-
This is where services like Kendra come in — they use AI to return results more relevant to users or embedded in apps issuing search queries.
-
Amazon says Kendra’s models are optimized to understand language from domains like IT, healthcare, and insurance, plus energy, industrial and many more.
-
Queries in Kendra can be tested and refined before they’re deployed, and they self-improve over time as the underlying AI algorithms ingest new data.
Amazon today launched Kendra in general availability, an AI and machine learning-powered service for enterprise search. It debuted in preview last December during in Las Vegas, and it’s now available to all AWS customers.
Enterprises typically have countless data buckets to wrangle; with upwards of 93% saying they store data in more than one place. Some of those buckets inevitably become underused or forgotten. A Forrester survey found that between 60% and 73% of all data within corporations is never analyzed for insights or larger trends. This is where services like Kendra come in — they use AI to return results more relevant to users or embedded in apps issuing search queries.
Once configured through the AWS Console, Kendra leverages connectors to unify and index previously disparate sources of information (from file systems, websites, SharePoint, OneDrive, Salesforce, ServiceNow, Amazon Simple Storage Service, relational databases, and elsewhere). Customers answer a few questions about their data (and optionally provide frequently asked questions (think knowledge bases and support documentation) and let Kendra build an index using natural language processing to identify concepts and their relationships.
Amazon says Kendra’s models are optimized to understand language from domains like IT, healthcare, and insurance, plus energy, industrial, financial services, legal, media and entertainment, travel and hospitality, human resources, news, telecommunications, mining, food and beverage, and automotive. (Support for additional domains is set to arrive in the second half of this year.) In practice, this means an employee can ask a question like “Can I add children as dependents on HMO?” and Kendra would (1) provide answers related to that person’s health care options, (2) highlight the source document where it found the answer, and (3) suggest other relevant links and sites.
Read More:
Kendra helps to ensure that search results adhere to existing access policies by scanning permissions on documents, so that results only contain documents for which the user has permission to access, and it encrypts data in transit and at rest.
Here’s a few of the other questions it can understand:
• “How do I set up my VPN?”
• “How long does it take for insurance policy changes to go into effect?”
• “When does the IT help desk open?”
• “What is the genetic marker for ALS?”
• “What are some of the proposed treatments for COVID-19?”
Queries in Kendra can be tested and refined before they’re deployed, and they self-improve over time as the underlying AI algorithms ingest new data. Companies can manually tune relevance, boosting certain fields in an index such as document freshness, view counts, or specific data sources. And the end-user prebuilt web app is designed to be integrated with existing internal apps, with signal-tracking mechanisms that keep tabs on which links users click and which searches they perform to improve the underpinning models.
Last year saw renewed interest from the corporate sector in AI-powered software-as-a-service (SaaS) products that ingest, understand, organize, and query digital content from multiple sources. Beyond Kendra, Microsoft kicked the segment into overdrive by launching , a service that taps AI to automatically classify and analyze an organization’s documents, conversations, meetings, and videos. It was in some ways a direct response to Google Cloud Search, which pulls in data from a range of third-party products and services running both on-premises and in the cloud, relying on machine learning to deliver query suggestions and surface the most relevant results.
In any case, the cognitive search market is exploding — it’s anticipated to be worth $15.28 billion by 2023, up from $2.59 billion in 2018, according to Markets and Markets.
Read More: