Objective

  • Enterprises typically have several people facing processes across their different departments. Some examples are: Employee facing process to handle IT requests such as raising a ticket to fix laptop, Customer facing process in a financial institution to take a new loan request.
  • Enterprises face two issues with human based interfaces. First issue relates to the fact that despite well-defined Standard Operating Procedure (SOP), humans tend to deviate from defined process leading to degradation of service. Second issue relates to the fact that human agents are not available 24 x 7 to handle requests.
  • AI driven Chatbots are capable of taking written or spoken requests to handle such processes automatically. They can be trained to handle different types of requests and can be made available 24x7.

Methodology

Requirements

Understand process being automated.

Document conversation flow & sign-off from business.

data and back-end interfaces.

First phase involves understanding the requirements for the BOT. Business Process is understood in detail and conversation flow (between chatbot user and chatbot) is documented in good level of detail. Also, need for back-end database and interfaces to customer’s existing IT system is documented.

BOT Training

Choose from AWS, Google, Microsoft.

Implement the flow.

Implement DB & interface.

Program & train middle layer in Python.

Second phase involves building the BOT using chosen technology platform such as AWS Lex, Google Dialogflow or Microsoft Chatbot Framework. The conversation flow is implemented in the form of intents, utterances and data slots. Back-end database and interfaces are developed. Middle-ware is developed in Python or equivalent and implemented on chosen platform such as AWS Lambda. End-to-end Chatbot is tested at development level.

Implement & Test

Test BOT as per conversation flow requirements.

Refine the solution as necessary based on user feedback.

Host in production environment and Go Live.

Thirst phase involves implementing and testing the BOT as per documented conversation flow. Any user feedback is incorporated and tested version of the BOT is implemented in productione environment before going live.

Case Studies

  • Learn how neurIOT helped India’s 3rd largest e-Commerce company implement Virtual Assistant to handle car loan queries.
  • Learn how neurIOT helped a hospital management services company in USA handle patient claim status requests using Chatbot