Bank of America Corporation

Hari Vuppala

Elvis Nyamwange

Rahul Yaksh

Amer Ali

Sailesh Vezzu

Pratap Dande

Brian Neal Jacobson

Rahul Shashidhar Phadnis

Erik Dahl

Erik D Dahl

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.

Detection of underutilized data center resources

Systems, computer program products, and methods are described herein an automated system for restarting large scale cluster supercomputers. The present disclosure is configured to receive a request to reboot a supercomputer cluster, wherein the request comprises a sequence of reboot instructions; determine, using a data integrity engine, whether a current state of the supercomputer cluster meets reboot requirements, wherein the reboot requirements are associated with a core logic of the data integrity engine; and execute the sequence of reboot instructions in an instance where the current state of the supercomputer cluster meets the reboot requirements.

Automated system for restarting large scale cluster supercomputers

An apparatus may include conduction of a secure transfer at a point of identification using image recognition and blockchain authentication. The apparatus may include a computer processor, a camera, an image capturing machine, a reference database, an XGBoost image recognition machine learning model, and a blockchain. The computer processor may be an edge computing device. The computer processor may be configured to identify a user at a point of identification by capturing an image, running the Features detection engine to identify sets of features, running the XGBoost image recognition machine learning model to identify labels in the sets of features, and matching the sets of features and labels to a record in the reference database. The computer processor may further be configured to seek user approval on the user's portable device before providing the transfer. Once the user has approved the transfer, the transfer may be recorded in the blockchain.

Automated image detection utilizing a convolutional XGBoost image recognition machine learning model on edge computing with blockchain mobile authentication

Aspects of the disclosure relate to detecting attempts to violate the security of an ATM. A computing system may determine whether an ATM is being used to perform a transaction. Based on the ATM not being used to perform a transaction, images of portions of the ATM may be generated. Estimated dimensions of the ATM may be determined. Digital twin data may be retrieved. The digital twin data may comprise a digital twin representation of the ATM and measured dimensions of the ATM. There may be a determination of whether the estimated dimensions of the ATM match the measured dimensions of the ATM. Based on the estimated dimensions of the ATM not matching the measured dimensions of the ATM, the ATM may be deactivated. Furthermore, a message indicating that the ATM was deactivated may be sent to a validation computing system.

Automated teller machine digital twin with an anti NFC/RFID skimming threat device through mist computation

Systems, computer program products, and methods are described herein for a machine learning based system for optimized CPU utilization in data transformation. The present disclosure is configured to receive a new data segment; retrieve characteristics of the new data segment; determine, using a trained machine learning model, an encryption algorithm, and a compression algorithm for implementation on the new data segment based on at least the characteristics of the new data segment; determine, using the trained machine learning model, an order of implementation associated with the implementation of the encryption algorithm and the compression algorithm; and implement the encryption algorithm and the compression algorithm on the new data segment in the determined order of implementation.

Machine learning based system for optimized central processing unit (CPU) utilization in data transformation

Systems, computer program products, and methods are described herein for determining data migration using an automated query analyzer tool. The present disclosure is configured to identify at least one input data set associated with at least one application; analyze, by an automated query analyzer tool, the at least one input data set; classify data of the at least one data set as at least one of a standard classification or a non-standard classification; determine at least one metric for the data of the at least one data set; generate a query complexity score for the at least one application; generate an application migration complexity report and an application migration complexity report interface component; and transmit the application migration complexity report interface component to a user device and configure a graphical user interface of the user device with the application migration complexity report interface component.

Systems and methods for determining data migration using an automated query analyzer tool

Systems, computer program products, and methods are described herein for validation of electronic data transfers in a distributed network via self-directed image data. The present invention is configured to receive a request for a transfer of electronic data from a first repository associated with a first user to a second repository associated with a second user, transfer the electronic data, generate and apply a first identifier to the electronic data, collect a geolocation of a second endpoint device, transmit the geolocation and a request for a verification of the geolocation to the first endpoint device, receive the verification of the geolocation, generate and apply a second identifier to the electronic data, transmit control signals to the second endpoint device to prompt collection of self-directed image data, and collect, using the second endpoint device, the self-directed image data.

System and method for the validation of electronic data transfers in a distributed network via self-directed image data

A computer performs a method for pro-actively administering a physical network of automated teller machines (ATM). The network may include ATMs. The network may be coupled, using an asynchronous transfer mode Wide Area Network (WAN) and the router, to a second plurality of ATMs via a digital subscriber line (DSL) module, a Closed Circuit Television (CCTV) system to provide CCTV television footage, and/or a 5-G cellular interface. The method receives input data using a data processing block coupled to the network of ATMs. The data may be derived from the plurality of ATMS, the WAN, the second plurality of ATMs, the CCTV and/or the 5-G cellular network interface. The method cleans and processes data and leverages a virtual digital twin to predictively provide status information of the ATMs based on the data. The method may formulate and maintain predictive data using a digital twin prediction model.

Automated teller machine (ATM) networks with a real time digital twin ecosystem for multi-region or wired wide area networks (WAN) in order to predict failures/faults

Systems, computer program products, and methods are described herein for selective data routing in a distributed network via data throughput analysis in a distributed ledger network. The present invention is configured to receive a request for a data transmission from an endpoint device of a network, determine, via a routing module, a throughput of data associated with the data transmission, determine a classification of the data transmission, and assign the data transmission to an assigned routing channel. The assigned routing channel may include either a first routing channel or a second routing channel based on the classification, wherein the first routing channel is a light load network comprising emitter devices operatively coupled to endpoint devices proximate the emitter devices, and wherein the second routing channel is a heavy load network comprising a first multicore optical fiber.

Growing community of inventors

Charlotte, NC, United States of America

Hari Vuppala