Caller-Agent Assignment Using ML Scoring and Conflict Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Call centers face inefficiencies in routing high volumes of calls to available agents, necessitating a more effective and streamlined solution for assigning callers to agents.
Innovation Solution
A computer-implemented system using a machine learning model and optimization algorithm to score caller-agent combinations based on demographic information and agent performance data, executing multiple iterations to avoid conflicting assignments and optimize call routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional call routing methods are used to assign callers to agents, then the routing process is simple to implement, but the call center efficiency and effectiveness deteriorate due to suboptimal caller-agent matching
Solution Approach 1:
The system performs preliminary actions by pre-calculating compatibility scores for all caller-agent combinations using machine learning models before actual call routing occurs. This allows the system to have optimization results ready in advance, improving call center efficiency without adding complexity during the actual routing moment.
Solution Approach 2:
The patent replaces traditional mechanical routing rules with intelligent machine learning-based scoring systems. The machine learning model automatically analyzes multiple factors including caller demographics, agent skills, and historical performance data to determine optimal assignments, substituting simple rule-based mechanics with adaptive intelligent systems.
2Reliability
If multiple iterations of optimization algorithm are executed to avoid concurrent agent assignments, then the caller-agent matching accuracy is improved, but the computational time and processing complexity increase
Solution Approach 1:
The system executes multiple iterations of the optimization algorithm in advance, before actual call assignments are needed. This preliminary optimization ensures that when real-time routing occurs, the system already has pre-computed, conflict-free assignments ready, eliminating both assignment conflicts and real-time processing delays.
Solution Approach 2:
The optimization system dynamically adjusts its processing schedule based on call center conditions. When call volumes are low, the system performs more extensive optimization iterations to improve matching quality. When call volumes increase, the system relies on previously computed optimizations, dynamically balancing between optimization thoroughness and response time.
Data Source
AI summary
Systems and methods for intelligent caller to agent assignment receive requests to establish a voice call session for a plurality of callers, identify demographic information, score a caller-agent combination to generate a plurality of scores, determine the caller-agent combination with a highest score of the plurality of scores, and assign a first agent of the caller-agent combination with the highest score to the voice call session for a caller, and when a first agent is concurrently assigned to another voice call session for another caller, execute one or more iterations until (i) the first agent is assigned to one of the voice call session for the caller and the another voice call session for the another caller and (ii) a second agent of another caller-agent combination is assigned to the other of the voice call session for the caller and the another voice call session for the another caller.