Tips for creating curated data sets for self-service BI users Data-driven storytelling opens analytics to all

4 ways natural language querying in BI tools can benefit users

Natural language queries help ease access to BI data and improve analytics insights. See how organizations are putting natural language querying techniques to work.

Natural language querying is designed to simplify the user interface in business intelligence applications. It enables both BI professionals and business users to generate queries and explore analytics data in natural language, using voice or text. Early implementations are focused mainly on enabling a larger number of employees to get information on common business metrics.

As natural language query technology matures, the process could be enhanced with AI guidance for improved insight, as well as natural language processing (NLP) techniques applied to back-end data analysis like conversational analytics and sentiment analysis. Conversational analytics evaluates customer service or employee-to-employee interactions, while sentiment analysis can help summarize consumer opinion from social media, emails and surveys.

Some advantages of using natural language querying tools include the following capabilities.

1. Simplifying employee access to BI data

Corporación Hijos de Rivera S.L., the Spain-based producer of Estrella Galicia beer and other beverage brands, is one early adopter of natural language querying to improve access to BI data for frontline business workers. JJ Delgado, the company's chief digital officer, has been working to add a natural language generation (NLG) interface on top of its MicroStrategy BI system -- an augmented analytics application that he said enables users to run new types of queries and more easily understand the results.

"We believe augmented analytics changes the game for us," Delgado said. "Not only can our users connect to the MicroStrategy platform to surface business information and get the insights they're looking for by asking Alexa a question, but they can also, through our NLG technology implementation, read intelligent narratives that describe the analyses they are seeing."

Marge Breya, chief marketing officer at MicroStrategy, said the BI vendor's experience with customers shows there are "large swaths of corporate employees that need immediate insights" from BI systems. But many business users lack the comfort level or skills to interpret complex graphs and other data visualizations themselves, she added.

Voice interfaces like Alexa will make it easier for these users to take advantage of voice-enabled technology to ask questions and get understandable answers in a natural manner, Breya said. For example, MicroStrategy has created NLP capabilities that can formulate a data visualization from a sentence of text entered by a user; it also has added Alexa connectivity and chatbot support.

2. Driving deeper business insights

Some experts believe that natural language querying could help drive deeper insights by lowering the expertise required to interact with BI and analytics tools. Instead of being limited to BI analysts, data scientists and other skilled analytics professionals, the tools become directly accessible to business users, which Gartner calls democratizing analytics.

Natural language query example for BI
Natural language queries enables BI users to explore data without having to write code.

In addition, it often takes multiple steps to get useful results from querying BI and analytics data, said Micha Breakstone, co-founder and head of R&D at conversational analytics platform vendor "Many deep insights come about through careful iterative processes where queries lead to noisy results with a very subtle signal hidden within, and through careful clean-up, cross-analysis and projections, the noise is cleaned, the signal becomes clearer and deep insights emerge," Breakstone said.

He added that the ability to use NLP for querying could vastly simplify such iterations and enable faster progress as data specialists and non-technical business experts collaborate more effectively, which ultimately should lead to better analytics insights.

Natural language querying also hides some of the complexity of locating related data in multiple systems. For example, if a user might be challenged in searching for a data element on credit card numbers across several data sources that use different names for the field, a natural language query could help identify and locate the various instances, said Gal Ziton, CTO and co-founder of Octopai, a metadata management platform vendor.

3. Reducing confusion about analytics results

To aid in the querying process, NLG technology enables BI tools to create narratives from data so that trends, variances and exceptions can be both visualized and described. The adage "A picture is worth a thousand words" is often true, but in many cases, there are different ways to interpret that picture -- or data visualization.

"Narration describes a visualization so there is no ambiguity [about] what it means," said John Hagerty, vice president of product management for business analytics at Oracle. Additionally, for many BI team members or business analysts, creating a narration of analytics results takes up huge amounts of time. NLG accelerates that activity in a profound way, Hagerty said.

4. Applying structure to unstructured data

The flip side of natural language querying on the front end lies in applying NLP techniques to help analyze unstructured data. "NLP makes sense of that unstructured data, making it organized, queryable and searchable," said Stephen Blum, founder and CTO of PubNub, a data management API provider.

A common example of unstructured data is social media data on a company's brand. Business executives want to know what people are saying and how they feel about the brand. NLP can both categorize social media mentions by topic and analyze the sentiments in posts. Those kinds of capabilities give business users a new way to query and analyze all the unstructured data in corporate systems, which an often-cited statistic says could be up to 80% of enterprise data overall.

Next Steps

7 steps to create a modern business intelligence strategy

Top 8 business intelligence challenges and how to handle them

5 valuable business intelligence use cases for organizations

Dig Deeper on Business intelligence technology

Data Management
Content Management