AI Intent Prediction for Intelligent IVR Call Routing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current IVR systems lack the ability to understand customer intent and route calls intelligently, leading to increased customer frustration and dissatisfaction due to inefficient call routing based solely on rules-based methodologies.

Innovation Solution

The system predicts entities and intents from captured speech using automated speech recognition and machine learning models, such as named entity recognition and support vector machines, to determine the next best action for call routing, ensuring calls are directed to the appropriate agent or IVR menu.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If rules-based IVR routing is used, then system simplicity is maintained, but call routing efficiency and customer satisfaction deteriorate

Engineering Contradiction:

ImproveIVR system structureVSAvoidcall routing efficiency

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The patent replaces the traditional rules-based mechanical routing system with an AI-powered semantic understanding system. Natural language processing and machine learning models analyze customer intent and speech patterns to dynamically determine call routing, substituting rigid rule-based mechanics with intelligent adaptive processing that improves routing efficiency while maintaining system manageability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the routing parameters from fixed rule-based criteria to dynamic semantic parameters including customer intent, speech context, and entity recognition results. This allows the IVR system to adapt routing decisions based on real-time analysis of customer needs rather than predetermined rule sets, significantly improving call routing efficiency

Inventive Principle:

Principle #35Parameter changes

2Ease of manufacture

If rules-based IVR routing is used, then implementation ease is maintained, but customer satisfaction and call resolution speed worsen

Engineering Contradiction:

Improvesystem implementationVSAvoidcustomer wait time

Core Design Contradiction:

Ease of manufactureVSLoss of time

Solution Approach 1:

The system performs preliminary semantic analysis of customer speech during the initial interaction phases, identifying intent and key entities before the call is fully routed. This preliminary processing enables faster, more accurate routing decisions that reduce customer wait time while the system is still gathering contextual information

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an AI language understanding intermediary layer between the customer and the routing system. This intermediary analyzes speech content, extracts intent, and translates natural language into routing parameters, mediating between customer expression and system action to accelerate call resolution while maintaining implementation feasibility

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If generic IVR menus are used, then system coverage is maximized, but personalization and customer experience deteriorate

Engineering Contradiction:

ImproveIVR menu coverageVSAvoidcustomer interaction experience

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent segments the generic IVR menu structure into dynamically generated personalized pathways based on real-time analysis of customer speech and intent. Instead of forcing all customers through the same generic menu hierarchy, the system creates customized interaction sequences tailored to each customer's specific needs while maintaining coverage of all possible service topics

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system transforms static generic menus into dynamic adaptive conversation flows that evolve based on customer responses and identified intent. The IVR structure dynamically adjusts its path, options, and depth based on real-time semantic analysis, providing personalized experiences while maintaining comprehensive service coverage across different customer scenarios

Inventive Principle:

Principle #15Dynamics

4Measurement precision

If AI-based entity and intent prediction is implemented, then call routing accuracy improves, but system complexity and processing requirements worsen

Engineering Contradiction:

Improveintent detection accuracyVSAvoidprocessing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies partial AI processing to speech segments based on their relevance to routing decisions. Not all speech content requires full NLP analysis - the system selectively applies entity recognition and intent classification to critical segments, achieving high routing accuracy while reducing overall processing complexity and computational requirements

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12183344B1Systems and methods for determining a next action based on entities and intents

Publication Date: 2024.12.31 WELLS FARGO BANK NA

AI summary

Systems, apparatuses, methods, and computer program products are disclosed for predicting an entity and intent based on captured speech. An example method includes capturing speech and converting the speech to text. The example method further includes causing generation of one or more entities and one or more intents based on the speech and the text. The example method further includes determining a next action based on each of the one or more entities and each of the one or more intents.