Semantic Rule-based Approach for an Intelligent Document Management System

Tracking #: 3567-4781

This paper is currently under review
Giovanna Di Marzo Serugendo
Gilles Falquet
Claudine Métral
Maria Assunta Cappelli
Assane Wade
Sami Ghadfi
Anne-Françoise Cutting-Decelle
Ashley Caselli
Graham Cutting

Responsible editor: 
Marta Sabou

Submission type: 
Full Paper
Organisations heavily dependent on paper documents still spend a significant amount of time managing a large volume of documents. An intelligent document management system (DMS) is presented to automate the processing of tax and administrative documents. A combination of artificial intelligence methods has been adopted to create a system that can perform multiple functions, including the classification of Swiss insurance and fiduciary documents, the definition of tax profiles, and the extraction of inferences from the application of SHACL rules on tax profiles. The DMS was designed to help all those companies that manage their clients’ tax and administrative documents daily. Automation speeds up the management process so that companies can focus more on value-added services such as consulting. The creation of the DMS is carried out in several steps, including the development of an ontology for Swiss tax returns; the use of two alternative approaches for document classification and information extraction; the definition of tax family profiles; the representation of extracted data using RDF triples; and the classification of users into distinct profiles based on the tax documents provided. The system was tested in a case study consisting of tax return preparation.
Full PDF Version: 
Under Review