A new energy operation and maintenance knowledge supplement method and system based on a knowledge graph

By constructing a multi-source heterogeneous data acquisition system and a confidence-weighted multi-source cross-validation mechanism, the problem of high error rate in supplementing new energy operation and maintenance knowledge has been solved. This has enabled dynamic knowledge expansion with high accuracy and timeliness, ensuring the integrity and consistency of the knowledge graph and supporting highly reliable intelligent operation and maintenance services.

CN122174947APending Publication Date: 2026-06-09SHAANXI HUADIAN NEW ENERGY POWER GENERATION CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHAANXI HUADIAN NEW ENERGY POWER GENERATION CO LTD
Filing Date
2026-03-09
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

The existing knowledge supplementation mechanism lacks multi-source verification, resulting in a high error rate in the automatic import of new energy operation and maintenance knowledge. Especially under high concurrency and multiple fault coupling emergency conditions, erroneous knowledge is rapidly spread, interfering with the accuracy of fault location and the generation of handling strategies, and threatening the safe and stable operation of the system.

Method used

A multi-source heterogeneous data acquisition system is constructed. By performing structured parsing and semantic alignment on the raw information from equipment logs, maintenance work orders, expert manuals, fault case libraries, and real-time monitoring systems, a multi-source cross-validation mechanism based on confidence weighting is introduced to perform consistency verification and conflict resolution on candidate knowledge triples, ensuring the accuracy and timeliness of knowledge.

Benefits of technology

It significantly reduces the error rate of automatically imported knowledge, achieves dynamic knowledge expansion with high accuracy and timeliness, ensures the structural integrity and consistency of the knowledge graph, and supports highly reliable intelligent operation and maintenance services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122174947A_ABST
    Figure CN122174947A_ABST
Patent Text Reader

Abstract

The application relates to the technical field of artificial intelligence, and discloses a new energy operation and maintenance knowledge supplement method and system based on a knowledge graph, which comprises the following steps: collecting original texts from device logs, operation and maintenance work orders, expert manuals, fault case libraries, real-time monitoring platforms and other multi-source heterogeneous data; performing text cleaning, term standardization and time alignment to generate a structured operation and maintenance event sequence; extracting candidate knowledge triplets based on a preset operation and maintenance ontology model; performing multi-source cross verification on the triplets through a weighted confidence model by fusing a data source authority weight and a data timeliness factor; injecting effective knowledge units with a confidence higher than a threshold into a knowledge graph in a standard format, performing entity alignment and relationship merging, and completing dynamic expansion. The system comprises the following units: a multi-source data collection unit, a preprocessing unit, a triplet extraction unit, a multi-source verification unit, a knowledge screening unit and a graph updating unit.
Need to check novelty before this filing date? Find Prior Art