Call Routing System Performance Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current call routing systems in contact centers often rely on random or simplistic methods to match callers with agents, leading to inefficient allocation of resources and suboptimal customer interactions, particularly when agents have limited performance data or low sales conversion rates.
Innovation Solution
Implementing a performance-based and pattern matching routing system that assigns agents with limited calls or high error margins an estimated performance characteristic, adjusting as actual data becomes available, and using algorithms to rank agents and match callers based on performance characteristics and demographic data for optimal interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If round-robin routing is used to connect callers to agents, then all agents can be utilized evenly, but the matching between caller and agent is essentially random and suboptimal
Solution Approach 1:
The patent changes the routing parameter from simple round-robin sequential assignment to performance-based matching. Agents are evaluated on multiple parameters including sales conversion rate, customer satisfaction scores, and average handle time. The routing system dynamically selects agents based on these performance parameters rather than fixed sequential rotation, thereby improving matching quality while maintaining agent utilization.
Solution Approach 2:
The patent replaces the mechanical round-robin routing mechanism with an intelligent algorithmic system. Instead of deterministic sequential assignment, the system uses performance data, pattern matching algorithms, and real-time agent availability to make routing decisions. This substitution transforms the routing process from a simple mechanical rotation to an adaptive intelligent system that optimizes both utilization and matching quality.
2Measurement precision
If agents with limited performance data are excluded from routing, then routing accuracy improves, but the number of available agents decreases
Solution Approach 1:
The patent applies preliminary action by establishing performance thresholds and confidence level criteria before routing decisions are made. Agents with insufficient performance data are identified in advance, and the system pre-calculates alternative routing options. This allows the system to maintain high measurement precision by excluding inadequately measured agents while preserving agent availability through proactive planning and alternative selections.
Solution Approach 2:
The patent introduces an intermediary layer between performance data collection and routing decisions. This intermediary layer evaluates whether agents have sufficient performance data through statistical confidence measures. Agents who meet the threshold are included in routing; those who don't are handled through alternative mechanisms such as default routing or prioritized data collection, thereby maintaining both measurement precision and agent availability.
3Reliability
If performance-based routing is implemented to optimize caller-agent matching, then customer satisfaction improves, but system complexity increases
Solution Approach 1:
The patent segments the routing system into distinct functional modules: performance data collection module, pattern matching algorithm module, agent evaluation module, and routing decision module. Each module handles a specific aspect of the complex routing process independently. This segmentation manages system complexity by breaking down the overall complex function into manageable, modular components that can be developed, maintained, and scaled independently.
Solution Approach 2:
The patent implements feedback mechanisms where routing outcomes are continuously monitored and fed back into the performance evaluation system. Customer satisfaction metrics, call outcomes, and interaction quality data are collected and used to refine agent performance profiles. This feedback loop enables the system to self-optimize over time, managing complexity through adaptive learning rather than requiring increasingly complex static rules.
Data Source
AI summary
Systems and methods are disclosed for estimating and assigning agent performance characteristics in a call routing center. Performance characteristics (e.g., sales rate, customer satisfaction, duration of call, etc.) may be assigned to an agent when the agent has made few calls relative to other agents or otherwise has a large error in their measure of one or more performance characteristics used for matching callers to agents (e.g., via a performance based or pattern matching routing method). A method includes identifying agents of a plurality of agents having a number of calls fewer than a predetermined number of calls (or an error in the performance characteristic exceeding a threshold), assigning a performance characteristic to the identified agents (that is different than the agent's actual performance characteristic), and routing a caller to one of the plurality of agents based on the performance characteristics of the plurality of agents.