Today, we’re announcing Data QnA, a natural language interface for analytics on BigQuery data, now in private alpha. Data QnA helps enable your business users to get answers to their analytical queries through natural language questions, without burdening business intelligence (BI) teams. This means that a business user like a sales manager can simply ask a question on their company’s dataset, and get results back that same way.
We built Data QnA to make it easier for non-technical users to access the data insights they need through natural language understanding techniques—all while maintaining the business’s governance and security controls. Data QnA is based on the Analyza system developed here at Google Research. Analyza uses semantic parsing for analyzing and exploring data using conversation, i.e., doing entity and intent recognition, then mapping to the underlying business datasets. Data QnA enables anyone to conversationally analyze petabytes of data stored in BigQuery and federated data sources. Data QnA can be embedded where users work, including chatbots, spreadsheets, BI platforms (such as Looker), and custom-built UIs. As part of this private alpha, we are rolling out support in English, and look forward to working with our customers to determine demand for regional localization.
In most enterprises, when business users need data, they request a dashboard or report from the BI team, and it can take days, or even weeks, for the already overloaded team to respond. When the users get those answers, they are often not able to get an answer to the next question, as that would require yet another report. Self-service access to analytics when users need it, without requiring deep technical knowledge, can improve productivity and business outcomes dramatically. With the help of Data QnA, you’re able to put BigQuery data right in front of the user, in the context of their business workflows.
“With Data QnA, Google Cloud is making a long term play at democratizing data insights for non-technical users,” said Mike Leone, Senior Analyst, ESG. “This self-service model will not only speed up the pace of innovation and digital transformation for businesses, but also help optimize overhead costs by saving valuable time and increasing the productivity of BI teams.”
“At Veolia, we were taking weeks responding to ad hoc analytics requests from our business partners. This was reducing the time we could spend on higher value activities,” said Fabrice Nico, Data and Robotic Manager at Veolia. “We at the BI team have since enabled self-service access to BigQuery data by asking questions in natural language. The Google service, through Sheets and chatbots, is going to free up our time significantly, and enable our business partners to execute faster through natural language-based analytics.”
How Data QnA works
Data QnA enables self-service analytics for business users on BigQuery data as well as federated data from Cloud Storage, Bigtable, Cloud SQL, or Google Drive. Users can ask free-form text questions, like: “What was the growth of product xyz last month?” and get answers interactively. Data QnA is natively available through Google Sheets and BigQuery UI. Data QnA API can be used to embed it in other interfaces. In addition, you can integrate Data QnA into experiences built with Google Dialogflow. Data QnA enforces all underlying customer-defined data access policies, automatically restricting access of data to the right users.
We’ve heard from customers, analysts and partners about Data QnA’s benefits, including self-serve analytics, increased BI team productivity, and saved time for both business users and IT teams.
Data QnA allows users to formulate free-form text analytical questions, with auto-suggested entities while users type a question. Then, both an English interpretation and the SQL query are returned with the answer. “Did-you-mean” clarifications are returned if a question is ambiguous. When using the BigQuery Web UI, Data QnA also enables data analysts to formulate SQL queries using natural language questions.
In addition, Data QnA has a management interface for data owners or admins to define business terms for underlying data, allowing business users to use the language they understand—initially just English, with more to come depending on demand. The interface also reports questions asked by the users along with the answers and SQL query, enabling the data owners to improve the service for their users.
Getting started with Data QnA
Data QnA is available at no additional cost for BigQuery customers. All underlying queries and storage are charged as per the customer’s BigQuery costs. Access in Sheets is through its Connected Sheets feature, which is included in G Suite Enterprise, G Suite Enterprise for Education, and G Suite Enterprise Essentials, and Data QnA is included for no additional cost. Data QnA is available for BigQuery data in the U.S. and EU, with support for more regions to follow.
You can work with the following Google Cloud partners to get started: Accenture, Deloitte, EPAM, Mavenwave (an Atos company), SADA, and Wipro.
“We’re eager to put Data QnA to work with our customers to help accelerate their self-serve analytics initiatives,” says Arnab Charkaborty, Head of Applied Intelligence, US West at Accenture. “Data QnA is effectively drawing a straight line between all the business apps our customers use everyday and their data in BigQuery so anyone—no matter their level of data literacy—can ask questions in natural language without leaving that environment. That’s data democratization at its finest!”
To learn more about the technology behind Data QnA and to see a few demos, register to watch our Next OnAir session: Data QnA: How Veolia democratizes access to BigQuery, available starting August 11.
Read More for the details.