Automated Agent Early Response via Real-Time Inquiry Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated call centers lack the ability for automated agents to 'barge-in' and respond early to user inquiries, leading to slower problem resolution and an unsatisfactory experience for callers.
Innovation Solution
An automated agent system that uses an action classifier and knowledge bank to score user input in real-time, allowing for early responses when a confidence threshold is exceeded, enabling the automated agent to intervene before the user completes their inquiry.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the automated agent waits for the user to complete the entire inquiry before responding, then measurement precision is improved (full inquiry is captured), but loss of time increases (resolution is delayed)
Solution Approach 1:
The automated agent performs preliminary analysis of the user's inquiry in real-time, scoring portions of the inquiry as they are spoken. When the running score exceeds a threshold, the agent interrupts and provides a response before the user finishes speaking, thus resolving the inquiry faster while maintaining sufficient accuracy
Solution Approach 2:
The system dynamically adjusts the response timing based on the running score of the inquiry portions. The agent continuously evaluates the accumulated information and decides whether to respond early or wait for the complete inquiry, making the system adaptive rather than static
2Loss of time
If the automated agent responds early before the user completes the inquiry, then loss of time is reduced (faster resolution), but measurement precision deteriorates (inquiry may be incompletely captured)
Solution Approach 1:
The system uses feedback from the running score evaluation to determine when to respond. The action classifier continuously scores the recognized speech portions, and when the score exceeds the threshold, this feedback triggers an early response, balancing speed and accuracy
3Measurement precision
If human agents manually monitor and respond to inquiries, then measurement precision is improved (accurate understanding), but productivity decreases (slower response rate)
Solution Approach 1:
The automated agent performs self-service by autonomously analyzing user inquiries, scoring them in real-time, and providing responses without human intervention. The agent independently determines when sufficient information has been captured and responds accordingly, maintaining both accuracy and high productivity
Solution Approach 2:
The patent replaces the mechanical system of human agents manually monitoring and responding to inquiries with an automated computational system. The action classifier and scoring mechanism substitute for human cognitive processing, achieving both accuracy and high-speed response
Data Source
AI summary
An automated agent system and method includes an action classifier which scores a representation of a portion of a user inquiry based on a knowledge bank. A comparing device compares a running score of the representation to a threshold to determine if enough information has been collected to respond early to the inquiry. An action mechanism provides an early response to the user prior to the user completing the inquiry if the threshold has been exceeded.