a training dataset for training a neural network detection model; identifying, using the neural network detection model, as trained, the non-compliant content in the synthetic training images; receiving, at the neural network detection model, at least one image; and utilizing the neural network detection model to determine whether the at least one image comprises the non-compliant content. Other embodiments are disclosed herein.

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of: generating a training dataset comprising synthetic training images for training a neural network detection model to identify non-compliant content in images; executing a training procedure that utilizes the synthetic training images to train the neural network detection model to identify the non-compliant content; receiving, at the neural network detection model, at least one image; and utilizing the neural network detection model to determine whether the at least one image includes the non-compliant content. Other embodiments are disclosed herein.

Some embodiments can comprise a system comprising one or more computer processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more computer processing modules a perform acts of: receiving, at the one or more computer processing modules and from a third-party electronic device, a title for a product; dividing, at the one or more computer processing modules, the title into a sequence of tokens; storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the sequence of tokens; determining, at the one or more computer processing modules and using a sequence labeling model, a type of each token of the sequence of tokens; storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the type of each token of the sequence of tokens; encoding, at the one or more computer processing modules, each token of the sequence of tokens to indicate the type of each token of the sequence of tokens, wherein the type of each token of the sequence of tokens can comprise a BIO encoding scheme, wherein: a label B of the BIO encoding scheme can indicate a first token of a brand name; a label I of the BIO encoding scheme can indicate a subsequent token of the brand name; and a label O of the BIO encoding scheme can indicate a token that is not part of the brand name; determining, at the one or more computer processing modules, a brand name present in the title using each token of the sequence of tokens, as encoded; storing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the brand name present in the title; normalizing, at the one or more computer processing modules, the brand name present in the title to create a standardized representation of the brand name; writing, by the one or more computer processing modules onto the one or more non-transitory storage modules, the standardized representation of the brand name present in the title to an empty database entry associated with the product; and in response to a search request from a user, transmitting instructions to a user display to display a representation of the standardized representation of the brand name for each token of the sequence of tokens. Other embodiments are also disclosed herein.

Method and system for attribute extraction from product titles using sequence labeling algorithms

A multi-modal computer classification network system for use in classifying data records is described herein. The system includes a memory device, a first classification computer server, a second classification computer server, and a policy computer server. The memory device includes an item records database and a labeling database. The first classification computer server includes a first classifier program that is configured to select an item record from the item database and generate a first classification record including a first ranked list of class labels. The second classification computer server includes a second classifier program that is configured to generate a second classification record including a second ranked list of class labels. The policy computer server includes a policy network that is programmed to determine a predicted class label based on the first and second ranked lists of class labels.

Growing community of inventors

Sunnyvale, CA, United States of America

Abhinandan Krishnan