AWS launches machine learning-based enterprise search service
Amazon Kendra doesn't require machine learning expertise or keywords
Kendra enables businesses to index all of their internal data sources, make that data searchable, and allow users to get precise answers to natural language queries with just a few clicks, according to AWS.
The service doesn't require machine learning expertise and can be set up completely within the AWS Management Console. A key part of it is that rather than using keywords to search through datasets, Kendra uses machine learning algorithms that can understand specific questions.
This enables businesses to search internal documents spread across portals and wikis, research organisations to create a searchable archive of experiments and notes, and contact centres can use it to find the right answer to customer questions across a library of documentation.
"Our customers often tell us that search in their organisations is difficult to implement, slows down productivity, and frequently doesn't work because their data is scattered across many silos in many formats," said Swami Sivasubramanian, VP of Amazon Machine Learning.
"Using keywords is also counterintuitive, and the results returned often require scanning through many irrelevant links and documents to find useful information."
Kendra is underpinned by technology that understands natural language, and as such employees can run searches with detailed questions. They can still use keywords, but it is optimised to understand complex language from multiple domains, including IT, healthcare and life sciences.
How manufacturers can push past the AI tipping point
The time to start with AI is nowDownload now
Kendra also supports industry-specific language from insurance, energy, industrial, financial services, legal, media and entertainment, travel and hospitality, human resources, news, telecommunications, mining, food and beverage, and automotive.
The service encrypts data in transit and at rest, according to AWS, and it integrates with commonly used data repository types such as file systems and relational databases, so developers can index their company's content with just a few clicks, and provide end-users with accurate search without writing a single line of code.