Abstract: Technology for optimizing automated inventory management is described. In an example implementation, a method, implemented using one or more computing devices, may generate unit identifier sets based on affinities between items uniquely identified by the unit identifiers, determine first and second contribution values for each of the unit identifier sets, and calculate a difference between the first and the second contribution values for each of the unit identifier sets. The method may further calculate an incremental carton and expense prevention opportunity (ICEPO) value for the unit identifier sets, calculate an adjusted fulfillment center stocking score using the ICEPO value and the difference between the first and the second contribution values for each of the unit identifier sets, select a subset of the unit identifier sets based on the adjusted fulfillment center stocking score, and output the subset to an inventory replenishment system that manages stocking of items.

Abstract: A system and method for providing a mobile interface for marking and organizing images is described herein. In some instances, the system may present, on a display device, an image region that displays a capturable image that is capturable by an image sensor of the wireless mobile electronic device and a preview region including a series of one or more annotatable image previews. The system may receive an input instructing the wireless mobile electronic device to capture a second image using the image sensor of the wireless mobile electronic device, generate a second image preview representing the second image, and update the graphical user interface to include the second image preview at the preview region. The system may receive an input including an annotation using an input device of the wireless mobile electronic device and update the graphical user interface to represent the annotation at the preview region.

Abstract: In an example embodiment, a method may generate an item layout map for a shelving unit, where the shelving unit stores item types associated with a product category. The method may determine product attributes associated with the product category and divider configurations of the shelving unit, where a divider configuration divides the shelving unit into one or more candidate regions. The method may generate an ontology entry associated with a product attribute and the divider configuration based on the item layout map and the divider configuration of the shelving unit, the ontology entry indicating a regional entropy values of a product attribute for the candidate regions generated by the divider configuration. In some instances, the method may generate a guidance instruction related to the product attribute of the product category based on the ontology entry and provide the guidance instruction to a user.

Abstract: A system and method for automated loading of delivery vehicles using automated guided vehicles is described. In an example implementation, a loading coordination engine may determine a delivery destination of a first item based on item data associated with the first item, assign the first item to a location in a delivery vehicle, and generate a task list including an instruction to an automated guided vehicle to position the first item in the delivery vehicle based on the assigned location in the delivery vehicle. In some instances, the automated guided vehicle may navigate to a loading area to retrieve the first item from the loading area, navigate to a point proximate to the assigned location in the delivery vehicle, and place the first item at the assigned location based on the task list.

Abstract: A system and method for automated loading of delivery vehicles using automated guided vehicles (“AGV”s) is described. In an example implementation, a loading coordination engine may assign a location on a mobile cart to an item and generate a task list including instructions to a first and a second AGV to position the item on the mobile cart based on the assigned location and to transport the mobile cart into a delivery vehicle. The first AGV may transport the item from an item loading area to a point proximate to the assigned location on the mobile cart and place the item at the assigned location based on the task list. The second AGV may transport the mobile cart from a cart loading zone into the delivery vehicle based on the task list and, in some instances, secure the mobile cart to the delivery vehicle based on the task list.

Abstract: A system and method for automated preparation of deliveries in delivery vehicles using automated guided vehicles is described. In an example implementation, the method may determine a future delivery in a set of deliveries assigned to a delivery vehicle, the future delivery including a first item and determine a storage location in the delivery vehicle of the first item. In some implementations, an AGV may, during transit of the delivery vehicle along a route for delivering the set of deliveries, navigate to a point proximate to the storage location of the first item in the delivery vehicle, and retrieve the first item from the storage location in the delivery vehicle. The AGV may then deliver the first item to a delivery point.

Abstract: An automated guided vehicle (AGV) is described. In an example implementation, the AGV may include a lift platform and an AGV controller configured to control one or more operations of the AGV. The lift platform of the AGV may include a support surface adapted to contact a surface of a shelving unit and provide support from underneath the shelving unit when the support surface is in an elevated position and the shelving unit is situated on the support surface, and a lifting mechanism including motor(s) coupled to the support surface and providing a first lifting force via a first portion of the support surface and a second lifting force via a second portion of the support surface, the first lifting force and the second lifting force vertically lifting or lowering the shelving unit via the support surface based on a weight distribution of the shelving unit on the support surface.

Abstract: Technology for optimizing carton induction in an order fulfillment picking system is described. In an example embodiment, a method, implemented using one or more computing devices, may include receiving scan data reflecting status of cartons being conveyed by a conveying system, receiving confirmatory input reflecting pick completion for a subset of the cartons being conveyed by the conveying system, and generating an estimated time of arrival for one or more cartons not yet inducted into the conveying system based on the scan data and the confirmatory input. The method may further include generating a load forecast based on the estimated time of arrival and inducting one or more of the one or more cartons into the conveying system based on the load forecast.

Abstract: A method determines a processing cluster including one or more stock keeping units (SKUs); divides the processing cluster into a first cluster and a second cluster based on SKU affinities between the one or more SKUs in the processing cluster; determines a first SKU of the first cluster to be replicated to the second cluster based on a demand correlation between the first SKU of the first cluster and a second SKU of the second cluster; replicates the first SKU of the first cluster to the second cluster; responsive to replicating the first SKU of the first cluster to the second cluster, determines whether the first cluster and the second cluster satisfy a defined constraint; and responsive to determining that the first cluster and the second cluster satisfy the defined constraint, assigns the first cluster to a first physical location and assigning the second cluster to a second physical location.

Abstract: A technology for managing space utilization using self-adjusting inventory slots is described. In an example embodiment, a system comprises a shelving unit including a shelf, and a shelf adjustment system including an electronic display strip extending parallel with the shelf of the shelving unit. The electronic display strip may display a first visual representation of a first adjustable inventory slot horizontally adjacent to a second visual representation of a second adjustable inventory slot, the first visual representation indicating a first portion of the shelf as the first adjustable inventory slot for a first item, and the second visual representation indicating a second portion of the shelf as the second adjustable inventory slot for a second item.

Abstract: Technology for predicting online user shopping behavior, such as whether a user will purchase a product, is described. An example method includes receiving current session data describing a current session for a current user, extracting a current clickstream from the current session data classifying the current clickstream as a purchase clickstream or a non-purchase clickstream by processing the current clickstream using one or more sets of Hidden Markov Model parameters produced by one or more Hidden Markov Models, and computing, using the one or more computing devices, a purchase probability that the current user will purchase a product during the current session based on the classifying.

Abstract: In an example embodiment, a method determines a container containing one or more items associated with one or more item types, the container located at a current position in a storage facility; determines one or more order likelihoods of the one or more item types contained in the container; determines a container utilization likelihood of the container based on the one or more order likelihoods of the one or more item types contained in the container; determines an optimal position for the container in the storage facility based on the container utilization likelihood of the container, the optimal position being different from the current position of the container; and instructing an automated guided vehicle (AGV) to transport the container from the current position of the container to the optimal position of the container in the storage facility.

Abstract: The technology includes an example method for parsing data to determine corollary objects and adapt attributes of the corollary objects using the data. In some implementations, the method may include receiving one or more images, performing text recognition to determine recognized text in the one or more images, and determining data cells containing information associated with a first item. The method may then classify one or more of the determined data cells, and may identify key cells in the determined data cells based on the classification of the one or more determined data cells. Correlations between information contained in the key cells and a second item, the second item including an interchangeable item to the first item may be determined, and the method may adjust attributes associated with the second item based on defined parameters and the recognized text.

Abstract: A restocking hub with interchangeable buttons mapped to item identifiers is described herein. In some instances, a local hub may receive an actuation signal from a particular button of a set of interchangeable buttons communicatively coupled with the local hub, the local hub being communicatively coupled with a remote server. The local hub may transmit a signal including a button ID of the particular button to the remote server based on the particular button being activated and the local hub receiving the actuation signal from the particular button. In some implementations, the remote server may determine an item associated with the particular button and attributes of the item based on the button ID of the particular button and a mapping of button IDs to items in a database accessible by the remote server, and execute a defined action using the attributes of the item associated with the particular button.

Abstract: A hybrid modular storage fetching system is described. In an example implementation, the system may include a warehouse execution system adapted to generate a picking schedule for picking pick-to-cart and high-density storage items, and an AGV dispatching system adapted to dispatch a cart automated guided vehicle and a modular storage fetching automated guided vehicle based on the picking schedule. The cart automated guided vehicle may be adapted autonomously transport a carton through a pick-to-cart area and to a pick-cell station. The modular storage fetching automated guided vehicle may be adapted to synchronously autonomously transport a modular storage unit containing items to be placed in the cartons from a high-density storage area to the pick-cell station.

Abstract: The disclosure relates in some cases to a technology for selecting one or more promotions to be presented to online customers using Bayesian bandits and affinity-based dynamic user clustering In some embodiments, a computer-implemented method determines a set of offers is determined, and computes affinity scores measuring affinities of users to items included in the offers. The method builds an affinity score distribution for the offers and identifies clusters of affinity scores for the offers using the corresponding affinity score distribution.

Abstract: According to an example implementation, a method comprises generating a graphical asynchronous messaging user interface including an input region containing a set of digital images of items and an activity region displaying graphical messaging elements respectively representing messages sent between a consumer node and a provider node, displaying the graphical asynchronous messaging user interface, receiving a first user input from a user via the input region selecting a first digital image associated with a first item from the set of digital images of items in the input region, generating a first message including the first digital image associated with the first item, including the first message including the first digital image associated with the first item in a first messaging element in the activity region displayed to the user on the display device, and transmitting the first message via a public computer network as a request to the provider node.

Abstract: A computer-implemented method and system are described for learning a vector representation for unique identification codes. An example method may include generating a unique identification code list using one or more virtual interaction contexts, the unique identification code list being a list of unique identification codes, selecting a target unique identification code in the unique identification code list, and determining, from the unique identification code list, an input set of unique identification codes using the target unique identification code, the input set including the target unique identification code and one or more context unique identification codes. Some implementations may further include inputting the input set of unique identification codes into a semantic neural network model, the semantic neural network model including one or more weight matrices, and modifying the one or more weight matrices using the input set of unique identification codes.

Abstract: A computer-implemented method and system are described for ordering items within a zone of a physical location. An example method may include wirelessly receiving at a server via a computer network a unique identifier associated with a physical ordering device, the physical ordering device being remotely located from the server, retrieving, at the server from an information source, item information describing an item configured to be associated with the unique identifier of the physical ordering device, retrieving, at the server from the information source, shipping data including a physical location uniquely associated with the physical ordering device, and generating at the server a purchase request for re-ordering the item. The method may further include processing at the server the purchase request, and authorizing at the server shipment of the item to the physical location associated with the physical ordering device responsive to the processing of the purchase request.