Abstract: Devices and systems can be used to enhance warehouse material handling operations. For example, this document describes pallet stands that make material handling processes more safe and efficient. In some embodiments, a pallet stand described herein includes a structure comprising a top configured for a pallet to rest on and a pedestal arranged to elevate the structure above a floor. The pedestal has an outer size that is less than the width of the top structure and less than the length of the top structure.

Abstract: A computer-implemented method is performed in a machine having at least one processor and storage. The at least one processor executes an agent and a host that are both stored in the storage. The at least one processor's execution of the agent causes the at least one processor to create a new partition of the storage while the at least one processor is executing the host. The at least one processor's execution of the agent causes the at least one processor to store a new operating system in the new partition of the storage while the at least one processor is executing the host. The at least one processor's execution of the agent causes the at least one processor to reboot the machine into the new partition to cause the at least one processor to execute the new operating system.

Abstract: 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.

Abstract: In some implementations, a system for verifying items in a retail environment includes a physical shopping cart including a first set of sensors, and an automated checkout station including a second, different set of sensors. The physical shopping cart receives item verification data for verifying an item, detects the item as it enters the physical shopping cart, and performs a primary verification of the item. The automated checkout station obtains a virtual shopping cart that corresponds to the physical shopping cart. The virtual shopping cart includes a list of items that have been placed in the physical shopping cart, and a verification status of each item. The second, different set of sensors generate station sensor data that represents the physical shopping cart and the items in the physical shopping cart. A secondary verification of the physical shopping cart and its contents is performed by the automated checkout station.

Abstract: A clustering and routing platform that applies capacity constraints at individualized routes as part of the process of clustering deliveries into groups is provided. In particular, vehicle capacity, route length, route efficiency/timing, and various other constraints may be used as part of the clustering process to better group delivery locations into routes.

Abstract: Methods and systems for generating and distributing data visualizations are provided. One method includes displaying a user interface including a canvas and a card builder toolset, the card builder toolset including a plurality of selectable options, each of the plurality of selectable options responsive to user input to present a definition screen including one or more card definition parameter input fields. The method further includes receiving user input into the one or more card definition parameter input fields for each of the plurality of selectable options and, in response, defining at least one aspect of a card to be included within a user dashboard presented on the canvas. The method also includes rendering a card within the canvas in accordance with parameters defined by the user input, the card being included within a dashboard to be displayed to users.

Abstract: Methods, systems, and platforms for managing machine learning models are described. A model registry system receives first data including a model and second data including metadata and at least one metric of the model. Via a local network, the first data is stored to a data storage device and the second data is sent to an application programming interface (API). The first data is retrieved from the data storage device to a model use case program operating in a software development environment native to where the model registry system stores the model. The second data, including the metadata and the at least one metric of the model, is sent to a user interface (UI) via the API. The stored model can be deployed from the model use case program via the API.

Abstract: In general, the present disclosure describes inventory management systems and methods which track all inventory of items within a retail supply chain. A computerized system aggregates inventory movement events to produce a common source of truth for the location and disposition of items within a supply chain. Order events and inventory events are received from multiple data sources. Additionally, a current inventory level for each item at each location within the supply chain is provided according to the data source. The computerized system normalizes the information in the event messages before it is stored in the centralized inventory database. The inventory information in the database can be accessed by multiple consumers through an API to obtain the most up-to-date information about the disposition and location of an item.

Abstract: The present application describes a method and systems for enterprise supply chain optimization by accounting for time, cost, product demand, capacity constraints, and other factors. The described application relates to solving for the optimal flow of products through a supply chain including overseas vendors and a selected set of import gateways by using a custom-built model based on linear programming techniques. The model described in the present disclosure relates to a model that optimizes the overall cost or time (or a balance of both cost and time) to ship products from origin ports to domestically located distribution centers. By doing so, the model also optimally allocates how shipping containers are sent to domestic ports. The model subsequently outputs the optimal flow, cost, and time for each route in the network, as well as providing other relevant output.

Abstract: Systems and methods disclosed can evaluate security detection rules in a network security computing environment. Results for a processed log of security events can be retrieved. The results can identify determined outcomes for instances triggering security detection rules. The security detection rules can detect specific behavior on a network by being processed against a log of security events. Scores for the security detection rules can be determined based on the results of the processed log of security events and the determined outcomes. The security detection rules can be ranked based on the scores, from highest to lowest score. The highest score can indicate that a corresponding rule is performing worst among the security detection rules and the lowest score can indicate that a corresponding rule is performing best among the security detection rules. A rules score report can be generated based on the ranked rules.