382results about "Alarm indicators" patented technology

A self-service POS terminal includes a tag reader, a camera, and a processor configured to: start a registration process to register items each of which has a wireless tag attached thereto, control the wireless tag reader to read tag information from wireless tags and store the tag information in memory, determine a number of the tags based on the tag information, control the camera to capture images and generate image data from each of the images, perform object recognition on the image data to determine a number of items shown in the images, compare the number of the tags with the number of the items, when the number of the tags is identical to the number of the items, perform a checkout process, and when the number of the tags is not identical to the number of the items, issue a notification signal.

A computer system for predicting an anomaly behavior (fraudulent behavior) for a user of a smart shopping cart (physical receptacle). The computer system gathers data associated with a physical activity of the user, the user being physically present at a location of a retailer and adding one or more items from the location of the retailer to the physical receptacle. The computer system applies a computer model to detect, based on the gathered data, one or more anomalies during the physical activity of the user, the one or more anomalies being indicative of the fraudulent behavior. In response to determining that the one or more detected anomalies satisfy a threshold condition for the fraudulent behavior, the computer system sends a communication to a management system of the retailer to cause at least one remedial action to be performed before the user physically leaves the location of the retailer.

An action detection system (10) includes an action specification unit (18) configured to start specification of at least one action ID based on at least part of skeleton information extracted from video data that is a captured video of a user in response to detection of the user visiting checkout machine determined in advance, a determination unit (20) configured to determine whether or not an action sequence including the specified at least one action ID corresponds to registration action sequences registered in advance, and a processing control unit (21) configured to execute processing determined in advance in accordance with a determination result.

An information processing terminal according to an embodiment includes a determination unit, a display control unit, an acquisition unit, and a transmission unit. The determination unit determines whether information regarding a registration of a product satisfies a photographing condition. The display control unit allows a display unit to display an automatic photographing guidance for the product based on a determination result of the determination unit. The acquisition unit acquires, based on automatic photographing of the product, photographed image data of the photographed product. The transmission unit transmits the photographed image data acquired by the acquisition unit.

An information processing device identifies a first feature amount related to the number of the product registered on the specific machine based on an acquired product information, generating, from an image capturing a user in front of the specific machine, a first area information, a second area information and an interaction between the first class and the second class, specifies an action of the user of registering the product to the specific machine based on the first area information, the second area information, and the interaction, identifies a second feature amount related to the number of time of carrying out the action; and generates an alert based on the first feature amount and the second feature amount.

A system providing self-service access to locked merchandise comprising: (a) providing a fixture that restricts access to the locked merchandise, wherein the fixture can automatically lock or unlock, allowing or restricting access to the locked merchandise; (b) providing a means of uniquely identifying an individual attempting to access the merchandise; (c) measuring a set of behaviors of the individual during any time the fixture is an open mode; (d) assessing whether the set of behaviors of the individual are suspicious or not relative to a set of suspicious event thresholds; (e) storing the individual and their set of behaviors as accessible records in at least one database; and (f) providing an algorithm which determines future access privileges of the individual to the enclosure based on a set of variables.

An interactive shopping system, or smart cart. The system allows a user to select items in a store and complete a purchase without having to wait in lines or interact with store personnel. The system can have a container for holding products selected by at least one user, a user interface, a scanner in communication with the user interface, a processor in communication with the user interface, and a data storage comprising computer instructions executable by the processor. A user can select products, place them within the container, scan the products, and initiate a payment transaction to complete a purchase.

A system for monitoring shopping carts uses cameras to generate images of the carts moving in a store. In some implementations, cameras may additionally or alternatively be mounted to the shopping carts and configured to image cart contents. The system may use the collected image data, and / or other types of sensor data (such as the store location at which an item was added to the basket), to classify items detected in the shopping carts. For example, a trained machine learning model may classify item in a cart as “non-merchandise,”“high theft risk merchandise,”“electronics merchandise,” etc. When a shopping cart approaches a store exit without any indication of an associated payment transaction, the system may use the associated item classification data, optionally in combination with other data such as cart path data, to determine whether to execute an anti-theft action, such as locking a cart wheel or activating a store alarm. The system may also compare the classifications of cart contents to payment transaction records (or summaries thereof) to, e.g., detect underpayment events.

A hybrid checkout system that enables in-motion, multi-signal, bulk item identification is disclosed. The hybrid checkout system includes a computer vision apparatus that includes a plurality of cameras fixed at different locations relative to a conveyor belt. The conveyor belt includes markings that assist a user with item placement. RFID sensors are provided with the hybrid checkout apparatus. The cameras capture multiple images of items placed on the belt as the items are in motion. Each camera captures multiple images of the items captured from different vantage points as the items are in motion. In addition, the RFID sensors gather RFID data from RFID tags affixed to the items, as the items are in motion. The image data and other sensor data is provided as a multi-signal input to a machine learning model that is trained to recognize items and output item identifiers for the items. Pricing information corresponding to the item identifiers received from the model is determined and the items and their respective prices are added to a transaction record.

To provide an exiting management system and the like that can support handling of an abnormality having occurred in relation to commodities to be taken out by an exiting customer when registration and settlement of commodities are performed through a portable terminal operated by the customer.SOLUTION: An exiting management system according to the present disclosure includes: code acquisition means for, when registration and settlement of commodities are performed through a portable terminal operated by a customer, acquiring a settled code from the portable terminal; settled commodity information acquisition means for acquiring the amount of settled commodities associated with the settled code; estimation means for estimating the amount of commodities to be taken out by the customer from an image captured by imaging baggage of the exiting customer; abnormality detection means for detecting an abnormality based on the acquired amount of settled commodities and the estimated amount of commodities to be taken out; and abnormality output means for outputting the fact that the abnormality has been detected.SELECTED DRAWING: Figure 1

A system includes predetermined item detection circuitry configured to detect the presence of a predetermined item other than items that are put in a shopping basket provided in a store; action detection circuitry configured to detect a predetermined item registration action, using an image taken of item registration work by a registering person who is registering items; and output circuitry configured to output an alert if the presence of the predetermined item is detected by the predetermined item detection circuitry but no predetermined item registration action for the predetermined item is detected by the action detection circuitry.

To ensure that articles to be checked can be checked by a clerk in a full self-service settlement system in which the articles to be purchased are registered by a customer.SOLUTION: A settlement device capable of operating in a first operation mode in response to customer operation and a second operation mode in response to clerk operation includes first display means and second display means. The first display means displays a check screen to call a clerk when an article to be checked is input in the first operation mode. The second display means displays, in the first operation mode, a selection screen to allow the clerk to select whether or not to sell the article to be checked.SELECTED DRAWING: Figure 4

Consistent with disclosed embodiments, systems, methods, and computer readable media for conducting wireless transaction communications may be provided. Embodiments may include at least one processor configured to access a data structure containing identities of display areas and identities of products associated with the display areas; receive a request for information related to a particular display area in a vicinity of a mobile communications device; receive location information associated with a locus of the mobile communications device; perform a lookup in the data structure to identify the particular display area; retrieve product-related information associated with products in the particular display area; and transmit the product-related information to the mobile communications device.

Disclosed herein is a novel system and method to reduce theft and errors in the self-checkout process. The system and methods disclosed herein reconcile purchased products with receipts for those products by corresponding, analyzing, and / or comparing information on self-checkout transaction receipts with captured images of purchase products from camera feeds to ensure that all products purchased via a self-checkout system have been properly scanned and accounted for.

Consistent with disclosed embodiments, systems, methods, and computer readable media for electronic security systems for retail establishments may be provided. Embodiments may include an electronic article surveillance (EAS) gate and at least one receiver configured to receive transmissions from wireless tags associated with products offered by a retail establishment. Embodiments may also include at least one processor configured to receive, from a device operated by a prospective purchaser, a tag ID associated with a specific product for prospective purchase; perform a lookup of the tag ID in a data structure to identify the specific product; initiate an electronic purchase transaction to debit an account associated with the prospective purchaser for purchase of the specific product; and disable an ability to initiate an alarm when the at least one receiver receives a transmission from a tag associated with the specific product in proximity to the EAS gate.

A dual RFID and AM label or tag, and method for making the same, including a first housing portion comprising a first bio-degradable material and having a side wall defining a cavity, a second housing portion comprising a second bio-degradable material and connected to the first housing portion, an acousto-magnetic resonator sized to moveably fit within the cavity, and an RFID label associated with one of the first housing portion or the second housing portion.

Self-checkout verification systems and methods are described. One aspect includes receiving a plurality of images from a camera, the images being associated with a customer self-checkout process. The images may be analyzed to detect one or more items in possession of the customer, count a first number of the items, categorize each item, and construct a first category set including the categorizing for all the items. One aspect includes receiving a point-of-sale record at a completion of the self-checkout process, the point-of-sale record including a second number of the items and a second category set including the categorizing for all the items. The first number and the second number, and the first category set and the second category set may be compared. An alert may be generated if there is a discrepancy between the first number and the second number, or the first category set and the second category set.

The present disclosure utilizes image data analysis to improve the accuracy and integrity of item characteristic information in a database. During point-of-sale (POS) transactions, a security exception may be triggered when an item's stored characteristic information, such as weight or dimensions, is found to be inaccurate or missing. By capturing images of procedures performed to resolve security exceptions, the system can analyze aspects of the individual's appearance or behavior to determine if measurement procedures are performed correctly. Measures from properly performed measurement procedures can be used to selectively update the item's characteristic information in the system, improving the accuracy and integrity the characteristic information.

Systems, computer program products, and methods are described herein for using an anomaly deterrent sensor within a self-service machine for dispensing physical items. The present disclosure is configured to: detect an interaction between a payment instrument with available resources and a self-service machine for dispensing physical items; receive an anomaly notification from an anomaly deterrent sensor within the self-service machine for dispensing physical items wherein the anomaly notification is associated with forced entry into the self-service machine, wherein the anomaly deterrent sensor detects forced entry into a physical item dispensing area within the self-service machine during the interaction between the payment instrument and self-service machine; and trigger a set of security measures associated with the self-service machine for dispensing physical items upon reception of the anomaly notification originating from the anomaly deterrent sensor, wherein the set of security measures comprises playing a pre-recorded alarm.

Method and apparatus for fraud detection are provided. Sensor data from one or more acoustic wave sensors is received, where the one or more acoustic wave sensors transmit acoustic waves towards a set of items within a receptacle and receive reflected acoustic waves from the set of items. A model for the set of items within the receptacle is generated based on the sensor data. One or more features for the set of items are identified by analyzing the model. Checkout data is retrieved from one or more checkout devices. The one or more features for the set of items identified from the model are compared with the checkout data. An alert is generated upon detecting a discrepancy between the one or more features and the checkout data.

A system for monitoring shopping carts uses cameras to generate images of the carts moving in a store. In some implementations, cameras may additionally or alternatively be mounted to the shopping carts and configured to image cart contents. The system may use the collected image data, and / or other types of sensor data (such as the store location at which an item was added to the basket), to classify items detected in the shopping carts. For example, a trained machine learning model may classify item in a cart as “non-merchandise,”“high theft risk merchandise,”“electronics merchandise,” etc. When a shopping cart approaches a store exit without any indication of an associated payment transaction, the system may use the associated item classification data, optionally in combination with other data such as cart path data, to determine whether to execute an anti-theft action, such as locking a cart wheel or activating a store alarm. The system may also compare the classifications of cart contents to payment transaction records (or summaries thereof) to, e.g., detect underpayment events.

The present invention relates to a self-checkout method. The method includes: executing following steps through a control module: activating a first image sensor to capture a first image that includes a hand; activating a second image sensor to capture a second image that includes an item; running a gesture recognition independent model to generate a first recognition result based on the first image; running an object recognition independent model to generate a third recognition result based on the second image; and executing and inputting the first recognition result and the third recognition result into a checkout assistance decision independent model to determine whether a missed scan event has occurred.

Transaction records for self-service checkout transactions are provided in real-time to a customizable machine-learning rescan audit service. Any retailer defined settings with respect to random audits are enforced by the service and the real-time transaction records are provided to a machine-learning model that returns rescan scores based on the real-time transaction records. The service compares the rescan scores in view of retailer-defined suspicious scores for both a full rescan of a given checkout transaction and a partial rescan of the given checkout transaction. The service alerts the retailer when a rescan audit is predicted to be warranted for any given self-service checkout transaction based on random selection or based on the computed rescan score. The machine-learning model is continuously and regularly retrained. In an embodiment, the service provides reports, a dashboard, and mining of the transaction records and the audits to the retailer though a service-provided interface.

In some embodiments, systems and methods provide distributed item authentication. In some embodiments systems comprise: a housing; a set of sensor systems; a transceiver; and an authentication control circuit configured to: obtain first sensor data of an item being authenticated, obtain an initial identification of the item; access an item authentication block specific to the item; obtain a first set of authentication instructions; control one or more sensor systems in accordance with the first set of authentication instructions; compare multiple current authentication sensor data to the set of multiple historic authentication sensor data; confirm that each of a threshold number of the multiple current authentication sensor data is consistent within a threshold variation of a corresponding one of the set of multiple historic authentication sensor data; and cause the item authentication block to be updated to include the confirmation of authentication of the item.

The invention relates to a self-checkout method, which comprises the following steps executed by a control module: driving a first image sensor to obtain a first image containing a hand; driving a second image sensor to acquire a second image containing the article; executing a gesture recognition independent model to generate a first recognition result based on the first image; executing an object recognition independent model to generate a third recognition result based on the second image; and executing and inputting the first identification result and the third identification result into a checkout auxiliary decision independent model so as to judge whether a swiping omission event occurs according to the first identification result and the third identification result.

An interactive shopping system, or smart cart. The system allows a user to select items in a store and complete a purchase without having to wait in lines or interact with store personnel. The system can have a container for holding products selected by at least one user, a user interface, a scanner in communication with the user interface, a processor in communication with the user interface, and a data storage comprising computer instructions executable by the processor. A user can select products, place them within the container, scan the products, and initiate a payment transaction to complete a purchase.

A method is provided. The method includes receiving image information corresponding to a point-of-sale (POS) transaction, the image information includes an item being weighed, receiving an indication of an item weight or an indication of an item identifier for the item associated with the POS transaction, determining an expected item weight or an expected item identifier for the item based on the image information, determining a condition exists between an item weight and the expected item weight or between an item identifier and the expected item identifier and managing the POS transaction based on the condition. A system is also provided.

To enable inexpensive and accurate detection of fraudulent acts in which articles are taken out of a store without being settled after registration.SOLUTION: A fraud detection device includes a person detection unit, an article detection unit, and a fraud reporting unit. The person detection unit detects persons in a first area around a target device based on an image of the target device, which is the subject of the fraud detection. The article detection unit detects at least one of the articles in a second area around the target device and a container containing the articles based on the image. The fraud reporting unit reports fraud when the person detection unit does not detect any person and the article detection unit does not detect either the articles or the container while the settlement process is being executed for the articles.SELECTED DRAWING: Figure 9

A smart offline shopping method for improving the offline shopping experience includes obtaining a shopping cart assembly. The shopping cart assembly includes an in-store shopping cart and a wireless computing device. The wireless computing device wirelessly communicates with a point-of-sale device and an inventory management system of a store. The wireless computing device temporarily retains a purchase order and communicates the purchase order to each of the point of sale device and the inventory management system. A customer may input an identification code associated with an item into the wireless computing device and add the item to the purchase order. An employee may fill the purchase order by gathering the item from an inventory stock room. An employee may bring the filled purchase order to the point-of-sale device, where the customer pays for the purchase order before leaving the store.

A method, computer program product, and computer system of artificial intelligence (AI) intervention to detect and mitigate an abnormality associated with an object moving during performance of a process. A trained recurrent neural network (RNN) determines, from sensor data, a probability (Pr1) that the abnormality existed at a first time, where Pr1 exceeds a threshold T1 and in response, an alternative generative adversarial network (AGAN) determines a probability (Pa1) that the abnormality existed at the first time. A score S1, which is computed as a function of Pr1 and Pa1, exceeds T1 and in response the RNN and the AGAN determines, from the senso data, a probability (Pr2) and a probability (Pa2), respectively, that the abnormality existed at a second time. A score S2, which is computed as a function of at least Pr2, Pa2, and (S1-T1), exceeds a threshold (T2) and in response, the abnormality is mitigated.