Intelligent Task Routing System for Contact Center Workforce Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing contact center systems face inefficiencies in routing tasks to multiple agents, as they often fail to accurately match tasks with agents based on relevant skills and availability, leading to suboptimal task processing and resource utilization.
Innovation Solution
A system comprising servers that analyze task content, assign pre-defined classifications, and utilize workforce management data to identify suitable agents, applying routing strategies to route tasks effectively, with refinements including periodic re-assignment and statistical data analysis for performance forecasting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If tasks are assigned to agents based on traditional routing methods, then the routing process is simple, but task processing efficiency and resource utilization are suboptimal
Solution Approach 1:
The system performs preliminary actions by analyzing task content before assignment and pre-matching agents based on skills and availability. Task objects are analyzed to determine classifications and relevant agent attributes are pre-identified, enabling efficient routing decisions without real-time complex computations during task assignment.
Solution Approach 2:
The patent introduces intermediary components including a task object structure with metadata, a workforce management data structure with agent attributes, and a routing strategy structure. These intermediaries mediate between task analysis and agent selection, simplifying the overall routing process while improving efficiency through structured data handling.
2Measurement precision
If agents are matched based on basic availability, then the assignment process is fast, but skill matching accuracy is insufficient
Solution Approach 1:
The system pre-analyzes task content to determine classifications and pre-identifies relevant agent attributes before the actual assignment process. This preliminary action enables accurate skill matching without requiring time-consuming real-time analysis during task distribution.
Solution Approach 2:
The patent changes parameters by introducing detailed classification metadata for tasks and corresponding attribute structures for agents. By transforming raw task content into structured classifications and matching them with structured agent attributes, the system achieves precise skill matching through parameter transformation rather than complex real-time computation.
3Reliability
If tasks are routed without continuous monitoring, then the system operation is simple, but workload imbalances and performance issues are not addressed
Solution Approach 1:
The system implements feedback mechanisms where task objects are analyzed to determine if performance criteria will be met, and agents are selected based on predicted performance. This feedback loop ensures reliable performance by continuously monitoring and adjusting task assignments based on real-time agent status and task requirements.
Solution Approach 2:
The patent introduces dynamic elements where routing decisions are adjusted based on changing agent availability, skill levels, and task characteristics. The system dynamically adapts to real-time conditions rather than using static routing rules, improving reliability through flexible, condition-based task distribution.
4Productivity
If multiple re-assignment cycles are implemented, then task processing optimization is improved, but system complexity and processing overhead increase
Solution Approach 1:
The system performs preliminary analysis of task content and agent attributes before each re-assignment cycle, preparing all necessary data structures and classifications in advance. This preliminary action reduces the computational overhead during actual re-assignment operations, enabling multiple optimization cycles without proportionally increasing system complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods for routing task objects to multiple agents, that involve analyzing content of each task object in an input buffer to determine a classification relevant to the content of the task object that is added to task object metadata, which is placed in a second buffer. Objects in the second buffer are analyzed and the classification in the object metadata used to search workforce management data representing agent characteristics to identify agents who match the classification. A routing strategy is applied to the object to select an agent and the object is routed to the agent's workbin. Another aspect involves organizing workbin tasks objects by priority, according to recent system conditions excluding objects that cannot presently be processed based on a workflow strategy or status data, and presenting remaining objects based on order of priority, or re-arranging objects between workbins based on recent status info.