Open AccessArtificial intelligence technologies to identify similar objects and formalization of inference rules
Author(s) -
Nafisa Yusupova,
О. Н. Сметанина,
E.Yu. Sazonova,
A I Agadullina
Publication year - 2021
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/1069/1/012015
Subject(s) - computer science , identification (biology) , task (project management) , inference , data science , knowledge base , selection (genetic algorithm) , knowledge management , knowledge extraction , business intelligence , decision support system , intelligence analysis , artificial intelligence , data mining , systems engineering , engineering , computer security , botany , biology
Analysis of data accumulated during the activities of the enterprise may be applied for creating novel business models and more efficient use of information resources. Specific requirements for analysis of data in socio-economic areas entail the need to develop or select the required tools and methods. This article considers identification of implicit knowledge on a complex of historical and operational data. The task statement and the methodology of solution are given. Data mining technologies are applied for identifying hidden common factors in data. Interpretation of the results, formalization of knowledge, formation of the knowledge base and use of the inference mechanism allow us to organize decision support. As an example, the task of personnel selection is considered. The choice of certain factors that are significant for each enterprise, which are the basis for the selection of personnel, will make it possible to spread the solution method for enterprises where strict requirements for information security are imposed. An analysis of decision-making support research in this area, is conducted with the use of artificial intelligence technology. Neural network technologies for data analysis are proposed to be used by the authors.