Information Governance is an enterprise-wide initiative that requires companies to take action and safeguard appropriate information. With the explosion of information being generated, coupled with the increasing need to identify and protect this information, most organizations have initiated programs to manage information more effectively across the enterprise. The progression of information management governance is now an essential business requirement to mitigate risk, reduce cost, and protect assets. However, even though companies are initiating these governance programs, you can not mitigate risk, reduce cost, and protect your information assets unless you can discover and identify every location where they exist.
Identifying sensitive information like passport number, medical ids, and social security numbers is easy for human beings, but with the vast amount of data in today’s organizations, that is neither a feasible, nor cost-effective approach. Today, there is a solution: Docxonomy.
Due to both the deep text parsing Docxonomy already performs to power its intelligent search and the contextual understanding our engine draws from the written prose, our system is perfectly positioned to go one step further. We’ve added to our system’s intelligent analysis the ability to recognize sensitive information. With Docxonomy’s mature machine learning and natural language processing algorithms, recognizing such sensitive text is quite simple.
Docxonomy gains intelligence and contextual understanding of words themselves and predicts what values will be expected.
Example – we use our deep contextual analysis to classify a document as a contract. Since we have determined it to be a contract we can then expect to find the names of the parties involved, a term length and approval dates, among other things.
Once automatically captured, these values can be used as any other metadata to safeguard the content identified and alert the appropriate users. With Docxonomy, the big difference is that a human did not have to enter these metadata values or import/migrate them from some database.
Docxonomy comes with certain pre-built identification algorithms already built-in and we give the customer the ability to configure additional algorithms that may be specific to their business. Once recognized we then know which documents potentially need review in order to confirm their level of sensitivity. This is done through tasks that are automatically generated by our recognition engine
Our system supports numerous pre-built connectors for various systems. These connectors allow Docxonomy to index files from any number of cloud and on-premise repositories. Docxonomy enables you to search from one platform for data in multiple storage locations. You can, of course, choose to store all of that data in our cloud repository, but you don’t have to. Just set up a connector and Docxonomy will index it all for you in our cloud, leaving the native files where they already live.
Contact us today to learn more about how Docxonomy can help you mitigate risk, reduce cost, and protect your information assets.
October 31, 2018
Archiving, Artificial Intelligence, File Classifications, Permissions, Security