User device characterization method based on network data traffic information, and network access control method thereof
Provided is a system for network access control. The system includes an authentication server configured to perform a basic authentication procedure for a user by communicating with at least one user terminal, a service server configured to provide a service to at least one user terminal passing through the basic authentication procedure, a collection device configured to acquire traffic data of the at least one user terminal passing through the basic authentication procedure from at least one of the service server and a network interface connected to the service server, acquire a traffic dataset by refining the acquired traffic data in accordance with correlation, and extract time-series feature points of the traffic dataset, and an artificial intelligence (AI) management device configured to train at least one AI model to define a traffic character template of the user on the basis of the time-series feature points.
1 . A system for network access control, the system comprising:
a service server configured to provide a service to at least one user terminal;
a collection device configured to acquire traffic data of the at least one user terminal from at least one of the service server and a network interface connected to the service server, acquire a traffic dataset by refining the acquired traffic data in accordance with correlation, and extract time-series feature points of the traffic dataset;
an artificial intelligence (AI) management device configured to train at least one AI model to define a traffic character template of the user on the basis of the time-series feature points; and
an authentication server configured to determine whether the periodically extracted time-series feature points correspond to the user's usage characteristics depending on a comparison result between time-series feature points periodically extracted by the collection device and the traffic character template of the user,
wherein the authentication server performs a basic authentication procedure of at least one terminal matching the user, and when the terminal passes through the basic authentication procedure and it is determined that the traffic data of the terminal does not correspond to the user's usage characteristics as a result of comparison with the traffic character template of the user, sets the terminal as an abnormal terminal and transmits a control message to the service server or the network interface to block a connection with the abnormal terminal.
2 . The system of claim 1 , wherein the collection device extracts the user's feature points regarding each of a plurality of time-series items acquired in accordance with a feature point element including at least one of a data usage characteristic, a data transmission volume characteristic, an application usage characteristic, and a terminal characteristic.
3 . The system of claim 2 , wherein the AI model generates the traffic character template of the user in accordance with a distance vector based on a difference between the user's feature points and a distribution of a plurality of user's feature points regarding each of the plurality of time-series items.
4 . The system of claim 1 , wherein the authentication server communicates with the abnormal terminal to additionally perform an enhanced authentication procedure which differs from the basic authentication procedure, and when the abnormal terminal passes through the enhanced authentication procedure, the AI management device trains the AI model on the basis of the traffic data of the abnormal terminal to update the traffic character template of the user.
5 . The system of claim 1 , wherein the authentication server compares the periodically extracted time-series feature points with the traffic character template of the user through the AI model to acquire similarity and determines whether the periodically extracted time-series feature points correspond to the user's usage characteristics on the basis of the similarity.