MINERÍA DE TEXTO

GEMA

Analysis of information contained in large volume files.

GEMA is a tool for analyzing information stored in large volumes of different formats and languages files, with information retrieval/sorting oriented functions.

GEMA is useful in:

  • The discovery and analysis of information in small and large file volumes.

GEMA allows:

  • Retrieving information through an effective search method by content.
  • Applying up-to-date techniques for information retrieval into the search results in order to obtain similar files, delete irrelevant results and group common documents.
  • Obtaining summaries of the most important ideas from a set of documents.
  • Facilitating the process of classifying documents in user-defined topics.
  • Displaying statistical reports facilitating the information analysis and system behavior.

GEMA's features are:

  • File downloading from directories, websites and databases.
  • Processing of documents with 82 written formats in 7 languages.
  • Extraction of texts from images using OCR techniques.
  • Ensuring information security by restricting, for each user, the access to the information available.
  • Keeping a record to audit user actions in the system.
  • Providing an Web services API for integration with other systems.

Comments

At your service