Search engines are pretty simple to understand. You enter keywords and get back results that match your string. However, while it’s convenient for searching on Google, search engines for company databases usually aren’t as efficient and easy to use.
Tech giants are quick to recognize this inconvenience, with Amazon already first in line to come up with a solution.
Last May 13, Amazon Web Services (AWS) launched Amazon Kendra, an enterprise search tool powered by machine learning. What makes the program different is its use of natural language processing (instead of typed phrases) for search, allowing users to ask a question and find an answer simply.
Aimed at enterprises, Kendra can be utilized to search internal documents from organizational archives. Its main goal is to improve productivity and precision in search by eliminating the use of ambiguous keywords that often bring pages of irrelevant results.
“Amazon Kendra reinvents enterprise search by allowing end-users to search across multiple silos of data using real questions (not just keywords) and leverages machine learning models under the hood to understand the content of documents and the relationships between them to deliver the precise answers they seek (instead of a random list of links),” AWS described. “Today, we’re excited to make Amazon Kendra available to our customers and enable them to empower their employees with highly accurate, machine learning-powered enterprise search, which makes it easier for them to find the answers they seek across the full wealth of an organization’s data.”
As of writing, Amazon Kendra is available in the US East (N. Virginia), US West (Oregon), and EU West (Ireland). Other regions to follow soon.