A method, system, and computer program product for co-located merchant anomaly detection obtain prior transaction data associated with a plurality of prior transactions, a first subset being associated with a first merchant, a second subset being associated with a second merchant, each prior transaction being associated with a same merchant location in the prior transaction data, and each prior transaction being associated with a same merchant name in the prior transaction data; extract a plurality of features associated with the plurality of prior transactions from the prior transaction data; and train based on the plurality of features associated with the plurality of prior transactions and labels for the prior transactions, a machine learning model to determine at least one of a prediction of whether a transaction is associated with the first merchant and a prediction of whether the transaction is associated with the second merchant.

The present disclosure discloses a method and a system for identifying goods of intelligent shopping cart. The method comprises: reading bar code information of a to-be-purchased goods and obtaining corresponding prestored goods information; continuously detecting and obtaining a total goods weight m.sub.n+1 in the shopping cart, and comparing the total goods weight m.sub.n+1 with a total goods weight m.sub.n acquired after a previous purchasing action is completed, to obtain a variation m.sub. of the total goods weight. According to the method of the present disclosure, when a customer puts a goods in the shopping cart in the shopping course, the correct goods is automatically identified and recorded in a shopping list, then the customer can directly settle the account after completing the shopping, accordingly a lot of time for the customers to wait for the settlement is saved.

The present disclosure discloses a method and a system for identifying goods of intelligent shopping cart. The method comprises: reading bar code information of a to-be-purchased goods and obtaining corresponding prestored goods information; continuously detecting and obtaining a total goods weight m.sub.n+1 in the shopping cart, and comparing the total goods weight m.sub.n+1 with a total goods weight m.sub.n acquired after a previous purchasing action is completed, to obtain a variation m.sub. of the total goods weight. According to the method of the present disclosure, when a customer puts a goods in the shopping cart in the shopping course, the correct goods is automatically identified and recorded in a shopping list, then the customer can directly settle the account after completing the shopping, accordingly a lot of time for the customers to wait for the settlement is saved.

A method includes supporting, by a support, a bag containing one or more items of an order and detecting, by a sensor coupled to an end of the support, a weight of the bag and the one or more items when the bag is suspended on the support such that the weight of the bag and the one or more items is exerted on the support. The method also includes comparing, by a hardware processor, the detected weight to an expected weight of the order and communicating, by the hardware processor, an alert when the expected weight is unequal to the detected weight.

A checkout system includes a register machine having a camera for capturing an image of a customer initiating a transaction, a checkout machine configured to perform checkout processing on the transaction, and a server in communication with the register machine and the checkout machine. The server includes a storage section in which the transaction information including an image of the customer captured with the camera, is stored, and a processor, which determines whether or not the checkout processing of the transaction has completed and erases the image of the customer at a first timing that is after determining that the checkout processing has completed, if an indication is received that the customer may have left behind an item, and at a second timing that is earlier than the first timing and is after determining that the checkout processing has completed, if the indication is not received.

A checkout system includes a register machine having a camera for capturing an image of a customer initiating a transaction, a checkout machine configured to perform checkout processing on the transaction, and a server in communication with the register machine and the checkout machine. The server includes a storage section in which the transaction information including an image of the customer captured with the camera, is stored, and a processor, which determines whether or not the checkout processing of the transaction has completed and erases the image of the customer at a first timing that is after determining that the checkout processing has completed, if an indication is received that the customer may have left behind an item, and at a second timing that is earlier than the first timing and is after determining that the checkout processing has completed, if the indication is not received.

A point of sale (POS) security system includes a POS device including a non-transitory memory, one or more hardware processors, and one or more environment sensors. A plurality of POS instructions are located on the non-transitory memory in the POS device and executable by the one or more hardware processors in the POS device to provide a POS engine that is configured to receive and transmit payment information for conducting a payment transaction associated with a purchase. A plurality of security instructions are located on the non-transitory memory in the POS device and are executable by the one or more hardware processors in the POS device to provide a security engine that is configured to receive environment signals from the one or more environment sensors in the POS device and analyze those environment signals to determine a security breach.

A point of sale (POS) security system includes a POS device including a non-transitory memory, one or more hardware processors, and one or more environment sensors. A plurality of POS instructions are located on the non-transitory memory in the POS device and executable by the one or more hardware processors in the POS device to provide a POS engine that is configured to receive and transmit payment information for conducting a payment transaction associated with a purchase. A plurality of security instructions are located on the non-transitory memory in the POS device and are executable by the one or more hardware processors in the POS device to provide a security engine that is configured to receive environment signals from the one or more environment sensors in the POS device and analyze those environment signals to determine a security breach.

The present invention addresses the problem of preventing products from being carried outside a store without complete a checkout process in a checkout system in which a product, a shopping basket in which the product is accommodated, or a shopping cart in which the product is accommodated is disposed in a checkout device when performing a checkout process. In order to solve the problem, a product registration device (10) registers the product. The checkout device (20) performs the checkout process for the product registered by the product registration device (10). An output unit (320) outputs information indicating that a target object (30) (in the example shown in the drawing, a shopping cart (32) in which a product is accommodated) has moved from the checkout device (20) on the basis of the presence or absence of movement of the target object (30) from the checkout device (20), and the state of the checkout process.

Aspects of the disclosure relate to edge-computing (EC)-based systems and methods for fraud mitigation. The systems and methods may utilize a multi-layer architecture. The architecture may include a set of N gatekeeper units, and each gatekeeper unit may be associated with an EC device. When a transaction request is received, the request may be processed at a first gatekeeper unit, and, if validated, successively processed by the set of N gatekeeper units. If any gatekeeper unit flags the request as suspicious, the unit may emit an audible alert that may be sensed by the associated EC device. The EC device may transmit a signal to one or more of the other gatekeeper units to perform additional processing for the request. When the request reaches the N.sup.th gatekeeper unit and achieves validation, the transaction may be executed via a central server connected to a transaction network.