西藏民族大学

To address the challenges of integrating multi-source heterogeneous data in the cultural heritage domain and the issues of traditional knowledge extraction methods relying on manual annotation and having a low degree of automation,this paper proposes a method for constructing cultural heritage knowledge graphs based on large language models(LLMs).Firstly,by integrating domain expert knowledge and cultural heritage industry standards,this paper constructs a knowledge ontology encompassing core cultural heritage concepts and their relationships.This ontology systematically defines spatio-temporal attributes,cultural attributes,and physical characteristics of cultural relics,as well as the associative relationships between them,forming a multi-dimensional,structured knowledge framework.Secondly,a joint extraction strategy with multi-stage task decomposition is designed.Leveraging the semantic understanding and generation capabilities of LLMs,the knowledge extraction process is decomposed into two subtasks:"entity-attribute extraction"and"triple extraction"guided step-by-step through prompt engineering.Simultaneously,a multi-dimensional verification mechanism is introduced to validate the generated triples from three aspects:logical consistency,domain normative compliance,and factual accuracy,ensuring the professionalism and reliability of the knowledge graph.Experiments show that the DeepSeek-R1 model achieves an F1-score of 86.25%in the extraction task,which is 3.13 percentage points higher than the BERT-BiLSTM-CRF model.Ablation studies also verify the effectiveness of each module.This method provides efficient and automated technical support for the digital preservation of cultural heritage and interdisciplinary research.

To investigate the flavor composition and characteristics of air-dried jerkies that are confused and difficult to distinguish with naked eye on the market, electronic nose (E-Nose) combined with headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS) was used to analyze the flavor profiles and compositions of different jerky types, including air-dried yak, beef, chicken, duck and pork jerkies. Through relative odor activity value (ROAV) and multivariate statistical analysis, the key volatile compounds and characteristic volatile compounds that contributed significantly to the overall flavor of different jerkies and helped distinguish between jerky types were screened. The E-Nose results showed that the overall flavor profiles of different jerkies were similar, although their responsiveness differed. A total of 42 volatile compounds were identified by HS-GC-IMS, including 9 alcohols, 5 ketones, 9 terpenes, 2 acids, 8 esters, 6 aldehydes, 2 pyrazines, and 1 furan. Among them, the highest percentage of relative content of alcohol compounds was 16.04% to 32.41%. The comprehensive analysis revealed that the principal component analysis based on E-nose data achieved good discrimination, and that the flavor profiles differed across different jerky types. The key volatile compounds of various jerkies included (R/S)-linalool, 3-hydroxy-2-butanone, α-pinene, ethyl acetate, isovaleraldehyde, 1-nonyl aldehyde, 1,8-cineole and β-myristate. Among them, isovaleraldehyde and 3-hydroxy-2-butanone-D were key volatile substances and characteristic volatile compounds, whose relative contents were correlated with chicken and yak jerkies, respectively. In conclusion, by analyzing the characteristics of flavour characteristics for different types of air-dried jerkies, which could provide theoretical support for the differentiation of air-dried jerky types.