Walmart Apollo, LLC

Alessandro Magnani

Abon Chaudhuri

Venkatesh Kandaswamy

Shreyansh Prakash Gandhi

Samrat Kokkula

Abhinandan Krishnan

Behzad Ahmadi

Omer Ovenc

Theban Stanley

Qian Li

Abilash Amarthaluri

Binwei Yang

Feng Quan Liu

Shie Mannor

Min Xie

Zhenrui Wang

Ajinkya More

Sachin Adlakha

Nikita Maple Sudan

Ajit Varghese Puthenputhussery

Suthee Chaidaroon

Paolo Messina

Tom Ben Zion Zahavy

Sapeksha Virinchi Vemulapati

Isha Ghai

Jianhui Zhang

Ashley Kim

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 system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising: training a visual similarity model to output one or more vector representations in a vector space; determining one or more nearest neighbors based on embeddings nearest to a respective embedding in the vector space for the item; ranking the one or more nearest neighbors for the item in an order; re-ranking the order of the one or more nearest neighbors of the item into a re-ranked order; inserting, into a display of the item, the one or more nearest neighbors of the item; and facilitating altering a graphical user interface (GUI) to convey the display of the item. Other embodiments are disclosed herein.

Systems and methods for retraining of machine learned systems

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of receiving one or more digital images; identifying a foreground of the one or more digital images; analyzing the foreground of the one or more digital images to identify a skin region in the foreground of the one or more digital images; when the skin region is identified, clustering a non-skin remainder of the foreground of the one or more digital images into one or more clusters; extracting one or more patches of the one or more digital images from the one or more clusters of the foreground of the one or more digital images; determining one or more scores for the one or more patches of the one or more digital images; and coordinating displaying a patch of the one or more patches on an electronic display based on the one or more scores for the one or more patches. Other embodiments are disclosed herein.

Systems and methods for extracting patches from digital images

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform: training a visual similarity model; determining one or more nearest neighbors for an item using the visual similarity model, as trained; ranking the one or more nearest neighbors using results of the visual similarity model, as trained; re-ranking the one or more nearest neighbors using a learning-to-rank algorithm; and facilitating altering a graphical user interface (GUI) displaying the item based upon the one or more nearest neighbors, as re-ranked. Other embodiments are disclosed herein.

A system for retrieving products in response to a customer query includes a computing device configured to obtain query information characterizing a query initiated by the customer on an ecommerce marketplace and to determine embedding-based search results comprising a first list of items. The computing device is also configured to obtain legacy search results comprising a second list of items and to blend the embedding-based search results with the legacy search results to obtain blended search results. The computing device is also configured to send the blended search results to the customer.

Methods and apparatuses for providing search results using embedding-based retrieval

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.

This application relates to apparatus and methods for ranking search results. In some examples, a computing device receives item data identifying items for a search query provided by a user. The computing determines, for each item, a first value based on a relevance of the item to the search query. The computing device also determines user engagement data for the user, where the user engagement data identifies engagements by the user on a webpage. The computing device determines, for each item, a second value based on the user engagement data. In some examples, the computing device determines the first values and second values by executing one or more machine learning models. The computing device further determines a ranking of the plurality of items based on the first values and the second values. The computing may transmit the ranking of the plurality of items, such as to a web server.

Methods and apparatus for automatically providing a ranking of items in response to a search request

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of receiving a digital image comprising multiple items; determining an embedding for the digital image using a machine learning algorithm trained on one or more combined digital images, the combined digital image comprising one or more annotated digital images; identifying an item of the multiple items in the digital image; and facilitating an alteration of a GUI on an electronic device in response to identifying the item in the digital image.

Systems and methods for identifying items in a digital image

A system for use in monitoring an operation of a classification model in generating estimated labels for item records is described herein. The system receives a current labeling budget value including a number of trusted labels available for use in a labeling operation, determines a current selection probability for each item record included in an item list as a function of the current labeling budget value, selects a plurality of item records from the item list as a function of each corresponding current selection probability, and generates a sampling list including the selected item records. The system determines a risk measurement value associated with the classification model indicating an accuracy of the estimated labels as compared to trusted labels associated with the item records.

Server computer and networked computer system for evaluating, storing, and managing labels for classification model evaluation and training

A product image evaluation system. In embodiments, the system comprises or interacts with a product database comprising a product information record that comprises a product identifier and a product category for a product, and an image database comprising a plurality of candidate images for the product. In embodiments the image database can comprise images received from a plurality of different sources. The system can comprise a parameterized grouping engine configured to separate images into groups of similar images, an image selector configured to select one or more images from each group, and an image sorter configured to determine an order of the selected images. Embodiments can distill the superset of all available images to provide a set of images that are 'sufficiently different' from each other and satisfy quality requirements. As a result, no images containing unique information are left behind, and images containing duplicate or irrelevant information are discarded.

Product image evaluation system and method

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of receiving one or more digital images from a repository of digital images; annotating the one or more digital images from the repository of digital images; digitally altering the one or more digital images, as annotated, from the repository of digital images; digitally combining the one or more digital images, as annotated and digitally altered, with at least one or more portions of one or more other digital images of the repository of digital images to create one or more combined digital images; training a machine learning algorithm on the one or more combined digital images; and storing the machine learning algorithm, as trained, in the one or more non-transitory computer readable storage devices.

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.

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 an image at a first-level analysis component comprising a first neural network structure; analyzing, using the first neural network structure of the first-level analysis component, the image to determine an image category associated with the image; selecting at least one second-level analysis component that is associated with the image category to analyze the image; analyzing, using a second neural network structure associated with the at least one second-level analysis component that was selected, the image to determine whether the image includes non-compliant content; and in response to determining that the image includes non-compliant content, executing a corrective measure. Other embodiments are disclosed herein.

Systems and methods for detecting content in images using neural network architectures

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

Menlo Park, CA, United States of America

Alessandro Magnani