Adaptive Generative Mediator for Unknown Intent Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing customer service interactions often require significant human customer involvement, leading to misunderstandings and frustration due to language issues, incomplete information, and repetitive data entry, especially when interacting with virtual agents or human agents.
Innovation Solution
A generative and auto-adaptive mediator system using large language models (LLMs) to automate customer-side interactions, adapting to new intents and minimizing user intervention by automatically handling communication tasks and resolving issues with conversational agents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If virtual agents or human agents are used for customer service interactions, then customer support functionality is provided, but significant human customer involvement is required leading to misunderstandings and frustration
Solution Approach 1:
The patent introduces an intermediary system that acts as a mediator between the customer and the agent (human or virtual). This intermediary automatically manages the interaction flow, interprets customer intent, and coordinates communication, thereby reducing the burden on customers and improving communication reliability by eliminating direct misunderstandings between customer and agent
2Reliability
If traditional customer service systems are used, then customer support is provided, but language issues and incomplete information cause misunderstandings and frustration
Solution Approach 1:
The system performs preliminary actions by proactively gathering complete information, identifying customer intent before the interaction fully begins, and preparing appropriate response strategies. This preliminary processing ensures that language issues and incomplete information are addressed upfront, improving communication accuracy without requiring overly complex real-time processing
3Productivity
If automated systems are used to reduce human involvement, then efficiency improves, but language issues and repetitive data entry cause frustration
Solution Approach 1:
The system enables self-service by automatically handling information gathering, intent recognition, and interaction management without requiring customer intervention for repetitive tasks. The system serves itself by autonomously processing data, eliminating language issues through automated interpretation, and removing repetitive data entry requirements, thereby improving both efficiency and user experience quality
4Extent of automation
If generative mediator system is used to automate interactions, then user intervention is minimized, but system complexity increases
Solution Approach 1:
The generative mediator system is designed as a universal platform that performs multiple functions including intent recognition, dialog management, information gathering, and coordination with different types of agents. By consolidating these diverse functions into a single multi-functional system, the patent achieves high automation levels while managing complexity through functional integration rather than proliferation of separate components
Data Source
AI summary
A generative mediator engine can perform a requested interaction with a conversational agent of a target entity on behalf of a user. An internal conversational platform can identify intents for the requested interaction. An external artificial intelligence engine can perform intent discovery when an intent is not identified above a confidence threshold. A discovered intent unknown to the generative mediator engine can be received from the external artificial intelligence engine and used, with input requirements determined by the generative mediator for the requested interaction, by a dialog generator to generate a sample dialog for the requested interaction. User feedback can be received after review of action items and expected inputs identified from the sample dialog. The generative mediator engine can perform the requested interaction with the conversational agent on behalf of the user and without receiving user intervention during the requested interaction.