Dynamic Contact Center Routing Based on Agent Success Likelihood
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current contact center routing strategies lack the ability to dynamically adjust customer segmentation and business objectives in real-time, leading to suboptimal agent assignment and potential customer dissatisfaction.
Innovation Solution
Implementing a system that detects pending interactions and identifies first and second objectives, determining the likelihood of success for each agent in achieving these objectives, and routing interactions to the agent with a higher likelihood of success, while also dynamically reassessing customer segmentation based on static and dynamic factors to adjust service levels and business objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional routing logic is used to assign interactions to agents, then the routing process is simple and fast, but the customer satisfaction and business outcome achievement are suboptimal
Solution Approach 1:
The routing system dynamically adjusts customer segmentation and business objectives in real-time based on interaction context, agent capabilities, and evolving customer needs. The system moves from static routing rules to dynamic decision-making that adapts during each interaction, improving satisfaction while managing complexity through automated real-time analysis.
Solution Approach 2:
The system changes routing parameters (customer segment, business objectives, agent selection criteria) based on real-time analysis of interaction dynamics. By continuously updating these parameters rather than using fixed routing rules, the system achieves better outcomes without requiring overly complex manual intervention.
2Productivity
If customer segmentation is adjusted dynamically in real-time, then the service level and business objective achievement improve, but the processing time and system complexity increase
Solution Approach 1:
The system performs preliminary analysis of customer segmentation and business objectives at the start of each interaction, preparing routing decisions in advance. By pre-assessing customer segments and potential business outcomes before full interaction details are known, the system reduces real-time processing delays while maintaining dynamic adaptability.
Solution Approach 2:
The system uses real-time feedback from interaction dynamics to continuously refine customer segmentation and business objective selection. This feedback loop enables the system to make rapid, informed decisions without excessive processing time, as it learns and adapts during the interaction rather than requiring complete analysis beforehand.
3Reliability
If interactions are routed based on multiple objectives and likelihood of success analysis, then the agent assignment quality improves, but the routing decision time increases
Solution Approach 1:
The system dynamically changes routing parameters (number of objectives considered, analysis depth, agent selection criteria) based on interaction priority and context. For high-value interactions, it performs comprehensive multi-objective analysis; for routine interactions, it uses streamlined criteria, balancing quality and speed adaptively.
Solution Approach 2:
The system applies partial analysis for routine interactions and excessive (comprehensive) analysis for high-priority interactions. By adjusting the level of analysis based on interaction characteristics, it maintains high assignment quality for critical cases while keeping routine routing fast and efficient.
Data Source
AI summary
A system and method for enhanced interaction processing in a contact center that includes routing interactions based on adaptable business objectives. A processor detects a pending interaction with a customer. The processor identifies first and second objectives of the contact center in response to detecting the pending interaction, where the first objective is identified as more important to the contact center than the second objective. The processor identifies a first agent for handling the first objective, and determines a likelihood of success of the first agent in achieving the first objective. The processor identifies a second agent for handling the second objective, and determines a likelihood of success of the second agent in achieving the second objective. In the event that the likelihood of success in achieving the second objective by the second agent is higher than the likelihood of success of achieving the first objective by the first agent, the processor transmits instructions to route the pending interaction to the second agent. The processor also prompts the second agent to pursue the second objective.