Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation

2025-07-14

AI Summary

Current automated dietary assessment systems overlook recipe substitutions, individual requirements (e.g., allergies, cultural preferences), and integration of region-specific nutritional data—particularly in Switzerland, where no unified, multidimensional food knowledge resource exists. To address this gap, we introduce SwissFKG, the first food knowledge graph tailored to Switzerland, uniquely integrating local recipes, ingredient substitutability, nutrient profiles, allergens, dietary restrictions, and national dietary guidelines. We propose an LLM-driven knowledge extraction and graph completion framework, coupled with a Graph-RAG-enhanced embedding retrieval architecture enabling fine-grained, context-aware nutritional question answering. Experimental evaluation demonstrates SwissFKG’s effectiveness and shows that multiple LLM-embedding combinations achieve high accuracy on nutrition-related queries. This work establishes a scalable, culturally grounded knowledge infrastructure for personalized, context-sensitive digital nutrition services.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

AI has driven significant progress in the nutrition field, especially through multimedia-based automatic dietary assessment. However, existing automatic dietary assessment systems often overlook critical non-visual factors, such as recipe-specific ingredient substitutions that can significantly alter nutritional content, and rarely account for individual dietary needs, including allergies, restrictions, cultural practices, and personal preferences. In Switzerland, while food-related information is available, it remains fragmented, and no centralized repository currently integrates all relevant nutrition-related aspects within a Swiss context. To bridge this divide, we introduce the Swiss Food Knowledge Graph (SwissFKG), the first resource, to our best knowledge, to unite recipes, ingredients, and their substitutions with nutrient data, dietary restrictions, allergen information, and national nutrition guidelines under one graph. We establish a LLM-powered enrichment pipeline for populating the graph, whereby we further present the first benchmark of four off-the-shelf (<70 B parameter) LLMs for food knowledge augmentation. Our results demonstrate that LLMs can effectively enrich the graph with relevant nutritional information. Our SwissFKG goes beyond recipe recommendations by offering ingredient-level information such as allergen and dietary restriction information, and guidance aligned with nutritional guidelines. Moreover, we implement a Graph-RAG application to showcase how the SwissFKG's rich natural-language data structure can help LLM answer user-specific nutrition queries, and we evaluate LLM-embedding pairings by comparing user-query responses against predefined expected answers. As such, our work lays the foundation for the next generation of dietary assessment tools that blend visual, contextual, and cultural dimensions of eating.

Problem

• Existing dietary systems ignore non-visual factors like ingredient substitutions
• Switzerland lacks a unified nutrition data repository for local context
• Current tools rarely personalize for allergies, culture, or preferences

Innovation

• SwissFKG integrates recipes, ingredients, and nutrition data
• LLM-powered pipeline enriches food knowledge graph
• Graph-RAG application enhances nutrition query responses