Contact Center Workload Rebalancing Across Locations and Shifts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing contact center systems require manual and time-consuming processes to rebalance workload across multiple locations in response to infrastructure disruptions, failing to align with Business Continuity Plans effectively.
Innovation Solution
A computerized method and system for automatically distributing workload from a source location to target locations in a contact center using a Workforce Management application, which includes receiving rebalancing requests, parsing workload information, marking overstaffed intervals, and generating new schedules based on net-staffing calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual allocation and evaluation of workload is performed via WFM application, then workload can be rebalanced across locations, but the process is time-consuming and delays business operations
Solution Approach 1:
The system enables automatic self-service workload distribution by using machine learning models to forecast contact volumes and optimize agent schedules without manual intervention. The automated schedule optimization engine continuously adjusts staffing plans based on real-time data, eliminating the need for manual workload evaluation and redistribution while maintaining accuracy.
Solution Approach 2:
The patent replaces manual mechanical processes with automated computational systems. Machine learning algorithms substitute human analysts for forecasting workload, and automated optimization engines replace manual schedule adjustment processes. This substitution dramatically reduces rebalancing time while maintaining or improving accuracy through data-driven decisions.
2Adaptability or versatility
If forecasts and schedules are re-generated manually to balance workload, then workload distribution can be adjusted, but the complexity of multiple steps increases operational difficulty
Solution Approach 1:
The patent merges multiple separate manual processes into a single automated workflow. Forecasting, schedule optimization, and workload distribution are combined into one integrated system that executes simultaneously. This consolidation maintains the flexibility needed for adaptable workload distribution while eliminating the complexity of coordinating multiple manual steps.
Solution Approach 2:
The automated schedule optimization engine serves multiple functions: it forecasts contact volumes, optimizes agent schedules, distributes workload across locations, and adjusts to changing conditions. This multi-functional system replaces several specialized manual processes, reducing overall complexity while maintaining or enhancing adaptability.
3Manufacturing precision
If manual evaluation of target SU capacity is performed, then realistic workload allocation can be achieved, but the process requires significant manual effort and resources
Solution Approach 1:
The system replaces manual evaluation processes with automated machine learning models that analyze historical data, current conditions, and target SU capacities to determine optimal workload allocation. This substitution maintains high precision in allocation decisions while dramatically increasing operational speed and reducing manual resource requirements.
Solution Approach 2:
The patent introduces an automated optimization engine as an intermediary between workload requirements and target SU capacities. This intermediary systematically evaluates capacity constraints and optimizes allocation based on multiple parameters, achieving precision that exceeds manual evaluation while operating at automated speeds with minimal human intervention.
Data Source
AI summary
A computerized-method for distributing workload of a working-shift of a source-location to working-shifts in target-locations, via a WFM-application in a multiple-locations contact center. The computerized-method comprising: (i) receiving a rebalancing-request and workload-information of the working-shift of the source-location; (ii) parsing the workload-information to extract affected-SUs, target-SUs and critical-skills; (iii) for each parallel time-interval in a parallel working-shift of each target-location and for each critical-skill: retrieving staffing-plans of the target-SUs, and marking the parallel time-interval as overstaffed for the critical-skill based on a net-staffing calculation; (iv) operating agents-distribution for each parallel time-interval and for each critical-skill based on the parallel time-intervals marked as overstaffed; and (v) configuring WFM-application to: update staffing-plans of parallel working-shift of each target-location, based on the operated agents-distribution; generate new-schedules for agents in the target-SUs based on the updated staffing plans of parallel working-shift of each target-location; and remove existing schedules of the affected-SUs of parallel working-shift.