Promethium has released a new AI-powered Data Navigation System that uses natural language processing for analytics, enabling users to generate SQL queries from human language requests.
The goal of this new platform, according to Promethium, is to ease the delivery of data to the business unit requesting it. Promethium claims using data analytics with AI and machine learning-driven contextual automation software enables data to be delivered to users in a more digestible form.
Natural language processing (NLP) is the combination of natural language understanding and natural language generation. These two aspects in systems help machines understand spoken, written and gestural communication, and gives them the ability to respond in that preferred language. Essentially, NLP helps computers understand, interpret and manipulate human language in an effort to bridge the gap between human communication and computer understanding.
With the natural language processing for analytics feature, the Data Navigation System enables business analysts and other non-technical professionals to use plain language to search their organization's data for answers to complex questions.
After users ask a question, Promethium locates the data, demonstrates how it should be assembled, automatically generates the SQL statement to get the correct data and executes the query.
The queries run across all databases, data lakes and warehouses to draw actionable knowledge from multiple data sources. Simultaneously, Promethium ensures that data is complete while identifying duplications and providing lineage to confirm insights.
Data Navigation System is offered as SaaS in the public cloud, in the customer's virtual private cloud or as an on-premises option.
There are other analytics vendors that incorporate NLP into products. Microsoft has Q&A, Tableau has Ask Data and Oracle can process 28 different languages. However, according to Donald Farmer, principal at TreeHive Strategy, Promethium's use of natural language processing for analytics is a little different.
"Most of these vendors focus on querying the business intelligence artifacts they work with, rather than using natural language as an interface to the underlying data store," he said. "So Promethium may be doing something unique, but whether it is more useful for business users it's difficult to say."
Organizations continue to find ways to use NLP within different platforms and software. Chatbots are one of the most popular uses of this technology, with natural language processing enabling bots to understand questions and outperform other chatbots. Most people are also familiar with Alexa and Siri -- bots from Amazon and Apple that use NLP to assist in daily tasks through conversational communication.
However, Farmer noted that while the theoretical advantage of natural language processing for analytics is the ability to craft queries without learning a query language, in reality it's not always so simple.
"In practice, the best results from natural language processing interfaces nearly always come from users who learn to carefully craft unambiguous, clearly stated questions which they know the system can answer," he said. "It's often not very natural."
In order to truly judge Promethium's Data Navigation System, Farmer said it's important to see it in action right from the beginning.
"How long does it take to train? How natural is the experience? How well does it handle ambiguity, synonyms and sentiment? All important, but open questions," he said.