Bank of America Corporation

Arjun Thimmareddy

Matthew I Cobb

Melissa A Fraser

Gerard P Gay

William R Conrad

Alexander S Lee

Bryan T King

Vaishnavi Varma

Juliet Abdul-Aziz

Tony Aidoo

Ramesh B Chandanala

Paula M Booze

Aarron Gull

Marcus Adrian Streips

Virinchi Ande

Asif Ahmad Bala

Surina Puri

Kimberly S Smith

Sreedhar Pagadala

Lance Cline Berry

Systems, computer program products, and methods are described herein for providing automated command access approval across a network. The method includes receiving a request for a command execution to be performed on a first node. The request for the command execution indicates a user attempting to execute the command on the first node. The method also includes comparing the request for command execution to one or more previous command execution determinations. The one or more previous command execution determinations are associated with the command to be performed. The method further includes determining an execution decision based on the comparison of the request for command execution to one or more previous command execution determinations.

System and method for automated command access approval across a network of servers

Methods for banking at an automated teller machine (ATM) using a mobile device. The ATM may automatically detect the presence of the mobile device in a vicinity of the ATM and initiate contact with the mobile device, or a mobile device may initiate contact with the ATM. After verifying user permission to access the ATM, the mobile device may be enabled to provide user access to one or more of the banking services available at the ATM using the mobile device and to view banking-related information on the mobile device. A mobile application on the mobile device may be used to access the ATM using the mobile device. While a mobile device is accessing the ATM, a screen on the ATM may become inactive for banking services and the option to select banking services directly at the ATM may be disabled.

Banking at an ATM using a mobile device

Systems, computer program products, and methods are described herein for tracking network traffic data and identifying rogue access patterns in an electronic network. The present invention is configured to receive a plurality of peer user accounts; receiving a plurality of peer user data associated with the plurality of peer user accounts; generating a relational mapping based at least on the predetermined group; and generating a plurality of peer historical data access patterns based on the plurality of peer user data over the historical predetermined period. The present invention may further be configured to receive a primary user account; receive a plurality of primary user data; generate a plurality of primary user access patterns; compare the plurality of peer historical data access patterns and the plurality of primary user access patterns to generate an abnormality score; and determine whether the abnormality score meets the abnormality threshold.

Systems, methods, and apparatuses for tracking network traffic data and identifying rogue access patterns in an electronic network

An ATM is configured to interact with a mobile device and provide user access to one or more of the banking services available at the ATM using the mobile device. Banking-related information may be viewed and/or input at the ATM using the mobile device. The ATM may have multiple vertical levels of deposit slots, withdrawal trays and/or receipt dispensers. A level at the ATM at which the user interacts with the ATM for deposits, withdrawals, or receipts may be selected. The level may be specified by the user of the mobile device, at the ATM or using the mobile device, or may be determined by the ATM.

Banking at a multi-level ATM

An information-security automated process for authorizing a user request for access to a module and for identifying anomalous user authorization requests, may be implemented on a computer machine and may include the steps of receiving a user request for access to a module, generating a peer group proximity dataset, generating a user dataset, calculating a critical score, determining if the critical score is less than an enterprise threshold, and generating an approval or denial of the user request based upon the critical score. In some examples the process may include the step of executing machine learning instructions to generate a second approval or a second denial of a second user request for access to a second module. In another examples an information-security automated process for validating a user authorization access profile is disclosed herein.

Alerting on anomalous authorization requests derived with proximity graph

A device that includes an enterprise data indexing engine (EDIE) configured to obtain a set of sentences from a document and to compare the words from each of the sentences to a set of keywords. The EDIE is further configured to identify one or more sentences that do not contain any of the keywords and to associate the identified sentences with a first classification type. The EDIE is further configured to identify a sentence that contains one or more keywords and to associate the sentence with a second classification type. The EDIE is further configured to link together the sentence that is associated with the second classification type and the sentences that are associated with the first classification type. The EDIE is further configured to obtain a classification description and a token and to link the classification description and its token with the classified sentences.

Classifying and mapping sentences using machine learning

A device that includes an enterprise data indexing engine (EDIE) configured to receive a set of sentences and to compare the words in the sentences to a set of predefined keywords. The EDIE is further configured to identify one or more sentences that do not contain any of the keywords and to associate the identified sentences with a first classification type. The EDIE is further configured to identify a sentence that contains one or more keywords and to associate the sentence with a second classification type. The EDIE is further configured to link together the sentence that is associated with the second classification type and the sentences that are associated with the first classification type.

Classifying and grouping sentences using machine learning

A tool may identify and revert changes that caused network hardware components or hardware servers to malfunction. The tool builds and maintains a graph that represents the hardware components and servers in the system and their dependencies. When a change is made to the system, links and weights in the graph are adjusted to account for the changes. When a component or server is reported as malfunctioning, the tool traverses the graph to locate the changes that are the most likely root causes of the malfunction. The tool may then revert the change to resolve the malfunction.

Software code change reversal tool

A device that includes an enterprise data indexing engine (EDIE) configured to receive a set of input sentences and to determine a set of similarity scores between the set of input sentences and a plurality of classification descriptions. The EDIE is further configured to identify a classification description that is associated with the highest similarity score and to identify a token that is associated with the identified classification description. The EDIE is further configured to link the identified token with the set of input sentences.

Identifying relationships between sentences using machine learning

A device that includes an enterprise data indexing engine (EDIE) configured to obtain a set of sentences from a document, to associate one or more of the sentences with a first classification type, to associate one of the sentences with a second classification type, and to link the classified sentences together. The EDIE is further configured to determine a set of similarity scores between the classified sentences and a plurality of classification descriptions. The EDIE is further configured to identify a classification description that is associated with the highest similarity, to identify a token associated with the identified classification description, and to output the token.

Mapping documents using machine learning

A device that includes an enterprise data indexing engine (EDIE) configured to receive a document that contains text and to convert the document into a markup language code. The EDIE is further configured to identify tags within the markup language code and to parse the markup language code into logical sections based on the tags. The EDIE is further configured to identify sentences within each of the logical sections and to link the identified sentences with a location identifier that identifies a location within the document where a sentence is located.

Parsing documents using markup language tags

A device that includes an enterprise data indexing engine (EDIE) configured to determine a first set of similarity scores between a first set of sentences from a first document and a plurality of classification descriptions. The EDIE is further configured to identify one or more classification descriptions that have a similarity score that exceeds a predetermined threshold value. The EDIE is further configured to determine a second set of similarity scores between a second set of sentences from a second document and the plurality of classification descriptions. The EDIE is further configured to identify one or more classification descriptions that have a similarity score that exceeds the predetermined threshold value. The EDIE is further configured to populate a data structure that identifies the tokens within the first set of tokens and the second set of tokens and the number of times each token appears.

Validating mappings between documents using machine learning

A device that includes an enterprise data indexing engine (EDIE) configured to receive a document comprising text and to convert the document into a markup language code. The EDIE is further configured to identify tags within the markup language code and to parse the markup language code into logical sections based on the tags. The EDIE is further configured to identify sentences within each of the logical sections and to link the identified sentences with a classification type. The EDIE is further configured to use the classified sentences to train a custom machine learning model.

Growing community of inventors

Charlotte, NC, United States of America

Arjun Thimmareddy