Abstract: Embodiments herein use a checkout application to summon an autonomous vehicle of a customer who is performing a checkout process. In one embodiment, the checkout application identifies the stage that the customer is in in the checkout process such as arriving at a point-of-sale (POS) system, logging into a retailer application, scanning items, selecting a payment option, completing payment, loading purchased items in a cart/basket, etc. One of these stages can be selected as a “trigger stage” which, when reached by the customer, triggers the checkout application to summon the customer’s vehicle to a designated area (e.g., a lane near the store’s exit, special parking spots, etc.).

Abstract: Techniques of self-checkout alerts based on packaging detection. A given bag type of a bag selected at a self-checkout kiosk is identified out of a bag types available from a bag dispenser associated with the self-checkout kiosk, the bag being an empty bag. A weight range of the empty bag is identified based on the given bag type. An allowed weight range of a combination of the empty bag and a desired item is determined based on the weight range of the empty bag, a weight of the desired item as measured by a terminal scale, and at least one of a measurement tolerance of the terminal scale and a measurement tolerance of a platform scale. A loss prevention alert is generated, and a transaction at the self-checkout kiosk is paused, upon determining that the allowed weight range is exceeded.

Abstract: The present disclosure utilizes excess processing capacity of a point of sale (POS) system by dynamically managing assigned tasks based on an expected activity of an individual. A resource management system can use image data and a trained neural network to analyzes aspects of an appearance or a behavior of the individual as captured in the image data to quantify a likelihood of the individual participating in a checkout procedure. The resource management system can dynamically allocate resources across different POS systems in anticipation of expected activity. This allows for the efficient use of the POS systems' resources while maintaining good system performance and a positive experience.

Abstract: Techniques for self-checkout alert reduction based on packaging detection. A deflection in a first bag reservoir associated with a self-checkout kiosk is determined. The first bag reservoir is positioned adjacent to a packing area and includes a first type of bags. The self-checkout kiosk includes a terminal scale and further includes a platform scale in the packing area. That an empty bag is retrieved from the first bag reservoir is determined based on the deflection in the first bag reservoir. A bag type and a weight range are identified for the empty bag. An allowed weight range of a combination of the empty bag and a desired item is then determined. Presence of the empty bag on the platform scale is prevented from causing a loss prevention alert to be generated when the desired item has been placed in the empty bag on the platform scale.

Abstract: Method and apparatus for computer vision-based tracking are provided. A set of images depicting a set of items in a receptacle of a user is accessed. At least a first item, of the set of items, is identified based on processing at least a first image of the set of images using one or more object recognition machine learning models. Based on a mapping, a caloric value of the first item is determined, and nutrition tracking information for the user is updated based on the caloric value. A set of user characteristics provided by the user is determined. In response to determining that the updated nutrition tracking information satisfies one or more criteria based on the set of user characteristics, a notification is transmitted to a mobile device of the user.

Abstract: Systems and methods of performing automated shelf stock management are provided. In one exemplary embodiment, a method is performed by a first network node operationally coupled to an optical sensor device having a field of view towards a shelf structure having a set of stocked items and operable to capture an image of the shelf structure. Further, the first network node is operationally coupled to a set of display devices disposed on the shelf structure with each display device being specific to and proximate a certain stocked item on the shelf structure and operable to display stocked item information. The method includes obtaining information associated with a current arrangement of the stocked items and the corresponding display devices on the shelf structure so as to determine whether the stocked item information of a certain stocked item is associated with the stocked item information displayed by the corresponding display device.

Abstract: The present disclosure utilizes excess processing capacity of a point of sale (POS) system by dynamically managing assigned tasks based on an expected activity of an individual. A resource management system can use image data and a trained neural network to analyzes aspects of an appearance or a behavior of the individual as captured in the image data to quantify a likelihood of the individual participating in a checkout procedure. The resource management system can dynamically allocate resources across different POS systems in anticipation of expected activity. This allows for the efficient use of the POS systems' resources while maintaining good system performance and a positive experience.

Abstract: Techniques for self-checkout alert reduction based on packaging detection. A deflection in a first bag reservoir associated with a self-checkout kiosk is determined. The first bag reservoir is positioned adjacent to a packing area and includes a first type of bags. The self-checkout kiosk includes a terminal scale and further includes a platform scale in the packing area. That an empty bag is retrieved from the first bag reservoir is determined based on the deflection in the first bag reservoir. A bag type and a weight range are identified for the empty bag. An allowed weight range of a combination of the empty bag and a desired item is then determined. Presence of the empty bag on the platform scale is prevented from causing a loss prevention alert to be generated when the desired item has been placed in the empty bag on the platform scale.

Abstract: Techniques of self-checkout alerts based on packaging detection. A given bag type of a bag selected at a self-checkout kiosk is identified out of a bag types available from a bag dispenser associated with the self-checkout kiosk, the bag being an empty bag. A weight range of the empty bag is identified based on the given bag type. An allowed weight range of a combination of the empty bag and a desired item is determined based on the weight range of the empty bag, a weight of the desired item as measured by a terminal scale, and at least one of a measurement tolerance of the terminal scale and a measurement tolerance of a platform scale. A loss prevention alert is generated, and a transaction at the self-checkout kiosk is paused, upon determining that the allowed weight range is exceeded.

Abstract: The present disclosure provides improved packaging detection at self-checkout kiosks by identifying a given bag type for a bag selected at a self-checkout kiosk out of a plurality of bag types available from a bag dispenser associated with the self-checkout kiosk; identifying a weight range for the given bag type; in response to determining that the bag has been moved to a packing area of the self-checkout kiosk, comparing a first weight in the packing area from before the bag was moved to the packing area with a second weight in the packing area that includes the bag; and in response to a difference between the first weight and the second weight falling outside of the weight range, generating a loss prevention alert and pausing a transaction at the self-checkout kiosk.

Abstract: A non-transitory computer-readable medium whose contents, when executed by a computing system, can cause the computing system to perform operations for an audited shopping system that include receiving scanned product information identifying a current product and an associated weight of the current product. An indication can be determined to place the current product in a selected bag among a plurality of bags. The associated weight of the current product can be added to a previous calculated weight of products in the selected bag to provide a current calculated weight of products in the selected bag and then all previous operations can be repeated until receiving an indication that shopping is done to provide a plurality of products that are distributed among the plurality of bags, wherein each bag has a respective calculated weight of all products in the bag and indicating a selected one of the plurality of bags as an audited bag for weighing.

Abstract: The present disclosure provides improved packaging detection at self-checkout kiosks by identifying a given bag type for a bag selected at a self-checkout kiosk out of a plurality of bag types available from a bag dispenser associated with the self-checkout kiosk; identifying a weight range for the given bag type; in response to determining that the bag has been moved to a packing area of the self-checkout kiosk, comparing a first weight in the packing area from before the bag was moved to the packing area with a second weight in the packing area that includes the bag; and in response to a difference between the first weight and the second weight falling outside of the weight range, generating a loss prevention alert and pausing a transaction at the self-checkout kiosk.

Abstract: A non-transitory computer-readable medium whose contents, when executed by a computing system, can cause the computing system to perform operations for an audited shopping system that include receiving scanned product information identifying a current product and an associated weight of the current product. An indication can be determined to place the current product in a selected bag among a plurality of bags. The associated weight of the current product can be added to a previous calculated weight of products in the selected bag to provide a current calculated weight of products in the selected bag and then all previous operations can be repeated until receiving an indication that shopping is done to provide a plurality of products that are distributed among the plurality of bags, wherein each bag has a respective calculated weight of all products in the bag and indicating a selected one of the plurality of bags as an audited bag for weighing.