|Amazon Releases Natural Language Query Tool|
|Written by Kay Ewbank|
|Monday, 04 October 2021|
Amazon has released a natural language query tool for use with its QuickSight BI service. QuickSight Q is for use with the Enterprise Edition of QuickSight.
QuickSight is a cloud-powered business intelligence service that was introduced in 2015. Amazon QuickSight connects to an organization's data in the cloud and can combines data from multiple sources, inlcuding AWS, third-party data, SaaS and B2B data. It provides security, global availability, and built-in redundancy, along with user management tools.
The new query tool uses machine learning to interpret what a user means when they ask a question. If you're thinking this sounds suspiciously easy, you're right to be suspicious. Dive deeper into the workings of QuickSight Q, and you discover that the ability to answer questions is achieved by first creating topics that are then used to interpret those questions.
Topics are collections of one or more datasets that represent a subject area that your business users can ask questions about. Developers or administrators create topics by adding one or more datasets to a topic, then configuring the fields in the datasets to make them natural-language-friendly by entering descriptive names for the topic and fields. This is required for Q to provide your business users with the correct visualizations and answers to their questions.
Amazon QuickSight Q then creates, stores, and maintains an index with definitions for data in that topic. Q uses this index to generate correct answers, provide autocomplete suggestions when someone asks a question, and suggest mappings of terms to columns or data values. This is how Q can interpret key terms in your readers' questions and map them to your data.
The announcement of the new service says that
"Amazon QuickSight Q does not depend on prebuilt dashboards or reports to deliver visualizations, which removes the need for business intelligence (BI) analysts to update a dashboard every time a new business question arises, so anyone can ask their questions and receive visual answers in seconds."
The machine learning comes into play for interpreting the users questions to work out the probable intent behind it. QuickSight Q also provides auto-complete suggestions for key phrases and business terms, and automatically performs spell checking and acronym/synonym matching.
To make this work, the natural language models have been trained to recognize vocabulary and concepts drawn from likely domains such as sales, marketing, retail, HR, advertising, financial services, and health care.
or email your comment to: email@example.com
|Last Updated ( Tuesday, 05 October 2021 )|