Amazon has announced its enterprise search service Kendra is now available. Kendra is powered by machine learning, and designed to help enterprises index, search, and gain insight across their data silos.
The company explained the solution is built to provide high-quality results to natural language queries instead of a random list of links in response to keyword searches. When users ask a question, machine learning algorithms understand the context in which it is asked and return the most relevant results.
Additionally, the algorithms require no machine learning expertise and can be set up within the AWS Management Console.
“Businesses can use Amazon Kendra to search internal documents spread across portals and wikis, research organizations can create a searchable archive of experiments and notes, and contact centers can use Amazon Kendra to find the right answer to customer questions across the complete library of support documentation,” Amazon wrote in a post.
Amazon also found that many businesses struggle to implement internal search across their siloed troves of data, requiring their end-users to use keywords that may appear in multiple documents in different contexts, and these searches typically generate long lists of random links that end-users have to sift through to find the information they seek.
Now with Kendra, instead of having to specify keywords, users can ask question using natural language and the machine learning models will understand the context of the question and make sure the content of a document is relevant, the company explained.
As an example, an employee can ask a specific question like “when does the IT help desk open?” and Amazon Kendra will give them a specific answer like “9:30 AM,” and highlight the passage in the source document where it found the answer, along with links back to the IT ticketing portal and other relevant sites.
Currently, Amazon Kendra is built to understand the industry-specific language from IT, healthcare, insurance, energy, industrial, financial services, legal, media and entertainment, travel and hospitality, human resources, news, telecommunications, mining, food and beverage, and automotive, with additional industry support coming in the second half of this year.
Amazon Kendra encrypts data in transit and at rest and easily integrates with commonly used data repository types such as file systems, applications, Intranet, and relational databases, so developers can index their company’s content without writing any code. Developers can also add data sources to their Amazon Kendra search index by selecting the connector type, and those connectors will maintain document access rights.
Additional details are available here.
