公开(公告)号：US20240187311A1

公开(公告)日：2024-06-06

申请号：US18061834

申请日：2022-12-05

Applicant: Bank of America Corporation

Inventor： Conor Mitchell Liam Nodzak ,  Fernando Maisonett ,  Shreyas Srinivas ,  Brian Busch ,  Kyle Scott Sorensen

IPC: H04L41/16 ,  H04L41/0681 ,  H04L41/14

CPC classification number: H04L41/16 ,  H04L41/0681 ,  H04L41/145

Abstract: A multitenant server application dependency mapping system maps data flows through multitenant infrastructure components through the use of a machine learning model framework that continually learns data flow patterns across the enterprise network and predicts the state of any given server. The multitenant server application dependency mapping system treats the network architecture as a whole and collects data accordingly, and uses that data to compute state probabilities conditioned upon both a point in time (and the observed prior states retrieved from the historical telemetry data. This provides a way to predict the likelihood of observing a tenant state being occupied, while also accounting for variations among the activity levels of various application. To forecast future states of all infrastructure components, the transition probabilities from tenant state to tenant state are then computed through time and used as inputs to the model to provide an accurate reconstruction of the data flows through all multitenant infrastructure components.

公开(公告)号：US20240348599A1

公开(公告)日：2024-10-17

申请号：US18756234

申请日：2024-06-27

Applicant: Bank of America Corporation

Inventor： Conor Mitchell Liam Nodzak ,  Fernando Maisonett ,  Shreyas Srinivas ,  Brian Busch

IPC: H04L9/40

CPC classification number: H04L63/083

Abstract: A multitenant server application dependency mapping system maps data flows through multitenant infrastructure components through the use of a machine learning model framework that continually learns data flow patterns across the enterprise network and predicts the state of any given server. The multitenant server application dependency mapping system treats the network architecture as a whole and collects data accordingly, and uses that data to compute state probabilities conditioned upon both a point in time (and the observed prior states retrieved from the historical telemetry data. This provides a way to predict the likelihood of observing a tenant state being occupied, while also accounting for variations among the activity levels of various application. To forecast future states of all infrastructure components, the transition probabilities from tenant state to tenant state are then computed through time and used as inputs to the model to provide an accurate reconstruction of the data flows through all multitenant infrastructure components.

公开(公告)号：US12052146B2

公开(公告)日：2024-07-30

申请号：US18061834

申请日：2022-12-05

Applicant: Bank of America Corporation

Inventor： Conor Mitchell Liam Nodzak ,  Fernando Maisonett ,  Shreyas Srinivas ,  Brian Busch ,  Kyle Scott Sorensen

IPC: H04L12/00 ,  H04L41/0681 ,  H04L41/14 ,  H04L41/16

CPC classification number: H04L41/16 ,  H04L41/0681 ,  H04L41/145

Abstract: A multitenant server application dependency mapping system maps data flows through multitenant infrastructure components through the use of a machine learning model framework that continually learns data flow patterns across the enterprise network and predicts the state of any given server. The multitenant server application dependency mapping system treats the network architecture as a whole and collects data accordingly, and uses that data to compute state probabilities conditioned upon both a point in time (and the observed prior states retrieved from the historical telemetry data. This provides a way to predict the likelihood of observing a tenant state being occupied, while also accounting for variations among the activity levels of various application. To forecast future states of all infrastructure components, the transition probabilities from tenant state to tenant state are then computed through time and used as inputs to the model to provide an accurate reconstruction of the data flows through all multitenant infrastructure components.

公开(公告)号：US11822435B2

公开(公告)日：2023-11-21

申请号：US17367912

申请日：2021-07-06

Applicant: BANK OF AMERICA CORPORATION

Inventor： Christopher Emmanuel Huntley ,  Musa Ajakaiye ,  Prasad V. Annadata ,  Dnyanesh P. Ballikar ,  Sina Bauer ,  Jason Kenneth Bellew ,  Timothy John Bendel ,  David Alan Beumer ,  Michelle Andrea Boston ,  Lisa Julia Brown ,  Robin J. Buck ,  Brian C. Busch ,  Salvatore Michael Certo ,  Ramesh Naidu Chatta ,  Lisa Michelle Cook ,  Joseph Corbett ,  Joseph Seth Cushing ,  Steven Paul Davidson ,  Shailesh Deshpande ,  Sevara Ergasheva ,  Maria Ervin ,  James Wilson Foy, Jr. ,  Noel Mary Fuller ,  Benjamin Judson Gaines, III ,  Candace Gordon ,  Jesse Antonio Hernandez ,  Christine Hoagland ,  Robert Charles Hoard ,  Michael Spiro Karafotis ,  Wesley Keville ,  Sandip Kumar ,  Terri Dorinda Lail ,  Mukesh Maraj ,  Wyatt Edward Maxey ,  Dari Ann Mckenzie ,  Ashley Meadows ,  Heather Newell ,  Conor Mitchell Liam Nodzak ,  Kenyell Javon Ollie ,  Jayshree G. Patel ,  David John Perro ,  Nivetha Raghavan ,  Nikhil Ram ,  Tara Michel Ramirez ,  Laurie Readhead ,  Mary Kathleen Riley ,  Elizabeth Rachel Rock ,  Angela Dawn Roose ,  Sanjay Singeetham ,  Kyle S. Sorensen ,  Shreyas Srinivas ,  Constance Jones Suarez ,  Viresh Taskar ,  Linda Trent ,  Sachin Varule ,  Bradley Walton ,  Christie M. Weekley ,  Yvette Alston ,  Ravindra Bandaru ,  Carmen R. Barnhill ,  Jamie Gilchrist ,  Namrata Kaushik ,  Fernando A. Maisonett

IPC: G06F11/14 ,  G06F11/07

CPC classification number: G06F11/1469 ,  G06F11/0751 ,  G06F11/0793 ,  G06F2201/84 ,  G06F2201/86

Abstract: Embodiments of the present invention provide a system for identifying occurrence of events and performing one or more actions to mitigate the impacts of the events. The system is configured for gathering data from one or more data sources of an entity, generating dataflows using the data gathered from the one or more data sources, identifying an anomaly based on one or more indicators and the dataflows, determining occurrence of an event and generating one or more propagation models associated with the event, performing event impact analysis based on the one or more propagation models, perform one or more actions to contain the event based on the one or more propagation models, identifying a last good copy of data based on the data gathered from the one or more data sources, retrieving the last good copy of data, and restoring the last good copy of data.

公开(公告)号：US20220004465A1

公开(公告)日：2022-01-06

申请号：US17367912

申请日：2021-07-06

Applicant: BANK OF AMERICA CORPORATION

Inventor： Christopher Emmanuel Huntley ,  Musa Ajakaiye ,  Prasad V. Annadata ,  Dnyanesh P. Ballikar ,  Sina Bauer ,  Jason Kenneth Bellew ,  Timothy John Bendel ,  David Alan Beumer ,  Michelle Andrea Boston ,  Lisa Julia Brown ,  Robin J. Buck ,  Brian C. Busch ,  Salvatore Michael Certo ,  Ramesh Naidu Chatta ,  Lisa Michelle Cook ,  Joseph Corbett ,  Joseph Seth Cushing ,  Steven Paul Davidson ,  Shailesh Deshpande ,  Sevara Ergasheva ,  Maria Ervin ,  James Wilson Foy, JR. ,  Noel Mary Fuller ,  Benjamin Judson Gaines, III ,  Candace Gordon ,  Jesse Antonio Hernandez ,  Christine Hoagland ,  Robert Charles Hoard ,  Michael Spiro Karafotis ,  Wesley Keville ,  Sandip Kumar ,  Terri Dorinda Lail ,  Mukesh Maraj ,  Wyatt Edward Maxey ,  Dari Ann McKenzie ,  Ashley Meadows ,  Heather Newell ,  Conor Mitchell Liam Nodzak ,  Kenyell Javon Ollie ,  Jayshree G. Patel ,  David John Perro ,  Nivetha Raghavan ,  Nikhil Ram ,  Tara Michel Ramirez ,  Laurie Readhead ,  Mary Kathleen Riley ,  Elizabeth Rachel Rock ,  Angela Dawn Roose ,  Sanjay Singeetham ,  Kyle S. Sorensen ,  Shreyas Srinivas ,  Constance Jones Suarez ,  Viresh Taskar ,  Linda Trent ,  Sachin Varule ,  Bradley Walton ,  Christie M. Weekley ,  Yvette Alston ,  Ravi K. Bandaru ,  Carmen R. Barnhill ,  Joseph Benet ,  Jamie Gilchrist ,  Namrata Kaushik ,  Fernando A. Maisonett

IPC: G06F11/14

Abstract: Embodiments of the present invention provide a system for identifying occurrence of events and performing one or more actions to mitigate the impacts of the events. The system is configured for gathering data from one or more data sources of an entity, generating dataflows using the data gathered from the one or more data sources, identifying an anomaly based on one or more indicators and the dataflows, determining occurrence of an event and generating one or more propagation models associated with the event, performing event impact analysis based on the one or more propagation models, perform one or more actions to contain the event based on the one or more propagation models, identifying a last good copy of data based on the data gathered from the one or more data sources, retrieving the last good copy of data, and restoring the last good copy of data.

公开(公告)号：US20240171473A1

公开(公告)日：2024-05-23

申请号：US17992840

申请日：2022-11-22

Applicant: BANK OF AMERICA CORPORATION

Inventor： Conor Mitchell Liam Nodzak ,  Kyle S. Sorensen ,  Brian C. Busch ,  Fernando A. Maisonett ,  Shreyas Srinivas ,  Angela Dawn Roose

IPC: H04L41/147 ,  H04L43/106

CPC classification number: H04L41/147 ,  H04L43/106

Abstract: Systems, computer program products, and methods are described herein for reconstructing time aware data activity across multiple software applications. The method includes receiving one or more node communication data packets. Each of the one or more node communication data packets are time-stamped and include two nodes of a plurality of nodes within a network. The method also includes generating a first time period path graph. The first time period path graph includes a directional data flow between the plurality of nodes during a first time period. The first time period path graph is generated based on the one or more node communication data packets. The method further includes determining a central node of the plurality of nodes for the first time period. The central node of the plurality of nodes is determined based on the first time period path graph.

公开(公告)号：US20240168939A1

公开(公告)日：2024-05-23

申请号：US17989139

申请日：2022-11-17

Applicant: BANK OF AMERICA CORPORATION

Inventor： Conor Mitchell Liam Nodzak ,  Brian C. Busch ,  Fernando A. Maisonett ,  Kyle S. Sorensen ,  Shreyas Srinivas

IPC: G06F16/23 ,  G06F16/242 ,  G06F16/2457 ,  G06F16/28

CPC classification number: G06F16/2365 ,  G06F16/244 ,  G06F16/2457 ,  G06F16/285

Abstract: Systems, computer program products, and methods are described herein for data community detection via data network telemetry. Packet header information and a corresponding record is received via a network sensing module. The record is analyzed to identify the direction(s) of the data transfer. The record is then validated and used to generate at least one directionality map, which is segmented into a plurality of time segments based on a user defined interval. A clustering algorithm is then used to determine at least one community for each of the directionality maps. The at least one directionality maps is then displayed at the user interface of an endpoint device. The at least one community is then provided with a functional group indicator, the functional group indicator compared to a stored functional group indicator to identify any mismatches.

公开(公告)号：US11983164B1

公开(公告)日：2024-05-14

申请号：US17989139

申请日：2022-11-17

Applicant: BANK OF AMERICA CORPORATION

Inventor： Conor Mitchell Liam Nodzak ,  Brian C. Busch ,  Fernando A. Maisonett ,  Kyle S. Sorensen ,  Shreyas Srinivas

IPC: G06F16/00 ,  G06F16/23 ,  G06F16/242 ,  G06F16/2457 ,  G06F16/28

CPC classification number: G06F16/2365 ,  G06F16/244 ,  G06F16/2457 ,  G06F16/285

Abstract: Systems, computer program products, and methods are described herein for data community detection via data network telemetry. Packet header information and a corresponding record is received via a network sensing module. The record is analyzed to identify the direction(s) of the data transfer. The record is then validated and used to generate at least one directionality map, which is segmented into a plurality of time segments based on a user defined interval. A clustering algorithm is then used to determine at least one community for each of the directionality maps. The at least one directionality maps is then displayed at the user interface of an endpoint device. The at least one community is then provided with a functional group indicator, the functional group indicator compared to a stored functional group indicator to identify any mismatches.