面向舰载航空枢纽作业解析的领域大模型构建方法OA

[Objective]Aircraft carrier air-hub operation parsing is a typical domain-specific structured un-derstanding task in carrier-based aviation scenarios.Its source data are primarily derived from unstructured mission logs,command messages,and support reports,and are characterized by strong temporal dependencies,complex spatiotemporal constraints,dense domain-specific terminology,and tight coupling among aircraft sta-tus,resource allocation,and operational phases.These characteristics make automatic parsing prone to errors,including omission of critical information,and structural inconsistency.Although cloud-based large language models(LLMs)offer a feasible solution due to their extensive prior knowledge and strong generative capabili-ties,their high computational cost and deployment requirements limit their applicability in highly resource-constrained carrier-side environments.In contrast,locally deployable LLMs are more suitable for sensitive op-erational scenarios,yet their domain-specific parsing capability remains insufficient.This study aims to con-struct a deployable domain-specific large language model for aircraft carrier air-hub operation parsing,with the goal of improving parsing accuracy,reliability,and consistency under local deployment constraints.[Method]We propose a domain-specific large language model construction method for carrier air-hub oper-ation parsing,termed the carrier air-hub operation parsing large model(CAOP).The proposed framework con-sists of two tightly coupled stages,namely high-dimensional knowledge distillation during training and collab-orative verification during inference.In the training stage,a cloud-based teacher model is employed to provide structured supervision across six key information dimensions,including entity recognition,relation extraction,statistical information extraction,predictive information extraction,joint semantic parsing of textual and nu-merical data,and abnormal event cue extraction.The outputs across these dimensions are further aligned and fused to construct transferable supervision signals,enabling the distillation of domain-specific parsing capabil-ities from the teacher model into a locally deployable student model via parameter-efficient optimization.In the inference stage,a carrier aviation operation knowledge base and a case-based retrieval mechanism are in-troduced to provide external evidence and similar historical instances.Based on these resources,collaborative verification is performed on candidate outputs by enforcing both evidence consistency and structural con-straints,thereby reducing hallucinations,minimizing redundancy,and correcting inconsistent information fields.[Results]Under the experimental settings adopted in this study,the proposed method improves the average score of the locally deployed Qwen3-32B model on carrier air-hub operation parsing from 13.3 to 18.4,yielding an absolute gain of 5.1 points and a relative improvement of approximately 38.3%.The result-ing performance not only surpasses that of the compared cloud-based models but also approaches expert-level evaluation.The improvements are primarily reflected in more complete information field extraction,stronger evidence alignment,and enhanced structural consistency of the final parsing results.[Conclusion]The re-sults demonstrate that the proposed CAOP framework significantly improves the accuracy,reliability,and con-sistency of carrier air-hub operation parsing under local deployment constraints.It provides a robust and trust-worthy structured data foundation for downstream tasks,including automatic scheduling generation,conflict detection,and optimization solving.