S. D. Kulik - Dr.Sc. (Eng.), Senior Research Scientist, Professor, National Nuclear Research University «MEPHI» (Moscow), Moscow State University of Psychology and Education (MSUPE)
K. I. Tkachenko - Head of Department, LIFEiT (Moscow). Email: konstantin.tki@gmail.com
A. A. Kondakov - Post-graduate Student, National Nuclear Research University «MEPHI» (Moscow). Email: alex.letbox@gmail.com

This paper briefly discusses the neural network and automated information systems formation of factographic data (AISFFD). AISFFD is the special class factographic systems. Method is proposed for evaluating effectiveness these systems. This method contains the necessary neural network. In article questions of construction of estimated characteristics of efficiency of technical systems by means of use neuronets algorithms are considered. Traditional methods of an estimation of efficiency mean serious expert working out of a subject domain for definition of those weight factors or other indicators, for example, at use multiplicativity a method of an estimation of efficiency what or systems. Briefly introduces the concept of building the AISFFD. The variant of a possible scheme of a specialized AISFFD for implementing it in practice are proposed. Now scientists group continue researches in this field. It is offered to use a special factographic information retrieval. This article is about automated information system of the formation factografic data (AISFFD). AISFFD is a special class of the factografic systems that help to generate factografic data with using neural network. Such system can be used in different applied tasks for generating sets of data (features) and using it for forming an object of the retrieval system. That technology lets to increase efficiency and performance of the systems using search engines of the special class or systems forming object with a sets of features. Also it can be useful for systems that work with large volumes of data. AISFFD consist several subsystems (analyze and decision-making unit, data preparing unit, factografic data generator, main factografic database, additional database, object forming system). Also AISFFD have human friendly interface that helps users (operators) to work with it without special training. In this article submitted descriptions of these subsystems and their communications, methods and algorithms that using in different units and using of the neural networks. Authors propose to use AISFFD in criminalistics systems of recreating objects by features or in a special class of retrieval systems that use features in research process. Such retrieval system use the special algorithms (differs from text retrieval systems) and can be used for searching data of different types. Now scientists group continue researches in this field. The results of the researches were successfully protected by the various security documents of ROSPATENT.