ML-Based Client Disposition Prediction for Adaptive Routing

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 interactions and computational resources, and being rigid in their menu structures, which hampers accuracy and efficiency.

Innovation Solution

An automated client interaction system utilizing a machine learning model to predict client dispositions and generate automated interaction responses, bypassing traditional menu options by extracting client features and analyzing them to provide accurate and context-specific responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional menu structures are used to guide clients, then the system can autonomously interact with clients, but the system routes clients to inaccurate terminal paths and fails to provide needed information

Engineering Contradiction:

Improverouting accuracyVSAvoidflexibility in guiding clients

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent applies dynamics by transitioning from static menu structures to dynamic, context-aware routing. The system adapts its interaction path based on real-time analysis of client features and predicted dispositions, allowing the routing mechanism to flexibly respond to different client needs rather than following predetermined menu paths

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes parameters by using machine learning models to predict client dispositions and adjust routing decisions dynamically. Instead of relying on fixed menu options, the system modifies its behavior based on predicted client intent, transforming the rigid parameter-based menu system into a flexible, prediction-driven routing mechanism

Inventive Principle:

Principle #35Parameter changes

2Loss of time

If conventional systems require excessive interaction with user interfaces to narrow down client contact reasons, then clients can provide information, but computational resources are wasted and interaction times increase

Engineering Contradiction:

Improveinteraction timeVSAvoidcomputational efficiency

Core Design Contradiction:

Loss of timeVSProductivity

Solution Approach 1:

The system performs preliminary action by using machine learning models to predict client dispositions before actual client responses are obtained. This advance prediction allows the system to prepare appropriate routing paths and information in advance, eliminating the need for multiple iterative interactions to narrow down client needs

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent applies skipping by bypassing traditional multi-step menu navigation processes. Instead of requiring clients to iteratively select options through multiple user interface interactions, the system uses predicted dispositions to skip directly to the relevant information or terminal path, dramatically reducing interaction steps and computational overhead

Inventive Principle:

Principle #21Skipping (Rushing through)

3Adaptability or versatility

If conventional systems present rigid menu structures to clients, then clients can select options, but the system inflexibly presents the same menu regardless of interaction context

Engineering Contradiction:

Improveflexibility in presentationVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system changes parameters by dynamically adjusting menu presentation based on predicted client dispositions. Instead of presenting identical rigid menus to all clients, the system modifies menu content, ordering, and style according to client-specific predictions, transforming a static presentation system into an adaptive one

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent applies dynamics by making the menu presentation flexible and context-dependent. The system transitions from static, predetermined menu structures to dynamic presentations that adapt in real-time based on client features and predicted dispositions, allowing the interface to flow naturally with each client's unique needs

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20230196210A1Utilizing machine learning models to predict client dispositions and generate adaptive automated interaction responses

Publication Date: 2023.06.22 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 a predicted client disposition classification and generate an automated interaction response. For example, disclosed systems utilize the machine learning model to generate a predicted client disposition classification and a corresponding disposition classification probability. The disclosed systems can utilize the predicted client disposition classification, the disposition classification probability, and a disposition classification threshold to generate an automated interaction response that references the predicted client disposition classification. Moreover, the disclosed systems can provide the automated interaction response to a client device, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.