BotFramework using RFPIO

 In this page, i'll explain on "How chatbot is responding to users questions by using RFPIO".

When any orgination planning to create a chatbot application, RFPIO is a good platform. RFPIO is easily integrate with any platform and able to fetch data from document library or QnA pairs. RFPIO is good choice for your knowledge base.

First we need to understand what is RFPIO ?

RFPIO is the market leader in response management software, trusted by some of the world's smartest companies to support RFP and Security questionnaire response, create and manage sales proposals, and resolve inefficiencies rooted in decentralized and inaccessible content and knowledge. The software's robust and bi-directional integrations, along with an open API, allow teams to digitally transform response management processes and to harness the power of the knowledge and content across their teams. RFPIO supports response management for growing organizations of all sizes including Google, Adobe, Atlassian, Microsoft, Tenable, Zoom Video and others. For more information on RFPIO, click here

Once you uploaded all the documents in RFPIO.  Create a LUIS intent and train the questions or else use Azure Text Analytics in place of LUIS. 

What is LUIS ?
LUIS stands for Language Understanding Intelligent Service. LUIS is one of the fastest NLP tool present in the market, it utilizes machine learning to give your bot natural language processing capabilities. By converting user requests in natural language to actionable bot commands, LUIS acts as a translator for your bot.It is a natural language processing service and it provides some awesome benefits like
- Built-in support from Microsoft Bot Framework.
- Well-trained prebuilt entities.
- A user friendly GUI portal where you can create, test and publish LUIS apps with just a couple of clicks
- LUIS API, Pre Build Machine learning NLP model, Easy understanding.

Limitations:
- LUIS limits 500 applications per Azure authoring resource
- Free Tier: 10,000 transactions per month (maximum of 5 calls per second).
- Basic Tier: 1 million transactions per month (maximum of 50 calls per second).

To know more details click here

what is Text Analytics ?

Azure text analytics is easy to detect sentiment, key phrases and languages in your text. It is programatically detect below
Sentiment - Is text positive or negative?
Key phrases - What are people discussing in a single article?
Topics - What are people discussing across many articles?
Languages - What language is text written in?

Limitation :
The maximum size of a single document that can be submitted is 10KB, and the total maximum size of submitted input is 1MB. No more than 1,000 documents may be submitted in one call.
To know more details click here

Once Bot received question from the user, question can be key phrase extraction by using Text Analytics and sending all keywords to the RFPIO document library and will receive relevant answer to the question. Incase user not satisified with the answer, bot will provide feedback option whether user satisfied with bot response or not. Sometimes users not satisfied with bot response, those questions posting on your sharepoint site. Your support team will identify these questions and prepare the content for the questions and uploading back to RFPIO library.

Finally log all your chatbot converstaion into the azure application insights and your dev team can generate the powerBI reports by using application insights,  Click here to understanding on Power BI reports from Application Insights

You develop reports like
- How many users using your bot application?
- How many questions requested by users?
- How many questions bot not answred?
- How many users satisfied with bot response?
- How many users not satisfied with bot response?
- What are the user questions and bot response?

.