News

Cortana, Power BI Integration Now In Preview

Developers can start testing a new feature that will allow users to ask Cortana to vocalize queries of data residing in Power BI-connected data sources.

Microsoft is showing a preview of the integration of Power BI and Cortana that lets users ask questions verbally or through typing and get answers back in the form of numbers, charts, maps or even complete reports. The melding of the two technologies adds the vocalization functionality to the natural language query ability already found in Power BI through theQ&A feature.

"One of the key ways Power BI enables more people to connect with and gain insight from their data is our natural language data search feature, Q&A," Microsoft exec Patrick Baumgartner said in a blog post Tuesday. "Now these Q&A capabilities are helping Cortana to intelligently reason over the data you have access to in Power BI and provide rich data-driven answers to your questions. Combined with the Cortana Analytics Suite, this opens up amazing new opportunities to use Cortana to enable your business, and your customers' businesses, to get things done in more helpful, proactive and natural ways."

The new preview is the latest embodiment of Microsoft's efforts to expand the functionality of Cortana -- a rival to Apple's Siri -- to other scenarios, including third-party partners like LinkedIn and internal services like Office 365, Cortana program manager Marcus Ash said in his own blog post. "As your truly personal digital assistant, we're enabling Cortana to call upon other services to help you get things done," Ash said.

To use the new feature in Power BI, the data being queried must already reside in Power BI, and Cortana rounds up the answers "herself" from raw data or extracts it from existing reports.

All that's required to get started is Windows 10 (November update or later) and adding a Power BI account to Windows 10. After that, verbally querying Cortana for Big Data insights is easy, Baumgartner said.

"Enabling data in Power BI to be accessed by Cortana is a simple process -- in fact all you have to do is pick a data source in Power BI and select 'Enable Cortana to access this dataset.'" Baumgartner said. "After that, any user who has access to the dataset in Power BI, via regular Power BI sharing, groups and content pack features will be able to get answers from the dataset in Cortana in Windows 10."

Microsoft also introduced a new Quick Insights feature that lets users point-and-click their way to hidden insights by using prebuilt analytical algorithms. "Through a partnership with Microsoft Research, we're honing a growing list of algorithms to discover and visualize correlations, outliers, trends, seasonality, change points in trends, and major factors within your data, automatically, within seconds," Baumgartner said.

Existing algorithms include a variety of time series-based explorations to discern overall trends, seasonality factors and others, along with new algorithms expected to be available soon, such as "change points in a time series" and "low variance."

Baumgartner invited users to try out the new functionality and provide feedback to improve the algorithms.

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • Compare New GitHub Copilot Free Plan for Visual Studio/VS Code to Paid Plans

    The free plan restricts the number of completions, chat requests and access to AI models, being suitable for occasional users and small projects.

  • Diving Deep into .NET MAUI

    Ever since someone figured out that fiddling bits results in source code, developers have sought one codebase for all types of apps on all platforms, with Microsoft's latest attempt to further that effort being .NET MAUI.

  • Copilot AI Boosts Abound in New VS Code v1.96

    Microsoft improved on its new "Copilot Edit" functionality in the latest release of Visual Studio Code, v1.96, its open-source based code editor that has become the most popular in the world according to many surveys.

  • AdaBoost Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the AdaBoost.R2 algorithm for regression problems (where the goal is to predict a single numeric value). The implementation follows the original source research paper closely, so you can use it as a guide for customization for specific scenarios.

  • Versioning and Documenting ASP.NET Core Services

    Building an API with ASP.NET Core is only half the job. If your API is going to live more than one release cycle, you're going to need to version it. If you have other people building clients for it, you're going to need to document it.

Subscribe on YouTube