Post1

Implementing Chatbot in IoT Ecosystem (Use-case)

Posted by Roshan Raj

In continuation with the Chatbot series, we are back with our next blog on implementing chatbot in IoT ecosystem.

Let’s get started.

What Did We Do?

With the help of Hallwaze Beats’ RTM API and a bot engine that uses popular Wit.ai for NLU and NLP, we created some very interesting bots.

We mashed up IoT and conversational bot to create a system where a bot was acting like an interface to the IoT ecosystem.

Beats is a messaging part of Enterprise Collaboration Ecosystem, Hallwaze. Now that it has opened up access to send and receive messages at real time, many new opportunities arise.

What Did We Use?

  • Beats RTM API
  • AI – Chatbot engine
  • Smart devices

How Did We Do It?

Once Wit.ai is ready for Natural Language Processing and Natural Language Understanding, we proceed to making the bot engine functional. Bot engine passes the received message to Wit.ai which returns scores of responses for user defined entities and sentiments. Upon which, Bot.ai decides what needs to be sent as response.

The next step was to integrate Wit.ai into the code for our bot’s engine. Wit.ai has well-documented open source libraries and SDKs for iOS, Ruby, Node.js, and Python which you can access at the Wit.ai Github page (https://github.com/wit-ai).

Workflow for Bot Conversation

Step 1. Fetch a bot identity from Beats server.

  • Log into beats and add bot from settings.
  • Get the connection string.

Step 2. Connect to messaging system using connection string provided over bot registration.

Step 3. Get bot’s NLU done right using Wit.ai.

Step 4. Once Wit.ai is ready for NLP and NLU, we can make bot engine functional. Bot engine passes the received message further to Wit.ai which in turn defines scores for user defined entities, its state and sentiments. Upon which Bot engine rule works.

Bot engine returns confidence or probability for the entity and its state, upon which rule engine works.

Step 5. The final step is to get rule engine done right by checking probability scores for entities and intents of sentence passed to Wit.ai.

This is the simplest way of implementing conversational bot in the IoT ecosystem. We hope you understood the procedure and are eager to try it out yourself. So, get started and let us know your experience in the comment section.

Until next time!

Techblog!

 

 

 

Related Posts

  • Implementing bot in IoT ecosystemImplementing bot in IoT ecosystem

    What we did... With the help of Hallwaze beat’s RTM api and a bot engine that uses popular Wit.ai for NLU and NLP. We cooked some very interesting bots. We…

  • AI in Banking(2) – ChatbotsAI in Banking(2) – Chatbots

    Hello readers, as promised, we are here with our 2nd blog in the series of blogs on “AI in Banking and Financial Services”, focusing on Chatbots. As discussed in the…

  • Introduction to Chat bots (Part 1)Introduction to Chat bots (Part 1)

    Chat bots Chat bots are Conversational agents or a Dialog system that simulates Intelligent conversation using text or speech. Why chat bots? In recent times, a sudden rise in interest towards…

  • ChatBots (Part 2) – How to make BotsChatBots (Part 2) – How to make Bots

    “It is said that to explain is to explain away. This maxim is nowhere so well fulfilled as in the area of computer programming, especially in what is called heuristic…

  • Mobile App Automation Testing using ‘ESPRESSO’

    If you are a Mobile Apps Test Engineer, you cannot overlook the very reliable Google Product i.e. Espresso. Espresso is an automatic UI testing or as we call it “hands…

  • Manager’s Dilema: SAS vs R vs Python

    There are countless articles on this topic already, and I must begin by accepting that I am quite late to this superstar battle. However, every time these champions of analytics…

Leave a Reply

Your email address will not be published. Required fields are marked *