Open AccessSemantic analysis implementation in engineering enterprise content management systems
Author(s) -
Anton Ivaschenko,
Anastasia Stolbova,
D N Krupin,
Arkadiy Krivosheev,
Pavel Sitnikov,
O Ja Kravets
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/862/4/042016
Subject(s) - computer science , configurator , graph , knowledge graph , semantic technology , information retrieval , semantic computing , semantic web , theoretical computer science , marketing , business
The paper introduces a new solution for semantic analysis implementation in modern enterprise content management (ECM) systems. The system of semantic analysis is intended for the intellectual analysis of enterprise official and technical documents based on machine learning, namely the extraction of the specified attributes from them for further use. In this paper it is proposed to implement semantic search using the extracted data configurator, which is responsible for creating and managing ontologies. From the configurator of the extracted data by the name of the document type, a graph is generated containing attributes to be extracted (official terms and sections, dates, etc.), regular expressions to search for sentences that probably contain the desired attribute, Yargy and regular rules for extracting attributes from the arrays of sentences. The proposed solution was successfully probated and tested on a dataset containing engineering enterprise contract agreements and protocols.