EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Study on a Food Pairing Knowledge Graph Construction Method Integrating Large Language Models and Relation Completion

Jia Yu, Tong Ji, Jiamin Zheng

Food-Energy-Water Nexus · 16.08.2026 · 2 (3) · 1-20

DOI: 10.63808/fewn.v2i3.430 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Food-Energy-Water Nexus, online erschienen am 16.08.2026. Verfasst von Jia Yu und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aiming at scattered knowledge sources, inconsistent entity expressions and insufficient relation extraction accuracy in food pairing, this paper proposes a food pairing knowledge graph construction method integrating large language models and relation completion. A domain ontology covering dishes, ingredients, nutrients, dietary restrictions, applicable populations and health goals is designed. Candidate entities and relations are then extracted from recipe texts, nutrition descriptions and dietary-restriction materials using a large language model, and entity normalization is performed through a domain dictionary and semantic embeddings. Finally, a relation scoring function integrating LLM confidence, semantic similarity and domain rules is used to filter, review and complete candidate triples. Experiments on a food pairing corpus show that the proposed method achieves a relation extraction F1 score of 88.71%, which is 6.05 percentage points higher than direct LLM extraction, and obtains a human-verified accuracy of 87.33% for completed relations. The results indicate that the proposed method can provide a reliable structured knowledge base for healthy diet recommendation and food pairing question answering.

Zitieren

APA

Yu, J., Ji, T., & Zheng, J. (2026). A Study on a Food Pairing Knowledge Graph Construction Method Integrating Large Language Models and Relation Completion. Food-Energy-Water Nexus, 2(3), 1-20. https://doi.org/10.63808/fewn.v2i3.430

Vancouver

Yu J, Ji T, Zheng J. A Study on a Food Pairing Knowledge Graph Construction Method Integrating Large Language Models and Relation Completion. Food-Energy-Water Nexus. 2026;2(3):1-20. doi:10.63808/fewn.v2i3.430

BibTeX
@article{Yu2026,
  author = {Yu, Jia and Ji, Tong and Zheng, Jiamin},
  title = {A Study on a Food Pairing Knowledge Graph Construction Method Integrating Large Language Models and Relation Completion},
  journal = {Food-Energy-Water Nexus},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {1--20},
  doi = {10.63808/fewn.v2i3.430}
}
Kostenlos starten →