Agent Estimation for Multi-Channel Chat Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ACD systems face difficulties in accurately estimating the number of agents required to service chat messaging when each agent handles multiple chat channels, especially as the number of agents, queue sizes, and chat channels increase, making it challenging to solve the resulting complex systems of equations and simulate multi-channel chat scenarios effectively.
Innovation Solution
The approach simplifies the estimation by analyzing the probabilities of agents and contacts being idle and deriving a formula for handle time inflation due to multiple channels, which is then used to estimate the number of agents needed to achieve a specified service experience using insights from the Erlang B model and other standard Erlang calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If agents handle multiple chat channels simultaneously, then productivity increases, but measurement precision of service quality deteriorates
Solution Approach 1:
The patent applies parameter changes by transforming the multi-channel chat problem into an equivalent single-channel problem through handle time inflation. The key parameter transformation is converting multiple chat channels into a single channel with adjusted (inflated) handle times, allowing standard Erlang models to be applied while maintaining accuracy for multi-channel scenarios.
2Quantity of substance
If the number of agents, queue sizes, and chat channels increase, then system capacity increases, but device complexity increases
Solution Approach 1:
The patent uses copying by creating a simplified equivalent model of the complex multi-channel system. Instead of directly analyzing the complex multi-channel scenario, the invention copies the essential characteristics into a single-channel model with inflated handle times, making the system manageable while preserving the core service quality metrics.
3Ease of operation
If standard Erlang models are used for multi-channel chat, then ease of operation increases, but measurement precision deteriorates
Solution Approach 1:
The patent resolves this contradiction by modifying the handle time parameter to account for multi-channel effects. The inflated handle time incorporates the complexity of managing multiple channels, allowing standard Erlang models to be used while maintaining measurement precision through the adjusted parameter.
Data Source
AI summary
Method and system of estimating a number of agents to service contacts arriving on multiple chat channels in an automatic contact distribution system. In some embodiments, estimated average times that agents and contacts spend, respectively, composing a single chat message and an estimated average time of a chat session are used to derive an inflated handle time for any selected number of chat channels, an effective number of agents is computed for the inflated handle time, and that effective number of agents is divided by the selected number of channels.