Telephonic NLU Routing With Real-Time Agent Guidance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing telecommunication systems face strain due to heavy network traffic and inefficient call handling, leading to long wait times and misrouting of customers in call centers, exacerbated by inadequate resources and interactive voice response systems.

Innovation Solution

A computing system with a natural language understanding model that iteratively trains to predict topics, context, and intents from conversational inputs, providing real-time guidance to agents via a unified desktop interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple call center divisions are created to handle different types of calls, then customer service coverage is improved, but network traffic strain increases due to customer transfers and wait times

Engineering Contradiction:

Improvecustomer service coverageVSAvoidnetwork traffic strain

Core Design Contradiction:

Adaptability or versatilityVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis of customer needs through natural language processing of conversational inputs before routing calls. This advance preparation enables accurate routing on first contact, reducing transfers and network strain while maintaining comprehensive service coverage across multiple divisions

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The natural language understanding model acts as an intermediary between customer inputs and call routing decisions. It processes and interprets customer needs, translating conversational data into accurate routing instructions that reduce unnecessary transfers and network traffic

Inventive Principle:

Principle #24Intermediary (Mediator)

2Speed

If more customer service agents are hired to reduce wait times, then service speed is improved, but training resources and operational complexity increase

Engineering Contradiction:

Improveservice speedVSAvoidtraining resources

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The system provides self-service capabilities through real-time natural language processing that automatically analyzes customer needs and generates appropriate routing and handling instructions. This reduces the training burden on agents while maintaining fast service response times

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements real-time feedback loops where natural language processing continuously monitors conversational inputs and adjusts routing decisions dynamically. This enables rapid service response without requiring extensive agent training, as the system adapts based on real-time analysis

Inventive Principle:

Principle #23Feedback

3Extent of automation

If existing interactive voice response systems are used for call routing, then automation is improved, but routing accuracy deteriorates leading to misrouting and long wait times

Engineering Contradiction:

Improvecall routing automationVSAvoidrouting accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The system replaces traditional mechanical interactive voice response systems with natural language processing technology. This substitution enables more accurate interpretation of customer needs through contextual understanding, significantly improving routing accuracy while maintaining high automation levels

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the fundamental parameters of call routing by using natural language processing to analyze conversational inputs. This transforms routing from keyword-based matching to contextual understanding, dramatically improving routing accuracy while preserving automation benefits

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260067399A1Systems for NLU of telephonic audio data to facilitate communication during a telephonic communication

Publication Date: 2026.03.05 TRUIST BANK

AI summary

Systems and methods iteratively train, using training data, a natural language understanding (NLU) model to interpret conversational inputs during a telephonic communication by predicting topics, context, and intents from the conversational inputs, the training comparing outputs to a target variable during each iteration and adjusting parameters of the NLU model during each iteration to improve predictability of the topics, context, and intents from the conversational inputs. A real-time telephonic communication is monitored and the trained NLU model to audio data derived from audio signals of the real-time telephonic communication to predict topic(s) and the context of the topic(s) from the conversational inputs of the audio date. An intent is determined from the topic(s) and the context of the conversational inputs and based thereon a set of textual instructions for addressing the determined intent is selected and displayed using a unified desktop.