Abstract: A transaction string of data for a transaction is received by a financial institution (FI) server from a retailer server during a payment for the transaction by a customer at a location. The transaction data is provided by the FI server to a cloud service where the data is cleansed and normalized. A first machine learning model (model) is processed to label entities in the normalized transaction data. A second model is processed to assign hierarchical-based classifications for each of the identified entities in the normalized transaction data. The entities and hierarchical-based classifications are provided back to the FI server to associate with and/or link to the payment for the transaction.

Abstract: A cash tender module (CTM) of a self-service terminal (SST) records transaction media usage and error or warning codes for media peripheral devices of the SST in one or more log files. The log files are processed to discover patterns and relationships between the error/warning codes. Predicted error/warning codes are generated for the peripherals based on the patterns and relationships. Service records are automatically and proactively generated based on the predicted error/warning codes. In an embodiment, the service records include links to knowledge articles that provide step-by-step actions to resolve the error/warning codes. In an embodiment, real-time media counts by denomination are render into a dashboard interface for monitoring in real time the media in the SST.

Abstract: A light source device comprises a first light combination module and at least two light sources. The light source device is configured to be connected with a light guide module. The at least two light sources include a first light source and at least one second light source. The first light combination module includes a first light combination element. The first light combination element is disposed between the light guide module and the first light source and configured to transform a first beam into a first transmitted light, the first beam being related to the first light source. The first light combination element is further configured to generate a first reflected light from at least one second beam emitted by the at least one second light source, and combine the first reflected light and the first transmitted light into a combined light.

Abstract: In an method for detecting a closed loop in MRI: 3D coordinates of key characteristic points of an MRI examination subject are acquired; the 3D coordinates of the key characteristic points are adapted to a 3D body standard model, to obtain a 3D virtual body model of the examination subject; 3D surface regions of pre-designated body parts are extracted from the 3D virtual body model; based on pre-defined body parts where skin contact is likely to occur, a distance between 3D surface regions of two body parts in each body part pair are calculated; and in response to the distance between the 3D surface regions of the two body parts in any body part pair being less than a preset first threshold, a risk of a closed loop in the examination subject is determined.

Abstract: Features from historical transaction and customer data of a financial institution are calculated and/or extracted. Each customer is assigned to a given profitability cluster within each interval of time over a historical period of time based on the corresponding features. A self-supervised machine learning model is trained on the features to predict the clusters in a future interval of time. Features for a most-recent past interval of time are provided as input to the model and the model returns a predicted cluster for a given customer in a future interval of time. When the customer-assigned cluster in the most-recent past interval of time is a higher prioritized cluster than the predicted cluster for the future interval of time, a system of a financial institution (FI) is notified to take one or more mitigating in an attempt to prevent customer churn with the FI.

Abstract: One or more machine learning models are trained on financial institution (FI) specific customer and enterprise data to predict future transactions, churn likelihood, and a customer lifetime value (CLV) per customer of the FI over a given period of future time. In an embodiment, the CLV for the given period of future time is calculated and predicted using statistical and/or heuristic analysis based on predicted transactions provided by one or more models. The predicted transactions, churn likelihood, and CLV are provided through an Application Programming Interface (API) for integration into systems of the FI and/or accessible through a web-based interface and/or mobile application interface to users of the FI.

Abstract: The present disclosure provides a transporting apparatus. The transporting apparatus can include the following components: a first frame support configured to support an object; a second frame support configured to roll the transporting apparatus and to move relative to the first frame support; and a plurality of shock absorbing elements positioned between the first frame support and the second frame support.

Abstract: The present disclosure provides a transporting apparatus. The transporting apparatus can include the following components: a first frame support configured to support an object; a second frame support configured to roll the transporting apparatus and to move relative to the first frame support; and a plurality of shock absorbing elements positioned between the first frame support and the second frame support.

Abstract: The disclosure relates to techniques for scan preparation in a medical imaging system. The technique includes triggering a 3D camera acquiring a 2D color and depth image of a patient when a patient bed is at an origin position, inputting the image into a pre-trained first body information model to obtain position information of multiple body feature site points, and calculating position information of multiple candidate scanning regions in the patient bed coordinate system. The technique further includes providing the position information of the multiple candidate scanning regions to a medical imaging application apparatus, so that the medical imaging application apparatus determines position information of a current scanning region in the patient bed coordinate system and controls the patient bed to move the current scanning region to a scanning center of a medical imaging device according to the position of the patient bed relative to the scanning center.

Abstract: Resource metrics are obtained for resources from distributed resources associated with operations of an enterprise. Metric types from the distributed resources defined in the metrics are grouped and aggregated into aggregated metric types within a data model. Each aggregated metric type data value of the data model is weighed. The weighted aggregated data values are used to calculate an overall service health value of the enterprise. A current instance of the data model is processed to render one or more single views within an interface to a user of the enterprise. Each single view includes the overall service health value along with a custom-level of detail for each aggregated metric type and the corresponding aggregated metric data values.

Abstract: Event streams of terminals for a given interval of time are preprocessed to label event types and label predefined time-based or sequence-based patterns associated with terminal power supply unit (PSU) failures. The labeled event streams are provided as input to a trained machine-learning model (MLM), which outputs a score for each terminal representing a likelihood that the corresponding terminal is or is not going to experience a PSU failure. In an embodiment, each score is compared against one or more threshold values and each terminal is classified as low risk, medium risk, or high risk of a PSU failure. In an embodiment, the scores and/or the classifications for the terminals are reported to an enterprise associated with the terminals at predefined intervals of time.

Abstract: Resource metrics are obtained for resources from distributed resources associated with operations of an enterprise. Metric types from the distributed resources defined in the metrics are grouped and aggregated into aggregated metric types within a data model. Each aggregated metric type data value of the data model is weighed. The weighted aggregated data values are used to calculate an overall service health value of the enterprise. A current instance of the data model is processed to render one or more single views within an interface to a user of the enterprise. Each single view includes the overall service health value along with a custom-level of detail for each aggregated metric type and the corresponding aggregated metric data values.

Abstract: Multiple types of machine learning models (MLMs) are trained on training data to provide predictions of terminal failures. The MLMs are tested on testing data and prediction scores are calculated for the MLMs based on the testing. An MLM having a highest prediction score is selected and deployed to a production environment for a current period of time to provide predictions of terminal failures. Current terminal data is provided as input to the deployed MLM, and the MLM's predictions are provided to an interface, system, or service of the production environment. The current terminal data is also provided to the non-selected MLMs, which generate candidate predictions during the current period of time. At the end of the current period of time, prediction scores of the selected and non-selected MLMs are calculated. A next MLM is selected for a next period of time for deployment based on the prediction scores.

Abstract: A dynamic incident management system and method receives and stores business customer sales information. This information includes information about sales by day and time of day for a period of time at each business location. A machine learning model is generated for forecasting revenue for each business location based on the received information. A plurality of work orders are received for service calls to certain business customer sales locations. A priority is assigned to each of the received work orders. A rank is assigned to each of the received work orders having a common priority, based on, at least in part, a revenue forecast provided the machine learning module of sales at a projected day and time for the service call. Updated work orders having the priority and rank information are supplied to an incident management supplier for performing the associated service calls based on the priority and rank information.

Abstract: The present invention discloses a method for designing an orthognathic surgical occlusal plate based on artificial intelligence, including scanning a gypsum model of the maxillary and mandibular dentition to obtain the corresponding three-dimensional model of the maxillary and mandibular dentition; then obtaining the fitting data and establishing a coordinate system; generating thickness control elements and two-dimensional contour lines; controlling thickness of the three-dimensional model and generating occlusal imprint: and modifying the thickness and occlusal imprint of the three-dimensional model to obtain an artificial intelligence occlusal plate. The invention can greatly save the time required for designing the occlusal plate, improve the work efficiency, and the accuracy of the artificial orthognathic surgery occlusal plate is not significantly different from that of the manual occlusal plate in the application of orthognathic surgery.

Abstract: Transaction usage metrics for terminals and maintenance records for the terminals are evaluated in view of suggested maintenance actions for peripherals and/or components of the peripherals associated with the terminals. Any open service records for terminals predicted to require a maintenance action based on the evaluation have the maintenance action added to their open service records. A new open service record is generated for any terminal predicted to require the maintenance action based on the evaluation when an existing open service record for the corresponding terminal was not detected. In an embodiment, service calls associated with the open service records are monitored for compliance and non-compliant actions are flagged for reporting.

Abstract: The present invention discloses a method for designing an orthognathic surgical occlusal plate based on artificial intelligence, including scaning a gypsum model of the maxillary and mandibular dentition to obtain the corresponding three-dimensional model of the maxillary and mandibular dentition; then obtaining the fitting data and establishing a coordinate system; generating thickness control elements and two-dimensional contour lines; controlling thickness of the three-dimensional model and generating occlusal imprint: and modifying the thickness and occlusal imprint of the three-dimensional model to obtain an artificial intelligence occlusal plate. The invention can greatly save the time required for designing the occlusal plate, improve the work efficiency, and the accuracy of the artificial orthognathic surgery occlusal plate is not significantly different from that of the manual occlusal plate in the application of orthognathic surgery.