Abstract: A service may provide an e-commerce platform through which users may search for, view, and purchase products. To ensure users receive relevant results when querying for particular products or product classes, a list of ranked classes may be generated, from which the query results are based. For example, products may be classified into classes and particular text from search data may be associated with one or more of the products based on click log data. For instance, input text from previously performed queries may be associated with products interacted with following those queries (e.g., products clicked on to view/purchase). Training data that associates the particular text with the respective one or more classes into which the clicked on products are classified may be generated, and in response to receiving a query including the particular text as input, the list of ranked classes may be generated based on the training data.

Abstract: A shopping cart includes a wheeled base and a basket. The basket is supported above a wheeled base and includes a hook. The basket defines a compartment, a top mouth open to the compartment, and an open slot positioned below the top mouth. The open slot is defined between a top edge and a bottom edge thereof, and the bottom edge is positioned opposite the top edge. The hook downwardly depends from the top edge of the open slot toward the bottom edge of the open slot to a free bottom end of the hook. The hook is configured to selectively receive a handle of a bag after the handle of the bag is wrapped around a portion of the basket defined between the open slot and the top mouth of the compartment, such that the bag selectively hangs along an outside surface of the basket opposite the compartment.

Abstract: Methods and systems for processing an order are disclosed. A unified shopping cart receives a first request from a first tenant interface and second request from a second tenant interface, different from the first tenant interface. Each request includes first request data including a customer identifier, a selection of one or more items, and a desired delivery mode. The first request and the second request are associated with the same customer, and are processed using a unified payment transaction.

Abstract: A process for preparing a natural fiber fabric for finishing the fabric with a botanical dye or printing content on the fabric with a botanical dye includes washing the natural fiber fabric in a washing solution comprising approximately equal parts washing soda and baking soda dissolved in water and rinsing the washed natural fiber fabric. The process also includes pre-treating the washed natural fiber fabric with a pre-treating solution comprising a bio enzyme in water and rinsing the pre-treated natural fiber fabric. After pre-treating, a pH of the washed and pre-treated the fabric load may be neutralized with a solution comprising vinegar in water.

Abstract: Warehouse automation and methods of handling materials can be used to make depalletization processes more safe and efficient. In some examples, the depalletization systems can include a U-shaped platform lift that supports one or more workers and that defines a location for a pallet of boxes to be unloaded or “depalletized.” The U-shaped platform lift can be raised and/or lowered to position the workers at the optimal elevations for transferring, with minimal lifting, the boxes from the pallet to a system of conveyors. Such systems are also reconfigurable in multiple ways to further minimize the manual lifting required for the depalletization process as well as the throughput of the depalletization process.

Abstract: Disclosed are techniques for identifying users within an enterprise who pose heightened security risks to the enterprise. A method can include receiving, by a computing system, information about users in the enterprise, grouping the users into groups based on at least one grouping feature and the user information, the at least one grouping feature including, for each of the users, behavior, activity, role, department, region, role-based risk score, event-based risk score, and/or composite risk score, identifying, for each group, normalized behavior of users in the group, generating, for each user in each group, a composite risk score based on deviation of the user's activity from the normalized behavior of the group, identifying, for each group, a subset of users in the group to be added to a watch list, and adding the subset of users to the watch list.

Abstract: A computer-implemented method includes receiving a message comprising an origin, a destination and a relationship type for a relationship between the origin and the destination. The message further includes a payload. A first node is created in a graph database for the origin and a second node is created in the graph database for the destination. A relationship is set between the first node and the second node in the graph database based on the relationship type. A node is created in the graph database for the message while preventing the payload from being stored in the graph database. A relationship is created between the first node and the node for the message. The message, including the payload, is stored in a searchable datastore separate from the graph database.

Abstract: In one embodiment, a storage container is disclosed. The storage container includes a plurality of sidewalls and a bottom wall operably coupled to the plurality of sidewalls. The bottom wall and the plurality of sidewalls together define a storage cavity. A storage container also includes a support bracket that transitions from a first position where the support bracket is contained within an exterior perimeter of the bottom wall to a second position where the support bracket extends past the exterior perimeter of the bottom wall. The support bracket may be used to support the storage container on an adjacent storage container, such that the storage container can be nested within an adjacent storage container or positioned above the adjacent storage container.

Abstract: Described herein are systems and methods for validating products that are added to a shopping cart. A shopping cart that can include product validation hardware and a controller, the product validation hardware including motion sensors positioned at least along a top perimeter of the shopping cart and at least one weight sensor positioned inside the shopping cart. The shopping cart can receive, from one or more of the motion sensors, motion data when the product is detected to be entering a top horizontal plane of the shopping cart, receive, from the at least one weight sensor, weight change data that is collected in real-time as the product settles inside the shopping cart, and correlate the weight change data with the motion data to generate a weight signature over time for the product. The weight signature can be used to validate the product that is added to the shopping cart.

Abstract: The disclosed technology provides for reconstructing products that are added to a shopping cart in three-dimensional space. The reconstructed products can be used for product validation. A shopping cart can include product validation hardware including light emitters and light sensors along a top perimeter of the shopping cart. The shopping cart can activate the light emitters to emit light across a top horizontal plane of the shopping cart, receive, from light sensors on a side of the shopping cart opposite a side where the activated light emitter is located, light intensity data as a product passes through the top horizontal plane and obstructs at least a portion of the emitted light from being detected by the light sensors, identify, from the light intensity data, slices of the product, and reconstruct the product in 3D space based on stitching together the slices.

Abstract: A third party item listing management system useable for validation of third party items to be included on a retailer website is disclosed. The third party item listing management system includes an application programming interface (API) accessible by a plurality of third parties and configured to receive item data. An item management process receives the item data and calls an item validation pipeline which includes a plurality of item validation stages including an item legalization stage. In the item legalization stage, the item data and the identity of the third party are validated against a plurality of item listing rules to determine whether the one or more items are allowed to be offered via the retailer website by the third party. The item listing rules can include a rule preventing the third party from listing an item included in a core item collection offered by the retailer via the retailer website.

Abstract: Described herein are systems and methods for determining whether a scanning motion occurred during a checkout process. The system includes a checkout lane having a scanning area that receives products to be purchased by a user, scanning devices, a point of sale (POS) terminal that identifies a product based on a scan, using the scanning devices, of a product identifier for the product as the product is moved through the scanning area, and an overhead camera that captures image data of the user's body movements and transmits, to a computing system, the image data. The computing system can, during runtime, identify whether a scanning motion occurred during the user's body movements based on application of one or more motion identification models to the image data and determine, based on identification of the scanning motion, that the user performed an affirmative scan during the checkout process.

Abstract: Disclosed are techniques for identifying unique byte sequences for malware families. A method can include receiving a collection of malware signature samples, grouping the samples in the collection by malware family, and for each family: identifying unique byte sequences in the samples and a number of instances of the unique byte sequences across the samples, adding the identified unique byte sequences to a dictionary for the malware family, retrieving a dictionary of at least another malware family, comparing the unique byte sequences in the dictionary for the malware family with byte sequences in the dictionary of the another malware family, identifying a conflicting byte sequence based on (i) the comparison and (ii) determining that a number of instances of the conflicting byte sequence is more than a threshold number of instances, and removing the identified conflicting byte sequence from the dictionary for the malware family.

Abstract: Methods and systems for managing register content is described. A register content management module receives an identity of the retail location register, identifies a geographic location associated with the retail location register, identifies a time for which the updated register content is requested, generates a new register content, and sends the new register content to the retail location register independently from sending an application update to the retail location register.

Abstract: Methods and systems for providing a product bundle recommendation are disclosed. One method includes receiving a selection of a first product. Data relating to historical customer shopping activity and data describing online shopping sessions in which products are selected for addition to historical shopping carts to which the first product was previously added is accessed. A list bundled products having a complementary relationship with the first product is generated. At least one product from the list of bundled products is selected and the at least one product is presented on a user interface on a customer device as a recommendation for purchase with the first product. A filter may be applied to the list of bundled products, such as a price filter. The method may be performed by a system including one or more computing devices communicating via a network with one or more data storage devices.