Dynamic Interaction Model Generation for Customer Service
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional customer service systems relying on predetermined interaction models are not robust to changes in circumstances, leading to inefficiencies and a negative customer experience, as they often fail to account for unexpected events or evolving assumptions, forcing customers to navigate through automated systems unnecessarily.
Innovation Solution
A computer-implemented method and system that employs a machine learning model to generate a further interaction model based on common root causes identified in customer communications, allowing the system to dynamically adapt by routing communications to either human agents or autonomous interactions, thereby improving responsiveness to changing circumstances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If predetermined interaction models are used to service customer communications, then standardization and efficiency are improved, but adaptability to changing circumstances and unexpected events deteriorates
Solution Approach 1:
The system dynamically adapts interaction models based on real-time analysis of customer communications. When a threshold number of communications share a common root cause, the system automatically generates updated interaction models to handle the new situation, transforming static predetermined models into dynamic adaptive models that evolve with changing circumstances
Solution Approach 2:
The system implements feedback loops where customer communications are continuously analyzed to identify common root causes. This feedback mechanism triggers automatic model generation and updates, allowing the system to learn from past interactions and improve its response to similar future communications, thereby bridging the gap between standardized processing and adaptive response
2Speed
If predetermined interaction models are used, then processing speed is improved, but robustness to changes in assumptions and events deteriorates
Solution Approach 1:
The system performs preliminary analysis of customer communications to identify common root causes before full processing. By detecting patterns early and proactively generating updated interaction models, the system prepares in advance for upcoming communication surges related to specific issues, ensuring both speed and robustness when similar communications arrive
Solution Approach 2:
The system autonomously monitors its own performance and automatically generates updated interaction models based on analyzed communications. This self-service capability allows the system to maintain robustness by continuously adapting to new assumptions and events without external intervention, while preserving processing speed through automated model updates
3Productivity
If autonomous automated systems are used for customer service, then productivity is improved, but customer experience deteriorates due to lack of human interaction
Solution Approach 1:
The system dynamically adjusts the level of automation based on the complexity and type of customer communication. For routine issues with identified root causes, autonomous automated handling maximizes productivity. For complex or novel situations, the system facilitates seamless transitions to human agents, maintaining customer experience quality while preserving overall system productivity
Data Source
AI summary
A computer-implemented method for operating an interactive customer service system may include: receiving interaction information of a plurality of customer communications that were each serviced by a respective interaction unassociated with a predetermined interaction model; and in response to determining, based on the received information, that a threshold number of the communications have a common root cause: generating a further interaction model of a further interaction, based on interaction information of the customer communications having the common root cause, by employing a machine learning model trained, based on (1) sets of previous interaction information with respective common root causes as training data and (2) respective interactions corresponding to the respective common root causes as ground truth, to generate an output interaction model for a given set of interaction information of customer communications having a given common root cause; and configuring the interactive customer service system such that a subsequent customer communication having the common root cause is serviced by the further interaction associated with the further interaction model.