• Researchers develop a system that can recommend personalized and healthy recipes

    Figure summarising the researchers’ personalized food recommendation architecture: Given a user query in natural language, along with the user’s context (comprising dietary preferences and health guidelines), the system finds top-ranked and personalized answers from the FoodKG food knowledge graph. QE, KA and CM stand for Query Expansion, Knowledge Graph Augmentation and Constraint Modeling, respectively. Positive constraints are in red, negative constraints in gray, and non-constraints in black. KBQA refers to the underlying knowledge graph question answering system. Credit: Chen et al. Researchers at Rensselaer Polytechnic Institute and IBM Research in New York have recently created pFoodReQ, a system that can recommend recipes tailored around the preferences and dietary needs of…