18074653. MACHINE LEARNING (ML)-BASED DUAL LAYER CONVERSATIONAL ASSIST SYSTEM simplified abstract (Bank of America Corporation)
Contents
MACHINE LEARNING (ML)-BASED DUAL LAYER CONVERSATIONAL ASSIST SYSTEM
Organization Name
Inventor(s)
Ramakrishna R. Yannam of The Colony TX (US)
Ion Gerald Mccusker of Allen TX (US)
Prejish Thomas of Plano TX (US)
Ravisha Andar of Plano TX (US)
MACHINE LEARNING (ML)-BASED DUAL LAYER CONVERSATIONAL ASSIST SYSTEM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18074653 titled 'MACHINE LEARNING (ML)-BASED DUAL LAYER CONVERSATIONAL ASSIST SYSTEM
Simplified Explanation: The patent application describes systems and methods for improving accuracy in an online chat interface using a machine-learning-based chat monitoring engine. It involves analyzing user requests and responses to ensure they align with the intended communication.
- Intercepting user requests
- Using a trained ML model to determine the intent of the request
- Generating a suitable response
- Analyzing the response to ensure it matches the target response
- Transmitting the response if it meets accuracy thresholds, or revising it if necessary
Key Features and Innovation:
- Utilization of a machine-learning-based chat monitoring engine
- Real-time analysis of user requests and responses
- Automated generation of accurate responses
- Threshold-based accuracy checks for responses
- Dynamic adjustment of responses to meet accuracy standards
Potential Applications:
- Customer service chatbots
- Online support systems
- Automated messaging platforms
Problems Solved:
- Ensuring accurate and relevant responses in online chat interactions
- Improving user experience by providing timely and appropriate responses
- Reducing errors and misunderstandings in online communication
Benefits:
- Enhanced accuracy in online chat interactions
- Improved customer satisfaction
- Streamlined communication processes
- Increased efficiency in handling user queries
Commercial Applications: Title: "Enhancing Online Chat Accuracy for Improved Customer Engagement" This technology can be applied in customer service chatbots, online support systems, and automated messaging platforms to enhance user experience and streamline communication processes. It can lead to increased customer satisfaction and improved efficiency in handling user queries.
Prior Art: No prior art information is available at this time.
Frequently Updated Research: There is ongoing research in the field of natural language processing and machine learning to further enhance the accuracy and efficiency of online chat interfaces.
Questions about Online Chat Accuracy: Question 1: How does the machine-learning model determine the intent of user requests? Answer: The machine-learning model analyzes patterns in user input to classify and understand the intent behind each request.
Question 2: What are the potential challenges in implementing this technology in real-time chat environments? Answer: Some challenges may include training the ML model with sufficient data, ensuring real-time processing capabilities, and managing response accuracy thresholds effectively.
Original Abstract Submitted
Systems and methods for increasing accuracy in an online chat interface are provided. Methods may be executed via a machine-learning (ML)-based chat monitoring engine. Methods may include intercepting a request utterance. Methods may include computing, via a trained ML model, an intent of the request utterance; generating a target response to the request utterance; intercepting a response utterance; and calculating a difference between the response utterance and the target response. In response to the difference being less than a threshold difference, methods may include releasing the response utterance to be transmitted as a response message. In response to the difference being more than a threshold difference, methods may include preventing the response utterance from being transmitted as a response message, generating a revised response utterance that is less than a threshold difference apart from the target response, and transmitting the revised response as a response message to a remote computing device.
