Picture from http://foodindustryexecutive.com/2016/04/the-internet-of-things-and-the-future-of-food/ Cognitive IoT Recipe Maven Cognitive IoT Recipe Maven Digital Expertise in the Kitchen Digital Expertise in the Kitchen Miguel Jiménez , Prashanti Angara , Harshit Jain, Kirti Agarwal, Roshni Jain, Miguel Jiménez , Prashanti Angara , Harshit Jain, Kirti Agarwal, Roshni Jain, Hausi Müller, Ulrike Stege, Joanna Ng Hausi Müller, Ulrike Stege, Joanna Ng IBM Canada LabWeek - CASTLE 2017 IBM Canada LabWeek - CASTLE 2017 University of Victoria University of Victoria
Motivation ● Food wastage is currently 40% in North America [1] Obesity rate is increasing globally [2] ● ● Limited context integration in existing applications ○ Nutrient information and dietary goals Effective use of expiry dates ○ ○ Knowledge of users’ taste, preferences, allergies and diseases Limited knowledge and time to cook healthy ● ● Sparse and duplicate data across multiple devices and applications [1] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3228640/ [2] https://www.hsph.harvard.edu/obesity-prevention-source/obesity-trends/obesity-rates-worldwide/ 2
Outline 1. Overview of the IoT Recipe Maven 2. Key stakeholders 3. Maven components a. CAPRecipes: context-aware personalized recipes recommender b. Foodie Fooderson: a conversational agent for the smart kitchen c. Smidge: Smart Refrigerator and Grocery d. SmartGrocer: a profit-aware store path optimizer 4. Challenges 5. Conclusion 3
Key Stakeholders Users Smidge ❖ SmartGrocer ❖ CAPRecipes ❖ Grocery stores Foodie ❖ Fridge Makers 4
Cognitive IoT Recipe Maven Weighing scale diabetes monitor Personal Web app Mobile app Foodie data Heart monitor Context Sphere Smarter mats Kitchen SmartGrocer CAPRecipes Smidge data Fridge camera Grocery Store Spoonacular Food data 5 [1] https://spoonacular.com/food-api
CAPRecipes : Context-Aware Recipe Recommendation Context Recommender Personal health information: allergies and diseases Content-based Cuisine and ingredient preferences filtering Preferences of family and friends Personalized +Reasoning Browser search history and social interactions Recipes Recipe preferences and ratings Collaborative filtering Time of day, location (general context) Expiry date, quantity and missing ingredients 6 Ratings
CAPRecipes : Hybrid interface Web UI Mobile Application 7
Foodie : A Cognitive Kitchen Assistant [...] how much fat is in that A cognitive conversational assistant connected to our recipe? recipe recommendation engine that: Foodie, I’d like to reduce my intake of sugar ○ Assists people in finding a suitable recipe ○ Describes step-by-step cooking instructions Provides nutrition information ○ ○ Helps people in creating and tracking dietary goals Sugar intake Cuisine Would you like I don’t How about I’m Sounds to make Lemon like Grilled Cheese hungry good! Garlic Chicken? garlic Pizza? Body Weight Ingredients 8
Foodie : A Cognitive Kitchen Assistant (2) Under the Hood ● #Intents Determine the purpose of arbitrary user input ○ ○ Example: “ I’m feeling hungry ” is classified under the intent #start_cooking @Entities ● ○ Keyword identification Example: “ I want to eat a french breakfast ” ○ ■ @cuisine = french ■ @mealType = breakfast Dialog ● ○ Possible flows of a conversation via nodes Nodes are triggered by conditions ○ ● Context Mechanism for passing information between the dialog and the application ○ 9
Smidge: Smart Refrigerator and Grocery FridgeCam r e t o S r y c e r o G Smarter Mats ● FridgeCam: Analyze contents ● Update ingredient inventory of the fridge through grocery receipts ● Smarter Mats: Track weights ● Personalize recommendations for contents in the fridge for coupons to increase ● savings 10
Smart Grocer : Profit-Aware Store Path Optimization Promote products by incentivizing customers: List item Promoted item ● Guide users through the Optimal Path Suggested Detour store to purchase a list of items ● Indicate additional items in or near the customer’s path that the store wants to promote or offer discounts Entry Cashier on. 11
Smart Grocer : Profit-Aware Store Path Optimization Optimal Path Smidge Grocery List Optimal Path + Smart Grocer Suggested Personal data Detours Context Sphere User’s preferences Kitchen Optimal Path + data Extra Detours 12
Challenges Discovering agents in a shared environment to accomplish tasks collaboratively. Effective context management Foodie Building a richer conversational agent is difficult. Platforms are not sophisticated enough yet. Accurate voice recognition services for people with accents and environments with noise Smidge Accurately identifying products inside the fridge 13
Key Takeaways Cognitive IOT Recipe Maven integrates food-related applications and uses context to collaboratively enhance the user experience. It includes CAPRecipes, a context-aware personalized recipes recommender, Foodie: a conversational agent for the smart kitchen, Smidge: An IoT Enabled Fridge and SmartGrocer: a profit-aware store path optimizer There is great potential for building systems which cross context barriers and enhance user experiences. 14
Thanks Miguel Jiménez , miguel@uvic.ca Prashanti Angara , pangara@uvic.ca Hausi Müller , hausi@uvic.ca Joanna Ng , jwng@ca.ibm.com 15
Recommend
More recommend
