Text Mining Indexer One-stop shop for meaningful results when searching different types of data. Search & Retrieve key information contained in emails, attachments, print media, and Web content!



FEATURES AND BENEFITS

Fully Automated Process: The Text Mining System automates the process of text data indexing and annotation, which previously was done manually. This reduces costs substantially while increasing productivity.

Web Pages: The Text Mining System includes the Sail Labs WebCollector, an application that analyses configurable places on the Internet for web pages and updates.

E-mail: The Text Mining System includes the Sail Labs E-mail Collector, an application that analyses content of E-mails of configurable POP3 and IMAP user ids.

Electronic Documents: The Text Mining System includes an electronic document converter that allows for indexing of Microsoft Word XP and 2003, HTML and PDF documents.

Instant Access / Real Time Indexing: The indexed results are obtained as soon as content is available. It is possible to search while the content is being indexed.

Scalable Architecture: The Text Mining System supports configuration options ranging from single machines to multiple machines.

Easy Customization: The system is flexible enough to integrate addition of categories, and topics, while maintaining optimal performance.

Multilingual Keyword Search: You can search for keywords and their translations in different languages.

Summarization Options: You can summarize a single report on the basis of topic, person, organization, location or speaker.

Notification: The Media Mining Server notifies you whenever new content matching your preferences is available.


Link back to top

The underlying technologies

Media Mining Explorer: The Media Mining Explorer is the graphical user interface used to retrieve information from the Media Mining Server.
It provides the user with an interface to search, summarize, and display any content stored in the Media Mining Server.

Text Mining Indexer: The Text Mining Indexer accepts media stream through media feeders. These convert input from sources such as eMails, office documents, web pages etc to a format compatible as input for the Text Mining Indexer. The Text Mining Indexer uses this input to produce XML files containing metadata about the content. This metadata is sent to the Media Mining Server.

Media Mining Server: The Media Mining Server creates an archive of all the indexed files it receives from the Text Mining Indexer. It facilitates selective retrieval of content by creating a structured hierarchy of information. The Media Mining Server also handles security aspects like access authorization.


Link back to top

INTEGRATION

The SAIL LABS Text Mining System can be easily integrated into other systems ranging from those handling storage and search-and-retrieval to those delivering media content. The industry-standard XML output of the Text Indexer simplifies the implementation of the technology in a turnkey or customized solution. Analogously to the Text Mining System, the Media Mining System converts audio and video data into manageable information. By combining the SAIL LABS Text Mining System with the SAIL LABS Media Mining System, user benefit from a world wide multimedia and data monitoring equipment, which provides them with actionable intelligence in real-time.