Target Brands, Inc.

Ryan David Siskind

Nicholas Scott Eggert

Corey Hadden

Stephen Radachy

Rachel Alderman

Edgar Cobos

Matthew Nokleby

Shalin Shah

Andrew James Wipf

Christopher Mark Brakob

Amit Pande

Jacob Portnoy

Jamie Barras

Francisco Cancino, Iii

Kathleen Jacqueline Roush

Brian Copeland

Methods and systems for performing named entity recognition are disclosed. One method includes using a multi-task approach to fine-tune a neural network to perform named entity recognition. A multi-task objective function can include a combination of a triplet loss and a named entity recognition loss. The triplet loss can include the use of supplementary texts. The method further includes using the fine-tuned neural network to identify one or more named entities in a text. Aspects of the disclosure also include integrating named entity recognition with one or more other natural language processing tasks.

Multi-task triplet loss for named entity recognition using supplementary text

Methods and systems for performing multi-task learning of query intent and named entities are provided. One method includes receiving a query comprising query text. The method further includes providing the query text to a neural network model implemented on a computing system, the neural network model having a plurality of layers, wherein at least one layer comprises a plurality of loss functions including a named entity tag learning loss function and an intent classification loss function. The method also includes obtaining, from the neural network model, an identification of a named entity and a query intent derived from the query text. A query response may be formulated based, at least in part, on the named entity and query intent.

Multi-task learning of query intent and named entities

Systems and methods for automating image annotations are provided, such that a large-scale annotated image collection may be efficiently generated for use in machine learning applications. In some aspects, a mobile device may capture image frames, identifying items appearing in the image frames and detect objects in three-dimensional space across those image frames. Cropped images may be created as associated with each item, which may then be correlated to the detected objects. A unique identifier may then be captured that is associated with the detected object, and labels are automatically applied to the cropped images based on data associated with that unique identifier. In some contexts, images of products carried by a retailer may be captured, and item data may be associated with such images based on that retailer's item taxonomy, for later classification of other/future products.

Large-scale automated image annotation system

Methods and systems for predicting relevant items to be presented to a user in an online environment are described. The methods and systems described herein generate models based on previous item selections to determine an overall time series model for predicting a relevant time of next item selection as well as items most likely to be selected at that time. Complementary items can be presented to the user alongside the selection of most relevant items.

Method and system for presenting items in online environment based on previous item selections

A computer-implemented method obtains a transaction log for a transaction at a self-service terminal during which the self-service terminal fails to detect the presence of an item at the self-service terminal. Features are extracted from the transaction log and the features are applied to a model to generate an inference for the transaction. The inference is used to determine whether to issue an alert that improper scanning has occurred at the self-service terminal.

Using transaction logs to determine that an undetected item was not scanned at a self-service terminal

Methods and systems for identifying one or more products in an electronic image are disclosed. The computer-implemented method to electronically recognize a product in an electronic image captured via an electronic mobile device is disclosed. The method includes receiving, by a server, a video stream from a camera of the electronic mobile device, the video stream including a plurality of frames. The server selects at least one of the plurality of frames from the video stream, the at least one of the plurality of frames from the video stream being selected is a captured image. The server segments a plurality of products in the captured image into a plurality of segments. The server performs an image recognition using each of the plurality of segments to identify the product in each of the plurality of segments. One or more recognized products identified in the image recognition is outputted by the server.

Electronic product recognition

A retail store including a server having a processor and a memory; a communication network; and a database are disclosed. The server includes an electronic product recognizer that receives a video stream including a plurality of frames from a camera of an electronic mobile device. At least one of the plurality of frames is selected as a captured image. A plurality of products in the captured image is segmented into a plurality of segments. Image recognition is performed using each of the plurality of segments to identify the product in each of the plurality of segments. One or more recognized products identified in the image recognition are output. The one or more recognized products identified in the image recognition are configured to be sent to a user device communicable with the server via the communication network, the server configured to cause one or more stickers to be displayed on the user device.

Growing community of inventors

Minneapolis, MN, United States of America

Ryan David Siskind