Customer Experience Optimization via Event Sequence Indexing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for managing customer experiences are time-consuming, not specific enough, and lack proper analysis tools, making it difficult for organizations to optimize and predict customer interactions, leading to sub-optimal paths and increased churn.
Innovation Solution
A computer-implemented system that creates and analyzes a 'customer journey' using an 'event sequence index' and 'customer experience data structure,' enabling real-time pattern matching and intervention through a 'Distributed Query Language' and 'pattern-matching' algorithms to redirect customer experiences proactively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated or depersonalized means are used to provide services to large numbers of customers, then service efficiency and scalability are improved, but customer satisfaction and experience quality deteriorate
Solution Approach 1:
The patent segments the customer experience into discrete events and interactions, creating an event sequence index that divides the overall service journey into analyzable components. This allows automated systems to track and analyze specific interaction points while maintaining efficiency at scale.
Solution Approach 2:
The system implements continuous feedback loops by monitoring customer interactions in real-time, analyzing event sequences, and providing feedback to both the automated service system and human agents. This enables the system to adapt and improve customer experience while maintaining automated efficiency.
2Measurement precision
If detailed tracking and analysis of customer interactions are implemented, then customer experience optimization is improved, but system complexity and data processing requirements worsen
Solution Approach 1:
The patent extracts only the essential elements of customer interactions by creating an event sequence index that captures key events and metadata. This extraction approach provides sufficient analysis accuracy without requiring complete detailed tracking of every interaction element, thereby reducing system complexity.
Solution Approach 2:
The system changes parameters by transforming raw interaction data into standardized event sequences with specific metadata fields. This parameter transformation enables efficient analysis and pattern recognition while simplifying the underlying data structure and reducing processing complexity.
3Reliability
If real-time monitoring and intervention capabilities are implemented, then customer churn reduction is improved, but processing time and computational resources worsen
Solution Approach 1:
The patent implements preliminary action by establishing event sequence patterns and thresholds in advance that automatically trigger interventions. This pre-configured approach enables real-time churn prevention without requiring complex real-time analysis decisions, thereby reducing processing time while maintaining effectiveness.
Solution Approach 2:
The system provides self-service capabilities through automated pattern recognition and intervention triggering. The event sequence index automatically identifies at-risk customer experiences and initiates appropriate responses without requiring continuous human oversight, reducing computational overhead while maintaining churn reduction effectiveness.
Data Source
AI summary
A system and a process using that system is provided for creating, analyzing and optimizing a customer journey. The process includes real-time creation and continuing analysis of an “Event Sequence Index,” (ESI) corresponding to a time-stamped labeled set of data points representing cumulative events along the customer journey. The data points are further associated with channels, which are modes of interaction between the customer and the organization, and mapped into a linked directed graph which is amenable to analysis through a recursive pattern matching method, such as a non-deterministic finite automaton, employing DQL (Distributed Query Language). Selected portions of these graphs can be identified, either statistically or causally, as signatures of highly satisfactory or unsatisfactory outcomes and may be stored in memory as real-time predictors of the course of a present customer experience and to suggest statistically feasible and effective interventions. Concurrently, the signatures may be used as feedback to an organization for improvements in customer relations.