Abstract: In some implementations, a computer-implemented method verifies item placed in physical shopping carts, using location data. An item verification engine receives an item scanned notification indicating that a mobile computing device has scanned an item, an item sensed notification indicating that a cart computing system has sensed the item being added to a shopping cart, item verification data that specifies an expected location of the scanned item, and actual location data that represents an actual location of the item in the retail environment. After receiving the item scanned notification, the item sensed notification, the item verification data, and the actual location data, a verification of the item is performed based at least in part on the item verification data and the actual location data. The item verification engine provides verification results based on performing the verification of the item, for receipt by the mobile computing device.

Abstract: The present disclosure relates to a fixture overlay algorithm that identifies the out-of-stock product by relying on shelf fixture start and end coordinate data points on an image to map the captured image to pre-existing planogram data. The present fixture overlay disclosure detects the start and stop shelf fixture positions for each of the shelves within the shelf image and uses the detected shelf fixture points to map the shelf image to the planogram coordinates in order to determine the identity of the out-of-stock product.

Abstract: A method includes receiving a first post from an electronic source including first content; determining a source identifier; determining an attribute for the source by broadcasting the first post to a first plurality of filter graph definitions configured to identify attributes of sources according to the respective filter graph definition; and storing in memory, as a source profile identified by the source identifier for the source, the attribute for the source; receiving a second post from the source including second content; determining a source identifier; using the source identifier, querying the memory to access the source profile; correlating the second post with attributes of the source stored in the source profile to produce a correlated second post; and broadcasting the correlated second post to a second plurality of filter graph definitions configured to identify posts with high value information according to the respective filter graph definition.

Abstract: Disclosed combinable gift card components for a gift card purchase. A gift card can include a card component having a front surface, a back surface, a window, and a first identifier, and a secure insert component having: a secure insert portion with a second identifier, teeth at a leading edge of the secure insert component to mate with corresponding teeth of a middle layer of the card component for fixed alignment of the secure insert component inside the card component, an adhesive-resistant covering that can fold over the secure insert portion to hide the second identifier before the secure insert component is inserted into the card component, and a tab affixed to an end of the adhesive-resistant covering that can be pulled to cause the adhesive-resistant covering to unfold out from inside the card component to reveal the second identifier through the window.

Abstract: In some implementations, a method performed by data processing apparatuses includes determining that a change has been made to interface configuration code of a service-providing platform. In response to determining that the change has been made, each interface configuration code unit of the interface configuration code of the platform can be validated. In response to successful validation of all of the interface configuration code units, an aggregated configuration code unit can be generated that includes computer code of each of the interface configuration code units, the aggregated configuration code unit can be translated into a computer language that is different from that of the interface configuration code units, and a translated configuration code unit can be generated. The translated configuration code unit can be used to configure the multiple different services of the platform.

Abstract: A method includes in a first package, defining a data type as implementing a method that returns a copy of a protected configuration value and in a second package, providing a function that accepts a variable of the data type and that calls the method to obtain the copy of the protected configuration value. The first package and the second package are imported into a common package so that the function in the second package can obtain the copy of the protected configuration value without being able to modify the protected configuration value.

Abstract: The disclosed technology provides for determining whether to audit a shopper in a retail environment based on a trust score assigned to the shopper. A method can include receiving, by a computer system, shopper information including an identifier for the shopper, retrieving bag checkout history data associated with the shopper based on the identifier, which includes the shopper's trust score, determining a weighted probability score for the shopper based on the trust score and shopper trust score groupings, determining, using a randomization process, whether to perform a bag check on the shopper based on the weighted probability score, returning bag check instructions based on the determination, receiving bag check data from performing the bag check after the shopper completes checkout, adjusting the trust score based on the bag check history data and the bag check data, and providing the adjusted shopper trust score for use in the shopper's subsequent visits.

Abstract: A gate for use on a shopping cart including a basket defining a compartment and a rear opening thereto. The gate includes a primary panel, a locking chamber, and a locking clip. The primary panel is rotatable between a first position, covering the rear opening, and a second position extending above the compartment, wherein the primary panel rotates about an axis defined through two coupling plugs near a top of the rear opening. The locking chamber includes an elongated slot and at least one locking notch. The locking clip is configured to slide within the at least one locking notch to interact with a bottom of one of the coupling plugs and includes a locking finger with a protruding block. The protruding block is configured to be selectively received within the at least one locking notch to secure the gate relative to the one of the two coupling plugs.

Abstract: A system for exchanging data between applications is disclosed. In an example embodiment, a printer communicatively coupled with a first application prints a plurality of codes, which are affixed to a plurality of loads. A second application later scans codes affixed to loads. Based on the scanned codes, the second application generates an aggregate code that encodes identifiers of the loads. The second application displays the aggregate code on a screen, and the first application may scan the displayed aggregate code. The first application may compare identifiers encoded by the aggregate code with a list of identifiers to determine whether the second application ingested all expected identifiers.

Abstract: Disclosed herein are systems and methods for determining whether an unknown product matches a scanned barcode during a checkout process. An edge computing device or other computer system can receive, from an overhead camera at a checkout lane, image data of an unknown product that is placed on a flatbed scanning area, identify candidate product identifications for the unknown product based on applying a classification model and/or product identification models to the image data, and determine based on the candidate product identifications, whether the unknown product matches a product associated with a barcode that is scanned at a POS terminal in the checkout lane. The classification model can be used to determine n-dimensional space feature values for the unknown product and determine which product the unknown product likely matches. The product identification models can be used to determine whether the unknown product is one of the products that are modeled.

Abstract: Disclosed are systems and methods for predicting tariff classifications. Item descriptions of historical items and associated tariff codes/classifications are submitted to a machine learning platform, thereby creating a trained model for predicting tariff classifications. The trained model receives product data associated with new items and is utilized to generate predicted tariff classifications, which correspond to particular tariff rates. In examples, a confidence/accuracy score is applied to the prediction. The predicted tariff codes are then analyzed in view of a set of safeguard rules. If any of the predictions fail the safeguard rules, a manual user review may be triggered. Manually corrected feedback is provided for use in subsequent retraining so that the machine learning model accuracy is improved over time. If any of the predictions pass the evaluation under the safeguard rules, the predictions may be automatically approved.

Abstract: Methods and systems for performing automated scene generation are described. One method for integrating products into generated scenes includes receiving a structure reference containing control features and positioned product images, and detecting control features from the structure reference to create a control image. The method further includes generating a scene using the control model and a text prompt, and segmenting products from both the structure reference and the generated scene to create product masks. The method includes replacing generated products with actual product images using the product masks, and applying inpainting to correct dimensional differences between the generated and actual products while preserving scene lighting and shadows.

Abstract: A shipping container is configured to transport goods from a distribution center, to a retail location, and onto the sales floor of the retail location. The shipping container glides on wheels and is stackable. The shipping container is configured to receive forklift forks from multiple sides. At least one of the channels includes a surrounding framework to safeguard against tilting. The lid is selectively mountable in two orientations to close the container or to provide handles for propelling and/or steering the shipping container. An expandable storage location for empty packaging is provided at an exterior of the shipping container.

Abstract: Disclosed are systems and techniques for identifying product identifiers in images. A technique can include receiving, by an edge computing device, x and y coordinates for a location of an out of stock shelf section, determining a frame of reference (FOR) based on the coordinates, the FOR including a location of a product identifier for the out of stock shelf section, determining incremental adjustments to a camera based on the FOR, instructing the camera to adjust by the incremental adjustments and capture an image of the location of the product identifier, performing image analysis on the image to identify the product identifier, determining second incremental adjustments to the camera to focus the camera on the location of the product identifier if the product identifier is not identifiable in the image, and instructing the camera to reset to original camera settings if the product identifier is identifiable in the image.

Abstract: The present disclosure provides methods and systems for tracking a shipping vessel travel route through a retail enterprise during a stock cycle. Location information associated with assets can be collected at a retail location, from which a detailed route through the retail location may be recreated and overlaid on map data reflecting a retail location layout. Further analysis may be performed on the route. Additionally, the route may be overlaid on a map, including product information and packaging information, allowing for various metrics and metric visualizations to be generated that can be further analyzed to achieve various objectives.

Abstract: Methods and systems for optimizing a ship-from-shore process are provided. A decision model receives forecasted demand and node data representing a plurality of possible shipping node configurations. The decision model generates output data that includes an assignment of the forecasted demand to nodes among the plurality of nodes based on the shipping cost data and the node data while optimizing a supply chain objective subject to a plurality of constraints, the plurality of constraints including a fulfillment of the forecasted demand within a predetermined delivery service level, and identifies an optimal configuration for each shipping node. In some aspects, the decision model segments the node data to improve efficiency of analysis.

Abstract: Plied yarns and methods of constructing plied yarns from two different yarns, manufactured using different fibers wherein the plied yarns possess enhanced properties. The yarns developed and described herein are plied yarns, rather than, and in direct contrast to intimately blended yarns. Examples of the fibers and/or yarns utilized in forming the yarns of different fibers described herein, include but are not limited to 100% cotton, Modal, and Lyocell. The yarns described herein can be used for various end uses, including but not limited to formation of terry fabric for use in towels, robes, apparel, and the like.

Abstract: The disclosed system provides real-time detection and remediation of metric anomalies in a replenishment network. A computer system can receive, from data sources, event data, retrieve historic metric data associated with a metric of a retail environment, aggregate the event data and historic metric data into aggregated data for the metric, store the aggregated data in a cache data store, determine, based on applying a statistical algorithms model to the cached aggregated data, (i) a predicted metric value and (ii) upper and lower tolerance bounds for the metric, iteratively receive the event data, aggregate the data, and determine (i) and (ii) until (a) determining a condition is triggered to evaluate the metric or (b) expiration of a time period to which the predicted value and the upper and lower tolerances apply, and return, based on determining the condition is triggered to evaluate the metric, information about metric anomalies.