-
公开(公告)号：US20250071027A1
公开(公告)日：2025-02-27
申请号：US18237745
申请日：2023-08-24
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Pushkar Taneja , Subhasree Baskaran , Durga Prasad Kutthumolu
IPC: H04L41/16 , H04L9/40 , H04L41/069
Abstract: Arrangements for an intelligent monitoring platform using a cybersecurity mesh and graph neural networks (GNNs) are provided. A platform may train multiple machine learning models (e.g., a GNN model, a cybersecurity engine, and a monitoring model). The platform may generate, using a GNN model, a suspicion score for a received event processing request. Based on determining the suspicion score satisfies a threshold, the platform may generate a threat score using a cybersecurity engine. The platform may generate an anomaly record for the event processing request based on the threat score and using a monitoring model. The platform may determine a preferred node of a cybersecurity mesh for routing the event processing request based on the anomaly record. The platform may determine a threat prevention response based on the preferred node. The platform may initiate one or more security actions based on the threat prevention response.
-
公开(公告)号：US20240378067A1
公开(公告)日：2024-11-14
申请号：US18144352
申请日：2023-05-08
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Sudhakar Balu , Siva Paini
Abstract: Aspects of the disclosure relate to monitoring, evaluating, and repairing bots in a hashchain-based distributed bot hub that process a workflow. In some embodiments, a computing platform may receive workflow information associated with performing a first workflow that includes executing one or more tasks using a plurality of virtual bots, identify a plurality of bots to process the first workflow, and compute, using a hash function, a hashchain for each identified bot of the plurality of bots. Thereafter, the computing platform may monitor the plurality of bots performing the one or more tasks of the first workflow by verifying tasks of identified bots based on analyzing hashchains of bots performing tasks of the first workflow, and, based on monitoring the plurality of bots, identify a potential anomalous activity by at least one bot.
-
3.发明公开公开(公告)号：US20240231794A9
公开(公告)日：2024-07-11
申请号：US17972711
申请日：2022-10-25
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Sathya Thamilarasan , Shyamala Manoharan , Siva Kumar Paini , Sri Doraiswamy , Srinivasa Dhanwada , Nagalaxmi Sama
Abstract: Aspects of the disclosure relate to upgrading an application within a simulated version of an enterprise system to detect and correct potential errors as a result of the upgrade. A computing platform may create a simulated version of the enterprise system by receiving metadata associated with the enterprise system, and converting the metadata into system parameters. Virtual parameters may be created by the computing system based on upgrading an application within the simulated version of the enterprise system. The computing system may determine errors caused by the application upgrade within the simulated version of the enterprise system based on differences between the system parameters and the virtual parameters. The computing platform may determine actions to correct the errors and input the results and feedback into an AI engine to further refine the accuracy and reliability of the computing platform over time.
-
公开(公告)号：US20240143354A1
公开(公告)日：2024-05-02
申请号：US17979333
申请日：2022-11-02
Applicant: Bank of America Corporation
Inventor： Siva Paini , Sakshi Bakshi
IPC: G06F9/451 , G06F40/186 , G06F40/40
CPC classification number: G06F9/453 , G06F40/186 , G06F40/40
Abstract: Methods and systems described herein for addressing issues associated with varying graph analytics tools that require different tool-specific coding languages. An artificial intelligence (AI) sub-system of various modules extracts metadata from a dataset and identifies nodes and relationships in the dataset using the metadata. The dataset is matched with a corresponding graph-analytics template in a data store, and a dynamic template modifier modifies the corresponding graph-analytics template. In some examples, the AI system generates smart guided videos with logical breakpoints that are embedded along with templates for quick learning and to build faster graphical analytics. The AI system includes a dynamic template modifier and a cognitive smart AI engine that includes a graph.
-
5.发明公开公开(公告)号：US20230334482A1
公开(公告)日：2023-10-19
申请号：US17721928
申请日：2022-04-15
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Siva Kumar Paini , Virendra Kumar Sharma , Ranjan Verma , Prashant Anna Bidkar
CPC classification number: G06Q20/389 , G06N10/60 , G06N10/20 , G06N10/80 , H04L9/50 , G06Q2220/00 , H04L2209/56
Abstract: A system for determining transactions eligible for currency transaction report (CTR) exemption using a quantum computing algorithm is described. The system may further leverage a distributed computing architecture for manual review and filing of CTRs and/or approving a CTR exemption as determined by the quantum computing algorithm.
-
Patent Agency Ranking
公开(公告)号：US20230010296A1
公开(公告)日：2023-01-12
申请号：US17371086
申请日：2021-07-08
Applicant: Bank of America Corporation
Inventor： Siva Kumar Paini , Sakshi Bakshi , Srinivasa Jitendra Dhanwada , Sudhakar Balu
IPC: G06F16/955 , G06K9/62 , G06F16/908 , G06F16/9535 , G06F3/0484
Abstract: A system for classifying tasks based on workflow patterns detected on workflows through a real time video feed that shows steps being performed to accomplish a plurality of tasks. Each task is associated with a different set of steps. The system accesses a first set of steps known to be performed to accomplish a first task on the webpages. The first set of steps is represented by a first set of metadata. The system extracts a second set of metadata from the video feed. The second set of metadata represents a second set of steps to perform a second task. The system determines whether the second set of metadata corresponds to the first set of metadata. If it is determined that the second set of metadata corresponds to the first set of metadata, the system classifies the second task in a class to which the first task belongs.
-
公开(公告)号：US20220358495A1
公开(公告)日：2022-11-10
申请号：US17315416
申请日：2021-05-10
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Siva Kumar Paini , Amod Jha , Amit Kumar Sati
Abstract: Systems, methods, and apparatus are provided for a dynamic contract payment term (“payterm”) generator. A machine learning algorithm may generate a replacement payment term for a contract based on market-based parameters and blockchain metadata for the contract. The blockchain metadata may encode hierarchical interdependencies between contracts using blockchain encryption. The blockchain metadata may be applied to auto-generate machine learning inputs for related contracts having interdependent payment terms. The machine learning inputs may include contract parameters that have been extracted and encrypted as blockchain metadata, as well as market-based parameters extracted from enterprise sources.
-
公开(公告)号：US20240427692A1
公开(公告)日：2024-12-26
申请号：US18819203
申请日：2024-08-29
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Srinivasa Dhanwada , Sathya Thamilarasan , Siva Paini , Shyamala Manoharan , Nagalaxmi Sama , Sri Lakshmi Priya Doraiswamy
Abstract: Aspects of the disclosure relate to upgrading an application within a simulated version of an enterprise system to detect and correct potential errors as a result of the upgrade. A computing platform may create a simulated version of the enterprise system by receiving metadata associated with the enterprise system, and converting the metadata into system parameters. Virtual parameters may be created by the computing system based on upgrading an application within the simulated version of the enterprise system. The computing system may create system nodes and virtual nodes. The system nodes and virtual nodes may be dynamically linked in order to determine errors caused by the application upgrade within the simulated version of the enterprise system. The computing platform may determine actions to correct the errors and input the results and feedback into an AI engine to further refine the accuracy and reliability of the computing platform over time.
-
公开(公告)号：US20240378614A1
公开(公告)日：2024-11-14
申请号：US18144353
申请日：2023-05-08
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi , Sharat Chandran , Arif Ahmad Khan , Durga Prasad Kutthumolu , Kapil Juneja , Arvind Bansal
Abstract: Aspects of the disclosure relate to a dual-system reconciliation process of trades. A first real-time trade processing and centralized reconciliation engine may continuously process trades in real-time and may perform centralized reconciliation of the trades. An anomaly detection and reconciliation mesh analysis engine may tokenize trade metadata received from the first real-time trade processing and centralized reconciliation engine, generate tokenized trade digital DNA, generate hashed tokenized trade digital DNA, evaluate and validate the hashed data, and perform decentralized reconciliation mesh analysis of the hashed data using a reconciliation mesh. The anomaly detection and reconciliation mesh analysis engine may send one or more monitory policies from the reconciliation mesh to a user device and may receive a first monitory policy selection from the user device. The anomaly detection and reconciliation mesh analysis engine may update the decentralized reconciliation mesh based on the first monitory policy selection.
-
公开(公告)号：US20240320530A1
公开(公告)日：2024-09-26
申请号：US18123411
申请日：2023-03-20
Applicant: Bank of America Corporation
Inventor： Sakshi Bakshi
IPC: G06N10/20
CPC classification number: G06N10/20
Abstract: Apparatus for quantum data lineage tracing using a quantum multipart entangled twin is provided. The apparatus may include an enterprise system, a quantum data lineage tracing system and a quantum twinning simulation engine. The enterprise system may include a plurality of subsystems. A first subsystem may receive data components. The tracing system may extract metadata, including data component properties, from data components. The tracing system may assign each property to a qubit. Each qubit may identify an entry location of the associated data component. The simulation engine may receive the qubits, process the qubits and entangle each qubit with one or more other qubits. The simulation engine may replicate a wave function for each qubit as the qubit is replicated to trace changes made to each data component as the data component is replicated. The simulation engine may use the replicated wave functions to identify changes made to data components.
-
-
-
-
-
-
-
-
-
Search Results
52
records
(took 0.025 seconds)
