Execution method of large model graph retrieval enhancement system oriented to software and hardware monitoring operation and maintenance

By building an operation and maintenance/fault knowledge graph based on the ontology model and combining a graph retrieval enhancement system with a large language model, the problems of low efficiency of knowledge graph retrieval, inaccurate results and low degree of automation in the existing technology are solved, and efficient and accurate fault location and processing are achieved.

CN120386898AActive Publication Date: 2025-07-29ADVANCED OPERATING SYST INNOVATION CENT (TIANJIN) CO LTD
6 Cites 8 Cited by

Patent Information

Application Number
CN202510890611.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-30
Publication Date
2025-07-29
Estimated Expiration
2045-06-30

AI Technical Summary

Technical Problem

When facing large-scale knowledge graphs, existing knowledge graph search technology has high computing power requirements, low retrieval efficiency, and lacks a deep understanding of contextual information, resulting in insufficient correlation of search results, lack of dynamic update mechanism, low degree of automation of fault processing processes, and difficult to quickly and accurately locate relevant knowledge and handle faults.

Method used

The graph search enhancement system is adopted, including graph construction and update module, graph search enhancement module, prompt word construction module, reasoning generation module and process analysis module. By building an operation and maintenance/fault knowledge graph based on the ontology model, two-stage filtering search and structured natural language question and answer are carried out, and combined with the reasoning generation capabilities of the large language model, fault analysis and process automation are realized.

Benefits of technology

It significantly improves the adaptability of knowledge reasoning and fault positioning, improves retrieval efficiency and accuracy, ensures the context fit of generated results and the stability of inference, and enhances the degree of automation of fault processing and the practical value of results.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent operation and maintenance, in particular to an execution method of a large model graph retrieval enhancement system oriented to software and hardware monitoring operation and maintenance, which comprises the following steps: S1, inputting fault information to the graph retrieval enhancement system; s2, a graph construction and updating module receives and processes the fault information, generates a triple, and writes the triple into an operation and maintenance / fault knowledge graph; s3, the fault information is input into a graph retrieval enhancement module for two-stage filtering retrieval, and sub-graph information is screened out; s4, the prompt word construction module converts the fault information and the screened sub-graph information into structured natural language prompt segments; and S5, a reasoning generation module performs natural language question and answer to generate a fault analysis result. Based on the above scheme, the execution method enhances the adaptive capacity of knowledge reasoning and fault positioning, gives play to the generalization reasoning capacity of a large language model while ensuring the accuracy, and enhances the practical value.
Need to check novelty before this filing date? Find Prior Art