Load-Based Interaction Distribution for Agent Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for remote customer support struggle to efficiently distribute interactions among agents based on load, leading to potential overload and reduced performance.
Innovation Solution
A method and system that utilize processing devices to obtain properties of interactions, determine load, track changes, analyze performance, and identify new interactions for distribution to agents, ensuring optimal load balancing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If interactions are distributed among agents without considering load, then the system can handle more interactions, but agent performance deteriorates due to overload
Solution Approach 1:
The system dynamically adjusts interaction distribution by continuously monitoring agent load levels and performance metrics. The load balancing mechanism adapts in real-time to changing conditions, redistributing interactions from overloaded agents to underutilized agents, thereby maintaining both high productivity and reliable agent performance
Solution Approach 2:
The system implements a feedback loop where agent performance data and load metrics are continuously collected, analyzed, and used to adjust interaction distribution decisions. This closed-loop control ensures that distribution strategies are optimized based on actual agent capacity and performance, preventing overload while maximizing throughput
2Reliability
If agent load is reduced to maintain performance, then agent performance is maintained, but the number of interactions handled decreases
Solution Approach 1:
The system merges the capabilities of multiple agents by intelligently distributing interactions across the agent pool. By combining available capacity across agents and optimizing the distribution algorithm, the system achieves higher overall interaction handling capacity while ensuring no single agent becomes overloaded, thus maintaining performance
3Productivity
If load monitoring and analysis are implemented, then interaction distribution is optimized, but system complexity increases
Solution Approach 1:
The system implements self-service mechanisms where agents automatically report their load status and performance metrics, and the distribution algorithm autonomously makes optimization decisions based on this data. This automated self-management reduces the need for complex external control systems while achieving efficient load balancing
Data Source
AI summary
A method includes obtaining one or more properties of one or more interactions associated with an agent and determining an amount of load for the agent generated by the one or more interactions based on the one or more properties of the one or more interactions. The method also includes tracking one or more changes in the one or more properties or a behavior of the agent and analyzing an effect on agent performance for the agent based on the amount of load for the agent and the one or more changes in the one or more properties or the behavior of the agent. In addition, the method includes identifying a new interaction for distribution to the agent based on analyzing agent performance data for an agent set including the agent, where the agent performance data for the agent set includes the effect on agent performance for the agent.