Network connected device and traffic estimation method thereof

1. A traffic estimation method, comprising:

capturing a plurality of network packets;

counting a quantity of query times for at least one domain name in the network packets, wherein the step of counting the quantity of query times for the at least one domain name in the network packets comprises:

parsing the at least one domain name to be queried in the network packets; and

adding up quantities of domain name system queries for each of the at least one domain name respectively to obtain the quantity of query times; and

determining network traffic according to the quantity of query times, wherein the step of determining the network traffic according to the quantity of query times comprises:

taking a plurality of historical network packets and corresponding actual traffic as a plurality of training samples;

training an estimation model with use of the training samples based on a machine learning technology, wherein the estimation model is obtained through feature extraction, wherein labels of type features are generated by the feature extraction based on a domain query record; and

inputting the quantity of query times to the estimation model to obtain the network traffic.

2. The traffic estimation method according to claim 1 , wherein the step of determining the network traffic according to the quantity of query times comprises:

acquiring a traffic contribution coefficient of each of the at least one domain name, wherein the traffic contribution coefficient is traffic corresponding to one query for the at least one domain name; and

respectively determining, according to the traffic contribution coefficient of the at least one domain name, the network traffic corresponding to the quantity of query times for each of the at least one domain name.

3. The traffic estimation method according to claim 1 or 2 , wherein the network packets flow through one of an access network, a transmission network, and a core network, and the step of determining the network traffic according to the quantity of query times comprises:

determining the network traffic flowing through the access network, the transmission network, or the core network according to the network traffic corresponding to all of the at least one domain name.

4. The traffic estimation method according to claim 1 or 2 , wherein the step of determining the network traffic according to the quantity of query times comprises:

setting a plurality of network service application types, wherein each of the at least one domain name at least corresponds to one of the network service application types;

determining, according to the quantity of query times of a user for the at least one domain name, corresponding network traffic of using each of the network service application types by the user; and

determining, according to the corresponding network traffic of each of the network service application types, one of the network service application types to which the user belongs.

5. A network connected device, comprising:

a communications transceiver, receiving a plurality of network packets; and

a processor, coupled to the communications transceiver and configured to:

capture the network packets;

count a quantity of query times for at least one domain name in the network packets, wherein the processor is further configured to:

parse the at least one domain name to be queried in the network packets; and

add up quantities of domain name system queries for each of the at least one domain name respectively to obtain the quantity of query times;

determine network traffic according to the quantity of query times;

take a plurality of historical network packets and corresponding actual traffic as a plurality of training samples;

train an estimation model with use of the training samples based on a machine learning technology, wherein the estimation model is obtained through feature extraction, wherein labels of type features are generated by the feature extraction based on a domain query record; and

input the quantity of query times to the estimation model to obtain the network traffic.

6. The network connected device according to claim 5 , wherein the processor is configured to:

acquire a traffic contribution coefficient of each of the at least one domain name, wherein the traffic contribution coefficient is traffic corresponding to one query for the at least one domain name; and

respectively determine, according to the traffic contribution coefficient of the at least one domain name, the network traffic corresponding to the quantity of query times for each of the at least one domain name.

7. The network connected device according to claim 5 or 6 , wherein the network packets flow through one of an access network, a transmission network, and a core network, and the processor is configured to:

determine the network traffic flowing through the access network, the transmission network, or the core network according to the network traffic corresponding to all of the at least one domain name.

8. The network connected device according to claim 5 or 6 , wherein the processor is configured to:

set a plurality of network service application types, wherein each of the at least one domain name at least corresponds to one of the network service application types;

determine, according to the quantity of query times of a user for the at least one domain name, corresponding network traffic of using each of the network service application types by the user; and

determine, according to the corresponding network traffic of each of the network service application types, one of the network service application types to which the user belongs.