Interactive Text Threads With ML Intent Routing And Escalation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional automated client interaction systems are inaccurate, inefficient, and inflexible, often routing clients to incorrect information, requiring excessive interactions, and relying on rigid menu structures that do not adapt to the context of the interaction.

Innovation Solution

Utilizing machine learning models to predict client intent classifications and escalation classes, generating personalized digital text reply options that dynamically guide clients to pertinent resources, reducing the need for agent escalations through self-service workflows.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional systems utilize predefined menu structures to guide clients, then the system maintains operational simplicity, but the system loses accuracy in routing clients to pertinent resources

Engineering Contradiction:

Improverouting accuracyVSAvoidsystem structure complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system transitions from static predefined menu structures to dynamic, context-aware routing. Machine learning models analyze client features, interaction history, and current context to dynamically generate personalized reply options, allowing the system to adapt its behavior to each specific client situation rather than following rigid predetermined paths

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameters used for routing decisions from simple menu selection to multiple client features including interaction history, client profile data, and contextual information. This parameter expansion enables more accurate routing by considering multiple factors simultaneously rather than relying on a single menu choice

Inventive Principle:

Principle #35Parameter changes

2Loss of time

If conventional systems require numerous user input interactions to narrow down client intent, then the system maintains thoroughness in understanding client needs, but the system increases interaction time and computational burden

Engineering Contradiction:

Improveinteraction timeVSAvoidclient intent understanding

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system performs preliminary analysis of client features and interaction patterns before the client needs to provide detailed input. By pre-processing available data and generating predicted intent classifications, the system can present targeted reply options that guide clients efficiently to their destination without requiring them to navigate through multiple sequential questions

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from predicted intent classifications and interaction patterns to continuously refine its routing decisions. By analyzing client responses and adjusting subsequent reply options based on predicted escalation classes and intent, the system can converge on accurate client needs more quickly, reducing the number of interactions required while maintaining reliability

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If conventional systems use rigid menu structures regardless of interaction context, then the system maintains operational consistency, but the system loses flexibility in adapting to different client situations

Engineering Contradiction:

Improvecontext adaptation flexibilityVSAvoidsystem operation simplicity

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system applies different routing strategies and reply options tailored to specific client contexts rather than using a uniform approach for all clients. By analyzing client features and interaction patterns, the system generates personalized reply options that are locally optimized for each client's specific situation, needs, and preferences

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system enables clients to receive personalized guidance without requiring complex manual configuration or agent intervention. By automatically analyzing client features and generating context-appropriate reply options, the system serves itself in adapting to different client situations, maintaining operational simplicity while achieving high flexibility

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20250220117A1Utilizing machine learning models to generate interactive digital text threads with personalized agent escalation digital text reply options

Publication Date: 2025.07.03 CHIME FINANCIAL INC

AI summary

The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to determine predicted client intent classifications and/or client-agent escalation classes to generate personalized digital text reply options within an automated interactive digital text thread. For example, disclosed systems utilize the machine learning model to generate predicted client-agent escalation classes and corresponding probabilities. The disclosed systems utilize the predicted client-agent escalation classifications and the escalation class probabilities to generate personalized digital text reply options. Moreover, the disclosed systems can provide personalized digital text reply options to a client device within an automated interactive digital text thread, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.