Power BI Report on Bot Analytics for Chatbot in Bot Framework Composer | Custom Trace Event in PowerBI report from Application Insights logs | Bot Analytics for Bot Framework Composer - Readymade template

{tocify} $title={Table of Contents}

Tutorial: View analytics with Power BI

Intro

Purpose

The BOT framework Composer sample provides a Power BI template that can be used to understand how your bot is performing.

Overall usage

Personalize your experience for your brand and customers.


All dialogs overview

All dialogs' popularity and status based off of SDK telemetry


Dialog overview

Review a specific dialog's popularity and status


LUIS intents

A count of LUIS intents per day

All conversation metrics

Highlights the average number of conversations per unique user and the average duration by day https://lkgforit.com/power-bi-report-on-bot-analytics-for-chatbot-in-bot-framework-composer

Conversations drill down

Per conversation, this highlights the dialogs triggered and common utterances https://lkgforit.com/power-bi-report-on-bot-analytics-for-chatbot-in-bot-framework-composer

Transcript

Review interactions, sessions, and the transcript between a bot and its users https://lkgforit.com/power-bi-report-on-bot-analytics-for-chatbot-in-bot-framework-composer

Demographics

See where users are connecting to your bot https://lkgforit.com/power-bi-report-on-bot-analytics-for-chatbot-in-bot-framework-composer

Word Cloud

Common user queries

Sentiment analysis

Average user sentiment results provided by LUIS

QnA Maker insights


Insights on matched user queries with QnA Maker

User feedback


Insights on user submitted feedback https://lkgforit.com/power-bi-report-on-bot-analytics-for-chatbot-in-bot-framework-composer


Prerequisites

•    Install Power BI Desktop

•    Download the Bot Composer analytics Power BI template

•    Create a Bot in Composer to deploy your Azure resources


Scenario

A Power BI dashboard showing Application Insights telemetry captured from a Bot Composer BOT.

Tutorial: View analytics with Power BI
Get your Application Insights Application ID

1.  Log in to the Azure Portal.

2.  Navigate to the Application Insights resource created.

3.  In the sidebar, navigate to Configure > API Access on the sidebar. 

4.  Copy the Application ID for the next step. 

Tutorial: View analytics with Power BI

Open the Power BI template

1.  Open the Bot Composer analytics template and paste your Application Insights Application ID. 

2.  After loading the tables with your populated data, you should now see insights from your Virtual Assistant.

Note: You may run into authentication issues when opening the template, particularly if you have opened the template previously using another Application ID. If so, perform the following steps to re-authenticate the template with your Application Insights service:

1.  Open the Template

2.  File > Options and Settings > Data Source Settings

3.  Click "Global permissions"

4.  Click on anything resembling "api.logalytics.io" and Clear Permissions > Clear Permissions > Delete

5.  Close and Re-open the Template

6.  Paste your Application Insights AppId

7.  Click Load

8.  Important: Select Organizational Account > Sign In > Connect

Additional Telemetry

By default, a Bot composer Bot based project collects personally identifiable information (e.g. Conversation drill-down and transcripts) which will lead to the respective sections in the PowerBI dashboard to function as expected. If you wish to not collect this information make the changes to appsettings.json by following this article: https://docs.microsoft.com/en-us/composer/how-to-capture-telemetry?tabs=v2x#configure-telemetry

Raised a PR to Bot Framework Composer: https://github.com/microsoft/BotFramework-Composer/pull/8641

Comments

Post a Comment

Popular posts from this blog

File Transformation (variable substitution) and issues faced in Azure Devops  -  YAML

Variable substitution in Azure Devops | File Transformation in azure devops using YAML | Troubleshooting File Transformation in Azure Devops {tocify} $title={Table of Contents} Following this document used file transformation task in Azure Devops to substitute variables in json and xml files: https://docs.microsoft.com/en-us/azure/devops/pipelines/tasks/utility/file-transform?view=azure-devops # File transform # Replace tokens with variable values in XML or JSON configuration files - task: FileTransform@1  inputs:  #folderPath: ‘$(System.DefaultWorkingDirectory)/**/*.zip’  #enableXmlTransform: # Optional  #xmlTransformationRules: ‘-transform **\*.Release.config -xml **\*.config-transform **\*.$(Environment.Name).config -xml **\*.config’ # Optional  #fileType: # Optional. Options: xml, json  #targetFiles: # Optional When using this you will get following error message: “ changes already present message ”. Got the changes already present message when directly targeting the source f
Read more

Low Level Design GitHub Materials | Low level design materials | Low level design end to end open source

{tocify} $title={Table of Contents} 𝟏 ) 𝐓𝐇𝐄 𝐋𝐋𝐃 Low level Design / Machine Coding Question Collections ————— What is Machine Coding Round ? Machine Coding Round has become very popular interview round in most Product and startup companies like Flipkart, Cleartrip, navi and Udaan,the way the round is structured is the candidate will be provided with a Problem statement and the minimum set of features which needs to implemented within the 90 min window period, we as a candidate need to identity the data models, the service interfaces which will be consumed by the clients and other set of functions and classes, we should be able to present the same to the panel with are design choices / design patterns being made / used and the complete working code. What is the purpose behind this LLD repo ? During my recent Preparation, found out that there was no single resources where we get a collections of all the questions and the corresponding Answers, so currently updating the repo
Read more