Technology

Discovery, Classify, Protect

Machine Learning (ML) and Natural Language Processing (NLP)

In Getvisibility, we are continuously improving our master ML model that is available to all our customers. We have built an extensive taxonomy set that covers over 70 various categorisation labels, as shown below. We label each document under a high-level category such as HR or Finance or Legal, and so forth. This allows us to have a very granular view of the data content, allowing our customers to precisely understand each document’s content and file stored across the company’s estate. We also allow you to create custom ML models that capture your perspective on data classification. You can create custom labels by showing our software samples of such data.

Technology

Getvisibility discovers unstructured data and documents across an organisation’s estate. Unstructured data usually refers to information that does not reside in a traditional row-column database and is usually in the form of documents and emails.

 

It is estimated that up to 90% of the data in any organisation is unstructured in this form. Additionally, the amount of unstructured data can rapidly increase over time. With Getvisibility, the discovery process is simple, with the platform being pointed to the various locations and granted access permissions. After a short installation and configuration process, organisations can point the platform to various data sources either individually, or as part of a phased roll-out, or all at once for company-wide discovery. Getvisibility can discover unstructured data from various sources such as file shares, cloud platforms (AWS, Azure) and discover over 70 file types, including but not limited to PDFs, all Microsoft documents, mark-up formats, and so forth.

 

 

Book a Demo
 

Technology

With state-of-the-art machine learning algorithms, Getvisibility combines natural language processing with neural networks and optical character recognition. This allows us to classify unstructured data across organisations with unparalleled accuracy and speed without affecting the file servers during the scan.

 

Using machine learning rather than traditional pattern matching (regular expressions) and dictionary lookup methods allows Getvisibility to understand the context of a document, thereby increasing accuracy. As the neural network does most of the work, organisations no longer must embark on the laborious and expensive task of creating rules and regex hits per department and document type. Getvisibility’s customisable tag set enables users to apply company-specific classification to their unstructured data, which the neural network learns with increasing accuracy. Training of the neural network can be done through our user-friendly interface, eliminating the need for the highly qualified engineers and data scientists associated with traditional methods.

 

 

Book a Demo

Technology

You cannot protect what you do not understand. Through accurate classification of unstructured data, Getvisibility provides organisations with an in-depth view of their unstructured data landscape.

 

Risk scores are also calculated per document assessing the confidentiality, permissions, context and content of a document. This enables organisations to make informed decisions surrounding their data security posture and focus on data at risk.

 

Getvisibility’s in-depth reports allow companies to monitor their security initiatives’ impact and assess their competency and success. Getvisibility also integrates with multiple Data Loss Prevention (DLP) platforms such as Microsoft AIP and Forcepoint. These integrations allow organisations to automatically apply DLP tags to unstructured data, depending on their classification and content. This greatly accelerates the data loss prevention project while reducing cost and increasing efficacy.

 

 

Book a Demo