DiscoveryOne Content Enrichment automatically tags and categorizes content. Typically, it is used to improve findability of information in an Electronic Content Management System (ECMS) by enabling faceted search. It also improves the ability to categorize content against business classification schemes and document retention policies within an organization.
DiscoveryOne is fast and easy to implement – keyphrases and named entities come out-of-the-box. It is automatic, therefore consistent, avoiding typical human errors. It supports multiple languages and provides data for faceted search, which is the single most desired feature, as indicated in user studies, for improving findability of documents.
Ceate Automatic Metadata and Fix Insufficient Metadata
Metadata enables ECMS’ search, information compliance, retention policies and workflows. Usually, to get metadata, users have to fill in new text fields every single time they add or update content. This is slow and painful, and in reality very few employees bother to do this – and if they do, it is very inconsistent across an organization. However, Pingar creates metadata automatically, so people can forget about doing it themselves. Furthermore, you can set up DiscoveryOne Content Enrichment to read and fix insufficient metadata.
What is DiscoveryOne Content Enrichment used for?
Pingar improves Enterprise Content Management System (ECMS) search by creating clearly classified and categorized metadata. It provides relevant search refiners, which allow your users to ignore irrelevant search results by showing categories, topics and other types of metadata. Automatic metadata extraction makes ECMS search fast and relevant.
Improve Data Migration
It is best practice to enrich existing content with correct and sufficient metadata before documents are migrated to a new Enterprise Content Management System. It decreases the cost and effort. Furthermore, DiscoveryOne Content Enrichment auto-categorizes your documents according to its true content, instead of focusing on previously created insufficient or incorrect metadata.
Extract Valuable Entites
DiscoveryOne Content Enrichment can quickly detect organizations or companies, people, locations, addresses, account numbers, dates, and many other custom created entities. It also handles a number of language issues, such as matching similar terms, misspellings of words, and equivalent spellings in different variations of English.
In the research paper “Search interface feature evaluation in biosciences”, conducted by Dr. Anna Divoli and Dr. Alyona Medelyan and published at HCIR 2011, our researchers found that faceted search is the single most desired feature for improving search relevance.
Faceted search enables users to decide how to start and explore results, but most importantly, it can reduce search results from hundreds of mostly irrelevant ones to the few that truly matter. Faceted search offers multi-dimensional filtering, which makes search intuitive, even for non-expert users on the subject.
What makes DiscoveryOne Content Enrichment special?
DiscoveryOne is founded on research and development on different technologies, methodologies and concepts by the Pingar team. We have a specialist team of text analytics experts including published PhDs who continue to do groundbreaking research for methods to improve the accuracy of entity extraction from complex documents. Some of the largest companies in the world rely on Pingar to read and extract meaning from millions of their documents.
The underlying Pingar technology is built on three pillars: keyphrases, pre-defined categories and named entities.
A named entity is a name or phrase that uniquely identifies an object from a set of other objects with similar attributes.
KeyPhrases are prominent phrases that describe the main topics inside the content.
A taxonomy is a hierarchical structure of terms and can enable search engines to find desired terms, even when the terms of interest are mentioned using synonymous terms.
Easy to Implement and Use
DiscoveryOne is easy and fast to implement and offers an intuitive interface. Users do not need to be text analytics experts to extract, analyse and report valuable information.
English, Chinese, German, French, Spanish, Dutch, Japanese, Italian and Arabic.
Other languages are available upon request.
DiscoveryOne can read, categorize and extract value from a variety of sources such as corporate documents, web articles, social media, RSS feeds, e-mails, forums, etc.
How can we help you?
Does SharePoint 2016 Improve Search?
SharePoint 2016 does include some search modifications; the most notable being those related to the new cloud hybrid search. These modifications may have had an impact on the underlying flow by which search results are retrieved. This is not...
There are two ways you can use this e-book: in a practical applied way – for example, by utilizing the check-list attached at the end of this e-book as part of your data migration process – or as an information resource – that is, as a reference guide to...
Storage requirements are growing between 45-60% annually. It is the fastest growing capital cost in datacenters . While storage per terabyte is getting cheaper, it is not matching the storage growth and is decelerating in...
We conducted a qualitative user study to systematically evaluate techniques to compute and present individual search features. In extended interviews, bioscientists rated the usefulness of features in common interfaces on baseline and their own queries, which...
Learn How to Reduce Time Pressure in Mergers and Acquisitions
One of the key challenges for an M&A deal team is to find and collect the right information to put together a comprehensive data room under time pressure. Even with the arrival of so- called virtual...
Departmental silos of information hinder collaboration and productivity. Tagging content by industry, region, document type, activity, risk and many other topics specific to your business allows your staff to filter out irrelevant search results to increase productivity....
Mountains of data but a struggle to find meaningful information. In this whitepaper we examine this search for meaning in the enterprise, and how enhancing findability can add significant value to the investment an organization makes in important tools like...
We help the complex become simple. At the heart of Pingar is extraordinarily powerful software that provides text analytics of unstructured data. Our customers have masses of data, and want to be able to find what is relevant now, using something elegant and simple. We sift and structure their data, and then visually display what they are looking for, enabling rapid drill downs to help make important decisions.