Chatbot Feedback Learning to Reduce Voice Escalation Traffic

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional chatbot systems fail to understand user requests, leading to increased network traffic due to users switching to voice-based communication for assistance, as they cannot effectively handle unresolved queries.

Innovation Solution

A system that identifies unresolved user queries in text-based communication and shares this information with a voice-based communication system to update the chatbot's machine learning model, refining its capabilities to handle similar queries in future text-based interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If conventional chatbot systems are used for text-based communication, then automation is improved, but understanding accuracy deteriorates leading to unresolved user queries

Engineering Contradiction:

Improvechatbot automationVSAvoidquery understanding accuracy

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The system implements feedback by detecting unresolved user queries in text-based communications and using them to retrain the machine learning model. The chatbot system continuously learns from failed interactions, converting unresolved queries into training data to improve future performance and reduce the need for voice-based escalation.

Inventive Principle:

Principle #23Feedback

2Reliability

If chatbot fails to understand user requests, then network traffic increases due to voice-based communication escalation, but user assistance quality improves

Engineering Contradiction:

Improveuser assistance qualityVSAvoidnetwork traffic volume

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system performs preliminary action by proactively detecting unresolved queries and using them for model retraining before similar issues recur. This preventive approach enables the chatbot to learn from past failures and improve its understanding capability in advance, reducing the likelihood of future escalations and associated network traffic.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If machine learning model is updated with unresolved queries, then chatbot performance improves, but system complexity increases

Engineering Contradiction:

Improvechatbot performanceVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system implements self-service by enabling the machine learning model to automatically retrain using unresolved queries from its own operational data. The chatbot system serves itself by identifying its own knowledge gaps and independently learning from failed interactions without requiring external intervention or complex manual retraining processes.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12438838B2Systems and methods for reducing network traffic

Publication Date: 2025.10.07 CAPITAL ONE SERVICES LLC

AI summary

Methods and systems for reducing network traffic between a service and client devices. In some aspects, the system receives a first data stream for a first type of communication between a service and a client device for a user. In response to determining that the first data stream includes an unresolved user query, the system determines that a second type of communication occurred between the service and the user. The system processes a second data stream for the second type of communication to determine that the second type of communication includes the unresolved user query and a service response to the unresolved user query. The system provides the unresolved user query and the service response to update a machine learning model used by the service to generate service responses to one or more user queries during a future communication of the first type.