AI Network Fault Mitigation Platform

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Complex modern networks, such as 5G, face challenges in rapidly identifying and resolving faults due to increased complexity and noise, leading to prolonged service degradations and high manpower requirements, especially with the rise of mission-critical applications and IoT devices.

Innovation Solution

The implementation of artificial intelligence and machine learning techniques to analyze historical network incident data, identify clusters, and generate models that determine the root cause of faults and recommend actions for real-time resolution, with the option for automatic execution or user notification through a graphical interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If traditional network incident resolution methods are used, then network complexity increases, but fault diagnosis time and service degradation duration increase significantly

Engineering Contradiction:

Improvenetwork complexityVSAvoidfault diagnosis time

Core Design Contradiction:

Device complexityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing historical network incident data to build trained machine learning models before actual faults occur. These models are ready to rapidly diagnose new incidents by comparing against the pre-analyzed historical patterns, eliminating the need for time-consuming real-time analysis when faults occur.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates simplified copies of complex network incident patterns through machine learning models. Instead of analyzing raw, complex network data in real-time, the system uses trained models that capture essential fault patterns, enabling rapid diagnosis without processing the full complexity of original network incidents.

Inventive Principle:

Principle #26Copying

2Productivity

If more manpower is allocated to diagnose network incidents, then fault resolution capability improves, but operational costs and resource requirements increase

Engineering Contradiction:

Improvefault resolution capabilityVSAvoidmanpower requirements

Core Design Contradiction:

ProductivityVSQuantity of substance

Solution Approach 1:

The system enables self-service by automatically diagnosing network faults using machine learning models without requiring human intervention for each incident. The trained models independently analyze new incidents, identify root causes, and recommend resolutions, freeing manpower from routine diagnostic tasks while maintaining high fault resolution capability.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the mechanical system of human analysts with an automated machine learning-based diagnostic system. The ML models perform the analytical work that previously required human expertise, substituting computational processes for manual fault diagnosis while maintaining or improving resolution effectiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of manufacture

If static knowledge databases are used for fault resolution, then implementation simplicity is maintained, but adaptability to emerging network incidents decreases

Engineering Contradiction:

Improvesystem implementation simplicityVSAvoidadaptability to emerging incidents

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The system transitions from static knowledge databases to dynamic machine learning models that continuously adapt to new network incident patterns. The models are trained on historical data and can evolve to recognize emerging fault types, maintaining simplicity of use while gaining adaptability to changing network environments and new incident patterns.

Inventive Principle:

Principle #15Dynamics

4Adaptability or versatility

If virtualization of network functionality is increased, then network capabilities and services are enhanced, but noise and difficulty in diagnosing incidents increase

Engineering Contradiction:

Improvenetwork capabilitiesVSAvoidincident diagnosis difficulty

Core Design Contradiction:

Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system introduces machine learning models as intermediaries between complex virtualized network components and fault diagnosis processes. These models act as mediators that translate complex virtualized network states into recognizable fault patterns, simplifying the detection and measurement of incidents in highly virtualized environments without reducing network capabilities.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20210397497A1Intelligent network operation platform for network fault mitigation

Publication Date: 2021.12.23 ACCENTURE GLOBAL SOLUTIONS LTD

AI summary

Embodiments of the present disclosure provide systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning to identify, diagnose, and mitigate occurrences of network faults or incidents within a network. Historical network incidents may be used to generate a model that may be used to evaluate real-time occurring network incidents, such as to identify a cause of the network incident. Clustering algorithms may be used to identify portions of the model that share similarities with a network incident and then actions taken to resolve similar network incidents in the past may be identified and proposed as candidate actions that may be executed to resolve the cause of the network incident. Execution of the candidate actions may be performed under control of a user or automatically based on execution criteria and the configuration of the fault mitigation system.