Predictive Networking Recommendation Grouping for Safer QoE Changes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Predictive networking systems generate overwhelming numbers of recommended actions, overwhelming network administrators and leading to high resource usage, with changes in network configuration posing risks of negatively impacting traffic.

Innovation Solution

A device generates recommendations for network actions, assigns scores to different groupings, and selects a particular grouping for implementation to optimize quality of experience, using predictive networking processes and machine learning to predict and minimize risks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If predictive networking generates multiple recommended actions for each application, path, and endpoint, then the system can provide comprehensive optimization, but the number of recommendations becomes overwhelming and difficult to manage

Engineering Contradiction:

Improvecomprehensive optimization coverageVSAvoidnumber of recommendations

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent combines multiple individual recommendations into grouped recommendations that address multiple applications, paths, or endpoints simultaneously. Instead of presenting separate recommendations for each element, the system clusters them into cohesive groups that can be evaluated and implemented as unified actions, reducing the overall number of recommendations while maintaining comprehensive optimization coverage.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent creates recommendations that can apply universally across multiple applications, paths, or endpoints through grouping. A single grouped recommendation can affect multiple network elements with similar characteristics or requirements, allowing the system to provide broad optimization coverage without generating an excessive number of individual recommendations for each specific element.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Productivity

If the system provides many individual recommendations, then more optimization opportunities are identified, but network administrator workload and resource usage increase significantly

Engineering Contradiction:

Improveoptimization opportunities identifiedVSAvoidadministrator review time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent merges multiple individual recommendations into consolidated grouped recommendations, allowing administrators to review and approve fewer unified actions instead of numerous individual ones. This grouping approach maintains identification of all optimization opportunities while reducing the time required for administrator review and decision-making.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary grouping and consolidation of recommendations before presenting them to administrators. By pre-organizing recommendations into logical groups with aggregated impact assessments, the system reduces the administrative burden of evaluating each recommendation individually, thereby decreasing review time while preserving comprehensive optimization identification.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If the system implements multiple configuration changes based on recommendations, then network optimization is improved, but the risk of negatively impacting traffic increases

Engineering Contradiction:

Improvenetwork optimization effectivenessVSAvoidtraffic impact risk

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent combines multiple configuration changes into grouped recommendations that are implemented together as unified actions. This approach reduces the total number of separate configuration changes and operational interventions required, thereby lowering the cumulative risk of traffic impact while maintaining network optimization effectiveness through coordinated implementation.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system evaluates and groups recommendations to assess cumulative risk before implementation. By analyzing the combined impact of grouped recommendations on network traffic and performance, the system can identify potential risks in advance and adjust grouping strategies to minimize adverse effects, providing a cushioning effect against unexpected traffic disruptions.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Data Source

PatentUS12556457B2Recommendation grouping for predictive networking

Publication Date: 2026.02.17 CISCO TECHNOLOGY INC

AI summary

In one embodiment, a device generates a plurality of recommendations for a network, each recommendation indicating a suggested action to optimize quality of experience of a corresponding application accessible via the network. The device assigns scores to different possible groupings of the plurality of recommendations. The device selects a particular grouping from among the plurality of recommendations, based on their scores. The device provides the particular grouping for implementation in the network.