DETECTION OF UNDERUTILIZED DATA CENTER RESOURCES

    公开(公告)号:US20250028621A1

    公开(公告)日:2025-01-23

    申请号:US18224112

    申请日:2023-07-20

    Abstract: An apparatus may include a computer processor operating in a data center and running an AI/ML model. The apparatus may include a trace log agent and a telemetry agent. The computer processor may be configured to train and run the AI/ML model to determine if a resource in the data center is being utilized or is idle by using data provided by the trace log agent and a telemetry agent. The apparatus may include a status check engine, a discovery engine, and an analytics engine. The computer processor may be configured to run each of these engines to confirm a prediction by the AI/ML model that the resource is idle. The computer processor may be configured to notify an administrator of the data center if the AI/ML model predicts the resource is idle and the engines provide increased confidence to the prediction.

    REFLEXIVELY-ROUTED TRANSACTIONS
    4.
    发明公开

    公开(公告)号:US20240144207A1

    公开(公告)日:2024-05-02

    申请号:US17975699

    申请日:2022-10-28

    CPC classification number: G06Q20/10 G06Q40/02

    Abstract: A system for providing a reflexively routed funds transfer is provided. The system includes a processor, and a receiver for receiving a request for a person-to-person value transfer. The request includes a request identifier. The system also includes a transmitter for transmitting the request to a shared database and a shared database. The database operates in combination with the processor to determine whether multiple targets are associated with the request identifier. When multiple targets are associated with the request identifier, the shared database operates in combination with the processor and the transmitter to notify the transfer initiator that multiple targets are associated with the request identifier, then prompts the transfer initiator to select one of the multiple targets to function as a recipient target for the value transfer. The receiver then receives a selection of one of the multiple targets to function as the recipient target. Then a router routes value transfer to the recipient target.

    SYSTEM FOR DYNAMIC, SECURE, TOKEN-BASED SNAPSHOT GENERATION

    公开(公告)号:US20250062908A1

    公开(公告)日:2025-02-20

    申请号:US18234254

    申请日:2023-08-15

    Abstract: Systems, computer program products, and methods are described herein for dynamic, secure, token-based snapshot generation. The present disclosure is configured to receive, via an alternative access point, a user request to receive a snapshot of one or more resource repositories associated with a user; generate, using a token generator, a token based on at least the user request; authenticate, using an authentication subsystem, the user using the token to confirm legitimacy of the user request; generate, using a snapshot generator, the snapshot of the one or more resource repositories based on at least confirming the legitimacy of the user request, wherein the snapshot is generated based on pre-defined user preferences; embed, using a digital signature subsystem, the snapshot with a digital signature serving as an attestation; and display the snapshot on the user input device.

    AUTOMATION OF FRAUD DETECTION WITH MACHINE LEARNING UTILIZING PUBLICLY AVAILABLE FORMS

    公开(公告)号:US20250061469A1

    公开(公告)日:2025-02-20

    申请号:US18234911

    申请日:2023-08-17

    Abstract: Systems and methods for alerting an organization about activity that may be fraudulent. Systems may include a computer processor, a storage module, a cleaning module, a preprocessing module, a features extraction module, and a machine learning module. The computer processor may be configured to run a fraud detection engine by collecting publicly available electronic forms every 36 hours, using the modules to store the forms, clean the data, preprocess the data, and run a machine learning model to extract features and to determine if a threshold indicating a risk of fraud has been exceeded. The machine learning models include a liquid, solvency, and profitability ratio classification model, a disclosure classification model, a sentiment analysis model, an anomaly detection classification model, an ownership analysis classification model, and an ESG disclosure classification model. When exceeding a threshold, the computer processor may notify an administrator of the exceeded threshold's identity.

Patent Agency Ranking