Skill Group Weight Scheduling for Contact Center Agent Placement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Contact centers face difficulties in determining the optimal scheduling assignment for agents with multiple skills across multiple queues due to the time-consuming nature of simulations, making it impractical for use with automated scheduling engines that evaluate thousands of schedule assignments.

Innovation Solution

Agents are grouped into skill groups based on their skills, and simulations are performed to calculate skill group weights, which are then used to quickly and efficiently assign agents to queues by evaluating different placements and selecting the best score, thereby reducing the need for real-time simulations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If simulations are performed to determine optimal agent assignments across multiple queues, then scheduling accuracy is improved, but computational time increases making it impractical for automated scheduling engines

Engineering Contradiction:
Improvescheduling accuracyVSAvoidcomputational time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent pre-calculates skill group weights by performing simulations ahead of time to determine how different skill groups contribute to queue performance. These pre-computed weights are then stored and reused during actual scheduling operations, eliminating the need to run simulations repeatedly for each scheduling decision while maintaining accurate agent assignment recommendations

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent segments agents into skill groups based on their skill sets, and pre-computes performance weights for each skill group separately. This segmentation allows the system to break down the complex scheduling problem into manageable components, where each skill group's contribution to different queues is independently evaluated and stored for rapid retrieval during scheduling operations

Inventive Principle:
Principle #1Segmentation

2Reliability

If simulations are run for each agent placement decision, then optimal queue assignment is achieved, but computational resource usage increases significantly

Engineering Contradiction:
Improveoptimal queue assignmentVSAvoidcomputational resource usage
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs simulations in advance to establish skill group weights that quantify each skill group's effectiveness on different queues. These pre-computed weights are stored and reused during scheduling operations, eliminating the need to run resource-intensive simulations for each individual agent placement decision while maintaining reliable queue assignment recommendations

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10931826B1Scheduling agents using skill group weights
Publication Date: 2021.02.23 TALKDESK INC
  • US10931826B1 patent drawing
  • US10931826B1 patent drawing
  • US10931826B1 patent drawing

AI summary

Agents are grouped into skill groups based on the skills of each agent. Simulation are performed for a contact center with multiple queues, where agents from the skill groups are assigned to the queues based on the skills of the skill groups and the skills of the queues. After running the simulations, for each skill group and for each interval, the time each agent spent working using each associated skill is determined, and an average time for each skill is calculated for each interval. The average times are used to create a skill group weight for the skill group for each interval. Later, when the schedule engine is determining an agent placement for one or more intervals, the skill group weights for the intervals are used to calculate a score for the queues based on different agent placements. The placement with the best score (e.g., lowest) is implemented.