Bank of America had 14 patents in internet of things during Q3 2023. Bank of America Corp filed several patents during Q3 2023. One patent describes a system that uses machine learning to predict anomalies in a production computing environment and take corrective actions. Another patent involves using smart glasses and distributed ledger technology for secure authentication in digitally hand signing documents. Another patent relates to a system that allows users to seamlessly switch between devices while maintaining their user interface and information. Another patent involves dynamically altering resource distribution thresholds based on user environment factors. Lastly, there is a patent for an augmented reality-enabled ATM that can dispense cash based on AR checks. GlobalData’s report on Bank of America gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

Bank of America grant share with internet of things as a theme is 29% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Automatic system anomaly detection (Patent ID: US20230273610A1)

The patent filed by Bank of America Corp describes a system for managing anomalies in a production computing environment. The system includes a production computing environment with multiple components, a centralized data repository, and at least one processor. The data repository receives and stores data feeds related to the components as a data log. The processor obtains the data log for each component and generates a current state vector based on the data log. It then compares the current state vector to a normal state vector of the component to determine if there is a deviation. If a deviation is detected, the processor predicts an anomaly associated with the component using an iterative machine learning method. The processor can also correct the predicted anomaly by taking pre-configured actions.

The system includes a hardware component and a software component in the production computing environment. The data feed received for each component includes information about the performance of the component. The processor obtains the data log for each component and generates a current state vector based on the data log. It compares the current state vector to a normal state vector to detect deviations. If a deviation is detected, the processor predicts an anomaly using an iterative machine learning method. The machine learning method uses multiple machine learning models and updates the training of each model using the most current data feed. The processor can also take pre-configured actions to correct the predicted anomaly.

The processor predicts the anomaly associated with the component by generating multiple machine learning models, each using a different algorithm. It predicts an anomaly using each model and compares the results to select the model with the highest accuracy. The selected model's predicted anomaly is considered the predicted anomaly of the component.

The processor can iteratively update the training of the machine learning models by generating a training dataset based on the most recent data feed and training the models according to a pre-configured schedule or when a deviation is detected.

For hardware components, the system includes at least one sensor that measures performance-related parameters. The current state vector represents the most recent measured value of the parameter, and the normal state vector represents the normal value or range of values for the parameter. Deviations are detected when the measured value does not match the normal value or range.

The system can also receive data feeds from an Internet of Things (IoT) hub, which includes measured values from sensors associated with hardware devices. The processor stores the data feed in the centralized data repository, searches for measured values associated with each hardware device, and generates the current state vector based on the most recent measured values.

Overall, the system uses machine learning and data analysis techniques to detect and predict anomalies in a production computing environment and take corrective actions.

To know more about GlobalData’s detailed insights on Bank of America, buy the report here.

Premium 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

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.