AI Banner Modeling for Unknown CPE Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Large computer networks face significant challenges in identifying unknown Common Platform Enumeration (CPE) data for software products and web services, leading to unresolved cybersecurity vulnerabilities due to the impracticality and cost of implementing conventional rules-based schemes, resulting in blind spots for IT administrators.

Innovation Solution

A CPE prediction service using AI/ML modeling to predict CPE data by analyzing web service banners, enabling rapid identification of matching software products and versions, and subsequently determining associated cybersecurity vulnerabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If conventional rules-based schemes are used to identify CPE data, then identification accuracy may be maintained for known software, but the system becomes impractical and costly to implement for large computer networks

Engineering Contradiction:

ImproveImplementation feasibilityVSAvoidCPE identification accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent replaces conventional rules-based schemes with machine learning models that analyze web service banners to predict CPE data. This substitution transforms the mechanical process of rule-matching into an intelligent system that learns patterns from banner data, achieving both implementation feasibility for large networks and maintained identification accuracy through automated model-based prediction

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the machine learning model to automatically predict CPE data from web service banners without requiring manual rule configuration or extensive human intervention. The model learns from training data and autonomously identifies software products and versions, making the system practical for large-scale deployment

Inventive Principle:

Principle #25Self-service

2Reliability

If comprehensive monitoring of all computers in large networks is implemented, then cybersecurity vulnerability detection improves, but the complexity and cost of monitoring increases significantly

Engineering Contradiction:

ImproveCybersecurity vulnerability detectionVSAvoidMonitoring system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts critical identification information from web service banners, which are already publicly available from running software. By taking out and analyzing only the essential banner data rather than monitoring all system activities, the system achieves improved vulnerability detection while keeping monitoring complexity manageable through focused information extraction

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The machine learning model serves multiple functions: it identifies software products, determines versions, predicts CPE data, and enables vulnerability assessment all through a single banner analysis process. This multi-functionality improves comprehensive security monitoring while reducing overall system complexity by consolidating multiple monitoring tasks into one unified system

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Productivity

If AI/ML models are used to predict CPE data from web service banners, then CPE identification speed and coverage improve, but the complexity of the prediction system increases

Engineering Contradiction:

ImproveCPE identification speedVSAvoidPrediction system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-training machine learning models on extensive banner and CPE data before deployment. This advance preparation enables the models to quickly predict CPE data during operation without requiring complex real-time processing, thus improving identification speed while managing system complexity through offline model preparation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces web service banners as an intermediary between the monitoring system and CPE identification. Banners serve as a simple, standardized data source that the machine learning model can process efficiently. This intermediary simplifies the input data structure while enabling rapid prediction, improving productivity without proportionally increasing system complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12549590B1CPE prediction using banner-prompted AI/ML modeling

Publication Date: 2026.02.10 CROWDSTRIKE

AI summary

Prediction of CPEs using banners greatly improves computer functioning. Many web services have an unknown common platform enumeration (CPE). When the CPE is unknown, a computer system is unable to obtain cybersecurity flaws and software fixes for a software product or web service. A CPE, though, is predicted by banner-prompting an AI/ML model using a web service banner. Once the CPE is predicted, vulnerabilities may be identified.