ASC scheduling anomaly identification method, system and model based on large language model and knowledge base construction method

Abstract

The invention discloses a large language model-based ASC scheduling exception identification method, system, model and knowledge base construction method, and the method comprises the steps: building an ASC scheduling exception identification rule knowledge base according to historical data; constructing an ASC scheduling exception identification model based on a large language model; performing scheduling exception classification based on the RAG framework, and outputting a classification result; and obtaining ASC scheduling data of the automated wharf in real time, inputting the ASC scheduling data into the ASC scheduling abnormity identification model based on the large language model, and obtaining a real-time ASC scheduling abnormity result. By constructing a multi-dimensional anomaly classification system and fusing field expert knowledge and an intelligent recognition model of a large language model, the technical defects of incomplete rule coverage, response lag and the like in a traditional method are overcome, accurate recognition and real-time monitoring of ASC scheduling anomaly are achieved, data-driven decision support is provided for optimization of an automatic wharf operation process, and the method is suitable for large-scale popularization and application. Therefore, the port operation efficiency is integrally improved.

Images