Abstract: Systems and methods of visually indicating a current user activity or status on a display of an ear wearable device are provided. In one exemplary embodiment, a method comprises, by an ear wearable device that includes a display that is configured to be viewable while the ear wearable device is worn, receiving, from a first network node over a wireless communication channel, a first display object of a set of display objects that represents user activity or status associated with the ear wearable device or an indication associated with the first display object, with each display object being configured for display on the display of the ear wearable device so as to visually indicate the current user activity or status, the first network node being enabled to determine the current user activity or status and obtain the first display object based on the current user activity or status.

Abstract: Systems and methods of multidirectional robotic shelf restocking are performed. In one exemplary embodiment, a multidirectional robotic shelf restocking apparatus is configured to operate in first and second adjoining regions. The first region being above or below the second region defined by opposing stocked shelf structures. The apparatus includes a vertical motion mechanism and a corresponding vertical motion drive operable to move the vertical motion mechanism in a vertical direction. Further, the apparatus includes an arm member and a corresponding rotational motion drive operable to rotate the arm member between the stocked shelf structures and a corresponding linear motion drive operable to linearly extend and retract the arm member. In addition, the apparatus includes an end effector coupled to the arm member and configured to transfer an item from the first region to the second region by the motion of the vertical motion mechanism and the arm member.

Abstract: Methods and apparatus for automated order placement and fulfillment monitoring are provided. An order is received from a Point of Sale (PoS) device. One or more items in the order are identified. Responsive to receiving a confirmation of the order, a status of each item, among the one or more items in the order, is monitored. A graphical element rendered in a display interface is updated, the graphical element displaying changes in the status of each item within the order.

Abstract: The present disclosure provides techniques for improved animal recognition and recommendations. One or more images of an animal associated with a user are captured at a check-in kiosk of an enterprise. A unique identifier of the animal is determined by processing the one or more images using an animal recognition machine learning model. One or more records indicating characteristics of the animal are accessed based on the unique identifier, and one or more recommended items for the animal are generated based on processing the one or more records using an artificial intelligence system. One or more physical locations of the one or more recommended items in the enterprise are determined, and one or more indications of the one or more physical locations are output to facilitate user navigation to the one or more physical locations of the one or more recommended items in the enterprise.

Abstract: The present disclosure describes a system and method for holding or storing items. The system includes a pad, a weight sensor, a shape sensor, a memory, and a processor communicatively coupled to the memory. The weight sensor detects a weight of an item when the item is positioned on the pad. The shape sensor detects a shape of the item when the item is positioned on the pad. The processor verifies that the item is positioned on the pad based on the detected weight and the detected shape and communicates a message that the item is positioned on the pad.

Abstract: Systems and methods of obtaining a virtual representation of a physical object at point of sale are presented. In one exemplary embodiment, a POS system includes a first sensor device operable to sense an identifier unique to a physical object and a second sensor device operable to capture a digital image of the physical object during checkout by the POS system. Further, the POS system is communicatively coupled to a blockchain network that includes network nodes that are collectively configured to operate a blockchain. The unique physical object identifier is associated with a cryptographic digital asset stored on the blockchain as a code that represents the unique physical object identifier and a code that represents a reference to a virtual object obtained based on a digital image of the physical object captured by the second sensor during the checkout by the POS system.

Abstract: The present disclosure provides techniques for improved animal recognition and recommendations. One or more images of an animal associated with a user are captured at a check-in kiosk of an enterprise. A unique identifier of the animal is determined by processing the one or more images using an animal recognition machine learning model. One or more records indicating characteristics of the animal are accessed based on the unique identifier, and one or more recommended items for the animal are generated based on processing the one or more records using an artificial intelligence system. One or more physical locations of the one or more recommended items in the enterprise are determined, and one or more indications of the one or more physical locations are output to facilitate user navigation to the one or more physical locations of the one or more recommended items in the enterprise.

Abstract: The present disclosure describes a system and method for holding or storing items. The system includes a pad, a weight sensor, a shape sensor, a memory, and a processor communicatively coupled to the memory. The weight sensor detects a weight of an item when the item is positioned on the pad. The shape sensor detects a shape of the item when the item is positioned on the pad. The processor verifies that the item is positioned on the pad based on the detected weight and the detected shape and communicates a message that the item is positioned on the pad.

Abstract: Techniques for animal identification based on animal behavior. A first video depicting a first animal associated with a user during a first visit to an enterprise location is received. One or more attributes pertaining to the first animal or to the user are received. A first behavior of the first animal as depicted in the first video is extracted and encoded into a first behavioral representation. One or more machine learning models are trained to identify the first animal based on the first behavioral representation and the one or more attributes.

Abstract: Systems and methods of multidirectional robotic shelf restocking are performed. In one exemplary embodiment, a multidirectional robotic shelf restocking apparatus is configured to operate in first and second adjoining regions. The first region being above or below the second region defined by opposing stocked shelf structures. The apparatus includes a vertical motion mechanism and a corresponding vertical motion drive operable to move the vertical motion mechanism in a vertical direction. Further, the apparatus includes an arm member and a corresponding rotational motion drive operable to rotate the arm member between the stocked shelf structures and a corresponding linear motion drive operable to linearly extend and retract the arm member. In addition, the apparatus includes an end effector coupled to the arm member and configured to transfer an item from the first region to the second region by the motion of the vertical motion mechanism and the arm member.

Abstract: The present disclosure provides techniques for graphics translation. A subset of a plurality of natural language image descriptions for an image of a product is received. A set of shared natural language descriptors is identified in the subset of the plurality of natural language image descriptions. The set of shared natural language descriptors is aggregated, and a description for the first image is generated based on the aggregated set of shared natural language image descriptions.

Abstract: The present disclosure provides techniques for graphics translation. A plurality of natural language image descriptions is collected for an image of a product. An overall description for the image is generated using one or more models, based on the plurality of natural language image descriptions, by: identifying a set of shared descriptors used in at least a subset of the plurality of natural language image descriptions, and aggregating the set of shared descriptors to form the overall description. A first request to provide a description of the first image is received, and the overall description is returned in response to the first request, where the overall description is output using one or more text-to-speech techniques.

Abstract: Systems and methods of visually indicating a current user activity or status on a display of an ear wearable device are provided. In one exemplary embodiment, a method comprises, by an ear wearable device that includes a display that is configured to be viewable while the ear wearable device is worn, receiving, from a first network node over a wireless communication channel, a first display object of a set of display objects that represents user activity or status associated with the ear wearable device or an indication associated with the first display object, with each display object being configured for display on the display of the ear wearable device so as to visually indicate the current user activity or status, the first network node being enabled to determine the current user activity or status and obtain the first display object based on the current user activity or status.

Abstract: A method and system are provided for validating a promotional token redeemed at a Point-of-Sale (PoS) terminal, can include receiving, at the Point of Sale (PoS) terminal located at a physical retail location, a promotional token ID from a mobile device associated with a customer. The promotional token ID can be configured to uniquely identify a promotional token to promote a consumer packaged good (CPG) distributed on a social media platform. A CPG is entered at the PoS terminal to determine a CPG ID configured to uniquely identify the CPG. Next, a validation request is generated. The validation request comprises the promotional token ID and the CPG ID. The validation request is then transferred to a server having access to a private blockchain ledger. Upon completion, the PoS terminal will receive, from the server, the redemption status for the promotional token ID based on information stored in the private blockchain ledger responsive to the validation request.

Abstract: A computing device provides shoppers with a frictionless commerce experience. The computing device determines, tracks, and stores certain physical characteristics and/or attributes of the products selected by a shopper for purchase. The device analyzes these attributes with respect to the shopper's particular purchasing habits and uses the results of that analysis to recommend products to the shopper. Additionally, the computing device may modify the sales price of the product, or augment the shopper's order with the same or similar products, based on the results of the analysis.

Abstract: The present disclosure provides techniques for graphics translation. A plurality of natural language image descriptions is collected for an image of a product. An overall description for the image is generated using one or more models, based on the plurality of natural language image descriptions, by: identifying a set of shared descriptors used in at least a subset of the plurality of natural language image descriptions, and aggregating the set of shared descriptors to form the overall description. A first request to provide a description of the first image is received, and the overall description is returned in response to the first request, where the overall description is output using one or more text-to-speech techniques.