Abstract: Examples provide a system and method for identifying unpaid items in real-time using computer vision object detection and recognition models. Images of a cart are selected based on proximity of the cart to one or more anchor points. The object detection and recognition models analyze the image data and identify a set of items in the selected cart. An e-receipt including a set of paid items is selected from a plurality of active electronic receipts based on matching the set of identified items to the set of paid items. Any unmatched items are added to a set of predicted unpaid items. When a receipt corresponding to the selected e-receipt is scanned, a notification identifying the set of predicted unpaid items is provided to a user device for display, enabling a user to identify any unpaid items in a basket of items quickly and accurately in real-time at store exit.

Abstract: Examples provide a system for filtering the contents of adjacent item storage compartments from item recognition results obtained using computer vision (CV) for more accurate mapping of item locations within a retail environment. A filter manager selects a vertical member and tracks it throughout a series of images generated by an image capture device. The selected vertical member defines at least a portion of a target compartment in each image. The vertical member can be a display case door or a vertical steel bar defining the side of an item storage compartment. A set of adjacent items located on each side of the target compartment is filtered from the item recognition results. The target compartment location is determined based on a location tag of the target compartment. The items remaining after filtering are mapped to the target compartment location while reducing CV item location false positives.

Abstract: Examples provide for pallet classification and pallet tag text recognition. The system includes a pallet text manager that classifies a type of pallet tag based on detected lines of text in the pallet tag using a classification model. Qualified lines of text are selected from the detected lines of text based on the classification type and corresponding format of the text. Each qualified line of text is associated with a pallet attribute, such as a pallet identifier (ID), an item ID, or a date of creation of the pallet tag. Attribute values from the set of qualified lines of text are paired with location data for the current location of the pallet. The attribute values and the paired location data are saved in a pallet attribute table. The pallet attributes are used to identify the location of pallets in a retail facility with improved accuracy and efficiency.

Abstract: Role-based access controls (RBAC) are extended to include multi-party authorizations for certain computing cluster operations or data items. Upon receiving a request to perform an operation over a computing cluster or its data, a check is carried out to determine if the operation (e.g., READ, WRITE, EXECUTE, DELETE, etc.) is subject to both a role-based access control as well as a multi-party authorization (MPA) consensus protocol. The determination to allow or deny the request includes (1) accessing a role-based access control record corresponding to the operation or data item, and (2) invoking the multi-party authorization consensus protocol. Prior to performance of the operation, a computer program collects “approve” or “deny” responses from individual ones of the multiple parties. When approval consensus is reached, the operation is performed. If approval is denied, or if an approval consensus is not reached within a time limit, then the operation is not performed.

Abstract: Embodiments of the disclosed technologies include, in response to receiving a query, matching the query to metadata from a plurality of heterogeneous data sources, and selecting one or more data sources from the plurality of heterogeneous data sources for answering the query, by sending the query and embeddings of the matched metadata to a generative artificial intelligence (GAI), and prompting the GAI to select matching data sources. Based on the data from the GAI, generating one or more custom queries targeted to the matching data sources selected by the GAI, the custom queries formatted to be sent to the selected data sources, executing the one or more custom queries across the selected data sources, and summarizing results from the executing and providing a response to the query.

Abstract: An adhesive composition includes, based on a total weight of the adhesive composition, 18 wt % to 30 wt % of a styrene-ethylene/butylene-styrene triblock copolymer, 6 wt % to 30 wt % of a tackifier, 30 wt % to 50 wt % of a white mineral oil, and 5 wt % to 35 wt % of an incompatible polymer composition. The styrene-ethylene/butylene-styrene triblock copolymer has a weight average molecular weight of 90,000 g/mol to 140,000 g/mol. The tackifier has a weight average molecular weight of 500 g/mol to 5000 g/mol, a glass transition temperature of 50° C. to 100° C., and a softening temperature of 100° C. to 140° C. The incompatible polymer composition includes at least two of a high density polyethylene, a crosslinked ethylene-propylene-diene rubber, and an olefin block copolymer.

Abstract: Apparatus and methods for aerosol removal from the vicinity of a patient's mouth. An apparatus can include a coupling having a proximal end and a distal end, the distal end of the coupling having a first port configured to couple to a suction tube, the coupling further comprising an interior cavity from the proximal end to the first port, a conduit having an interior cavity coupled to the proximal end of the coupling connecting the interior cavity of the coupling to the interior cavity of the conduit, the conduit extending to form a circumferential boundary around an area that is sized to fit inside a patient's mouth, and openings arranged on a surface of the conduit, the openings allowing substances in the vicinity of the openings to enter the conduit, and the openings, the conduit, and the coupling forming a passageway through which substances are evacuated from the patient's mouth.

Abstract: An example method includes, outputting, for display by a display device, a graphical user interface of an application executing at a computing device; responsive to receiving an indication of a start of a user input swipe gesture: outputting, for display by the display device and at least partially concealed by the scaled version of the graphical user interface of the application, a visual indication of a result of the user input swipe gesture: and responsive to receiving an indication of a commitment of the user input swipe gesture, outputting, for display by the display device, a graphical user interface that corresponds to the result of the user input swipe gesture.

Abstract: Role-based access controls (RBAC) are extended to include multi-party authorizations for certain computing cluster operations or data items. Upon receiving a request to perform an operation over a computing cluster or its data, a check is carried out to determine if the operation (e.g., READ, WRITE, EXECUTE, DELETE, etc.) is subject to both a role-based access control as well as a multi-party authorization (MPA) consensus protocol. The determination to allow or deny the request includes (1) accessing a role-based access control record corresponding to the operation or data item, and (2) invoking the multi-party authorization consensus protocol. Prior to performance of the operation, a computer program collects “approve” or “deny” responses from individual ones of the multiple parties. When approval consensus is reached, the operation is performed. If approval is denied, or if an approval consensus is not reached within a time limit, then the operation is not performed.

Abstract: Methods, systems, and computer program products for thwarting a malware attack. A data storage system stores data items, some of which data items correspond to snapshots. Upon identification of a possible ransomware attack on a data item, the system identifies a version of the snapshot that is not subject to the ransomware attack and seeks to protect the data state of the system from further damage (e.g., due to performance of unauthorized operations on the version of the snapshot that is not subject to the ransomware attack) by requiring consensus from a multi-party authorization (MPA) consensus regime before carrying out requested operations over the snapshot. The MPA consensus regime operates by determining that the operation is subject to a role-based access control (RBAC) as well as a multi-party authorization (MPA) consensus protocol, and then allowing or denying execution of the requested operations based on achieving consensus from among candidate approvers.

Abstract: Maxillary and mandibular appliances can be mounted to a user's upper and lower jaws. The appliances can include a palatal pad, buccal tubes, hamular notch tubes, and an anterior deprogrammer. The various portions of the appliances can provoke beneficial reactions by muscles in the tongue and jaw area, massage the same muscles, or provide other beneficial effects.

Abstract: Maxillary and mandibular appliances can be mounted to a user's upper and lower jaws. The appliances can include a palatal pad, buccal tubes, hamular notch tubes, and an anterior deprogrammer. The various portions of the appliances can provoke beneficial reactions by muscles in the tongue and jaw area, massage the same muscles, or provide other beneficial effects.

Abstract: Techniques described herein relate to a method for managing financial service requests. The method includes obtaining, by a prediction manager, a financial service request (FSR) from a client; obtaining historical information associated with the FSR; generating prediction model inputs using the FSR and the historical information; identifying FSR agent comments associated with the FSR; generating a request vector using the FSR agent comments; generating an FSR authenticity index using the request vector and the prediction model inputs; applying a first machine learning model to the FSR authenticity index and the prediction model inputs to generate a first prediction; providing the first prediction to a first approver; and obtaining first approver comments from the first approver.

Abstract: Disclosed is a process for creating an elastic film or sheet by calendaring a composition, including a polymer and a fabric. The composition may include a polymer, a cotton, or a combination of both. The calendared composition can form tough, flexible films and sheets. The film and sheet can have optical and physical properties that make them suitable as a replacement for some PVC films. Also disclosed is a composition for calendaring including a fabric and a polymer.