The service uses a natural language query tool that makes it easier for users to ask questions.
Known simply as “Q”, the tool allows a company’s employees to ask business questions using natural language. For example: “How many customers bought product X and in which month did they make the purchase?”. They then receive accurate answers in the shape of visualizations based on data. The tool aims to help users quickly search and gain insights from company databases using normal language.
Amazon QuickSight Q relies on natural language processing and machine learning. These services have been trained on multiple business areas and data points.
Q extracts terms such as “revenue,” “growth,” “allocation” and the like, as well as the intent of the user’s question. It then surfaces related data that has the answers to that question. It also provides answers in the form of numbers or graphs.
Jeff Barr, Chief Evangelist for AWS, announced the general availability of Quicksight Q in a blog post this week. “To recap, Q is a natural language query tool for the Enterprise Edition of QuickSight,” he writes.
“Powered by machine learning, it makes your existing data more accessible, and therefore more valuable. Think of Q as your personal Business Intelligence Engineer or Data Analyst,” he says.
Here’s how it works
Q uses Natural Language Understanding (NLU) to discover the intent of the user’s question, Barr explains. The tool is aided by models that have been trained to recognize vocabulary and concepts drawn from multiple domains . These include sales, marketing, retail, and so forth. Q is thus able to answer questions that refer all data sources supported by QuickSight.
This means Q can analyze data from multiple AWS sources. These include Amazon Redshift, Amazon Relational Database Service (RDS), Amazon Aurora, Amazon Athena, and Amazon Simple Storage Service (Amazon S3). It can also handle data from third party sources & SaaS apps such as Salesforce, Adobe Analytics, ServiceNow, and Excel.