Conversational Knowledge Graph Virtual Assistant for APM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional Application Performance Management (APM) products require technology-savvy users and do not intuitively capture the relationships between performance data, making it difficult for non-technical users to effectively utilize their interfaces and arrive at desired outcomes.
Innovation Solution
A conversational knowledge graph-powered virtual assistant that processes natural language inputs by translating user queries into intents, retrieving relevant context information, customizing backend service calls, and providing intuitive responses, leveraging artificial intelligence, machine learning, and deep learning to enhance user interaction and recommendation capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional APM user interface is used, then APM specific monitoring and analysis functions are provided, but the interface requires technology-savvy users and is not intuitive
Solution Approach 1:
A virtual assistant acts as an intermediary between users and the APM system. The virtual assistant receives natural language queries from users, translates them into technical intents, and retrieves relevant performance data through a fulfillment service, thereby shielding users from interface complexity while maintaining access to advanced APM functions
Solution Approach 2:
The patent replaces the traditional mechanical click-based UI interaction with a natural language processing system. The NLU system processes spoken or typed queries, converting them into structured intents that trigger appropriate APM functions, making the system accessible to non-technical users while preserving complex analytical capabilities
2Loss of information
If traditional APM interface is used, then performance data can be accessed, but the relationship of performance data is not captured intuitively
Solution Approach 1:
The virtual assistant incorporates feedback mechanisms where it analyzes user queries, retrieves relevant performance data along with their relationships, and presents contextualized answers. The system learns from user interactions and refines its understanding of data relationships, ensuring that contextual information is preserved and communicated intuitively
Solution Approach 2:
The system performs preliminary analysis of performance data relationships before user queries are fully processed. The knowledge graph pre-computes and stores relationships between performance metrics, enabling the virtual assistant to immediately provide contextualized answers that capture data relationships without requiring users to manually explore complex interfaces
3Measurement precision
If multiple questions are asked to arrive at desired outcome, then accurate information can be obtained, but the process becomes manual and time-consuming
Solution Approach 1:
The virtual assistant performs preliminary processing of user intent and proactively retrieves related performance data in a single operation. Instead of requiring multiple sequential queries, the system anticipates related information needs and fetches contextualized data upfront, maintaining accuracy while significantly reducing the time required to obtain comprehensive information
Solution Approach 2:
The patent merges multiple data retrieval operations into a single unified process. The fulfillment service consolidates requests for related performance metrics, traces, and contextual information into one coordinated query against the APM system, returning comprehensive accurate results in a single response rather than requiring multiple separate questions
Data Source
AI summary
In one embodiment, a method of processing a natural language input using a conversational knowledge graph in a virtual assistant is disclosed. The method includes receiving a natural language query from a user; translating the natural language query received from the user into corresponding intents; retrieving conversational knowledge context information based on the intents; using the retrieved conversational knowledge context information to customize back-end service calls to downstream applications; receiving a result of the customized back-end service calls; sending the result of the customized back-end service calls in a response to the natural language understanding system; translating the response from the fulfillment service system into a natural language response; and providing the natural language translated response to the user.