A method, device and system for realizing generative reasoning based on knowledge graph

By combining Neo4j graph database and MySQL relational database, receiving fault alarm information and matching fault solutions, the problem of inability to combine productive inference rule database and graph database in the existing technology has been solved, and the efficiency of fault diagnosis and maintenance has been improved, and the efficiency of fault diagnosis and maintenance has been expanded. The scope of application of knowledge graph.

CN114492807BActive Publication Date: 2024-11-19HANGZHOU HOLLYSYS AUTOMATION
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202210125519.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-10
Publication Date
2024-11-19
Estimated Expiration
2042-02-10

AI Technical Summary

Technical Problem

In the prior art, it is impossible to combine the generative inference rule database with the graph database, and it is difficult to achieve fault diagnosis through the graph database, which limits the fault diagnosis and maintenance efficiency.

Method used

By receiving fault alarm information, obtaining graph database identification statements from the relational database based on fault description information, executing these statements to determine target inference rules, and matching the fault solution from the pre-stored production inference rule library, combined with Neo4j Graph database and MySQL relational database implement production inference.

Benefits of technology

The application scope of knowledge graph has been expanded, fault diagnosis and maintenance efficiency has been improved, and productive reasoning based on knowledge graphs has been realized.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114492807B_ABST
    Figure CN114492807B_ABST
Patent Text Reader

Abstract

The present invention discloses a method, device, system and computer-readable storage medium for realizing generative reasoning based on knowledge graph, the method comprising: receiving fault alarm information; obtaining graph database recognizable statements corresponding to each reasoning rule from a relational database according to the fault alarm information; wherein the graph database recognizable statements corresponding to the reasoning rules are stored in the relational database in advance; executing each graph database recognizable statement to determine a target reasoning rule from each reasoning rule according to the fault description information in the fault alarm information; according to the target reasoning rule, matching a fault solution corresponding to the target reasoning rule from a pre-stored generative reasoning rule library; the present invention can realize generative reasoning based on knowledge graph, expand the application scope of knowledge graph, and is conducive to improving fault diagnosis efficiency and maintenance efficiency.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Power grid fault intelligent diagnosis method and device, computer equipment and storage medium

    CN110646710A

  • Industrial fault analysis expert system based on knowledge graph

    CN110705710A

  • Hydroelectric generating set fault diagnosis method and system based on knowledge graph

    CN110941725A

  • Decision support system architecture and method based on water conservancy knowledge-fact coupling network

    CN111368095A

  • Power equipment fault knowledge graph construction method

    CN111737496A