Dine_Bot_

Between allergies, fad diets, and cultural restrictions, it is a miracle if a catered meal satisfies anyone. Our webpage allows you to RSVP your guest's preferences, then we find the perfect meal.🦃🎄

Comment

Empowerment (Education, Health) Web

Inspiration

If you’ve ever catered an event, you know how stressful it can be to meet everyone’s constantly changing needs. Whether preparing for Thanksgiving, Hanukkah, or Easter, were ready to make your life a little easier by finding the optimal recipes to accommodate the pickiest guest.

What it does

Just give us the phone number, and our chat will not do the rest. Once your attendees respond, we will send you tailored catering and recipe choices that everyone will be happy with. (The no risky links, No hassle.)

Q0. Do you have any of the following health concerns that require dietary accommodation? Text back the appropriate letters one at a time, if any, then type NEXT a. General Health b. Brain c. Cardiovascular d. Digestive e. Infection f. Female Health
Q1. Do you have any allergies? Text back the appropriate letters one at a time, if any, then type NEXT a. Shellfish b. Gluten c. Tree nut d. Egg e. Soy f. Sesame g. Fish Q2. What are your other dietary restrictions? Text back the appropriate letters one at a time, if any, then type NEXT a. Vegetarian b. Vegan c. Kosher d. Keto e. Low Carb f. Halal Q3. It is a post-meal survey. Q3. (1-10)

How we built it

Every project starts with research, and we read two books, 183 articles, and 65 studies and conducted customer discovery by interviewing people who follow the diets in question. Our team is diverse, so our collective lifetime culinary knowledge has much to pull from.

Herbs and Spices have been long-standing home remedies to cure sickness, not only complementary treatments for the symptoms of chronic conditions like menopause: arthritis, bone density loss, hot flashes, and anxiety.

So food of interest with nutritional content can act not only as the optimal nutrition for recovery but for preventative medicine. We chose to focus on chronic illnesses because other conditions are, by nature, random, thus producing too sparse of a signal to track.

A patient often compromises with food items that are tasteless and something that does not align with their interest. Food is so essential and co-related with the mood of the person and hence with their physiological processes.

We started with a personalized meal planning App that intakes data from the user in the form of a questionnaire, which functions as follows: Q0. What type of physiological help do you seek from the food? (In the state of health target options) a. Digestive b. General Health c. Brain d. Infection e. Cardiovascular f. Female Health Q1. Do you have any allergies? Q2. What are your dietary restrictions? Q3. How are you feeling now? Q4. What would you like to eat? ( The datasets have the (food, recipes, time to make, calories, no. of ingredients, and all components). From this dataset, we will recommend using a food choice. The answers would be taken as JSON inputs and passed onto the backend through the API for processing. From the input user data, we will recommend food - guessing the user interest from the input. The user will have the food, and for three days, we will get feedback from the user about the effects of that food on their body). Each time user receives food; the feedback system will be due in 36 hours. Feedback will be in the form of a rating scale from (0 - 10). Upon user feedback, we will track their personalized food interest impact of the recommended food on their physiology, follow the progress and update the type of recommendation prediction. Hence making the chronic-illness-meal planning personalized and beneficial for the user.

We then expanded its function to group planning by developing a Twillio SMS chat Bot to RSVP each person's diet needs.

Challenges we ran into

We set out to interview a General Physician, a Doctor of Nutritional Science, and a small sample group of Halal and Kosher followers. Unfortunately, the only General Physician to respond was available after the hackathon competition date. My sample size for Halal was only two. My sample size for Kosher was one, but he was an expert on historical and modern Hebrew food law.

Testing the chatbot interface on a trial account was difficult, as we had limited accessibility to Twilio.

What's next for Dine Bot

  1. Continue R&D about the Big-data formation and database management for personalization records of the individual user.
  2. Making a B2C business model running on google ads.
  3. Develop a mobile android app and iOS app.
Share this project:

Updates