Power grid engineering project auditing and early warning method and system based on bimodal attention

Power grid engineering project auditing and early warning method and system based on bimodal attention

The invention provides a power grid engineering project auditing and early warning method and system based on bimodal attention, and relates to the technical field of power engineering data auditing and early warning, and the method comprises the steps: obtaining structured and unstructured bimodal...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHOU CHENGXUAN, ZHAO LI, ZHANG BOYU, LU MING, CHI WEIDONG, LYU DEZHI, WU QINGHUA, ZUO CHANGHAO, WANG JUN, LIU DAN, ZHU CHAO, YANG GUIZHEN, YIN BIN, LIU MINGZHI, ZHANG ZHENDONG
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
PHYSICS
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides a power grid engineering project auditing and early warning method and system based on bimodal attention, and relates to the technical field of power engineering data auditing and early warning, and the method comprises the steps: obtaining structured and unstructured bimodal power data in a power project; inputting the structured power data and the unstructured power data into a risk auditing early warning model to respectively obtain structured context features and unstructured context features; according to the obtained context features of the bimodal data, generating associated information between bimodals by adopting a cross attention mechanism, and adjusting context feature distribution of the bimodals by utilizing the associated information between the bimodals to obtain structured data features and unstructured features; and the structured data features and the unstructured features are fused, and the auditing early warning result label is output by using the fused bimodal combi