Echo Dot (3rd Gen) - Smart speaker with Alexa - Charcoal

Use your voice to play a song, artist, or genre through Amazon Music, Apple Music, Spotify, Pandora, and others. With compatible Echo devices in different rooms, you can fill your whole home with music.

Buy Now

Wireless Rechargeable Battery Powered WiFi Camera.

Wireless Rechargeable Battery Powered WiFi Camera is home security camera system lets you listen in and talk back through the built in speaker and microphone that work directly through your iPhone or Android Mic.

Buy Now

Order processing during pandemics for offline mode – Build Smart. Build Secure. IBM Developer



This code pattern explains how to build an AI-powered back-end system that can take your daily essential orders through an offline mode.


To contend with panic purchases and hoarding during crises, how can you maintain social distancing while getting the essentials that you need?

Because many people do not know how to use or have access to available online portals, there must be a different option for them to receive their essential items such as food and medicine. For example, a toll-free phone number-based approach to contacting a control tower might be a better option. In this option, the user can call the toll free number and order their essentials. However, with large numbers of people using this toll-free number-based approach, the traffic at the back end will be high, and to process these calls manually is tedious.

In this code pattern, we build an AI-powered back-end system that can take the daily essentials orders through an offline mode. The system processes the audio request by converting it to a formatted order list. Then, this system can be connected to the inventory database for optimizing supply chain management. This solution can be applied to various domains, such as ordering medicine and ordering groceries.



  1. Feed the audio to the Speech to Text service.
  2. Convert the text into English using Watson Language Translator.
  3. Feed the English text to the Watson Knowledge Studio model, which is deployed on Watson Natural Language Understanding.
  4. The model deployed on Watson Natural Language Understanding identifies all of the required attributes from the text.
  5. These extracted attributes get stored on Db2 on IBM Cloud.
  6. Visualize the order and customer details from the recordings on a dashboard.


Find the detailed steps for this pattern in the readme file. The steps show you how to:

  1. Clone the GitHub repository.
  2. Set up the Watson Speech to Text service.
  3. Set up the Watson Language Translator service.
  4. Set up Watson Knowledge Studio and Watson Natural Language Understanding.
  5. Set up IBM Db2.
  6. Add the credentials to the application.
  7. Deploy the application to Cloud Foundry.
  8. Analyze the results.

Read More


Please enter your comment!
Please enter your name here