Fuente: Foods - Revista científica (MDPI) Foods, Vol. 15, Pages 1647: Nutrient-Aware Personalized Meal Recommendation Using Structured Food Knowledge and Constraint Verification
Foods doi: 10.3390/foods15101647
Authors:
Yu Fu
Linyue Cai
Ruoyu Wu
Yongqi Kang
Yong Zhao

Along with the enhancement of people’s public health consciousness and the requirement for individual diet arrangement getting more urgent, the meal recommendation method, which is based on artificial intelligence, has hence become an active research domain in the field of intelligent health. One system that makes practical recommendations must deal with the user’s unclear queries, while at the same time, it must satisfy strict nutrient demands. A great number of existing methods at present either do not take into account verifiable food composition data, or they handle implicit dietary restrictions in a not good way. For solving these problems, we put forward CARE (Constraint-Aware Recipe Engine). Beginning from a mixed Retrieval-Augmented Generation (RAG) basic model (CARE v1.0), we have developed CARE v2.0, which is a suggestion engine that unites intention polish, knowledge graph enlargement, and rule-based checking in a unified working line. Instead of depending on huge black-box models, our framework utilizes an effective language model that possesses 1.5 B parameters. User inquiry content are undergone parsing to become structured nutrition targets; a food knowledge graph links abstract health notions to specific cooking materials; and the obtained candidate results are filtered in accordance with strict diet restrictions, with optional checking carried out by an automatic agent-based reviewer. Under a zero-shot cold-start situation, the system attains a semantic recall@5 of 0.825 on 400 k recipes coming from Recipe1M+ and a newly created fuzzy-query benchmark (CAREBench-150), and it thus has a better performance than dense retrieval baselines (0.550) as well as direct zero-shot prompting. The constraint satisfaction rate is located at 85.0% in fast mode, and it rises to 98.5% when the verification module is in the working state; therefore, it supports the safety of recommendations. These findings indicate that structured food knowledge, which matches a compact algorithmic framework, can therefore connect unclear user intentions and accurate nutrition requirements effectively.