Abstract: Methods and systems are described for novel uses and/or improvements to federated learning. As one example, methods and systems are described for improving the applicability of federated learning across various applications and increasing the efficiency of training a global model through federated learning. As another example, methods and systems are described for ensuring comprehensive training data is available to models assigned by the federated learning server. Additionally, methods and systems are described for improving the rate of training a global model through federated learning.

Abstract: Methods and systems are described here for porting accounts to multiple computing platforms. Blockchain technology may be used and in particular cryptographic tokens (e.g., non-fungible tokens) may be used. A cryptographic token may represent a user account and may enable usage of the cryptographic token to provide portability of the user account. An access control system may be used to perform operations described herein. The access control system may receive a request for using, at a computing platform, an account of the user. The request may include an identifier of a cryptographic token. The access control system may determine, based on the cryptographic token, that access to the user account may be permitted and the request may be fulfilled.

Abstract: Embodiments disclosed are directed to a computing system that provides for on-demand scanning for changes in cloud-based object storage systems. The changes can include modifications, additions, or deletions of objects stored in a cloud-based object storage system. The computing system scans, at a first runtime, objects stored in a cloud-based object storage system. The computing system retrieves lookup information associated with a second runtime of a previous scan. Based on the lookup information, the computing system identifies a subset of the objects that were changed or added after the second runtime and before the first runtime. Subsequently, the computing system generates an electronic notification including a consolidated list of the subset of the objects.

Abstract: In certain embodiments, an application may be triggered to request data related to a user account associated with a financial entity. In some embodiments, during a time period in which the application is not executing on a user device, identification data of an identification signal (received from a wireless transmitter associated with the financial entity) may be determined to correspond to the wireless transmitter; Based on the determination, the application associated with the financial entity may be determined to (i) execute on the user device and (ii) transmit, to a server system associated with the financial entity, a request for data relating to the user account. The requested data may be presented via a display of the user device.

Abstract: The disclosed embodiments include systems and methods for extracting information from a transaction description. In one embodiment, a system is disclosed that may include one or more processors and one or more memory devices storing instructions that, when executed by the one or more processors, performs operations consistent with the disclosed embodiments. In one embodiment, the operations may include receiving a transaction description. The operations may also include identifying known location information corresponding to the transaction description and determining whether information from the transaction description corresponds to the identified known location information. The operations may further include removing location information from the transaction description based on the determination. In another aspect, the operations may also include extracting additional location information from the transaction description that is not associated with the known location information.

Abstract: A self-service lender portal provides lenders with a suite of tools for interacting with a multi-lender architecture configured to provide loan applicants with automated pre-qualification and eligibility evaluation for multiple candidate lenders. The lender portal provides lenders with an interface for uploading rule sets defining lending and eligibility criteria, downloading operational data generated from processing loan applicant information, generating and managing security keys for encryption and decryption of sensitive data, and managing access policies for providing single sign-on by interfacing with the lender's own identity management systems.

Abstract: Methods and systems are described herein for using cryptographic tokens that represent real-world items to enable those items to be used in different virtual worlds (e.g., game worlds). In particular, an object retrieval system may be used to retrieve a cryptographic token that encodes parameter data for an object to be used (e.g., displayed) within a plurality of computing platforms. The object retrieval system may determine (e.g., using a cryptographic signature) that the user is allowed to use the object and may then generate a set of parameters for representing the object with the particular computing platform requesting the object. The object retrieval system may then transmit the parameters to the requesting platform. The object retrieval system may perform the same operations for requests from other platforms, such that the object retrieval system may uniquely encode the parameters for the particular platforms.

Abstract: In certain embodiments, token data may be generated, updated, and presented on a token display of a token. In some embodiments, a communication session may be initiated between a token and a terminal. Authentication data stored on the token may be replaced with updated authentication data. Updated token data may be generated based on updated authentication data. The token data on an electrophoretic display may be replaced with the updated token data.

Abstract: Methods and systems described herein for validating machine learning models in federated machine learning model environments. More specifically, the methods and systems relate to unloading training and validation techniques to client devices using newly collected data to improve accuracy of federated machine learning models.

Abstract: Methods and systems are described for novel uses and/or improvements to federated learning. As one example, methods and systems are described for improving the applicability of federated learning across various applications and increasing the efficiency of training a global model through federated learning. As another example, methods and systems are described for ensuring comprehensive training data is available to models assigned by the federated learning server. Additionally, methods and systems are described for improving the rate of training a global model through federated learning.

Abstract: Computer-implemented techniques and systems for generating vehicle profiles may include scanning a plurality of vehicles, each vehicle located at a respective vehicle location, identifying respective vehicle locations for each of the plurality of vehicles, based on scanning the plurality of vehicles, associating a vehicle identification tag for each vehicle with its respective vehicle location, interpreting a signal to determine a user location, determining that the user location is within a threshold distance from a first vehicle location of a first vehicle from the plurality of vehicles, providing a first vehicle identification tag corresponding to the first vehicle based on determining that the user location is within the threshold distance, generating a first vehicle profile based on the first vehicle identification tag, and providing the first vehicle profile to a user device.

Abstract: Aspects described herein may allow for receiving, by a detection server, a plurality of configuration parameters, wherein each configuration parameter includes a type of a risk and an associated level of the risk, with a corresponding automated remediation action for each configuration parameter. A remediation management framework authenticates the detection server for access to the remediation management framework and initiates a scanning of a system of interest, based on the plurality of configuration parameters, by the detection server, to identify one or more risk findings. The remediation management framework receives the identified one more risk findings; and matches each of the one or more risk findings with the plurality of configuration parameters, which then triggers by the remediation management framework, the corresponding automated remediation action associated with each of the one or more risk findings.

Abstract: In some embodiments, a plurality of devices may be respectively mapped to a plurality of interaction types. Statistical models may be generated, where the statistical models are indicative of relationships between aggregated interaction data related to the interaction types and aggregated resource utilization data related to the devices. With respect to each interaction type of the interaction types, the statistical models may be scored based on strength of one or more of the relationships. A subset of the statistical models may be selected based on the scoring for the interaction types. As an example, a first statistical model is included in the subset based on the scoring related to a first interaction type and a second statistical model is included in the subset based on the scoring related to a second interaction type different from the first interaction type. One or more of the devices may be remapped to one or more interaction types based on the selected subset of the statistical models.

Abstract: Example embodiments of systems and methods for data transmission between transmitting and receiving devices are provided. In an embodiment, each of the transmitting and receiving devices can contain a master key. The transmitting device can generate a diversified key using the master key, protect a counter value and encrypt data prior to transmitting to the receiving device. The receiving device can generate the diversified key based on the master key and can decrypt the data and validate the protected counter value using the diversified key.

Abstract: Systems and methods are disclosed for managing workload among server clusters is disclosed. According to certain embodiments, the system may include a memory storing instructions and a processor. The processor may be configured to execute the instructions to determine historical behaviors of the server clusters in processing a workload. The processor may also be configured to execute the instructions to construct cost models for the server clusters based at least in part on the historical behaviors. The cost model is configured to predict a processor utilization demand of a workload. The processor may further be configured to execute the instructions to receive a workload and determine efficiencies of processing the workload by the server clusters based at least in part on at least one of the cost models or an execution plan of the workload.

Abstract: A smart device is provided with an application program for displaying a video feed received from the smart device's camera. The application can determine the coordinates for an intersection point, which is a point on the ground where the smart device is pointing at. The application can display a target on the visual representation of the intersection point. Based on whether the smart device is at an appropriate distance from the intersection point, the user interface can superimpose an indicator on the video feed received from the camera. This can inform the user whether the smart device is at an optimal scan distance from the intersection point (or an object) so that the object can be identified by a machine learning model.

Abstract: An enhanced analytical engine system may perform the steps of providing optimized individual transaction recommendations. The system may receive a request comprising customer financial information, customer identification information, and vehicle identification information. The system may collect information associated with one or more vehicles within an inventory listing associated with one or more dealership systems. The system may then provide data representing information associated with the one or more vehicles within an inventory listing associated with the one or more dealership systems. The system may receive data indicating selection of a vehicle of interest. The system may determine a proposed offer package for the vehicle of interest comprising an associated overall price and at least one from among a warranty option, maintenance option, and service contract option based on the customer preferences information and historical transaction data.

Abstract: Embodiments may generally be directed components and techniques to detect a request to provide banking account information over a one or more voice connections, identify the requested banking account information, and generate speech data representing the banking account information requested. In embodiments further include communicating the speech data to another device.

Abstract: A system including: one or more processors; a memory storing computer program code that controls the one or more processors to: receive usage metrics associated with a first application; determine whether the first application comprises a cyclic usage pattern, a batch usage pattern, or a non-cyclic usage pattern; select a scaling technique based on the determination; and automatically scale the first application with the selected scaling technique. The system may determine that at least one virtual machine should be added to a first plurality of virtual machines in response to a resource usage of an application exceeding a maximum usage allocation and determine that at least one virtual machine should be removed to the first plurality of virtual machines in response to a minimum usage allocation exceeding the resource usage of the first plurality of virtual machine instances.