Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions, that when executed on the one or more processors, cause the one or more processors to perform operations including: obtaining triangle data of a 3D model of an item; generating a first mask texture of the 3D model based on the triangle data; generating a second mask texture of the 3D model larger than the first mask texture by extruding the triangle data; and rendering a 3D outline mesh onto an image of the 3D model to highlight the 3D model, such that the 3D outline mesh subtracts the first mask texture for the second mask texture. Other embodiments are disclosed.

Abstract: Automated storage and retrieval systems for managing storage of inventory at a retail facility include a storage structure with storage locations configured to store containers that contain retail products, and a conveying system that conveys the containers between the storage locations and a product picking station. A processor-based control circuit analyzes one or more business rules governing product merging between the containers being conveyed toward the picking station by the conveying system to identify two containers that are eligible for the product merging therebetween. When the control circuit detects that the two containers identified as product merging eligible arrived at the picking station, these two containers are kept by the conveying system at the picking station until all of the products are removed from a first one of these two containers and merged together with the products stored in a second one of these two containers.

Abstract: In some examples, a system may be configured to obtain a set of features of a set of users including one or more features of transactional data of the set of users and one or more features of engagement data of the set of users. Additionally, the system may be configured to implement a first set of operations that generate output data including a plurality of trial membership scores, based on the set of features. In some examples, each trial membership score of the plurality of trial membership scores are associated with a particular user of the set of users and characterize a likelihood of an acquisition event of the corresponding user changing from a non-member status to a trial member status.

Abstract: A method including automatically determining, by a machine learning model trained based at least in part on sample items stored in a sample database, a query embedding vector for a query image of a query item. The method further can include determining, based on a respective embedding distance between the query image of the query item and a respective image of each of the sample items, neighboring items from among the sample items. The respective embedding distance can be calculated based on the query embedding vector for the query image and a respective embedding vector for the respective image of each of the sample items. Each of the sample items can include the respective image and at least one respective item label. The method also can include determining a respective normalized weight for each of the neighboring items based on the respective embedding distance between the query image and the respective image of the each of the neighboring items.

Abstract: Automated storage and retrieval system for managing storage of inventory at a retail facility includes a storage structure with storage locations configured to store containers that contain retail products, and a conveying system that conveys the containers between the storage locations and a product picking station. A computing device analyzes one or more business rules to identify at least two containers that are eligible for the product merging therebetween and causes the conveying system to move these two containers from the storage structure toward a picking station selected by the control circuit. When the two containers identified as product merging eligible arrive at the picking station, these two containers are kept by the conveying system at the picking station until all of the products are removed from a first one of these two containers and merged together with the products stored in a second one of these two containers.

Abstract: There is provided a conveyor assembly for sorting merchandise items. In one form, the conveyor assembly includes: a merchandise identification module; sortation modules each comprising a multi-directional sorting portion with two sets of rollers, a first wing including a third set of rollers, a second wing including a fourth set of rollers, and a controller configured to receive an IP address; a first, disassembled state of the sortation modules; a second, assembled state of the sortation modules; a merchandise database; and a control circuit configured to receive identifying information about an unsorted merchandise item, assign a unique IP address to each sortation module corresponding to the position of the sortation module, determine a sortation destination for the unsorted merchandise item, determine the sortation module corresponding to the sortation destination; and instruct the controller of the corresponding sortation module to divert the unsorted merchandise item to the sortation destination.

Abstract: Systems and methods of monitoring inventory of a product storage facility include an image capture device configured to move about the product storage areas of the product storage facility and capture images of the product storage areas from various angles. A computing device coupled to the image capture device obtains the images of the product storage areas captured by the image capture device and processes the obtained images of the product storage areas to detect individual products captured in the obtained images. Based on detection of the individual products captured in the images, the computing device analyzes each of the obtained images to extract meta data from the packaging the individual products to detect one more keywords and determine the locations of the detected keywords on the packaging, and then utilize this information to predict an identity of the products associated with the packaging.

Abstract: A supply chain forecasting system with blockchain controls is discussed. The supply chain forecasting system can include a central computing system communicating with a third party computing system. The central computing system and third party computing system can initiate, adjust, and fulfill smart contracts associated with the delivery of physical objects using blockchain controls.

Abstract: Provided are a refrigeration heat reclaim unit and method, comprising a heat exchanger, comprising a refrigerant inlet that receives a flow of refrigerant having a first state; a refrigerant outlet that outputs the flow of refrigerant having a second state; a water loop inlet that receives a flow of liquid at a first temperature; a water loop outlet that outputs the flow of liquid from the reclaim heat exchanger at a second temperature that is greater than the first temperature in response to the flow of refrigerant. The refrigeration reclaim unit also comprises a refrigerant flow control device having outputs to the refrigerant inlet and an air-cooled condenser, respectively for controlling the flow of refrigerant to at least one of the refrigerant inlet and the air-cooled condenser for maintaining a predetermined flow quality value at the refrigerant outlet.

Abstract: In some embodiments, apparatuses and methods are provided herein useful for ordering and securely delivering products. In some embodiments, a system for ordering and securely delivering products comprises an inventory system associated with a retailer, a system controller, and a storage container. The storage container includes a housing that enclosing a product cavity, a locking door configured to enable access to the product cavity, a user interface coupled to the housing, a wireless communication device, and a container control circuit configured to receive, via the user interface, an electronic purchase order for products from the retailer, transmit to the inventory system the electronic purchase order, receive from the system controller a signal instructing the container control circuit to unlock the door, and perform an electronic unlocking function causing the door to unlock.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed configured to run on the one or more processors, cause the one or more processors to and perform operations: receiving a command from a user; transforming, using a trained machined learning model, the command by detecting an intent to add one or more recipe ingredients; determining a recipe from a set of recipes; determining one or more items and one or more quantities or sizes of the one or more items; selecting a respective quantity or size from quantities or sizes of available items of the one or more items, wherein the respective quantity or size, as selected, is overruled when a different quantity or size preference is indicated by the user; and automatically adding to the shopping cart the one or more items. Other embodiments are described.

Abstract: A method including determining, in real-time, a diversity preference score for a user based at least in part on an anchor item chosen by the user via a user interface executed on a user device of the user. The method also can include determining, in real-time, a comparison result between the diversity preference score and a diversity preference threshold. The method further can include generating, in real-time, a personalized recommendation pool based on (a) the comparison result, (b) a complementary recommendation pool generated based at least in part on the anchor item, and (c) a diversity objective function. In many embodiments, when the comparison result indicates that the diversity preference score is greater than the diversity preference threshold, the diversity objective function can be associated with cross-domain diversity.

Abstract: A system for rush order fulfilment optimization is discussed. The system includes mobile devices that are each associated with a worker and a rush fulfillment engine executed by a computing system which dynamically updates a task queue of each worker upon receipt of a new rush order according to a task completion rate difference between an estimated task completion rate and the current task completion rate of the worker.

Abstract: A method including obtaining information about a trailer that has been partially loaded with preloaded stacks in a manner that deviates from an original load design. The trailer is loaded with stacks of pallets including (i) the preloaded stacks that have already been loaded in the trailer and (ii) unloaded stacks that have not yet been loaded into the trailer. The method also can include determining positions of empty floor spots remaining in the trailer. The method additionally can include determining a first portion of an incremental load design for the unloaded stacks using a gap-filling pattern behind an uneven rear edge of the preloaded stacks in the trailer. The method further can include determining a second portion of the incremental load design.

Abstract: A computer file system for managing data storage resources is provided. The system comprises storage server configured to receive data file from a client application, modify the file name to include an expiration stamp, upload the at least one data file to the data storage device, generate a file link associated with the at least one data file, and transmit the file link to the client application, wherein the at least one data file is retrievable by the end user via the file link. A maintenance server is communicatively coupled to the data storage device, the maintenance server configured to execute an erase operation to autonomously erase the at least one data file from the data storage device based on the expiration stamp.

Abstract: An electronic indication of a nil pick is received. Item information associated with the desired product, sales data concerning the desired product, supply chain information associated with the desired product, and a perpetual inventory (PI) value of the desired product are stored. An adjustment to the PI of the desired product is blocked when a predetermined event occurs at the retail store, or when information that contradicts the validity of the nil pick is received from the retail store. When the adjustment to the PI of the desired product is not blocked, an amount of the adjustment is determined based upon one or more of: the item information associated with the product, the sales data concerning the product, and the supply chain information associated with the desired product.

Abstract: In some embodiments, apparatuses and methods provide long term scheduling at a plurality of retail stores including storing a forecasted data over at least eight weekly scheduling periods; determining based on the forecasted data a first baseline hours demand value for each day of a week for each job function of a first set of job functions at a particular retail store; determining based on the forecasted data a second baseline hours demand value for each day of the week for each job function of a second set of job functions at the particular retail store; automatically generating a plurality of fixed schedules for a set of task resources at each of the plurality of retail stores; automatically instructing a user electronic device to display a notification indicating that a first fixed schedule associated with a first task resource is available.

Abstract: This application relates to apparatus and methods for training machine learning models using supervised, or semi-supervised, learning. In some examples, a computing device obtains training data that includes labelled, and unlabeled, data for training a machine learning model. The computing device applies the machine learning model to the training data to generate output data. The machine learning model executes with a plurality of coefficients applied to a plurality of hyperparameters. The computing device further applies a loss model to the training data and the output data to generate a loss value. Based on the loss values, the computing device determines updated values for the plurality of coefficients of the machine learning model. The computing device may continue to determine updated values for the plurality of coefficients until one or more conditions are satisfied. The computing device may then store the final coefficient values in a data repository.