OpenText Auto-Classification

The OpenText company provided in December, 2011 the innovative technology of OpenText Auto-Classification — the application first in the history for the transparent and protected automatic classification of information. The solution is proposed to the companies by a new method of distribution control and preserving of large volumes of the automated content, including contents of social networks, e-mail, office documents and contemporary records that helps to reduce legal risks and costs for the system of electronic detection of data eDiscovery.

"When we discuss technologies of automatic classification of data with our clients, their greatest concerns concern how to make this process ordered for all content and how to control this process. The OpenText Auto-Classification application is developed for the solution of such problems — James Lethem, the marketing director of OpenText company commented. — We created the industry-first system of computer classification of data with the built-in statistical check and a quality assurance that does process of classification of content at the same time open and protected. Our solution in a root changes processes of maintaining digital documentation".

Employees who monitor business processes and document flow of the company should be able to work competently with business documentation, namely to be able to classify, save, delete, take, to use and protect effectively these ("business records"). Recently they even more often should deal with huge volumes of temporary or, at first sight, insignificant data from social networks and e-mails. Despite small volume, information such can be valuable and its removal is risky. Classification of information is a major component of work with digital documentation as it allows the companies to define what content needs to be saved and of what it is necessary to get rid. Earlier directly users had to be engaged in classification of content. But low figures of merit of process and accuracy of information led to additional costs in the form of penalties and use of an expensive system of electronic detection of data of eDiscovery.

OpenText Auto-Classification provides ordered and safe classification of all content directly after installation and start of a system. Process takes place without participation of end users. The application is used by the OpenText Content Analytics mechanism which processes each document, the e-mail or a post on social network, classifying data retrieveds according to corporate policy and requirements of the legislation. Unlike search or the analysis of the text on a key word, OpenText Content Analytics codifies the specific language features of the text determined by specialized groups of linguists that allows to improve the accuracy of classification of data many times.

The application from OpenText exceeds other classification systems, model-based "a black box" as includes tools for determination of samples of documents and rules and also for selection of data from huge number of documents in a continuous duty. Such technology promotes permanent improvement of a system and increase in efficiency and quality of classification. It provides to the companies that level of security which is necessary for adaptation of a system of automatic classification of data to their changing requirements.

The OpenText Auto-Classification application which was developed at close cooperation with users of OpenText ECM Suite is integrated with OpenText Records Management that allows to use the existing orders of classification and the classified data already in the course of an application tuning. Among customers who took part in application testing there was a Canadian company Translink servicing city transport of the city of Vancouver.

"Participating in beta testing of the program, we had an opportunity to play a role in development of systems of automatic classification for document management. This product not only will improve and will expand use of a classification system and schemes of preserving of data for needs of our company and customers, but also will simplify identification of content for processes of eDiscovery and also archiving and distribution" — Noella Bordian, the head of department of office-work of Translink company said.

The OpenText Auto-Classification application will be available to customers at the end of 2011. For further information visit the www.opentext.com/auto-classification website.