Bank of America has patented a method using machine learning and artificial intelligence to assess user sentiment during interactions with an interactive response system. The method involves processing user utterances, extracting signals, and using a neural network classifier to output sentiment scores, improving efficiency and resource consumption. GlobalData’s report on Bank of America gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Bank of America, Virtual banking assistant was a key innovation area identified from patents. Bank of America's grant share as of February 2024 was 89%. Grant share is based on the ratio of number of grants to total number of patents.

Method for sentiment analysis using machine learning in conversations

Source: United States Patent and Trademark Office (USPTO). Credit: Bank of America Corp

A recently granted patent (Publication Number: US11922928B2) outlines a method for enhancing conversation sentiment scoring in interactive response systems. The method involves pre-processing user utterances before feeding them to a sequential neural network classifier. The process includes a conversation manager receiving API requests with utterances, previous utterance data, and labels, a natural language processor determining utterance intent and semantic meaning, a signal extractor generating utterance signals, an utterance sentiment classifier identifying rules, and a sequential neural network classifier processing data inputs to output sentiment scores. This pre-processing reduces data input, speeding up sentiment score returns and decreasing resource consumption by the neural network.

The patent also details the inclusion of previous utterance data, semantic meanings, and intent parameters in the pre-processing stage, allowing for a more comprehensive analysis of user interactions. The method is adaptable for various interactive response systems, including interactive voice response systems, chatbots on mobile devices, and cloud-based APIs. By optimizing the pre-processing of user utterances, the system can efficiently generate responses based on sentiment scores, enhancing the overall user experience. Additionally, the method includes training the sequential neural network with labeled data to improve accuracy and performance, ensuring effective sentiment analysis in real-time interactions. Overall, the patented method offers a structured approach to sentiment scoring in conversational interfaces, improving response generation and user engagement.

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

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.