Full
Outline
As river geomorphology research increasingly relies on large−scale literature integration and analysis, the challenge of extracting structured knowledge from unstructured texts has become central to advancing digital and semantic approaches in geomorphological science. This study proposes a GPT−based method for automatic knowledge extraction in the field of fluvial geomorphology. A structured Few−shot prompt framework was designed to guide the model in identifying geomorphic entities and their relations, enabling the generation of standardized knowledge triples in the form of <entity1, relation, entity2>. The workflow consists of corpus preparation, prompt engineering, model invocation, and structured output. Applied to 30 high−quality English−language journal articles, the approach extracted a total of 7605 knowledge triples, encompassing 22815 entities and relations. Evaluation results demonstrate that the method achieves high accuracy (Precision=0.834), good recall (Recall=0.789), and stable overall performance (F1=0.862). Nonetheless, limitations remain in the handling of abstract logic, long−range dependencies, and relation directionality. Future improvements may involve domain−specific model fine−tuning, integration of geographic ontologies, and multimodal data fusion. This research provides a practical solution for intelligent knowledge construction in fluvial geomorphology and expands the methodological toolkit at the intersection of geographic information science and artificial intelligence.
509
252
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
