NETWORK DEVICE AND MODEL LEARNING METHOD

1 . A network device comprising:

a memory; and

a processor coupled to the memory and the processor configured to:

calculate, based on acquisition statuses of packets in a capture device that acquires the packets transmitted from an application device to a terminal device over a network, first group information indicating the acquisition statuses for each of a plurality of packet groups each including a plurality of packets having a predetermined relationship with each other; and

generate a learning model by learning teacher data including the first group information calculated, first communication condition information indicating communication conditions of the packets in the network, and first quality information indicating quality in terms of output of the packets on the terminal device.

2 . The network device according to claim 1 , wherein

the packets are packets constituting moving image data that is distributed from the application device to the terminal device and reproduced on the terminal device, and

the first quality information is information indicating QoE (Quality of Experience) of the moving image data on the terminal device.

3 . The network device according to claim 2 , wherein

the plurality of packets having the predetermined relationship with each other are a plurality of packets used to reproduce the moving image data in a same time period.

4 . The network device according to claim 1 , wherein

the processor acquires the packets transmitted from the capture device, and

the processor calculates the first group information based on the acquisition statuses of the packets.

5 . The network device according to claim 4 , wherein

the processor calculates the first communication condition information based on the acquisition statuses of the packets.

6 . The network device according to claim 1 , wherein

the capture device generates the first communication condition information based on the acquisition statuses of the packets in the capture device,

the processor acquires the first communication condition information transmitted from the capture device.

7 . The network device according to claim 1 , wherein

for each of the packet groups, the processor generates, as at least one piece of the first group information, information indicating a time difference between a reception timing of a packet received first among the packets included in the packet group and a reception timing of a packet received last among the packets included in the packet group.

8 . The network device according to claim 1 , wherein

for each of the packet groups, the processor generates, as at least one piece of the first group information, information indicating a time difference between a reception timing of a packet received first among the packets included in the packet group and a reception timing of a packet received last among the packets included in a packet group transmitted immediately before the packet group.

9 . The network device according to claim 1 , wherein

for each of the packet groups, the processor generates, as at least one piece of the first group information, information indicating a time difference between a reception timing of a packet received first among the packets included in the packet group and a reception timing of a packet received first among the packets included a packet group transmitted immediately before the packet group.

10 . The network device according to claim 1 , wherein

for each of the packet groups, the processor generates, as at least one piece of the first group information, a total amount of data of the packets included in the packet group.

11 . The network device according to claim 1 , wherein

the processor calculates, based on the acquisition statuses of other packets transmitted from the application device to the terminal device over the network, second group information indicating the acquisition statuses for each of a plurality of packet groups,

the processor acquires second quality information output from the learning model as a result of input of the second group information calculated and second communication condition information indicating communication conditions of the other packets in the network; and

the processor outputs the acquired second quality information.

12 . A model learning method comprising:

calculating, by a processor, based on acquisition statuses of packets in a capture device that acquires the packets transmitted from an application device to a terminal device over a network, first group information indicating the acquisition statuses for each of a plurality of packet groups each including a plurality of packets having a predetermined relationship with each other; and

generating, by the processor, a learning model by learning teacher data including the first group information calculated, first communication condition information indicating communication conditions of the packets in the network, and first quality information indicating quality in terms of output of the packets on the terminal device.

13 . The model learning method according to claim 12 , further comprising:

calculating, by the processor, based on the acquisition statuses of other packets transmitted from the application device to the terminal device over the network, second group information indicating the acquisition statuses for each of a plurality of packet groups;

acquiring, by the processor, second quality information output from the learning model as a result of input of the second group information calculated and second communication condition information indicating communication conditions of the other packets in the network; and

outputting, by the processor, the acquired second quality information.