Dynamic Adaptive Routing for Deferrable Contact Center Work
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact centers face challenges in efficiently managing deferrable work, such as email responses, due to factors like agent availability, priority scoring, and backlog management, which can lead to unmanageable email backlogs and inefficient handling of urgent emails.
Innovation Solution
A computer-implemented method that utilizes natural language processing (NLP) models to prioritize deferrable work interactions by generating NLP scores and priority scores, which are then used to optimize the workflow by assigning tasks to suitable agents based on availability and workload forecasts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If deferrable work is managed without dynamic prioritization, then system complexity is reduced, but email backlogs become unmanageable and urgent emails are not handled efficiently
Solution Approach 1:
The system dynamically changes the priority parameter of deferrable work items based on multiple factors including customer history, issue type, and current workload. This allows urgent emails to be automatically reprioritized without manual intervention, resolving the contradiction between handling efficiency and system complexity by using automated parameter adjustment rather than complex manual routing rules
Solution Approach 2:
The system performs preliminary prioritization and routing decisions before work items are fully processed. By pre-calculating priority scores and assigning work to appropriate agents in advance, the system prevents backlog accumulation without requiring complex real-time decision-making, thus improving productivity while maintaining manageable system complexity
2Measurement precision
If multiple NLP models and optimization processes are used to prioritize deferrable work, then routing precision is improved, but device complexity increases
Solution Approach 1:
The prioritization system is segmented into multiple specialized NLP models, each handling specific aspects such as sentiment analysis, urgency detection, and customer value assessment. This modular approach improves measurement precision by dedicating specific models to specific tasks while managing complexity through clear separation of functions and independent model deployment
3Productivity
If deferrable work is assigned without considering agent availability forecasts, then assignment speed is increased, but agent utilization becomes inefficient and backlogs grow
Solution Approach 1:
The system performs preliminary analysis of agent availability forecasts and workload predictions before assigning deferrable work. By pre-identifying suitable agents and optimal assignment timing, the system achieves efficient agent utilization without requiring complex real-time negotiations, thus improving productivity while minimizing time loss through advance planning
Data Source
AI summary
A method for optimizing a workflow of deferrable work interactions in a contact center that includes: providing a NLP models and a priority model; using text derived from received deferrable working interactions as inputs to the NLP models to generate the NLP scores; using the LP scores as inputs to the priority model to generate the priority score; identifying candidate agents of the agents for handling the deferrable work interactions; receiving an inbound work forecast; receiving agent work schedule data; using an optimization process to generate an optimized workflow for the deferrable work interactions, where the optimized workflow includes assignments in which an agent from the candidate agents is selected to handle the deferrable work interaction and a target timeframe for handling is scheduled; and routing the deferrable work interactions in accordance with the assignments of the optimized workflow.