Adaptive chatbot dialogs

Intents and dialog flows

Bot:  how can I help?
User: I need a duplicate bank statement
Bot: ok which year?
User: 2020
Bot: which month?
User: may

Dynamic slot filling

Bot:  how can I help?
User: I need a duplicate bank statement for may 2020
Bot: ok which year?
User: i just told you

Part of Speech Tagging & Dependency Parsing

Bot:  how can I help?
User: I need a duplicate bank for the last month
Bot: ok which year?
User: this year of course

Capturing the right data

  1. product
  2. style
  3. brand
  4. fabric
  5. colour
  6. size
  7. price

The risk of over qualifying the need

  1. We may force the user to be so specific that we can’t actually find any matches in our database.
  2. The dialog may be so long that the user gets bored and gives up.

The risk of under qualifying the need

Striking the balance

  1. Meet the user’s needs
  2. Offer real value, beyond that which is achievable through other means (e.g. a website)
  3. Stimulate and retain the user’s interest (AIDA)
  • the intent / need
  • the time of the day
  • the device used
  • new vs repeat/loyal customer

Using machine learning to drive the dialog flow

Summary

Don’t forget to give us your 👏 !

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store