Emotional State Routing for Support Agents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users interacting with software applications often require assistance, but existing systems struggle to route them to the most suitable support agents based on their emotional states, leading to inconsistent customer experiences due to variations in agent skills and user needs.
Innovation Solution
A method that utilizes paralinguistic features from user audio input to predict emotional states and route users to support agents based on specific conditions, using a predictive model to select agents with matching attributes and expertise, ensuring timely and effective assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional call routing based on agent availability and skills is used, then calls can be routed to available agents, but customer satisfaction varies due to mismatch between user emotional needs and agent capabilities
Solution Approach 1:
The system performs preliminary analysis of paralinguistic features (tone, pitch, speech rate) before routing the call to determine the user's emotional state in advance. This allows the routing system to proactively match users with emotionally compatible agents before the interaction begins, ensuring consistent customer satisfaction without requiring complex real-time adjustments during calls
Solution Approach 2:
The patent introduces an intermediary emotional compatibility assessment layer between the user and agent. This intermediary system analyzes paralinguistic features and agent profiles to determine compatibility, acting as a mediator that enhances reliability without significantly increasing overall system complexity
2Adaptability or versatility
If support agents with diverse skills and personalities are deployed, then various customer needs can be addressed, but routing accuracy decreases due to difficulty in matching specific user needs with appropriate agents
Solution Approach 1:
The system changes the parameters used for routing from traditional skills-based metrics to include paralinguistic emotional compatibility parameters. By analyzing tone, pitch, and speech rate characteristics, the system creates a new dimension for matching that improves routing accuracy while preserving agent skill diversity. The predictive model weights multiple parameters including emotional state, agent personality traits, and technical expertise to achieve precise matching
3Ease of operation
If emotional state analysis is added to the routing system, then user needs can be better understood, but system complexity increases due to additional processing requirements
Solution Approach 1:
The system extracts only the most relevant paralinguistic features (tone, pitch, speech rate) from audio input rather than analyzing all possible audio characteristics. This extraction approach enables emotional state detection while minimizing processing complexity by focusing only on the critical features needed for effective routing decisions
Solution Approach 2:
The patent replaces complex manual assessment of user needs with automated paralinguistic analysis using machine learning models. This substitution reduces the need for extensive human judgment and manual routing processes, improving ease of operation while the automation actually reduces operational complexity despite adding computational elements
4Device complexity
If all users are routed through standard queues, then routing is simple to manage, but wait times increase for users with urgent or emotionally charged issues
Solution Approach 1:
The system performs preliminary emotional state assessment and priority classification before queuing, allowing urgent or emotionally charged issues to be identified and routed to appropriate priority queues in advance. This preliminary action reduces wait times for critical cases while maintaining simple queue management through predefined priority levels based on emotional compatibility and issue urgency
Data Source
AI summary
Embodiments presented herein provide techniques for inferring the current emotional state of a user based on paralinguistic features derived from audio input from that user. If the emotional state meets triggering conditions, the system provides the user with a prompt which allows the user to connect with a support agent. If the user accepts, the system selects a support agent for the user based on the predicted emotional state and on attributes of the support agent found in an agent profile. The system can also determine a priority level for the user based on the score and based on a profile of the user and determine where to place the user in a queue for the support agent.