Automated Root Cause Discovery in Contact Center Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for analyzing conversations in contact centers rely on manual data collection and analysis, which is time-consuming and delays the identification of trends and issues, and fail to categorize conversations with newly identified phrases or concepts.
Innovation Solution
A method and system for automatically discovering and extracting concepts from interactions using a processor to identify elements, detect sequences, generate association rules, and determine root causes without human assistance, enabling the categorization of conversations based on newly identified concepts and trends.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data collection and analysis is used, then human insight and judgment can be applied to complex conversations, but the process is time-consuming and creates long delays in identifying trends and issues
Solution Approach 1:
The patent replaces manual mechanical analysis processes with an automated computer system that uses natural language processing, machine learning models, and pattern recognition algorithms to analyze conversations, thereby eliminating time delays while maintaining analytical quality through sophisticated computational methods
Solution Approach 2:
The system performs self-service analysis by automatically collecting data from multiple sources, processing it through integrated algorithms, generating insights, and presenting recommendations without requiring continuous human intervention, thus reducing time loss while maintaining high measurement precision through automated intelligent processing
2Productivity
If predefined keywords and phrases are used for categorization, then existing categories can be quickly identified, but newly identified phrases or concepts cannot be appropriately categorized
Solution Approach 1:
The patent implements dynamic categorization by using machine learning models that continuously learn from new conversation data, allowing the system to automatically adapt to newly identified phrases and concepts while maintaining the ability to quickly categorize existing patterns through predefined keywords
Solution Approach 2:
The system incorporates feedback mechanisms where newly identified concepts and phrases are fed back into the learning models, enabling the categorization system to evolve and improve its ability to handle both existing and emerging topics while maintaining high productivity through automated processing
3Reliability
If Bayesian networks are used to identify correlations between events, then probabilistic relationships can be modeled, but human input is required to specify network parameters which increases complexity
Solution Approach 1:
The patent implements self-service configuration by using automated algorithms that learn network parameters and causal relationships from data patterns, eliminating the need for manual human specification of Bayesian network parameters while maintaining reliable correlation identification through computationally derived models
Data Source
AI summary
A method for determining a cause of events detected in a plurality of interactions includes: identifying, on a processor, a plurality of elements in the interactions; detecting, on the processor, a plurality of sequences of elements in the interactions; mining, on the processor, the plurality of sequences for generating a set of supported patterns; computing, on the processor, association rules from the set of supported patterns; and returning the computed association rules.