Automated capturing of Enterprise documents
by RIX TECHNOLOGIES JSC
What is Automated capturing of Enterprise documents?
The solution provides means for automated classification of documents captured into Enterprise systems. The solution learns on document classification history data to classify new documents and may be tuned for the document classification rules of the Enterprise. The automated capturing process provided by the solution suggests document types, folders, cases, staff members to route documents to, thus reducing the manpower necessary for the process.
Where is it used?
The solution provides for a flexible framework of machine learning based text classification algorithms and consists of:
> Back-end system of configurable machine learning based document classification routines and training sample retrieval routines (implemented on top of python machine learning libraries)
> Elasticsearch based storage for handling of training sample and classification performance testing data
> web based user front-end allowing for easy configuration of the classification and machine learning process and for interactive analysis of the classification performance
