Tech Stack : Whatsapp api, Twillo, flask, IBM Watson
To enable mobile users to leverage IBM Watson® services through a messenger app, complete this developer code pattern and build a framework that can act as an intermediator in connecting Watson services to WhatsApp Messenger.
OPTION 1 : Project
Industry Mentor from CEW will be assigned to help on the project.
Project Lifecycle will be : Scope, Architecture & Planning, Design, Coding, Testing, Go-Live/Award
Technology Involved : Whatsapp api, Twillo, flask, IBM Watson , Agile, Functional & Non Functional Requirements Capturing, Architecture & Solution Design, Project Plan, Project Estimatation, Use Case Modelling, UML Design, Process Flow Diagrams, UX Personas, Stakeholder Analysis, UX Best Practices, Responsive Design, Coding Best Practices, Unit Testing, Github, Deployment of Project, Devops, Automation, Go Live Procedures + this project
(limited time offer)
OPTION 2 : Class & Project
Industry Expert Teachers from CEW will be assigned for 12 weeks coaching on the technologies used in project.
After 12 weeks of teaching, project work will start.
Industry Mentor from CEW will be assigned to help on the project.
Project Lifecycle will be : Scope, Architecture & Planning, Design, Coding, Testing, Go-Live/Award
Technology Involved : Whatsapp api, Twillo, flask, IBM Watson , Agile, Functional & Non Functional Requirements Capturing, Architecture & Solution Design, Project Plan, Project Estimatation, Use Case Modelling, UML Design, Process Flow Diagrams, UX Personas, Stakeholder Analysis, UX Best Practices, Responsive Design, Coding Best Practices, Unit Testing, Github, Deployment of Project, Devops, Automation, Go Live Procedures + this project
(limited time offer)
No Other Class in the world teaches you Real life implementation | Agile Implementation | Requirements Capturing | Architecture & Solution Design | Project Plan | Project Estimatation | Use Case Modelling | UML Design | Process Flow Diagrams | UX Personas | Stakeholder Analysis | UX Best Practices | Responsive Design | Coding Best Practices | Unit Testing | Github | Deployment of Project | Devops | Automation |Go Live Procedures + this project of the projects like we do
What you will learn ?
- Real-world how IT projects are implemented
- Implement project using Whatsapp api, Twillo, flask, IBM Watson
- Capture Requirements of the project using Use Case Modelling (Stakeholders, Personas, Main Scanario, Alternate, Negative, Edge Cases)
- Define Functional & Non-Functional Use Cases
- Create project design using UML Modelling
- Implement project coding using code respositories.
- How Google Analytics, Search Engine Optimization(SEO) are implemented.
- How UX Banners are created.
- Testing using unit tests(create & execute)
- Deployment of the project in cloud
- User Acceptance Testing - How client identify issues, how you fix issues
- Go Live of the project
Description
There are currently 2.4 billion users on WhatsApp, and the number keeps climbing. For medium and large businesses, WhatsApp introduced WhatsApp Business, which powers communication with customers all over the world so they can connect with businesses on WhatsApp in a simple, secure, and reliable way. To make the conversations smarter, Watson AI can be infused as the back end to deliver advanced AI capabilities to customers.
In this code pattern, you will learn to build a framework to connect Watson Machine Learning, deploy a simple house price-prediction model, and access it from your WhatsApp Messenger. When you have completed this code pattern, you will understand how to:
Integrate IBM Watson services into WhatsApp.
Deploy the application to IBM Cloud® Foundry.
Deploy machine learning models to IBM Cloud Object Storage.
Manage machine learning models in IBM Watson Studio.
FLOW
1. User sends a message through WhatsApp.
2. The message is redirected to the Twilio Programmable Messaging service.
3. Twilio Programmable Messaging will forward the message to the back-end app hosted on IBM Cloud.
4. The back-end app interacts with Watson Machine Learning to get the response.
5. Watson Machine Learning does the necessary computations and returns a response.
6. The back-end app processes the response and converts it to user-readable format and forwards to Twilio.
7. Twilio forwards this message as a reply on WhatsApp.
8. The user will receive this as a response from Watson Machine Learning service on WhatsApp.
Timelines : 8 weeks
Project will go through the phases of scope, design, coding, unit testing, UAT, Award(Go Live)
Winner will be chosen for each phase(scope,design,coding,unit testing,UAT,Go-Live) of the project, cash prize from CEW ′, certificate, cloud credits will be provided for each phase.
