Skip to content

kenextra/WhatsappMessenger

Repository files navigation

Climate Messenger

License Community Website

Climate Messenger is a whatsapp-based bot that uses machine learning to predict Agriculture Producer Prices based on users location, provide latest agricultural news and search options.

Contents

Short description

Whatsapp-based bot, for agriculture news, price prediction and search options

What's the problem?

Approximately 9 percent of the global population is suffering from hunger. And, much of the world’s food is grown by small-scale, independent farms and distributed through local community cooperatives who sell the surplus produce. These independent farmers and co-ops do not have accessible tools/platforms to get the right information for better crop production and price fairness.

How can technology help?

By providing access to useful information to independent farmers and co-ops through a familiar platform that is easy to use.

The idea

To improve access to information using technologies that are already accessible and familiar to farmers and co-ops so they don't have to learn new technology.

Demo video

Watch the video

The architecture

architecture

Flow

  1. User sends a message through WhatsApp.

  2. The message is redirected to Twilio Programmable Messaging service.

  3. Twilio Programmable Messaging service will further forward the message to the framework hosted on IBM Cloud.

  4. The framework interacts with one of the Watson services to get the response.

  5. The Watson service does the necessary computation and returns a response accordingly.

  6. The framework processes the response and converts it to user readable format and forwards it Twilio.

  7. Twilio forwards this message as a reply on WhatsApp.

  8. The user will receive this as a response from Watson service on WhatsApp.

The workflow of the app is as follows:

NOTE: The user has to follow the exact same workflow for the WhatsApp to reply as intended.

User Reply Screenshot
Hi The message, 'Hi' that you typed on your phone, went through Whatsapp -> Twilio -> Python App hosted on IBM Cloud and returned back to you from Python App hosted on IBM Cloud -> Twilio -> Whatsapp. How Cool is that!! Try asking What can you do? 1
What can you do? I am a bot who is connected to watson services on IBM Cloud! Try asking What are the services you are connected to? 2
What are the services you are connected to? I found the following services associated to me: 1. Watson Machine Learning -> ready Enter the number to know more. 2. Watson Visual Recognition -> No Custom Model Deployed 3. Watson Assistant -> For Agriculture News 3
1 WML Model id: xxxx-xxxx-xxxx WML Model Name: Deployment of Food Price Prediction WML Model Status: ready Try asking I want to know food prices 4
I want to know food prices Please enter the details with the below format: Predict:<Country>,<Item>, Example: Predict:Germany,Apples 6
2 Watson Assistant Type News for Agriculture News 7

Long description

More detail is available here

Project roadmap

See below for our proposed schedule on next steps after Call for Code 2021 submission.

See ROADMAP.md

Getting started

See SETUP.md

Built with

Contributing

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

Authors

Acknowledgments

  1. Augment IBM Watson Services to WhatsApp

  2. Augment Watson Visual Recognition service with WhatsApp

License

This project is licensed under the Apache 2 License - see the LICENSE file for details.

About

Call for code 2021 Climate Messanger

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published