Eating out is part of life. In the United States, consumers have spent more money on restaurants than on grocery for the first time in history. Millennials are showing an increased desire to eat prepared foods, and as the entire industry grows, a new frontier in the technology world develops. Restaurants have been among the slowest industries in adopting technologies, but there's a need for a more efficient dining ecosystem. A couple weeks ago, when flying out for a skiing trip, we discovered Ziosk at an airport Italian restaurant. Ziosk is a tablet that allows the user to pay, order, and play games all at the table. It's a great concept for an airport where the speed of checking out is key, and large chains that work at an economy of scale that function in an environment of saving money at every corner. Applebees, Olive Garden, and others have begun to use some sort of tablet (whether it be Ziosk or it's competitor, Presto) across many of their eateries, and it's only logical that companies which need to minimize workforce costs, and that rely on rewards programs (the tablets let you sign up on spot) replace a homely feel with a lifeless touchscreen slab. The dining industry is huge - Ziosk and Presto only work on a limited segment, a side where speed and scale are prioritized over everything else. What about the mom and pop shops? What about the trendy places full of chatter and excitement? The restaurant is an unforgiving environment, and so many delicious meals have never been served because establishments, no matter their popularity, struggle to compete and make the profits that massive chains can. Data and efficiency make the difference between success and failure. There's a market out there for technology that can fill this gap. We developed Expediter with the intent of improving the dining experience across the board while being affordable. Expediter cuts costs, analyzes data, and increases the productivity of the workforce. The consumer appreciates the convenience of an always listening waiter. In short, Expediter is the technology that your restaurant has been waiting for. Get ready to revolutionize your business!

What it does

Expediter uses the Amazon Echo Dot as a personal waiter at every table. A web of Dots, all connected by the Amazon cloud, facilitate orders and dictate requests to a staff. While the waiter isn't replaced, they take on a new role. The best way to understand how our service works is by outlining the process: A hostess will greet customers and sit them at a table, handing out physical menus. To interact with the Dot, one simply needs to say "Alexa, launch waitress." The diners can then make requests. "I'll order the Miso Ramen.." or "What is Miso Ramen?" An order would be sent to the kitchen, where it'll be displayed on a dashboard. If a customer calls for a waiter, a notification will be sent to the Pebble Watch of waiters "Table 4 needs assistance." Whereas a single waiter might have covered 5 tables without Expediter, they can now cover anywhere from 7-10. Expediter immediately collects data, as every order and request translate into tangible and beneficial information for the owner. Owners understand their popular dishes and clearly see revenue which makes paying taxes easier. By implementing machine learning algorithms with Wolfram in the future, owners have the potential to understand demand for dishes in the future. We envision Expediter to be sold on a restaurant per restaurant basis. Rather than selling it as a service, we want to make it a one time purchase. The low cost of the Dot and technologies we use make this an affordable alternative to our competition.

How we built it

We used Amazon Web Services (php and SQL database), AWS Lamda, the Amazon Alexa, and the Pebble smartwatch(C), Node.js, chart.js, and Bootstrap, and Wolfram Alpha to build this working prototype.

Challenges we ran into

Implementing the Pebble smartwatch proved to be a major challenge. Understanding how the Alexa interacts in a loud environment, and hashing out a plan to use multiple Dots in conjunction proved a powerful brainstorming exercise. The Wifi going down didn't help, but we made it through.

Accomplishments that we're proud of

We're proud that we built a working prototype for a much larger concept.

What we learned

We learned that any major idea starts off small, and that small contextualization need a bigger picture view.

What's next for Expediter

We intend on using machine learning with Wolfram to predict popular products.

Share this project: