DEVELOPMENT OF PERSONALIZATION SYSTEM OF SPECIALIZED WEB PORTAL
Науковий журнал «Радіоелектроніка, інформатика, управління»
Переглянути архів Інформація| Поле | Співвідношення | |
| ##plugins.schemas.marc.fields.042.name## |
dc |
|
| ##plugins.schemas.marc.fields.245.name## |
DEVELOPMENT OF PERSONALIZATION SYSTEM OF SPECIALIZED WEB PORTAL |
|
| ##plugins.schemas.marc.fields.720.name## |
Axak, N. G.; Kharkiv National University of Radio Electronics, Kharkiv, Ukraine |
|
| ##plugins.schemas.marc.fields.653.name## |
personalization; JSM-method; neural network clustering; multi-agent system; informative portrait of user. |
|
| ##plugins.schemas.marc.fields.520.name## |
Context. The actual task of personifying a Web portal providing business services (telemedicine, consultations, remote monitoring,<br />distance education, etc.) has been solved.<br />Objective - development of a personalization system for a web portal that provides specialized services, which allows to take into account<br />preferences of users for the improvement of quality of service, an acceleration of information search, an exception of uninteresting pages, and а customer retention.<br />Method. The generalized process personalization model of Internet service is offered. The method of adaptation of the Web-resource<br />based on the combination of agent and neural network technologies is proposed in a model which automatically generates content for certain<br />categories of Internet users. The document object model of site in a graph form to search of relevant information was proposed that allows the site personalization. The use of multi-agent structure allowed to realize interaction of the components of the developed model. The method includes the following actions: automatic generation of hypotheses, which determines the presence or absence of target properties of the user; analysis of the user’s behavior on his surfing the Internet that allows to give more relevant results; construction of information portrait for collection statistically significant set of information characteristics for the purpose of planning of further actions; parallel clustering of users with use of the self-organizing Kohonen maps for the purpose of an acceleration of processing big data. The self-organizing Kohonen maps are adapted to symmetric multiprocessing system for accelerating computations. Thus, the configuration of the computing system shall be a multiple of the dimension of the input data for reduction of computation time.<br />Results. For the proposed models and method, software and a web interface are developed. They are used to realization computing<br />experiments to verification of the models, valuation of the adequacy and study the properties of the model and method.<br />Conclusions. The conducted experiments have confirmed the proposed models and methods. The use of a set of methods and tools can<br />be used in practice to promote goods and services in the network, to provide various services or individual parts of it, for business development. |
|
| ##plugins.schemas.marc.fields.260.name## |
Zaporizhzhya National Technical University 2018-05-29 13:24:17 |
|
| ##plugins.schemas.marc.fields.856.name## |
application/pdf http://ric.zntu.edu.ua/article/view/131570 |
|
| ##plugins.schemas.marc.fields.786.name## |
Radio Electronics, Computer Science, Control; No 1 (2018): Radio Electronics, Computer Science, Control |
|
| ##plugins.schemas.marc.fields.546.name## |
ru |
|
| ##plugins.schemas.marc.fields.540.name## |
Copyright (c) 2018 N. G. Axak |
|