Business Problem

Recently one of our customers in Australia came to us to solve a problem yet they were facing in the support department. They still receive a lot of support requests daily. The solutions for most of these requests are already available in the user manuals, support site, and other materials to which the customers have access. Since many of these requests are easy to fix, it’s a struggle to invoice the customers properly. Also, a lot of support staff is needed to meet the demand. Our client wanted us to come up with a solution to this problem.

We looked at the following parameters to suggest a solution.

The channels of support request

The volume of resources (support documents)

The channels of support requests.

• Microsoft Teams
• Help desk system
• Email requests

The volume of the resources

• Support site
• User manuals
• Q&A site

Based on these facts we decided to organize the resources in a manner that a customer would be able to find out the answers using one of the above-mentioned mediums without having to contact the support staff.

Proposed Solution

We proposed an intelligent Chat-Bot that will be deployed on Microsoft Teams and in their Help Desk system. So, the customers would first chat with the bot and the bot would analyze the available resources for possible solutions. However if the Chat-Bot failed to respond positively then, it would create a support ticket and assign it to support staff.

Tools

We then looked at the tools that we can use to develop our Chat-Bot. Furthermore there are plenty of resources out there but, we felt the suite of tools provided by Microsoft are more reliable and easy to use. Microsoft has invested a lot in AI and Natural language processing and has come up with several tools that are ideal to build an intelligent Chat-Bot. Also, it’s easy to test and deploy these tools because of the integration with Azure.

• App Service (https://azure.microsoft.com/en-us/services/app-service/)
• QnA (https://www.qnamaker.ai/)
• Adaptive Cards (https://adaptivecards.io)
• Cosmos DB (https://docs.microsoft.com/en-us/azure/cosmos-db/introduction)
• Microsoft Teams (https://teams.microsoft.com)

QnA service

QnA service extracts question and answer pairs from the content that you upload. The content can be uploaded as URLs, PDFs, Excel files, SharePoint documents, and many more.

Adaptive cards

Adaptive Card is an open-source toolset that helps apps and services exchange rich snippets of native UI.

Microsoft Teams

Microsoft Teams is a unified communications platform that combines persistent workplace chat, video meetings, file storage, and application integration.

Azure Cosmos DB

Azure Cosmos DB is Microsoft’s globally distributed, multi-model database service. With a click of a button, Cosmos DB enables you to elastically and independently scale throughput and storage across any number of Azure regions worldwide.

Chat Bot Behavior

The ChatBot uses QnA service to query the proposed answers for customer queries. We have used Cosmos DB to store the chat session and related data. It’s deployed to Microsoft Teams as a plugin and is available on the support site as a widget.

Generally speaking, once a user enters the chat room in Microsoft Teams he would be initiating a chat with the Bot. The rest of the flow is as follows,

• A customer initiates a chat with the bot in Microsoft Teams
• The customer is greeted and shown a welcome card asking for the name and email address
• Customer types in his question
• Chat-Bot responds with an answer or more options to fine-tune the response
• A customer gives feedback on the answers
• If Chat-Bot is unable to find the best answer then, A feedback form is displayed
• A customer fills in the feedback form
• Chat-Bot creates a support ticket with all the information
• Send the link to the customer

Implementation

We first created the repository using all the documents, manuals, and URLs. The QnA service allows us to import these different types of resources and generates question and answer pairs. Also, we can extract multipart answers as well so that when a customer asks a question it will be able to refine the answers by giving options.

QnA Maker

We first set up the knowledge base in the QnA maker. Go to https://www.qnamaker.ai/ and click on Create a knowledge base. You must go through 5 steps to set up the knowledge base.

• Create QnA service in Microsoft Azure
• Connect your QnA service to KB
• Name your KB
• Populate your KB
• Create your KB
• Publish your KB

Once the QnA maker is set up it gives us an interactive window to test the chat. Also, we can build a tool to train our Bot using the Train API. In the process of setting up QnA, we need to set up a QnA service in Azure as well. This is an app service where the Bot deployed and hosted.

Cosmos DB

Go to the Azure dashboard and set up Cosmos DB instance.

appsettings.json

Bot app is a .Net Core Web API project. Hence, it has the same structure as a Web API Project. The Bot client communicates using JSON.

The request received by the BotController and passed over to Microsoft.Bot.Builder.IBot instance. This configuration added in the startup.cs as follows,

services.AddTransient<​IBot, QnABot.Bots.QnABot>();

The IBot instance has three delegates,

• OnMembersAddedAsync
• OnTurnAsync
• OnMessageActivityAsync

OnMembersAddedAsync

This delegate triggered when a new chat window is created. This is the delegate we use to send a welcome notification to the user.

OnTurnAsync

When implemented in a bot, handles an incoming activity.

OnMessageActivityAsync

This is the delegate that is triggered when a message is sent by the client to the bot.

In our application, we identified 4 chat states which are,

• User-information
• Chat-information
• User-feedback
• Support-ticket

User-information

This is the initial state. User information is when we capture the user’s name and email and show a welcome message.

Chat-information

Chat information is when we capture user’s requests and send the data to the QnA service. The QnA service would return either response or prompts. This goes on until the user receives the answer he is looking for or he decides to create a support ticket.

User-feedback

User feedback when we capture whether the user’s request answered properly or whether a support ticket needs to be created. When the support ticket created we log the entire chat history in the ticket.

Support-ticket

The support ticket is the step of creating a support ticket in the ticketing system( https://www.servicenow.com/) based on user feedback.

Source Code

Source code can be downloaded from here. Once you download the source code you should do the following.

• Take a copy of appsettings_dev.json
• Rename appsettings_dev.json to appsettings.json

#Chatbots #Azure #Luis #Microsoft Bot Framework

Authored by Pragash Rajarathnam @ BISTEC Global

LinkedIn is the #1 platform for Lead Generation according to DemandWave state of B2B Digital Marketing Report in both 2016 & 2017

If LinkedIn was a country, it is only second to China & India. With over 560 million users, it stands 3rd in the list well ahead of the USA.

LinkedIn members come from 200 countries & 18 million companies. So the power of the LinkedIn platform is enormous.

In 2016 Microsoft purchased LinkedIn for 26.2 billion USD in cash. 

Beyond the numbers, let’s look at why LinkedIn should be your main marketing platform!

LinkedIn as a marketing platform

LinkedIn has been traditionally thought of as a platform to maintain a professional profile. Although this is true even today, B2B Digital Marketing Report identifies LinkedIn as the #1 platform for lead generation both in 2016 & 2017.

Let’s look at why LinkedIn has gained its status as the #1 marketing platform.

• LinkedIn has more than 9 billion content impressions per week. This means there are more than 9 billion views by LinkedIn users in total.
• 100 million users out of 560 million are influencers & decision makers. This means whatever you published has significant chance of viewed by people who can take a business decision.
• LinkedIn audience has two times more buying power than average web audience according to LinkedIn Audience 360 study

If you are looking to enhance your marketing and improve lead generation, LinkedIn is THE place to go.

What benefits you get out of LinkedIn as a marketing platform?

The two words answer is “cost-effectiveness”.

It is said that around 10% of the total company budget is going to marketing. This money can go a total waste unless planned correctly. Below are five reasons why you should choose LinkedIn to spent most of your marketing budget.

1. LinkedIn is a focused platform: You will not somebody’s vacation pictures in LinkedIn. By design LinkedIn downgrades not relevant content. Therefore your marketing messages and content has a comparatively much greater chance of reaching the target audience compared with other digital marketing platforms.
2. Free marketing: LinkedIn marketing is not depends on paid ads & content. You can do posts, publish articles, make comments, send direct messages, etc. without paying a single cent. These non-paid activities will give you a huge milage in terms of lead generation & brand awareness.
3. Target marketing: In terms of paid advertisements, LinkedIn has a powerful campaign manager & where you can use it to narrow down your target audience. It provides many parameters to target the exact audience you want compared to traditional marketing.
4. Complete ecosystem: LinkedIn comes with wide array of tools which can be used to market product or services. For example, you can use company page or showcase pages to provide marketing content to its 563 million users. LinkedIn introduces tools such as LinkedIn forms, plugins, etc. to make the lead generation efficient. Further many third party companies have developed tools on top of LinkedIn. Further, LinkedIn creates lot of content by themselves to help businesses to grow. Example is LinkedIn for small businesses.
5. LinkedIn communities & groups: LinkedIn is having a rich & vibrant communities & groups. You can use these groups to further narrow down your marketing segments and activities to have a better hit. LinkedIn official and unofficial community gatherings provides opportunities for face to face marketing.

Summary

You have a higher chance of connecting to a person whom you don’t know on LinkedIn. The chance of an unknown professional in the USA accepting your connection request is higher in LinkedIn compared to Facebook or any other social marketing platform.

Also the % digital marketing spending will take over the traditional marketing within the next 5 years. companies will invest heavily in digital marketing in the coming years.

If you want to be at the helm of this trend and to get the best value for the money you spent in marketing, you need to make a move to LinkedIn today.

You can download our white paper to understand how you should LinkedIn for your marketing activities. Please fill in the form. At #bistec, we understand this and would love to help you in your journey.