Algorithms, methods and approaches to details and enrich data, including personal data

Abstract

This article presents the results of a study of algorithms, methods and approaches to depersonalization and enrichment of data, including personal data. Among the types of data enrichment, demographic, geographic and behavioral data enrichments were considered, as well as statistical, semantic and pragmatic data enrichment algorithms were studied. In addition to data enrichment, categories of ontology enrichment were considered, namely expressive ontologies, lightweight ontologies such as taxonomies, and a category that includes works that use reasoning to partially replace traditional methods of knowledge extraction. Ontology enrichment is a broad area of research that can be divided into three categories of work devoted to extracting semantic knowledge from heterogeneous data. As a result of the analysis, it was found that data enrichment processes optimize sales, as well as reduce business costs, by saving finances through information management. The advantages and disadvantages of the considered approaches and methods of data enrichment and ontologies were presented. The main benefit of fortification is the increased value and accuracy of information that helps companies make important business decisions. The main disadvantage is the risk of growing redundant data, which can lead to incorrect analytics and, accordingly, to wrong business decisions, which in turn harms the business. The significance of the analysis is also presented – on the basis of the studies carried out, it is planned to form a technical proposal for creating the basic infrastructure of the project of the NTI Central Committee "Trusted Information Exchange Environment" for further research on the topic of data enrichment and depersonalization.