Development of the formal model of the optical recognition mechanism for tabular documents

Abstract

The article describes the tasks of the optical recognition system for tabular documents and the development of a formal model of the optical recognition mechanism for tabular documents. The aim of the study is to use the developed system of automatic analysis of platform-type documentation as expert and training to support decision making, semantic analysis or audit of any content, including in other industries based on the principle of automatic filling of ontologies. The proposed system will allow to overcome this barrier in a cardinal way – by automatically creating a database. In this case, the user’s role will be reduced to the choice of sources for filling ontologies (the choice of thesauruses, corpus of texts in machine-readable or natural language, etc.) and the configuration of inference rules, i.e., essentially, to the configuration operations.

Hybrid client‐server implementation and microservice architecture of automatic documentation analysis software

“…High resiliency due to redundancy of critical services. Availability of analytics tools, so it is easy to track dependencies between services [4].…”