Dynamic Confidence Threshold for Agent Intervention

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to dynamically adjust the confidence factor threshold for live agent intervention in automated customer engagements, failing to account for the availability of live agents and their proficiency, leading to inefficient utilization and unsatisfactory customer experiences.

Innovation Solution

A system and method that utilize an intervention prioritization module to dynamically adjust the confidence factor threshold based on live agent availability and attributes, ensuring optimal agent selection and intervention in automated customer engagements, using Avaya Aura and Avaya Experience Manager technologies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a static confidence factor threshold is used for live agent intervention, then the system is simple to operate, but it cannot dynamically adapt to changes in live agent availability and proficiency

Engineering Contradiction:

Improvedynamic adjustment of confidence factor thresholdVSAvoidsystem complexity for threshold management

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic adjustment of the confidence factor threshold based on real-time live agent availability and proficiency. The system continuously monitors agent status and automatically modifies the threshold to optimize intervention timing, transforming a static parameter into a dynamic one that adapts to changing conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms that monitor live agent availability, engagement confidence factors, and intervention outcomes. This feedback loop enables the system to learn from past interactions and continuously optimize the confidence threshold, improving adaptability while maintaining operational simplicity through automated decision-making.

Inventive Principle:

Principle #23Feedback

2Reliability

If the confidence factor threshold is lowered to increase live agent intervention, then customer satisfaction improves, but live agent availability is reduced

Engineering Contradiction:

Improvecustomer satisfactionVSAvoidlive agent availability

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent dynamically changes the confidence factor threshold parameter based on live agent availability and engagement characteristics. By adjusting this parameter in real-time, the system optimizes the balance between customer satisfaction (through appropriate interventions) and agent availability (by avoiding unnecessary interventions), resolving the contradiction between these two objectives.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system applies different confidence thresholds to different engagements based on local conditions such as agent availability, agent proficiency, and engagement characteristics. This localized approach ensures that interventions occur where they are most beneficial while preserving agent availability for critical situations.

Inventive Principle:

Principle #3Local quality

3Reliability

If live agents are deployed to all automated engagements, then customer service quality improves, but agent utilization efficiency decreases

Engineering Contradiction:

Improvecustomer service qualityVSAvoidagent utilization efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent implements partial intervention by deploying live agents only to engagements where the confidence factor indicates potential failure or where agent attributes suggest high value. This selective approach provides sufficient service quality for critical cases while avoiding unnecessary deployments that would reduce overall agent utilization efficiency.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The automated engagement system handles the majority of customer interactions independently without human intervention. Live agents serve as a backup resource that activates only when the automated system's confidence indicates potential failure, enabling the system to self-serve most cases while maintaining quality through selective human intervention.

Inventive Principle:

Principle #25Self-service

4Productivity

If the confidence factor threshold is raised to reduce live agent intervention, then agent availability is maintained, but customer satisfaction deteriorates

Engineering Contradiction:

Improvelive agent availabilityVSAvoidcustomer satisfaction

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system dynamically adjusts the confidence threshold parameter based on real-time conditions including agent availability, agent proficiency, and engagement characteristics. This dynamic parameter change ensures that the threshold is high enough to maintain agent availability but low enough to ensure customer satisfaction when interventions do occur.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9621728B2System and method for prioritizing agent intervention into automated customer engagements

Publication Date: 2017.04.11 AVAYA INC

AI summary

A system for prioritizing intervention of live agents into automated customer engagements in a communication system is disclosed. The system includes an intervention prioritization module configured to identify a live agent to intervene into an automated customer engagement in a communication system based on a confidence factor corresponding to the automated customer engagement and one or more live agent attributes corresponding to the live agent. The system further includes a live agent conference module configured to cause the identified live agent to intervene into the automated customer engagement.