Emotion-Aware Virtual Agent Routing for Customer Experience
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Standard virtual agents (VAs) fail to consider customer emotions and sentiments, leading to degraded customer experience and increased time spent on interactions by human agents, as they are not trained to handle emotions like anger and often deflect interactions to human agents inefficiently.
Innovation Solution
A computer-implemented method and apparatus that generates a value representative of a customer's emotional state during interactions with VAs, deflecting the interaction to a human agent or a specialized VA capable of empathy if the emotional state is non-neutral, ensuring appropriate assistance and maintaining high-quality customer experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If standard VAs are used to handle customer queries, then automation level is improved, but customer experience quality deteriorates due to inability to handle emotions
Solution Approach 1:
The patent segments the VA population into standard VAs and specialized VAs with emotional intelligence capabilities. Standard VAs handle routine queries while specialized VAs handle emotionally charged interactions, allowing the system to maintain high automation overall while providing enhanced quality when needed.
Solution Approach 2:
The patent applies local quality by equipping only specific VAs (specialized VAs) with emotional intelligence and empathy capabilities rather than requiring all VAs to have these traits. This allows the system to maintain simplicity in standard VAs while providing enhanced capabilities locally where needed.
2Reliability
If VAs deflect interactions to human agents, then customer experience quality is maintained, but human agent time consumption increases
Solution Approach 1:
The system performs preliminary emotional state assessment during the VA interaction before deflection to human agents. By detecting emotional states in advance and routing to specialized VAs or human agents accordingly, the system prevents unnecessary deflections and ensures human agents only handle interactions that truly require their involvement.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors customer emotional states during VA interactions and adjusts routing decisions accordingly. This feedback loop ensures that deflections to human agents are made only when emotionally charged situations are detected, optimizing the balance between automation and human intervention.
3Reliability
If specialized VAs with emotional intelligence are deployed, then customer experience quality is improved, but device complexity increases
Solution Approach 1:
The patent segments the VA population into standard VAs and specialized VAs with emotional intelligence capabilities. Standard VAs handle routine queries while specialized VAs handle emotionally charged interactions, allowing the system to maintain high automation overall while providing enhanced quality when needed.
Solution Approach 2:
The patent implements a universal routing mechanism that can direct interactions to either standard VAs, specialized VAs, or human agents based on the situation. This multi-functional routing system simplifies management by using a single decision framework rather than requiring separate systems for different interaction types.
Data Source
AI summary
A method and apparatus for managing agent interactions with customers of an enterprise are disclosed. The method includes generating a value representative of an emotional state of a customer engaged in an ongoing interaction with a virtual agent (VA) associated with the enterprise. The value is generated based, at least in part, on one or more inputs provided by the customer during the ongoing interaction. The value is compared with a predefined emotional threshold range to determine whether the emotional state of the customer is a non-neutral state. The ongoing interaction is deflected to one of a human agent and a specialized VA capable of empathetically handling the ongoing interaction if it is determined that the emotional state of the customer is the non-neutral state.