Adaptive Read Technology (ART)

Open Text Capture Document Reader (DOKuStar) Open Text Capture Document Extraction (DOKuStar) Open Text Capture Document Validation (DOKuStar) Adaptive Classification Technology Adaptive Read Technology Document Technologies for SharePoint ®

Adaptive Read Technology (ART) converts scanned documents into data; this way, business processes associated with documents are automated. ART stands for “Adaptive Read Technology”, a patented procedure that allows the software to learn, based on samples, how to find necessary data on unstructured documents. ART is used as an addition to the established recognition engine Open Text Capture Document Extraction with its approved rule-based method. Both products are integrated into data capture systems, capture platforms or specialist systems such as SAP. Input documents are transferred to ART via a programming interface; the result is then available to the subsequent application as an XML document. Both products, ART and Document Extraction, can be used together.

Components of ART

ART comes with software for the following tasks:

Data extraction: The ART engine locates the matching, learnt example linked to the document at hand and extracts the data defined.
Learning: A training station is set up to train in identified examples. The workstation can be integrated into the actual production queue.
Definition: The application is defined using a definition tool. Central to this are the various types of documents and the data to be extracted.
Administration: Database management including all examples learnt and application definition.
Process monitoring: Monitoring of ongoing production and identification of document types to be trained.

Adaptive Read Technology (ART)

Components of ART

Related Documents