PII Extraction Demo

Cover Image for PII Extraction Demo

What it does

Our service finds sensitive information in text documents – this can be personally identifiable information (PII) such as credit card numbers or names but also information about ethnicity and religion.

We use a combination of best of breed proprietary and open source technologies plus our own special sauce to find what’s relevant in a document. We do not blindly apply pre-defined lists or regular expressions, but take into account document structure, context and connections to other information found.

In order to check this out live, follow the link at the bottom and register with Auth0. If you already have an Auth0 or Google-Account, you can simply use that to access the demo.


How it works

  • You can either type the text you want to be analyzed into the text-box, or paste an article into it, start with the sample text, or select a local file from your computer. This can be a document (e.g. PDF, Word, Powerpoint, etc.) or an image.
  • If you want to process a local file, simply select it using the “Select File” option and wait for it to be converted to text. The status indicator at the bottom will let you know when all text was extracted.
  • Once the text was added to the text-box, you can start analyzing it with the “Extract Entities” option.
  • As soon as all entities have been identified, you will find the original text on top with all entities highlighted and a structured table at the bottom, that includes the types of entities and the respective values.
  • With “Result”, “Split” and “Entities” you can easily adjust the view to you preference.
  • The “Clear” option let’s you start all over.

What you need

  • Text-based content - either a document (e.g. PDF, Word, Powerpoint, etc.), an image that includes text or just pure text
  • Sign-in or register with Auth0 - you can also use your existing Google-Account