TFM (MUTIA)

A comparative study of computational intelligence software for enhancing the capabilities of business document management systems

Abstract

The proliferation of electronic documents in business, traditionally constituting a huge amount of printed paper, is a reality nowadays. In recent years there has been a transformation of this kind of document to a new format, which has involved the search for a new way to transform, manage and process the information in these documents properly.

However, traditional systems of recovery and processing of this information have not been able to meet the growing needs, as for example, searches. The fact of searching in the traditional systems meant having a very large quantity of useless content to users. Under these assumptions, it is intended to perform a study of the existing tools in order to optimize all the procedures for processing this information.

To do this, we will make use of various tools implementing Soft Computing techniques, in order to discover the most appropriate set of document processing tools in a purely business context.

[Wiki] (https://github.com/RomRuben/TFM/wiki)

Planning

• Project Charter
• Project Management Plan
• [Scope Statement] (https://github.com/RomRuben/TFM/wiki/Scope%20Statement)
• Project Scheduling

Tracking and Control

• Control structure of tasks in progress

Research lines

• Language Detection
• Tokenizers
• POS Taggers
• Weight Terms
• Content Search
• Document Classification