Automatic Agent Training System for Call Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional call center training methods are not customizable to individual agents' needs, as mock calls are pre-determined and do not account for unique training requirements.
Innovation Solution
A system and method that automatically selects training scenarios for call center agents based on their attributes, using a proctor portal, automatic call director, and database to connect agents with suitable proctors for tailored training sessions over a communications network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If pre-determined mock calls are used for training, then training structure is simplified and easier to manage, but training effectiveness is reduced because it cannot address individual agent needs
Solution Approach 1:
The training system dynamically adapts mock call scenarios based on individual agent attributes, performance history, and skill gaps. The system automatically adjusts training content, difficulty level, and scenario selection to match each agent's specific needs, transforming static pre-determined calls into dynamic personalized training experiences.
Solution Approach 2:
The system changes multiple parameters including scenario selection, call complexity, evaluation criteria, and training objectives based on agent attributes. By varying these parameters automatically, the system maintains both management efficiency and training effectiveness for each individual agent.
2Reliability
If personalized training scenarios are created for each agent, then training effectiveness is improved, but system complexity increases
Solution Approach 1:
The system automatically selects and configures appropriate mock call scenarios based on agent attributes without requiring manual intervention. The automated selection process, performance tracking, and scenario adaptation occur autonomously, reducing the operational complexity despite the personalized nature of training.
Solution Approach 2:
A single unified system performs multiple functions including agent assessment, scenario selection, call management, performance tracking, and adaptive scenario generation. This multi-functional approach consolidates complexity into one system rather than requiring separate systems for each training function.
3Adaptability or versatility
If manual staging of mock calls is used, then training can be customized to some extent, but time consumption and resource requirements increase
Solution Approach 1:
The system replaces manual staging processes with automated computer-based selection and management of mock call scenarios. Algorithms automatically match agents with appropriate training scenarios based on their attributes, eliminating the need for manual coordination while maintaining high levels of customization.
Solution Approach 2:
An automated intermediary system serves as the bridge between agent attributes and appropriate training scenarios. This intermediary automatically processes agent data, selects suitable scenarios, and manages the training workflow, replacing manual intervention while preserving training customization.
Data Source
AI summary
An exemplary method for training call center agents over a communications network using automatically selected training scenarios comprises the steps of obtaining confirmations of availability of a plurality of call center agents, determining a proctor based on proctor attributes stored in a database, selecting an agent from the plurality of agents, based on agent attributes stored in the database, to be trained by the proctor, automatically determining a training scenario based on the selected agent's attributes, and enabling the proctor and the agent to engage in the training scenario.