Train TJBot to Shine with an Intent in Node-RED

Today we’ll train TJBot how to understand natural language and shine the light a color using the converse node and the Watson Conversation service.

TJBot can use intents, entities, and dialog responses from the IBM Watson Conversation service to understand natural language and take action as requested. Create a Conversation service to train the intent #shine_light. Feel free to add other phrases to recognize.

And train an entity, @color, with the colors shown. Feel free to add other supported colors.

In the Dialog tab, check for the condition when #shine_light and @color are recognized and respond with a confirmation of what color was recognized.

If #shine_light is matched but no color is recognized, provide a friendly reminder of the available colors.

Copy the Conversation credentials into the Conversation section in the TJBot configuration.

Make sure to enable the LED by ticking the LED option in the TJBot configuration.

When the shine intent and color entity is recognized, TJBot outputs the confirmation that it changed the light to the requested color.

If no color is recognized, TJBot outputs a friendly reminder in the debug window.

Here’s a video of how to train TJBot to recognize the shine intent and color entity using the IBM Watson Conversation service.

That’s it for today’s skill. What can you train TJBot to do now that it can shine its light using natural language commands?

Come back tomorrow and we’ll talk about analyzing the language style with the help of the Watson Tone Analyzer service.

This post is part of a series of skills you can train TJBot to perform.