17850282. SYSTEMS AND METHODS FOR GENERATING REAL-TIME DYNAMIC CONVERSATIONAL RESPONSES DURING CONVERSATIONAL INTERACTIONS USING MACHINE LEARNING MODELS simplified abstract (Capital One Services, LLC)

SYSTEMS AND METHODS FOR GENERATING REAL-TIME DYNAMIC CONVERSATIONAL RESPONSES DURING CONVERSATIONAL INTERACTIONS USING MACHINE LEARNING MODELS

Organization Name

Capital One Services, LLC

Inventor(s)

Md Arafat Hossain Khan of Dallas TX (US)

Isha Chaturvedi of Mountain View CA (US)

Arturo Hernandez Zeledon of Arlington VA (US)

Mohammad Sorower of McLean VA (US)

SYSTEMS AND METHODS FOR GENERATING REAL-TIME DYNAMIC CONVERSATIONAL RESPONSES DURING CONVERSATIONAL INTERACTIONS USING MACHINE LEARNING MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17850282 titled 'SYSTEMS AND METHODS FOR GENERATING REAL-TIME DYNAMIC CONVERSATIONAL RESPONSES DURING CONVERSATIONAL INTERACTIONS USING MACHINE LEARNING MODELS

Simplified Explanation

The patent application describes methods and systems for generating real-time dynamic conversational responses using machine learning models. These models are trained based on historic intents and user-specific interactions. Here are the key points:

• The invention uses machine learning models to generate real-time dynamic conversational responses.
• The models are trained using historic intents and user-specific interactions.
• One model selects a first intent from a range of intents based on historic data.
• Another model selects a first interaction-specific intent from a range of interaction-specific intents based on interaction-specific data for a user.

Potential Applications

This technology has potential applications in various fields, including:

• Customer service: It can be used to provide automated and personalized responses to customer queries in real-time.
• Virtual assistants: Virtual assistants can use this technology to generate more natural and context-aware responses during conversations.
• Chatbots: Chatbots can benefit from this technology to improve their conversational abilities and provide more accurate and relevant information.

Problems Solved

The technology addresses several problems in conversational interactions, such as:

• Lack of real-time dynamic responses: Traditional conversational systems often provide static and predefined responses, which may not be suitable for dynamic conversations.
• Limited personalization: Without user-specific training, conversational systems may struggle to understand and respond to individual users' needs and preferences.
• Contextual understanding: By considering historic intents and interaction-specific data, the technology enables better understanding of the context and generates more relevant responses.

Benefits

The use of this technology offers several benefits, including:

• Improved user experience: Real-time dynamic responses make conversations more engaging and natural, enhancing the overall user experience.
• Personalization: By considering user-specific data, the technology can tailor responses to individual users, making interactions more personalized.
• Enhanced efficiency: Automated and context-aware responses save time and effort for both users and conversational systems.

Original Abstract Submitted

Methods and systems are presented for generating real-time dynamic conversational responses during conversational interactions using machine learning models based on historic intents for a plurality of users and user-specific interactions. The machine learning models comprise a neural network trained to select a first intent from a plurality of intents based on historic data accumulated prior to the conversational interaction and a neural network trained to select a first interaction-specific intent from a plurality of interaction-specific intents based on interaction-specific data for a user.