ML-Based Intent Classification for Automated Text Threads

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional automated client interaction systems are inaccurate, inefficient, and inflexible, often routing clients to incorrect resources, requiring excessive user interactions, and being rigid in their menu structures.

Innovation Solution

The system utilizes machine learning models to predict client intent classifications and generate personalized digital text reply options, extracting client features and analyzing them to provide accurate and context-specific responses within automated interactive digital text threads.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional systems use predefined menu structures to guide clients, then the system structure is simple and easy to implement, but the accuracy of routing clients to pertinent resources deteriorates

Engineering Contradiction:

Improveaccuracy of routing clientsVSAvoidsystem structure complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical predefined menu structure with a machine learning-based intent classification system. The ML model analyzes client messages and automatically determines intent, substituting the rigid mechanical menu navigation with an intelligent system that adapts to different client needs and communication styles, thereby improving routing accuracy without requiring complex manual menu configuration.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the parameter of client interaction from fixed menu selections to natural language processing. By transforming client inputs from structured menu choices to unstructured messages and using ML to classify intent, the system achieves more accurate routing while maintaining operational simplicity through automated intelligence rather than complex structured menus.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If conventional systems use predefined menu options, then the system is easy to operate, but the number of user interactions required increases

Engineering Contradiction:

Improveinteraction efficiencyVSAvoiduser interaction burden

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The machine learning system performs self-service by automatically analyzing client messages and determining intent without requiring clients to navigate predefined menus. The system serves itself by processing natural language inputs, classifying intentions, and routing to appropriate resources, thereby reducing the interaction burden on users while improving productivity through automated intelligence.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by pre-processing and analyzing client messages to determine intent before routing. The ML model proactively identifies the purpose of client communications and prepares appropriate responses or resource routing in advance, eliminating the need for clients to systematically navigate through multiple menu levels and reducing the number of interactions required.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If conventional systems use rigid menu structures, then the system implementation is straightforward, but the flexibility to adapt to different client contexts deteriorates

Engineering Contradiction:

Improveflexibility in client interactionVSAvoidsystem implementation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent substitutes the rigid mechanical menu structure with a flexible machine learning-based intent classification system. This replacement enables the system to adapt to different client contexts, communication styles, and resource needs automatically, providing versatility without requiring complex manual configuration or rigid structural implementation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The machine learning system provides universality by handling diverse client intents and communication patterns through a single adaptable model. Rather than requiring separate menu structures for different client types or contexts, the ML model universally processes various inputs and routes them appropriately, achieving flexibility without proportionally increasing system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250202845A1Utilizing machine learning models to generate interactive digital text threads with personalized digital text reply options

Publication Date: 2025.06.19 CHIME FINANCIAL INC

AI summary

The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a machine learning model to determine predicted client intent classifications and 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 intent classifications and corresponding intent classification probabilities. The disclosed systems utilize the predicted client disposition classifications and the disposition classification 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.