header-915122_1920

We all know Artificial Intelligence (AI) is coming in a big way and one industry that’s grappling with this question is the ERP space. Where and how will AI augment ERP systems and the businesses that use them? Without a doubt, AI will have a profound impact on the footprint of ERP solutions in the foreseeable future. AI will enable organizations to further optimize their operating model made up of business processes, software applications, governance structures and technology infrastructure.

AI-enabled ERP solutions will by default impact the heart and soul of day-to-day operations. The mix of people, process and technology is going to change. AI solutions will take over routine tasks in the end-to-end business process model that are currently being performed by humans. This change is driven by an ongoing need to reduce operational cost.

Think of a BOT as an app that users interact with, in a conversational way. Bots can communicate conversationally with text, cards or speech. A bot may be as simple as basic pattern matching with a response, or it may be a sophisticated weaving of artificial intelligence techniques with complex conversational state tracking, and integration to existing business services.

Bot service enables you to build bots that support different types of interactions with users. You can design conversations in your bot to be freeform. Your bot can also have more guided interactions where it provides the user choices or actions. The conversation can use simple text strings or more complex rich cards that contain text, images, and action buttons. Infact, you can add natural language interactions, which let your users interact with your bots in a natural and expressive way.

Chat-bot conversation usually has three parts:

  1. An intent
  2. An utterance that the human user inputs to articulate their needs, and
  3. Chat-bot prompts, with which the chat-bot responds

The bot connector is the central component connecting our bot to Microsoft’s infrastructure. The infrastructure then provides the connections to various channels such as Skype, Mail, Text, or a variety of other possibilities. We do not need to adjust our application for these different channels.

During the process of creating a bot using bot service, you specify a name for your bot, set up its hosting plan, choose a pricing tier, and configure some other settings. After your bot has been created, you can change its settings, configure it to run on one or more channels, and test it within Web Chat.

Bot service is the piece we code. Bot service provides the core components for creating bots, including the Bot Builder SDK for developing bots and the bot framework for connecting bots to channels. Bot service provides five templates you can choose from, when creating your bots with support for .NET and Node.js. We should know how to use bot service to create a new bot that uses the Bot Builder SDK.

The problem usually with bots is that they are regarded as “stupid”. We enter some text snippet and if it’s a little bit off the norm, we will get an error. The level of tolerance and text understanding is certainly below any expectation from a normal conversation.

Microsoft realized this problem some time ago and built a solution to tackle it. It is called Language Understanding Intelligence Service (LUIS). It is part of Microsoft’s cognitive services, which may be familiar under their former name project Oxford. At its core, it’s a machine learning solution with a language knowledge layer.

The Microsoft Bot Framework offers different kinds of persistence. We can store data per user, per channel, or per user in channel. The mechanism is always the same, which is like using cookies. An incoming message contains the previously set entries applicable to this message, while the outgoing message contains the changed entries.

Modern messaging platforms support a variety of multimedia content, so instead of the traditional text-based statuses, the customers can get required information on a chat channels like images, maps etc., that the bot can generate.

 

Posted on – April 12th, 2018
By – Venkataramireddy AllaTechnical Lead

 

Read our Case Study on “AI using Chat-bots” to know more

Leave a Reply

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

Post comment