Abstract: An apparatus for monitoring and replenishing an inventory of goods includes a first inventory area and a first movable structure having a first optical code associated with the first distinct inventory area. The first movable structure is placed in a replenishment signaling area after a supply of goods in the inventory area is depleted. Boundary optical codes are disposed near a boundary of the replenishment signaling area. A camera generates periodic images of the replenishment signaling area and the boundary optical codes. A computer processor detects the boundary optical codes in the images and determines a boundary line of the replenishment signaling area based thereon. The processor determines a spatial relationship between the first optical code and the boundary line in the images and generates a replenishment notification based on the spatial relationship. The replenishment notification indicates that the supply of the first type of goods needs to be replenished.

Abstract: A computer-implemented system and method to collect and store data related to product stored in a container. In response to filling the container with the product, the following data are stored in at least one first record in an external database (such as a distributed ledger, e.g., blockchain): a product type of the first product; an amount of the first product filled into the first container; a unique identity of the first container; and a unique identity of a first user of the first container at the time of filling the first container with the first product. Data representing a unique identity of a container data module on the container are stored in the container data module. As the container moves, dispenses product, and undergoes changes in possession and ownership, data representing such events are stored in the distributed ledger and/or the container data module. As a result, a verifiable application/consumption record of the product within the container is generated.

Abstract: The present invention relates to a production system (10), in particular for producing biological-pharmaceutical products (20), and/or a method for producing a product (20), in particular a biological-pharmaceutical product (20).

Abstract: This disclosure describes systems and techniques for recognizing, or identifying, produce items being purchased at a self-checkout device. The self-checkout device may use a produce-recognition system that uses image-based recognition techniques so that items, such as produce, may be identified without the need for users to enter in keywords or price look-up (PLU) codes. The produce-recognition system may compare feature representations between the produce to be purchased, produce categories, and produce subcategories. Based on similarities with produce categories and produce subcategories, the identity of the produce item may be predicted. Ranked produce categories and subcategories may presented to the user. The presentation of produce categories and subcategories may depend on confidence levels associated with the predicted produce categories. The produce item may then be identified and added to a virtual cart.

Abstract: A learning device intended to be included in a mobile cyber-physical system provided with actuators, the device comprising at least one perception sensor for perceiving the external environment of the system, at least one internal sensor able to provide information concerning the state of the system, a first learning unit configured to render a perception of the environment from the data acquired by the at least one perception sensor, a second learning unit configured to control the actuators, a generator for generating simulation scenarios of the system in its environment controlled by the first learning unit and the second learning unit, a scenario simulator and a virtualization platform for simulating the behavior of a digital twin of the system in the scenarios simulated by the generator and for adapting the parameters of the second learning unit in order to control the system so that it adapts to its environment.

Abstract: A method, system, non-transitory computer readable media, and communication system for generating an Application Programming Interface (API) inventory. The method comprises obtaining source code associated with a software application and analyzing the source code to identify one or more first API endpoints in the software application. The method further comprises obtaining API traffic between a server running the software application and a client device and analyzing the API traffic to identify one or more second API endpoints in the software application. Then the method comprises generating an API inventory by combining the identified one or more first API endpoints and the one or more second API endpoints into a single data structure.

Abstract: A customer return management system operates to categorize reverse items for resale, such as returned items or overstock inventory, and deliver the categorized items through a variety of different reverse supply chains in a way to increase a net recovery rate. The system uses a sortation system that performs a two-step process for sorting the reverse items into different reverse supply channels. In a first step, the items can be scanned and divided into two categories based on their value, such as high value items and low value items. The low value items can be quickly liquidated as a bulk. In a second step, high value items can be categorized into a number of different sorts, which are taken to different resale channels.

Abstract: A computer-based system to determine a distribution of times a vehicle spends at different locations on a route has a global positioning system, a microprocessor, an output device and computer instructions. The instructions cause the system to read in from the GPS a monitored location of the vehicle and an associated time. The system then calculates a corrected location of the vehicle based on the closest point of the route to the monitored location. The system then computes the distribution of the times the vehicle spends at different locations on said route based at least in part on the corrected location and associated time. The system then outputs the distribution on a computer screen.

Abstract: This disclosure describes, in part, systems for enabling physical retail stores and other facilities to implement automated-checkout techniques for the purchase of items that are priced per unit weight. For example, the described systems may enable a facility to implement technology where users are able to remove items from inventory locations, place the items on weight sensors, and then be charged for the prices of the items without performing manual checkout of the items. The price of an item is determined based at least in part on the identifier of the item and the price per unit weight of the item. The systems described herein thus enable customized retail facilities, as opposed to a retail facility that allows automated-checkout only for prepackaged-type or otherwise non-customizable merchandise.

Abstract: The improved systems and methods utilize a detection and tracking device in communication with a plurality of media acquisition devices strategically placed within a defined space, which is divided in a grid fashion such that each media acquisition device senses at least three points within the space, with adjacent media acquisition devices overlap, such that the plurality covers the entire space. Objects in the space are sensed by respective media acquisition devices, annotated with a tracking identifier, and tracked while moving therein by either the media acquisition devices or the detection and tracking device. The detection and tracking device derives input data points from each media acquisition device for projection onto a groundplot of the space, clusters the input data points from corresponding media acquisition devices into a single cluster, assigns the tracking identifier to a centroid of the cluster, and tracks the object as it moves.

Abstract: Systems and methods for evaluating attributes in supply chain management is disclosed. The system may receive data from a set of data sources corresponding to a supply chain associated with at least a product, pre-process the data based on integration of the data from each of the set of data sources, generate supply chain data based on the integrated data, analyze, via an orchestration engine, the supply chain data to assess an impact of the supply chain data on the supply chain, predict, via the orchestration engine, a state associated with a purchase event of the product in the supply chain, and generate a resolution flow to be executed in the supply chain for managing the predicted state associated with the purchase event of the product.

Abstract: An apparatus for monitoring and replenishing an inventory of goods includes a first inventory area and a first movable structure having a first optical code associated with the first distinct inventory area. The first movable structure is placed in a replenishment signaling area after a supply of goods in the inventory area has been depleted. Boundary optical codes are disposed near a boundary of the replenishment signaling area. A camera generates periodic images of the replenishment signaling area and the boundary optical codes. A computer processor detects the boundary optical codes in the images and determines a boundary line of the replenishment signaling area based thereon. The processor determines a spatial relationship between the first optical code and the boundary line in the images and generates a replenishment notification based on the spatial relationship. The replenishment notification indicates that the supply of the first type of goods needs to be replenished.

Abstract: Examples provide an automatic item display reconfiguration guidance system providing sequential reconfiguration instructions presented to a user coordinated across multiple display devices in real-time as the modular item display is being reconfigured from an original item configuration to a new item configuration. A sequence of graphical instructions for removing a set of items, moving a set of items, and adding a set of new items to the modular item display are generated and presented to a user via a user interface (UI) on a user device and/or one or more shelf display device(s) on the modular item display in a substantially simultaneous manner. The graphical instructions including, color-coded indicators and/or images of the items, are presented to the user in real-time as items are removed, moved, or added in sequence enabling fast and efficient reconfiguration of items on the display with minimized expenditure of labor and reduced error rate.

Abstract: The present tree seedling inventory system includes both a mobile platform used to obtain images of seedlings and a tree seedling inventory system to count the seedlings. A recurrent neural network can receive processed imaging data and utilize a model to accurately count the seedlings as the mobile platform passes along a seedling bed. The system may also provide additional accurate seedling quality data about the seedlings, such as shoot height, root collar diameter, and needle coloration.

Abstract: A system and method are disclosed for modeling restorage cost for reverse sourcing of regular items. The method includes detecting a return request from a customer for an item, identifying a supply type for the item, predicting a demand for the item at potential restorage sites in a supply chain network, deriving a likelihood of potential restorage sites meeting service level agreements, and calculating a restorage cost for each of the potential restorage sites, and based on the calculated restorage costs, recommend a restorage plan to a user, where the recommended restorage plan is based, at least in part, on a threshold value of the item. The method further includes identifying the potential restorage sites based, at least in part, on a geographic range and assigning a manual quality check to verify a condition of the item.

Abstract: Methods, apparatus, and processor-readable storage media for automated resource prioritization using artificial intelligence techniques are provided herein.

Abstract: An AI inference platform comprises a logic die including an array of AI processing elements. Each AI processing element including an activation memory storing activation data for use in neural network computations. The platform includes a memory die that includes an array of 3D memory cells and a page buffer that facilitates storage and retrieval of neural network weights for use in neural network computations. A plurality of vertical connections can directly connect AI processing elements in the logic die and page buffers of corresponding ones of the memory cells in the memory die, enabling storage or retrieval of a neural network weight to and from a particular page buffer of a corresponding 3D memory cell for use in neural network computations conducted by a corresponding AI processing element in the logic die.

Abstract: A computer-implemented method for supporting execution of batch production by a production system includes, over a sequence of steps: acquiring a system state defined by a shop floor status, inventory status and a demand of the product types, and processing the system state using a reinforcement learned policy including a deep learning model to output a control action defining an integer batch size of a selected product type. The control action is determined by using learned parameters of the deep learning model to compute logits for a categorical distribution of predicted product types and a categorical distribution of predicted batch sizes from the system state. The logits are processed to transform the categorical distribution of predicted product types into an encoding of the selected product type and reduce the categorical distribution of predicted batch sizes into an integer batch size, for producing a next batch on the shop floor.

Abstract: A system for managing and tracking digital images of drill cuttings includes at least one networked database configured to store the digital images. A supplier portal is configured to enable a supplier to upload the digital images into the database and a customer portal is configured to provide customer access to selected ones of the digital images in the database. A networked blockchain ledger is in communication with the database, the supplier portal, and the customer portal. The blockchain ledger is configured to initiate a smart chain contract for each of the digital images, record customer access events within each smart chain contract for each of the digital images, and create a micro invoice including charges related to the recorded customer access events.

Abstract: A method for predicting inventory availability, involving receiving a delivery order including a plurality of items and a delivery location, and identifying a warehouse for picking the plurality of items. The method retrieves a machine-learned model that predicts a probability that an item is available at the warehouse. The machine-learned model is trained, using machine learning, based in part on a plurality of datasets. The plurality of datasets include data describing items included in previous delivery orders, whether each item in each previous delivery order was picked, a warehouse associated with each previous delivery order, and a plurality of characteristics associated with each of the items. The method predicts the probability that one of the plurality of items in the delivery order is available at the warehouse, and generates an instruction to a picker based on the probability. An instruction is transmitted to a mobile device of the picker.