Image: © Andrei/Stock.adobe.com
The company has launched Amazon Kendra, which can be used to search internal documents spread across portals and silos.
On Monday (11 May), Amazon Web Services (AWS) announced the general availability of Amazon Kendra, its enterprise search service powered by machine learning.
Businesses can use Amazon Kendra to search internal documents spread across portals and wikis, while research organisations can create a searchable archive of experiments and notes. Kendra can also be used by contact centres to help employees find the right answer to customer questions across a complete library of support documentation.
The company explained that when users ask a question, Kendra uses machine learning algorithms to understand the context and return the most relevant results, whether that’s a precise answer or an entire document.
It can be set up completely within the AWS Management Console, and customers can get started with Kendra here.
A problem for enterprises
In a statement about the release of Amazon Kendra, AWS said that searching for information within an organisation is still a “vexing problem” for enterprises, with many businesses struggling to implement internal search across their siloed troves of data.
“Organisations have vast amounts of unstructured text data, much of it incredibly useful if it can be discovered, stored in many formats and spread across different data sources,” the company said.
“Even with common web-based search tools widely available, organisations still find internal search difficult because none of the available tools do a good job indexing across existing data silos, don’t provide natural language queries, and can’t deliver accurate results.”
Kendra’s features
AWS said that natural language understanding has been built into the core of Kendra’s search engine, so users can search for specific questions, such as ‘When does the IT help desk open?’ and the search tool will provide a specific answer.
Kendra encrypts data in transit and at rest and can integrate with commonly used data repository types, such as file systems, applications, intranet and relational databases, so developers can index their company’s content within a few clicks.
The tool supports industry-specific language from a variety of industries, including IT, healthcare, human resources, financial services, legal, travel and hospitality, telecoms and automotive.
Swami Sivasubramanian, vice-president of Amazon machine learning at AWS, said: “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.
“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 organisation’s data.”
