Abstract: Disclosed herein are systems and methods for determining whether an unknown product matches a scanned barcode during a checkout process. An edge computing device or other computer system can receive, from an overhead camera at a checkout lane, image data of an unknown product that is placed on a flatbed scanning area, identify candidate product identifications for the unknown product based on applying a classification model and/or product identification models to the image data, and determine based on the candidate product identifications, whether the unknown product matches a product associated with a barcode that is scanned at a POS terminal in the checkout lane. The classification model can be used to determine n-dimensional space feature values for the unknown product and determine which product the unknown product likely matches. The product identification models can be used to determine whether the unknown product is one of the products that are modeled.

Abstract: The disclosed technology provides for generating best images of a person in a retail environment. A method may include receiving, by an edge computing device from a camera, a continuous stream of image data of the retail environment, detecting, using object detection techniques, a person in the image data, the image data including a group of images that are part of a time series, generating bounding boxes for each of the group of images around the person based on detecting the person as they move in the images, identifying, based on applying a features model to each bounding box, at least one feature of the group of images depicting the person, selecting a subset of the bounding boxes having at least one feature that satisfies best images criteria, the subset having best images of the person, and returning the best images of the person.

Abstract: The disclosed technology provides for determining whether to audit a shopper in a retail environment based on a trust score assigned to the shopper. A method can include receiving, by a computer system, shopper information including an identifier for the shopper, retrieving bag checkout history data associated with the shopper based on the identifier, which includes the shopper's trust score, determining a weighted probability score for the shopper based on the trust score and shopper trust score groupings, determining, using a randomization process, whether to perform a bag check on the shopper based on the weighted probability score, returning bag check instructions based on the determination, receiving bag check data from performing the bag check after the shopper completes checkout, adjusting the trust score based on the bag check history data and the bag check data, and providing the adjusted shopper trust score for use in the shopper's subsequent visits.

Abstract: The disclosed technology provides for automatically detecting and responding to potentially suspicious or risky activity in a retail environment. A method can include receiving, from monitoring devices in a retail environment, a stream of activity data, applying a model to the stream of activity data to identify a portion of the data corresponding to guest activity during a checkout process, identifying whether a risk event is associated with the activity, determining a guest risk impact score, selecting (i) a particular manual response from among candidate manual responses and (ii) a particular automated response from among candidate automated responses based on the risk impact score satisfying manual response criteria and/or automated response criteria, transmitting instructions to a POS terminal to implement the particular automated response, and/or transmitting instructions to implement the particular manual response to one or more mobile devices, that prompt employees to perform the manual response.

Abstract: Disclosed herein are systems and methods for determining whether an unknown product matches a scanned barcode during a checkout process. An edge computing device or other computer system can receive, from an overhead camera at a checkout lane, image data of an unknown product that is placed on a flatbed scanning area, identify candidate product identifications for the unknown product based on applying a classification model and/or product identification models to the image data, and determine based on the candidate product identifications, whether the unknown product matches a product associated with a barcode that is scanned at a POS terminal in the checkout lane. The classification model can be used to determine n-dimensional space feature values for the unknown product and determine which product the unknown product likely matches. The product identification models can be used to determine whether the unknown product is one of the products that are modeled.

Abstract: Described herein are systems and methods for determining whether a scanning motion occurred during a checkout process. The system includes a checkout lane having a scanning area that receives products to be purchased by a user, scanning devices, a point of sale (POS) terminal that identifies a product based on a scan, using the scanning devices, of a product identifier for the product as the product is moved through the scanning area, and an overhead camera that captures image data of the user's body movements and transmits, to a computing system, the image data. The computing system can, during runtime, identify whether a scanning motion occurred during the user's body movements based on application of one or more motion identification models to the image data and determine, based on identification of the scanning motion, that the user performed an affirmative scan during the checkout process.

Abstract: Disclosed are systems and methods for determining whether an unknown product matches a scanned barcode during checkout. The system includes a checkout lane having a flatbed scanning area with scanning devices and a point of sale (POS) terminal that scans a product identifier of an unknown product, identifies a product associated with the scanned product identifier, and transmits, to a computing system, product information. An overhead camera idnentifies, based on detecting an optical signal from the POS terminal, that a scanning event occurred, captures image data of the unknown product, and transmits, to the computing system, the image data.

Abstract: Described herein are systems and methods for generating security event case files with unstructured data. For example, the method can include receiving, by a computing system, unstructured data and system-based inferences from devices positioned throughout a store, and adding structure to the unstructured data and system-based inferences based on applying one or more structuring models. Adding structure can include labeling the data and system-based inferences, classifying them into security event categories, and identifying objective identifiers to identify users in the data and system-based inferences. The method also can include generating case files for each of the objective identifiers, where the case files include the associated data. The method can include determining whether the case files satisfy alerting rules. The case files can then be reported out and acted upon (e.g., based on satisfying the alerting rules) and/or stored for subsequent analysis and use.

Abstract: Described herein are systems and methods for generating a watch list of users who pose specific security threats to a store. The method can include retrieving, by a computer system from a data store, case files that document activity that poses a security threat by a user at the store, predicting, based on applying prediction models to the case files, future activity associated with the case files, determining threat scores for the case files based on the predicted future activity, ranking the case files into a candidate list from highest to lowest threat score, generating a watch list for the store that includes a subset of the ranked case files based on which case files pose a greatest current threat to the store, generating summary videos for each case file in the watch list, and transmitting the watch list and summary videos to a user device.

Abstract: Disclosed herein are systems and methods for determining whether an unknown product matches a scanned barcode during a checkout process. An edge computing device or other computer system can receive, from an overhead camera at a checkout lane, image data of an unknown product that is placed on a flatbed scanning area, identify candidate product identifications for the unknown product based on applying a classification model and/or product identification models to the image data, and determine based on the candidate product identifications, whether the unknown product matches a product associated with a barcode that is scanned at a POS terminal in the checkout lane. The classification model can be used to determine n-dimensional space feature values for the unknown product and determine which product the unknown product likely matches. The product identification models can be used to determine whether the unknown product is one of the products that are modeled.