Skip to content

J0SAL/Rush-Estimator-for-Corporate-Cafeteria

 
 

Repository files navigation

image

IBM HackChallenge - 2022

  • Team Name: EliteCoders
  • Project Title: Rush Estimator for Corporate Cafeteria
rush-estimator

RushEstimator


❄️ Demo

🛠️ Technology Stack

Website Next JS React Bootstrap Chart.js

Backend Flask MongoDB

Desktop App Python

⚔️ IBM Services Used:

  • IBM Cloud Functions
  • IBM Web Hooks
  • IBM Watson Assistant
  • IBM Watson Studio

🌟 Vision

The food waste generated from restaurants in India which is around 67 million metric tonnes of food waste per annum which is valued at INR 92,000 crore growing at 8–10% per year is a serious the issue which needs to be solved. We are proposing a solution which will help cafeterias prepare the right amount of food to meet the demand. We will be estimating the number of people visiting the restaurant on the given day and providing the restaurant information on how much raw materials to buy and food to prepare so that there is no food shortage or wastage.

🌟 Purpose

Estimating the number of people who will visit at a specific time is crucial when managing a cafeteria since we need to make the appropriate preparations for the rush. To produce good revenues and provide clients with ample food, estimations must be accurate. What if the estimate is incorrect? In which case the estimation is useless. If it is higher, whatever food is left will be ruined, resulting in money being squandered and having a negative social impact. Our proposed solution will tackle this issue by making accurate predictions and offering services to the restaurant which will curb food wastage

❄️ Features

  • FootFall Analysis

    • Analyzing your cafeteria footfall has never been so easy.
    • Thanks to our powerful Machine Learning Model and analytical tools, we bring it to your fingertips.
    • drawing
  • Revenue Prediction

    • This tool can estimate the revenue of your cafeteria.
    • It will help you to analyze your cafeteria's performance and to determine the feasibility of opening a new outlet.
    • drawing
  • Inventory Management

    • Our very special feature is the inventory management system.
    • Update your menu online for the coming week and predict how much raw materials need to be purchased to meet the demand.
    • drawing
  • Chatbot

    • Stuck Anywhere? Our Chatbot will guide you through!
    • The Chatbot is powered by IBM watson!
    • drawing
  • Footfall Detection

    • Detect Footfall from real-time footage of the restaurant's IP camera through MobileNet SSD model and centroid tracking algorithim.
    • Application to be installed on the restaurant's computer and expected to run 2-3 months to get accurate predictions.
    • Note : If any interruptions in the software runtime it can be resumed from that checkpoint.
    • drawing
    • drawing

🏃 Local setup - Frontend

Before starting 🏁, you need to have Git and Node installed.

# Clone this repository
$ git clone https://github.com/smartinternz02/SBSPS-Challenge-9305-Rush-Estimator-for-Corporate-Cafeteria.git
# Go into the repository
$ cd SBSPS-Challenge-9305-Rush-Estimator-for-Corporate-Cafeteria
$ cd Frontend
# Install Dependencies
$ npm install
# Run Application
$ npm dev
# The server will start at <http://localhost:3000>

🏃 Local setup - Backend

Before starting 🏁, you need to have Git and Python installed.

# Clone this repository
$ git clone https://github.com/smartinternz02/SBSPS-Challenge-9305-Rush-Estimator-for-Corporate-Cafeteria.git
# Go into the repository
$ cd SBSPS-Challenge-9305-Rush-Estimator-for-Corporate-Cafeteria
$ cd Backend
# Create & Activate Environment (optional) here's a sample code
$ python -m venv project_env
$ project_env\Scripts\activate.bat
# Install dependencies
pip -r requirements.txt
# Run the app
python app.py
# The server will start at <http://localhost:8080>

🤠 Team Members

  1. @Joy Almeida
  2. @Dylan Dsouza
  3. @Aniket Gawade
  4. @Sudhanshu Kulkarni

About

Rush Estimator for Corporate Cafeteria

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • TeX 38.9%
  • Jupyter Notebook 30.8%
  • HTML 20.0%
  • JavaScript 4.6%
  • Python 3.0%
  • Tcl 2.4%
  • Other 0.3%