Rogue Classification Policy Analysis for Adaptive Network Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing network management systems struggle with accurately and efficiently identifying and classifying rogue devices in communication networks, relying on manual and suboptimal predefined policies that fail to adapt to evolving network conditions.

Innovation Solution

Implementing a rogue policy analysis engine that includes a rogue snapshot engine and a rogue rule auto-profiler engine to evaluate the performance of active rogue classification policies using statistical machine learning algorithms, providing real-time recommendations for improving these policies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If manual and predefined policies are used for rogue device classification, then device complexity is reduced, but measurement precision and reliability of rogue device identification deteriorate

Engineering Contradiction:

Improveclassification system complexityVSAvoidrogue device identification accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The classification system performs self-service by automatically evaluating its own active rogue classification policies using statistical machine learning algorithms. The rogue policy analysis engine continuously monitors classification accuracy and generates recommendations without requiring manual intervention, allowing the system to self-optimize while maintaining high measurement precision

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms where classification results are continuously evaluated against actual network conditions and rogue device behaviors. The rogue policy analysis engine uses this feedback to generate refined classification policies, creating a closed-loop system that improves accuracy over time while automating the process

Inventive Principle:

Principle #23Feedback

2Device complexity

If manual evaluation of classification policies is performed, then device complexity is reduced, but productivity and adaptability to evolving network conditions deteriorate

Engineering Contradiction:

Improvepolicy evaluation system complexityVSAvoidpolicy optimization speed

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The patent replaces manual mechanical evaluation processes with automated statistical machine learning algorithms. The rogue policy analysis engine uses computational methods to rapidly evaluate classification policies, generating recommendations at machine speed rather than human pace, thereby dramatically improving productivity and response time to evolving threats

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system dynamically changes evaluation parameters by adapting statistical models to current network conditions and threat patterns. The rogue policy analysis engine modifies classification thresholds, feature weights, and algorithm parameters based on real-time data, enabling rapid adaptation to new rogue device types and behaviors without manual reconfiguration

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If predefined classification policies are used, then ease of operation is improved, but adaptability to evolving network conditions deteriorates

Engineering Contradiction:

Improvepolicy implementation easeVSAvoidnetwork condition adaptability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The classification system transitions from static predefined policies to dynamic adaptive policies. The rogue policy analysis engine continuously updates classification rules based on evolving network conditions and rogue device behaviors, allowing the system to remain easy to operate while simultaneously adapting to new threats through automated learning and adjustment

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS12598203B2Analyzing and recommending rogue classification policies for a communication network

Publication Date: 2026.04.07 HEWLETT PACKARD ENTERPRISE DEV LP

AI summary

In certain embodiments, a method performed by a processing device includes obtaining, at multiple times, rogue classification information for electronic devices detected within a communication network. The rogue classification information for each time includes: timestamp information identifying the time; corresponding sets of attribute values for the electronic devices detected within the communication network at the time; and respective rogue classifications, as determined according to active rogue classification policies and the corresponding sets of attribute values, for the electronic devices. The method includes analyzing the rogue classification information for the multiple times to determine whether to modify the active rogue classification policies by analyzing, using a statistical machine learning algorithm, the respective rogue classifications and the corresponding sets of attribute values for the electronic devices for the multiple times. The method includes generating, in response to determining to modify the active rogue classification policies, a recommended rogue classification policy.