Customer Journey Score for Intent Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current customer journey management approaches are limited in their ability to accurately infer customer intent and intervene proactively, often relying on small sample sizes, historical data, and human interpretation, which can lead to inaccurate and counterproductive results.
Innovation Solution
A system and method for determining a customer journey score in real-time using a combination of subjective and objective data, allowing for automated interventions based on predefined thresholds, which can be applied at various interaction points throughout the customer's journey.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If customer journey mapping is used to assemble all interactions into one timeline, then a comprehensive view of customer interactions is achieved, but the ability to accurately infer customer intent is limited
Solution Approach 1:
The patent introduces customer journey scores as an intermediary metric that bridges the gap between comprehensive interaction data and accurate intent inference. These scores are calculated based on multiple data sources including survey responses, behavioral events, and contextual information, serving as a mediator that translates raw interaction data into actionable intent indicators.
Solution Approach 2:
The patent combines multiple types of data (subjective survey responses, objective behavioral events, contextual information) to create a composite customer journey score. This composite approach integrates diverse data sources with different characteristics to achieve both comprehensive coverage and precise intent inference, similar to how composite materials combine different substances to achieve superior properties.
2Loss of information
If surveys are sent to customers at critical points in their journey, then attitudinal data is collected, but only a small subset of customers can be polled without frustrating them
Solution Approach 1:
The patent implements a hybrid approach where surveys are sent to a partial subset of customers (those at critical journey points) while complementary data is collected from all customers through automated behavioral tracking. This partial surveying approach avoids customer frustration while maintaining data quality through the supplementation of automated data collection from the full customer base.
Solution Approach 2:
The system uses automated behavioral event collection that operates without customer intervention, allowing the system to self-collect objective data from all customers simultaneously. This self-service data collection complements the survey approach, enabling broad data gathering without imposing additional burden on customers.
3Reliability
If only behavioral events are used without survey data, then objective data is available, but customer attitude and intent cannot be revealed
Solution Approach 1:
The patent merges objective behavioral event data with subjective survey response data into a unified customer journey scoring system. This combination allows the system to leverage the reliability and objectivity of behavioral data while simultaneously capturing customer attitude and intent through survey responses, achieving both goals concurrently.
4Extent of automation
If heuristics based on business assumptions are used to infer customer intent, then some level of automation is achieved, but the accuracy is limited by the simplicity of the heuristics
Solution Approach 1:
The patent transitions from simple heuristic-based automation to a more sophisticated parameter-driven approach using customer journey scores. These scores incorporate multiple parameters including survey responses, behavioral events, and contextual information, allowing for more accurate and nuanced intent inference while maintaining automation. The system dynamically adjusts scoring parameters based on customer segment and journey context.
Data Source
AI summary
Systems and methods of managing customer journeys are implemented using one or more processors in a computing system. Each journey may comprise a succession of interactions at interaction points such as telephone conversations, responses to an interactive voice response “IVR” system and viewing a web page. Customer journey scores are determined for customers at one or more interaction points along the customer journey and the customer journey score is used to determine whether and when an intervention should take place. Models for determining customer journey scores may be created for a set of customers based on one or both of subjective and objective data relating to a subset of the set of customers that have made some or part of the journey, e.g. customers that have responded to polls. An intervention may take place during the journey or after completion of the journey.