Chatbot User Feedback for Predictive Application Routing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing network optimization methods rely on poor proxies for user experience, such as network metrics, which fail to accurately predict and prevent service level agreement violations, leading to unnecessary rerouting that can negatively impact application experience.

Innovation Solution

Implementing a chatbot to directly collect user feedback on application experience, integrating it with performance metrics to predict and prevent service level agreement violations through predictive application aware routing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If network metrics are used to predict service level agreement violations, then proactive routing can be implemented, but the accuracy of predicting true application experience is poor

Engineering Contradiction:

Improveprediction accuracyVSAvoidapplication experience measurement

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The system implements feedback by collecting actual user experience data through chatbot interactions and using this feedback to continuously improve the predictive models. User ratings and chatbot conversations provide ground truth data that validates and refines the network metric correlations, making future predictions more accurate.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces traditional objective network metric measurements with subjective user experience measurements obtained through chatbot interactions. This substitution allows direct capture of true application experience rather than relying on indirect proxies like packet loss or jitter metrics.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If proactive routing is implemented based on predicted violations, then service level agreement violations can be prevented, but unnecessary rerouting can negatively impact application experience

Engineering Contradiction:

Improveservice level agreement complianceVSAvoidapplication experience degradation

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary actions by proactively rerouting traffic before service level agreement violations occur. By using machine learning models to predict future degradation based on current network conditions, the system can switch paths in advance, preventing poor user experience rather than reacting after problems occur.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses automated chatbots to monitor and assess user experience in real-time, enabling the network to self-adjust routing decisions based on actual user feedback without manual intervention. This creates a closed-loop system that continuously optimizes routing based on user-perceived quality.

Inventive Principle:

Principle #25Self-service

3Loss of information

If user feedback is collected at the end of application sessions, then user experience ratings can be obtained, but the information is insufficient for predicting when degradation will occur

Engineering Contradiction:

Improveuser experience informationVSAvoidprediction timing

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

Instead of collecting feedback after sessions end, the system proactively engages users during active sessions through chatbots. This preliminary collection of experience data allows the system to identify degradation patterns while they are occurring, enabling timely routing adjustments before user experience is significantly impacted.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements continuous monitoring of user experience through chatbot interactions throughout application sessions rather than single-point end-of-session surveys. This continuous data stream provides ongoing information about user experience quality, enabling real-time detection of degradation trends and continuous optimization of routing decisions.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS12536402B2Using chatbots to collect direct user feedback on application experience

Publication Date: 2026.01.27 CISCO TECHNOLOGY INC

AI summary

In one embodiment, a device associates one or more performance metrics with a particular session of an online application. The device makes a determination that a user of the online application associated with the particular session should be queried for feedback regarding their application experience. The device obtains, based on the determination, feedback from the user regarding their application experience, by causing a chatbot to be presented to the user and query the user for feedback regarding their application experience. The device associates the feedback from the user regarding their application experience with the one or more performance metrics.