Natural-Language Network Diagnosis Workflows for Self-Service
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large-scale data center networks rely heavily on manual on-call services for network diagnosis, which is tedious and time-consuming due to the need for extensive expertise and processing of vast monitoring data, creating a gap between user needs and network monitoring primitives.
Innovation Solution
A network diagnosis platform utilizing a virtual assistant (chatbot) that processes natural language queries, leveraging network engineer expertise through a dialogue engine, workflow engine, and data engine to automate the diagnosis process by determining a target workflow and executing machine-executable tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual on-call services are used for network diagnosis, then network engineers can handle complex diagnosis tasks, but the process becomes tedious and time-consuming
Solution Approach 1:
The system enables self-service network diagnosis by allowing users to submit diagnosis requests through natural language queries without requiring manual intervention from network engineers. The automated workflow engine executes diagnosis tasks and retrieves monitoring data automatically, eliminating the need for engineers to manually process each diagnosis request while maintaining reliable diagnosis outcomes.
Solution Approach 2:
The patent replaces the mechanical manual process with an automated computational system. The workflow engine translates natural language queries into machine-executable tasks, and the system automatically executes diagnosis workflows, retrieves monitoring data, and generates results without human intervention, thereby reducing diagnosis time while maintaining reliability.
2Reliability
If manual on-call services are used for network diagnosis, then network engineers can process monitoring data, but extensive expertise and considerable efforts are required
Solution Approach 1:
The workflow engine acts as an intermediary between the user's natural language query and the complex monitoring data processing system. It translates simple user requests into structured diagnosis workflows, manages the complexity of data retrieval and processing, and coordinates between different system components, thereby hiding the system complexity from users while maintaining accurate diagnosis results.
Solution Approach 2:
The diagnosis system is segmented into independent modular components: the workflow engine for task coordination, the data engine for monitoring data retrieval, and the execution layer for running diagnosis tasks. This segmentation allows each component to handle specific functions independently, making the overall system more manageable and maintainable while preserving diagnosis accuracy through specialized processing.
3Productivity
If automated diagnosis processes are implemented, then diagnosis efficiency improves, but the system complexity increases
Solution Approach 1:
The workflow engine serves multiple functions: it receives natural language queries, translates them into diagnosis workflows, coordinates task execution, manages data retrieval, and processes results. By consolidating these diverse functions into a single multi-functional engine, the system achieves high automation efficiency without proportionally increasing overall system complexity, as the same core engine handles all automation tasks.
Data Source
AI summary
A method is proposed for network diagnosis. In the method, a user query on the network diagnosis expressed in a natural language is obtained. A target workflow including a set of machine-executable tasks for a network diagnosis process on a target category of the network diagnosis is determined based on the user query and a diagnosis result is generated by performing the set of machine-executable tasks in a network diagnosis process.