Bank of America Corporation

Awadhesh Pratap Singh

Dinesh Narendra Jibhe

Prabakar Rangarajan

Vinay Laxmikant Bade

Suki Ramasamy

Samson Paulraj

Amit Sareen

Ravi Kanth Bommakanti

Systems for dynamically performing pattern recognition and data reconciliation functions are provided. In some examples, a system may receive data, from one or more computing systems. In some examples, one or more machine learning datasets may be used to identify datasets, data elements, or the like, for comparison. The identified datasets, data elements, and the like, may be compared to pre-stored patterns to determine whether the pattern matches a pre-stored pattern. If not, the pattern may be flagged as a new pattern and instructions for further processing may be requested. In some arrangements, the identified datasets, data elements, or the like, may be compared to determine whether a pattern and/or value of the datasets, data elements, or the like, matches. If not, one or more machine learning datasets may be used to generate a corrective action to align the data. In some examples, the generated corrective action may be automatically executed to align the data.

Dynamic pattern recognition and data reconciliation

Embodiments of the present invention provide a system for executing, securing, and non-repudiation of pooled conditional smart contracts over a distributed blockchain network. In particular, the system may receive an instrument request from a beneficiary entity, where the instrument request includes an instrument amount. The system can then identify a lead contribution amount that a lead entity is willing to provide to meet a portion of the instrument amount. A set of supporting entities can be identified as willing to provide supporting contribution amounts to meet the remainder of the instrument amount. A conditional contract can be sent to each supporting entity that, when signed, authorizes the system to transfer contribution amounts, which may be in the form of cryptocurrency, from blockchain addresses of the lead and supporting entities to a blockchain address of the beneficiary entity. Once the instrument amount has been secured, the system executes the transactions.

System for executing, securing, and non-repudiation of pooled conditional smart contracts over distributed blockchain network

Methods and systems for a crypto-machine learning enabled blockchain based profile pricer are described herein. In one example, computer-readable instructions are stored in memory, and one or more processors execute the instructions to determine requested information for a user that can be displayed on a user interface in real-time or near real-time of the user's request. In addition, the provided data can be customized for the user based on a user profile stored in the memory as well as based on third party data stored in a database of related information. The data is communicated to the user using blockchains. At least some advantages of such an arrangement are providing requested data to a user, for display on a user interface, in a transparent, secure, and timely manner.

Crypto-machine learning enabled blockchain based profile pricer

A crypto-machine learning enabled blockchain based profile pricer processes computer-readable instructions to determine requested information for a user that can be displayed on a user interface in real-time or near real-time of the user's request. In addition, the crypto-machine learning enabled blockchain based profile pricer processes provided data to be customized for the user based on a user profile stored in the memory as well as based on third party data stored in a database of related information. The pricer communicates the data to the user using blockchains via a smart contract using a private key and initiates a data transfer based on an input received from the user.

Systems for dynamically detecting unauthorized activity are provided. A system may receive data from one or more computing devices associated with one or more different channels of communication (e.g., email, telephone, instant messaging, internet browsing, and the like). The received data may be formatted or transformed from an unstructured format to a structured format for further analysis and evaluation. In some arrangements, machine learning may be used to determine whether triggering content was identified in data received from the one or more systems and to evaluate the identified triggering content to determine whether the content, alone or in combination with triggering content from other channels of communication, may indicate an occurrence of unauthorized activity. If so, the identified occurrence may be evaluated to determine whether a false positive has occurred. If a false positive has not occurred, an alert or notification may be generated and/or operation or functionality one or more communication channels may be modified.

Dynamic detection of unauthorized activity in multi-channel system

Embodiments of the present invention provide a system for converting ubiquitous language instructions to robotic process automation executable action steps and executing the action steps. A managing system receives an encrypted user input from a computing device of the user, where the user input comprises instructions entered in ubiquitous language (e.g., common vernacular, or other non-complex programming language). The user input is decrypted and an action keyword is identified from the ubiquitous language instructions. The action keyword for each instruction is compared to a conversion database to determine a set of execution steps associated with each action keyword. These execution steps are in a format that enables a robotic process automation system to perform the execution steps. The set of execution steps is then transmitted to the robotic process automation system that automatically performs the set of execution steps through a workstation or other operating station of the user.

Robotics assisted production support utility

A machine learning tool for resolving a compiler error in an application is provided. The application and an associated application metadata file may be stored on a server. The machine learning tool may identify one or more referenced external dependencies causing the compiler error. The machine learning tool may comprise a web crawler configured to locate one or more comparable external dependencies. The web crawler may retrieve an external dependent metadata file for each of the located comparable external dependencies and download the comparable external dependent metadata files. The machine learning tool may be configured to compare the metadata of each comparable external dependent metadata file to the metadata of the application metadata file, assign a confidence level relative to a pre-determined confidence level, for each located comparable external dependency, and download the located comparable external dependencies having a confidence level greater than the pre-determined confidence level.

Intelligent software compiler dependency fulfillment

Apparatus and methods for transformation of a digital scanner image using machine-learning algorithms are provided. The apparatus and methods may include a portable USB device configured for connection to a scanner port. The device may access and store a scanned digital image captured by the scanner. A device processor may use OCR to generate an editable PDF file and use one or more machine-learning algorithms to apply auto-corrections to the PDF file. The processor may communicate with a user interface configured to display each line from the scanned digital image in line with the corresponding auto-corrected text. The user interface may receive separate inputs accepting each line of auto-corrected text. Auto-correction acceptance data may be transmitted to the device processor. Each accepted auto-correction may be associated with a quantified value. A machine-learning algorithm may be configured to maximize a total value for auto-corrections in a scanned document.

Reinforcement learning based document scanner

Embodiments of the present invention provide a system for the utilization of a robotic process automation system for functional evaluation and improvement of back end instructional constructs. The system may scan a set of code to identify an exception comprising an exception tag and an exception string located at a first location within the set of code. The system may then transmit the set of code and the identified exception to a robotic process automation system, along with instructions for the robotic process automation system to compare the exception tag and exception string to a replacement code database to identify an exception string. The robotic process automation system can then replace the exception string in the set of code with the identified replacement string.

Growing community of inventors

Hyderabad Telangana, India

Awadhesh Pratap Singh