Abstract: A machine-learning algorithm is trained with features relevant to a visual/video analysis performed on subjects conducting transaction at transaction terminals. The algorithm is also trained on weather data known at the time of the transactions and on selective details of the transactions. The algorithm produces as output predictions relevant to: whether a given subject for a current transaction is likely to enter a store, likely items that the given subject might purchase if the subject were to enter the store and likely amount of money that the subject would spend in the store, an effectiveness of providing an incentive for the subject to enter the store, and what type of incentive would most likely entice the subject to enter the store.

Abstract: A fraud detection system for a self-service terminal which has a card reader includes an optical proximity sensor and an electrode for a capacitive proximity sensor mounted adjacent to a slot in the card reader. A controller is coupled to the optical proximity sensor and the capacitive proximity sensor. The controller compares a proximity signal from the optical proximity sensor with a first predetermined proximity threshold that is adjusted based on a level of ambient infrared light at that sensor, and sets an alarm signal when an object is closer than the adjusted first predetermined proximity threshold. The controller also compares a proximity signal from the capacitive proximity sensor with a second predetermined proximity threshold that is adjusted based on a level of luminosity light at the optical proximity sensor, and sets an alarm signal when an object is closer than the adjusted second predetermined proximity threshold.

Abstract: Workload Images comprising one or more artifacts are managed in a decentralized and centralized manner. Local management comprises breaking any image/artifact into blocks, encrypting each block with a key known and available only to the local processing environment, and uniquely signing each encrypted block. Published versions of the images/artifacts are retained remotely in a cloud/server in encrypted and signed block format. When retrieval, modification, addition, deletion, and deployment of any given image/artifact is needed, the target device/server that is to receive the image/artifact provides a listing of encrypted blocks with the corresponding signatures that are already present on that device/server and a centralized cloud/server schedules and manages download of just those encrypted blocks that are missing to the target device/server.

Abstract: A machine-learning algorithm is trained with features relevant to a modeled set of input directed to patterns of activities specific to a given behavior. The trained algorithm is also trained on success and failures of remediation actions that change or do not change the given behavior. The trained algorithm is then provided the modeled set of input at predefined intervals of time and supplies as output expected deviations/changes that are predicted for the given behavior along with an indication as to whether the remediation actions are likely to prevent or change the expected behaviors.

Abstract: Disclosed are systems and methods for detecting a printer jam. The systems and methods can include receiving a reference image of a printer opening and a second image of the printer opening. A lack of a receipt between the second image compared to the reference image can be detected. The lack of the receipt can indicate the printer jam. After detecting the printer jam, operation of the self-service terminal can be terminated.

Abstract: A distributed interface is provided with real-time updates. A first user accessing the interface through a first user window is dynamically updated within the first user window and in real time when a second user accessing the interface through a second user window changes a field/character within the second user window. In an embodiment, the updated notification is achieved without window refreshing and without a committed update for the field/character change being committed by the second user to a back end system associated with the distributed interface.

Abstract: Time-stamped images are captured for unknown items within a store. Portions of the images are cropped to restrict the cropped images to attributes associated with the unknown items. A set of time ordered cropped images are proved to a trained machine-learning item recognition algorithm, which produces an output of confidence values that map to specific items of the store. When the confidence value meets or exceeds a predefined threshold, the specific item associated with that confidence value is used to identify the unknown item. The known item is assigned to an appropriate shopping cart of a shopper based on tracking from the images of the shopper while in the store.

Abstract: A system and method for providing an augmented reality (AR) interaction zone to a user of a mobile device to provide remote access to a self-service terminal (SST) having a controller, a display for providing information and instructions to a user, a keypad for entering user data and user commands, and a camera (preferably a depth camera). A mobile device selectively initiates, based on a user command, a transaction by establishing a wireless communications channel with the SST. The controller generates the AR interaction zone based on signals from the camera, provides a signal to the mobile device to display an AR input field on an integral display, processes signals from the camera to monitor the AR interaction zone for user movement corresponding to input, identifies input based on the signals from the camera, and causes the SST to process a requested user transaction based on the identified input.

Abstract: A peripheral device is tracked between connections to host devices. A peripheral driver is dynamically configured and associated with a peripheral of a host device. A current association between the peripheral device and a current host device is maintained for purposes of providing the peripheral driver of the peripheral device on the current host device to remotely executing applications. The association is dynamically changed/updated based on a connection between the peripheral device and a given host device.

Abstract: A scan avoidance monitoring system detects instances in which a respective customer in a retail environment fails to properly scan or tally one or more retail items for purchase. To avoid generating false positives, such as flagging of events as scan avoidances when they really are not or likely are not scan avoidances, the scan avoidance system can be configured to require a level of confirmation by one or more other analyzers to flag a particular circumstance as a scan avoidance.

Abstract: An autonomous enterprise bot observes video, audio, and operational real-time data for an enterprise. The real-time data is processed and a predicted activity needed for the enterprise is determined. The bot proactively communicates the predicted activity to a staff member of the enterprise for performing actions associated with the predicted activity.

Abstract: A terminal receives card details for a payment card to process payment for a transaction. The card and transaction details are sent to an intermediate server. The card details are identified as being associated with a card issuer associated with a first currency while the terminal is associated with a second different currency from the first currency. A currency conversion entity selection request is sent to the card issuer. The card issuer requests a consumer select a currency conversion entity for payment at the terminal. A mobile device of the consumer generates encoded data representing: a selected currency conversion entity, the card details, and the transaction details. The encoded data is processed to verify and process payment for the transaction with the selected currency conversion entity preventing any override by a merchant to use a different currency conversion entity at the terminal.

Abstract: During a pairing process between a connecting device and a server, a shared certificate is translated into a graphical scene by a validating client device of the server and the connecting device and the corresponding graphical scenes are independently displayed on each device for visual comparison by an operator of the validating client device. A validation word or code is also presented on the connecting device. When the validation word or code is correctly entered into a pairing validation interface on the client device by the operator, the server permits the connecting device to pair/connect with the server. In an embodiment, even single bit differences between the shared certificate expected by the server creates significant differences in the graphical scene depicted on the connecting device from that which is depicted on the client device.

Abstract: Various embodiments herein each include at least one of systems methods, software, and data structures for electronic lock control and audit. The various embodiments, although widely applicable, are well suited for retail use where higher-value and access-controlled merchandise is stored in locked cages, closets, rooms, and cabinets to prevent theft. One method embodiment includes receiving, via a network from a mobile device app, an unlock request including an employee identifier and a lock identifier to unlock a secured resource of the lock identifier. The method proceeds in processing the request by validating the employee identifier is authorized to unlock the lock of the lock identifier at a current date and time and retrieving a key-code that will unlock the lock of the lock identifier. The method then proceeds with transmitting the key-code to the mobile device app to enable unlocking of the lock.

Abstract: Techniques for automated mobile transaction processing are provided. A consumer traverses to a web portal or other type of enterprise terminal device of an enterprise and proceeds to shop. During checkout, the portal contacts a transaction service and is delivered back an identifying barcode or Quick Response (QR) code. The consumer uses a mobile device to scan the code and send it to the transaction service. Previously registered payment details of the consumer are located and payment is received from the consumer. The portal is notified that payment is completed by the transaction service.

Abstract: A bunch of valuable media items are transported along a track surface within a deskew/pick module of a depository until a bottom item of the bunch covers a track sensor adjacent to an exit. Upper rollers are disengaged from a topmost item of the bunch and lower track-surface rollers are rotated in a direction that is perpendicular to a sidewall forcing a bottommost item of the bunch in alignment to the sidewall. Upper rollers are lowered onto the topmost item and pick rollers are activated to urge the bottommost item through the exit of the module. Upper rollers are raised off the topmost item and lower track-surface rollers are rotated; upper rollers are lowered onto the topmost item and pick rollers are activated to urge a next bottommost item through the exit. This process is repeated until no items are left in the bunch to process.

Abstract: A vison-based self-checkout terminal is provided. Purchased items are placed on a base and multiple cameras take multiple images of each item placed on the base. A location for each item placed on the base is determined along with a depth and the dimensions of each item at its given location on the base. Each item's images are then cropped, and item recognition is performed for each item on that item's cropped images with that item's corresponding depth and dimension attributes. An item identifier for each item is obtained along with a corresponding price and a transaction associated with items are completed.

Abstract: A Virtual Reality (VR) system and method are provided that integrates transaction processing. A VR session customer transaction information is obtained and a transaction is concluded with the transaction information during the VR session.

Abstract: Disclosed are barcode scanners and methods for scanning a barcode. The barcode scanners and methods for scanning a barcode may include receiving a raw image from a scanner. Channel information may be extracted from each pixel of the raw image. A composite image may be created using the channel information from each pixel of the raw image. Finally, product information may be extracted from the composite image.

Abstract: Video frames from a video are compressed into a single image or a single data structure that represents a unique visual flowprint or visual signature for a given activity being modeled from the video frames. The flowprint comprises a computed summary of the original pixel values associated with the video frames within the single image and the flowprint is specific to movements occurring within the video frames that are associated with the given activity. In an embodiment, the flowprint is provided as input to a machine-learning algorithm to allow the algorithm to perform object tracking and monitoring from the flowprint rather than from the video frames of the video, which substantially improves processor load and memory utilization on a device that executes the algorithm, and substantially improved responsiveness of the algorithm.