Enhancing FKG.in: automating Indian food composition analysis

2024-12-06

International Conference on Pattern Recognition

AI Summary

This study addresses key challenges in digitizing Indian food composition data—namely, multilingualism, structural heterogeneity, and semantic ambiguity. To tackle these, we propose the first LLM-enhanced knowledge parsing framework specifically designed for the complexity of Indian dietary patterns. Methodologically, the framework integrates an India-specific Food Knowledge Graph (FKG.in), multi-source nutritional databases (IFCT, INDB, Nutritionix API), and large language models within a hybrid workflow combining rule-based processing and generative reasoning. This enables automated recipe ingredient parsing, imputation of missing nutrient values, and cross-source knowledge alignment. The framework is domain-agnostic and generalizable to other regional cuisines. Experimental evaluation demonstrates end-to-end nutritional analysis for hundreds of Indian recipes, achieving significant improvements in coverage and accuracy. Furthermore, it supports the generation of personalized dietary and health recommendations.

Technology Category

• Natural Language Processing: Information Extraction
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)

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
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This paper presents a novel approach to compute food composition data for Indian recipes using a knowledge graph for Indian food (FKG.in) and LLMs. The primary focus is to provide a broad overview of an automated food composition analysis workflow and describe its core functionalities: nutrition data aggregation, food composition analysis, and LLM-augmented information resolution. This workflow aims to complement FKG.in and iteratively supplement food composition data from verified knowledge bases. Additionally, this paper highlights the challenges of representing Indian food and accessing food composition data digitally. It also reviews three key sources of food composition data: the Indian Food Composition Tables, the Indian Nutrient Databank, and the Nutritionix API. Furthermore, it briefly outlines how users can interact with the workflow to obtain diet-based health recommendations and detailed food composition information for numerous recipes. We then explore the complex challenges of analyzing Indian recipe information across dimensions such as structure, multilingualism, and uncertainty as well as present our ongoing work on LLM-based solutions to address these issues. The methods proposed in this workshop paper for AI-driven knowledge curation and information resolution are application-agnostic, generalizable, and replicable for any domain.

Problem

• Automating food composition analysis for Indian recipes
• Addressing challenges in digital representation of Indian food data
• Providing automated nutrition data aggregation and analysis workflow

Innovation

• LLM-augmented food composition analysis
• Knowledge graph for automated nutrition workflow
• Application-agnostic AI curation methods