AI Query Enrichment for Multi-Layer Packet-Optical Assurance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network assurance systems fail to provide comprehensive, real-time multi-layer network troubleshooting and fail to effectively combine various types of data when characterizing network problems, often leading to incomplete resolution of issues due to a lack of integration of AI and ML approaches.
Innovation Solution
The integration of Large Language Models (LLMs) and cognitive search modules with real-time network telemetry data and network topology to enhance network assurance, enabling proactive and reactive problem detection and resolution in multi-layer networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional network assurance systems are used, then basic network monitoring is provided, but comprehensive real-time multi-layer troubleshooting and effective data integration are not achieved
Solution Approach 1:
The patent merges multiple data sources including real-time telemetry data, network inventory information, and enterprise knowledge base content into a unified analysis framework. This integration combines disparate data types (performance metrics, alarm events, PM data, topology information) to provide comprehensive multi-layer network troubleshooting while maintaining system coherence through a centralized AI/Gen-AI processing architecture.
Solution Approach 2:
The patent introduces an intermediary enhancement module that acts as a bridge between the user's natural language query and the AI/Gen-AI network assurance solution. This module enriches the original query by incorporating relevant context from real-time network data, inventory information, and knowledge base articles, thereby improving the accuracy and relevance of the analysis without requiring users to directly interact with complex system components.
2Measurement precision
If real-time telemetry data and enterprise content are integrated, then more accurate network problem detection is achieved, but data processing complexity increases
Solution Approach 1:
The patent segments the data processing workflow into distinct functional modules: a query enhancement module that prepares enriched queries, an AI/Gen-AI analysis engine that processes the enhanced queries, and a results synthesis module that consolidates findings. This segmentation allows each module to handle specific data types and processing tasks independently, reducing overall system complexity while maintaining high detection accuracy through specialized processing at each stage.
Solution Approach 2:
The patent performs preliminary actions by pre-processing and enriching user queries before they reach the AI/Gen-AI analysis engine. The query enhancement module proactively incorporates relevant context from real-time telemetry data, network inventory, and knowledge base articles, preparing comprehensive input data in advance. This preliminary enrichment reduces the processing burden on the analysis engine and improves detection accuracy without requiring complex real-time data integration during the analysis phase.
3Productivity
If AI/Gen-AI solutions with LLM and cognitive search are implemented, then faster network issue resolution is achieved, but computational resource requirements increase
Solution Approach 1:
The patent applies partial action by selectively retrieving and processing only the most relevant enterprise content and knowledge base articles that pertain to the specific network issue being analyzed. Rather than processing all available data, the system identifies and focuses on pertinent information through the enhanced query mechanism, reducing computational resource consumption while maintaining fast issue resolution speeds through targeted analysis of critical data subsets.
Data Source
AI summary
Systems, methods, and non-transitory computer-readable media are provided for conducting user query searches for performing network assurance queries. According to one implementation, a method includes a step of receiving a user query regarding network assurance for ensuring that a network domain is operating reliably, wherein the user query relates to one of finding an issue in the network domain, understating the issue, and determining corrective actions for the issue. The method also includes a step of obtaining real-time telemetry information and inventory information associated with the network domain. Also, the method includes a step of using the real-time telemetry information and inventory information to create an enhanced user query. The method further includes a step of feeding the enhanced user query to an Artificial Intelligence (AI) network assurance solution.