Enterprise search consists of two components: the search experience itself and the content organizing and indexing activities that precede it -- and AI streamlines the connections between the two.
Enterprise search is the technology category for finding things within enterprise-scale content silos. When business users have a problem, they need to look for an answer within the company's collection of enterprise repositories. The more precisely you can define your query, the better the results -- retrieving exactly the information you want within the content collection, without sifting through many nonrelevant items. Your enterprise search experience may include different facets for searching and suggest relevant criteria to use. Depending on the design of the UI, it may list valid search terms in a drop-down menu or recommend terms through type-ahead suggestions.
Initially, enterprise search is an exercise in explicit indexing. Somebody within the business must define the schema of search criteria and introduce a controlled vocabulary -- or taxonomy -- of search terms for retrieving unstructured content from the repository. People must tag content items by relevant search terms, supplementing basic metadata, such as file name and date last modified, provided by the underlying OS. Sometimes, this tagging occurs within the flow of everyday work -- for example, when office workers fill out forms before filing a document.
Content analytics is what makes these explicit activities implicit. For instance, indexing services can automatically catalog a collection of documents by extracting individual words and phrases within documents, identifying all the places where the terms appear and running a Boolean search query to retrieve all items that meet the search criteria. Other techniques include latent semantic analysis, text sentiment analysis and similarity analysis.
AI in enterprise search -- also known as cognitive search -- is that class of promising algorithms that extracts meaning from different types of digital assets, including documents. The technology is now beginning to enter the corporate mainstream. To keep things in perspective, indexing services and latent semantic analysis were once considered AI but are now mainstream technologies.
Today, AI comes in different flavors of cognitive services. Industry stalwarts, such as Microsoft, Google and IBM, provide some, while others are invented by a host of promising, highly focused startups. AI in enterprise search includes multiple techniques to enrich content through machine learning algorithms, identify objects within images and videos, and organize information to solve predefined knowledge domains. New algorithms and approaches are continually on the horizon.
Dig Deeper on Enterprise search engines and strategy
Related Q&A from Geoffrey Bock
While business process management and workflow work together, they have two very different functions. Learn how they can fit into your business model. Continue Reading
Integrating e-commerce with a CMS can be a challenge, but many vendors are building compatibility into the cloud. Here's how and why those processes ... Continue Reading
Programs such as Box Shield use machine learning to better secure content, as it monitors existing content continually to learn about new threats ... Continue Reading
Have a question for an expert?
Please add a title for your question
Get answers from a TechTarget expert on whatever's puzzling you.