Dynamic Contact Management System for Customer Service Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional customer service systems face inefficiencies in assigning customer contacts to appropriate agents and authorizing actions due to static and manual processes, leading to suboptimal resolution times and customer experiences.
Innovation Solution
A dynamic contact management system that uses machine learning models to generate scores based on agent and context data, empowering agents to perform actions beyond their default authorization levels for effective contact resolution without manual supervision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If static authorization levels and manual supervision are used, then security and control are maintained, but contact resolution time and efficiency deteriorate
Solution Approach 1:
The patent implements dynamic authorization levels that automatically adjust based on real-time agent performance metrics, contact complexity, and contextual factors. Instead of static authorization tiers, the system continuously evaluates agent capability and grants temporary elevated authorization when appropriate, eliminating the need for manual supervision while maintaining security through automated risk assessment.
Solution Approach 2:
The system changes the authorization parameter from fixed to variable by introducing a dynamic scoring model that evaluates multiple factors including agent performance history, contact type, customer risk profile, and issue complexity. This parameter transformation enables automated decision-making that adapts to each specific situation, resolving contacts faster without compromising control.
2Ease of operation
If hierarchical authorization structures are maintained, then control and security are preserved, but agent autonomy and resolution speed deteriorate
Solution Approach 1:
The patent enables agents to self-authorize for elevated actions by automatically presenting their case to an AI evaluation system that assesses their capability and the contact's requirements. The system serves itself by making automated authorization decisions without human intervention, granting agents autonomy while maintaining security through objective, data-driven evaluation of agent performance and contact context.
Solution Approach 2:
The manual hierarchical authorization system is replaced with an automated machine learning-based evaluation system. Instead of human supervisors reviewing and approving requests, an AI model processes agent performance data, contact information, and risk factors to make real-time authorization decisions, eliminating the mechanical complexity of manual approval workflows.
3Reliability
If manual supervisor approval is required for elevated actions, then security is maintained, but contact resolution time increases
Solution Approach 1:
The system implements continuous feedback loops where agent actions, contact outcomes, and customer satisfaction metrics are fed back into the machine learning model. This feedback mechanism allows the system to learn from past decisions and improve its authorization accuracy over time, maintaining security through validated decision-making while enabling faster automated approvals as the system gains confidence in its predictions.
Solution Approach 2:
The system performs preliminary evaluation of agent capability and contact requirements before authorization is needed. By pre-assessing agent performance metrics and contact complexity, the system prepares authorization decisions in advance, allowing for rapid approval when conditions are favorable without requiring real-time supervisor intervention, thus maintaining security while accelerating resolution.
Data Source
AI summary
A dynamic contact management system is provided for managing customer contacts in a customer service center and dynamically determining which actions to take—or which actions are permitted to be taken—with respect to customer contacts. The system can process data regarding attributes of an agent or group of agents, and generate scores to use in making the dynamic determinations. Based on the scores, the system can temporarily authorize agents to perform actions that they would not otherwise be authorized to perform, assign customer contacts to agents who are most likely to resolve a contact in a satisfactory manner, generate dynamic comparisons of agents, and the like.