Bank of America had six patents in regtech during Q3 2023. Bank of America Corp filed four patents during Q3 2023.
1. The first patent is for an apparatus and methods to accelerate the remediation of broken transactions using parallel machine learning processing and optimization. It involves selecting a bionic element within a bio-mesh network for processing the broken transaction and running machine-learning algorithms to identify an optimal routine for fixing the broken transaction.
2. The second patent is for a system that tracks and tags communication using electronic non-fungible resources within a distributed network. It retrieves an NFT for an ongoing unresolved issue, displays the description of the issue, and authorizes the communication based on user input.
3. The third patent is for a system that receives user criteria associated with an operation and determines operation structure candidates based on aggregating segment candidates from different sources. It prioritizes the operation structure candidates based on user criteria and communicates the output indicating the candidates.
4. The fourth patent is for a system that leverages a tokening system to authenticate a traveler while maintaining their anonymity. It involves a secure central server, a mobile token application, and a travel service provider to enable reserving a travel reservation file and verify the token identifier with the central server. GlobalData’s report on Bank of America gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Bank of America grant share with regtech as a theme is 33% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Bio-mesh network leveraging natural selection optimization for intelligent auto-healing (Patent ID: US20230259917A1)
The patent filed by Bank of America Corp. describes apparatus and methods for accelerating the remediation of broken transactions using parallel machine learning processing and optimization. The methods involve a network access point receiving a broken transaction from an application programming interface (API) and selecting a bionic element within a bio-mesh network for processing the broken transaction. The bionic element receives the broken transaction, extracts a set of features from it, and transmits the set of features to a policy bank. If the policy bank fails to identify a stored routine associated with the set of features for fixing the broken transaction, the bionic element runs two machine-learning algorithms in parallel to identify an optimal routine for fixing the broken transaction.
The patent includes several claims that further detail the method. These claims describe additional steps and features of the method. For example, the network access point may transmit the fixed transaction to the API and receive a response indicating whether the fixed transaction has been accepted or rejected. In response to a rejection, the network access point may transmit a command to the bionic element to output a second policy to fix the broken transaction. The bionic element then adjusts the optimization algorithm to optimize both speed and accuracy and selects a second optimized solution for each step of the broken transaction. The second optimized solutions are combined to create a second policy, which is transmitted to the policy application pipeline for implementation.
The set of features extracted from the broken transaction may include an account time stamp, transaction type, transaction amount, transaction time stamp, origin account, and destination account. The compliance protocols used in the method may include checking for a match between a debit entry and a corresponding credit entry, verifying the correct value date, and ensuring each step is associated with a key generated during the step by the processing entity.
The bio-mesh network mentioned in the patent consists of multiple bionic elements, and a gateway cache is used to store a log of the routing of broken transactions and maintain a prioritization algorithm for determining which bionic element should receive an incoming broken transaction.
Overall, the patent describes a method that utilizes parallel machine learning processing and optimization to accelerate the remediation of broken transactions, improving efficiency and accuracy in transaction processing.
To know more about GlobalData’s detailed insights on Bank of America, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
